Bioengineering

16 pages, 476 KiB

Open AccessArticle

Genetic Algorithms for Feature Selection in the Classification of COVID-19 Patients

by Cosimo Aliani, Eva Rossi, Mateusz Soliński, Piergiorgio Francia, Antonio Lanatà, Teodor Buchner and Leonardo Bocchi

Bioengineering 2024, 11(9), 952; https://doi.org/10.3390/bioengineering11090952 - 23 Sep 2024

Abstract

Background: Severe Acute Respiratory Syndrome CoronaVirus-2 (SARS-CoV-2) infection can cause feared consequences, such as affecting microcirculatory activity. The combined use of HRV analysis, genetic algorithms, and machine learning classifiers can be helpful in better understanding the characteristics of microcirculation that are mainly affected [...] Read more.

Background: Severe Acute Respiratory Syndrome CoronaVirus-2 (SARS-CoV-2) infection can cause feared consequences, such as affecting microcirculatory activity. The combined use of HRV analysis, genetic algorithms, and machine learning classifiers can be helpful in better understanding the characteristics of microcirculation that are mainly affected by COVID-19 infection. Methods: This study aimed to verify the presence of microcirculation alterations in patients with COVID-19 infection, performing Heart Rate Variability (HRV) parameters analysis extracted from PhotoPlethysmoGraphy (PPG) signals. The dataset included 97 subjects divided into two groups: healthy (50 subjects) and patients affected by mild-severity COVID-19 (47 subjects). A total of 26 parameters were extracted by the HRV analysis and were investigated using genetic algorithms with three different subject selection methods and five different machine learning classifiers. Results: Three parameters: meanRR, alpha1, and sd2/sd1 were considered significant, combining the results obtained by the genetic algorithm. Finally, machine learning classifications were performed by training classifiers with only those three features. The best result was achieved by the binary Decision Tree classifier, achieving accuracy of 82%, specificity (or precision) of 86%, and sensitivity of 79%. Conclusions: The study’s results highlight the ability to use HRV parameters extraction from PPG signals, combined with genetic algorithms and machine learning classifiers, to determine which features are most helpful in discriminating between healthy and mild-severity COVID-19-affected subjects. Full article

(This article belongs to the Section Biosignal Processing)

► Show Figures

Figure 1

14 pages, 939 KiB

Open AccessArticle

Stepwise Corrected Attention Registration Network for Preoperative and Follow-Up Magnetic Resonance Imaging of Glioma Patients

by Yuefei Feng, Yao Zheng, Dong Huang, Jie Wei, Tianci Liu, Yinyan Wang and Yang Liu

Bioengineering 2024, 11(9), 951; https://doi.org/10.3390/bioengineering11090951 - 23 Sep 2024

Abstract

The registration of preoperative and follow-up brain MRI, which is crucial in illustrating patients’ responses to treatments and providing guidance for postoperative therapy, presents significant challenges. These challenges stem from the considerable deformation of brain tissue and the areas of non-correspondence due to [...] Read more.

The registration of preoperative and follow-up brain MRI, which is crucial in illustrating patients’ responses to treatments and providing guidance for postoperative therapy, presents significant challenges. These challenges stem from the considerable deformation of brain tissue and the areas of non-correspondence due to surgical intervention and postoperative changes. We propose a stepwise corrected attention registration network grounded in convolutional neural networks (CNNs). This methodology leverages preoperative and follow-up MRI scans as fixed images and moving images, respectively, and employs a multi-level registration strategy that establishes a precise and holistic correspondence between images, from coarse to fine. Furthermore, our model introduces a corrected attention module into the multi-level registration network that can generate an attention map at the local level through the deformation fields of the upper-level registration network and pathological areas of preoperative images segmented by a mature algorithm in BraTS, serving to strengthen the registration accuracy of non-correspondence areas. A comparison between our scheme and the leading approach identified in the MICCAI’s BraTS-Reg challenge indicates a 7.5% enhancement in the target registration error (TRE) metric and improved visualization of non-correspondence areas. These results illustrate the better performance of our stepwise corrected attention registration network in not only enhancing the registration accuracy but also achieving a more logical representation of non-correspondence areas. Thus, this work contributes significantly to the optimization of the registration of brain MRI between preoperative and follow-up scans. Full article

(This article belongs to the Section Biosignal Processing)

► Show Figures

Figure 1

14 pages, 968 KiB

Open AccessArticle

FTSNet: Fundus Tumor Segmentation Network on Multiple Scales Guided by Classification Results and Prompts

by Shurui Bai, Zhuo Deng, Jingyan Yang, Zheng Gong, Weihao Gao, Lei Shao, Fang Li, Wenbin Wei and Lan Ma

Bioengineering 2024, 11(9), 950; https://doi.org/10.3390/bioengineering11090950 - 22 Sep 2024

Abstract

The segmentation of fundus tumors is critical for ophthalmic diagnosis and treatment, yet it presents unique challenges due to the variability in lesion size and shape. Our study introduces Fundus Tumor Segmentation Network (FTSNet), a novel segmentation network designed to address these challenges [...] Read more.

The segmentation of fundus tumors is critical for ophthalmic diagnosis and treatment, yet it presents unique challenges due to the variability in lesion size and shape. Our study introduces Fundus Tumor Segmentation Network (FTSNet), a novel segmentation network designed to address these challenges by leveraging classification results and prompt learning. Our key innovation is the multiscale feature extractor and the dynamic prompt head. Multiscale feature extractors are proficient in eliciting a spectrum of feature information from the original image across disparate scales. This proficiency is fundamental for deciphering the subtle details and patterns embedded in the image at multiple levels of granularity. Meanwhile, a dynamic prompt head is engineered to engender bespoke segmentation heads for each image, customizing the segmentation process to align with the distinctive attributes of the image under consideration. We also present the Fundus Tumor Segmentation (FTS) dataset, comprising 254 pairs of fundus images with tumor lesions and reference segmentations. Experiments demonstrate FTSNet’s superior performance over existing methods, achieving a mean Intersection over Union (mIoU) of 0.8254 and mean Dice (mDice) of 0.9042. The results highlight the potential of our approach in advancing the accuracy and efficiency of fundus tumor segmentation. Full article

(This article belongs to the Special Issue Diagnostic Biomedical Image and Processing with Artificial Intelligence and Deep Learning)

► Show Figures

Graphical abstract

16 pages, 17310 KiB

Open AccessArticle

Machine Learning and Optical-Coherence-Tomography-Derived Radiomics Analysis to Predict the Postoperative Anatomical Outcome of Full-Thickness Macular Hole

by Yuqian Hu, Yongan Meng, Youling Liang, Yiwei Zhang, Biying Chen, Jianing Qiu, Zhishang Meng and Jing Luo

Bioengineering 2024, 11(9), 949; https://doi.org/10.3390/bioengineering11090949 - 22 Sep 2024

Abstract

Full-thickness macular hole (FTMH) leads to central vision loss. It is essential to identify patients with FTMH at high risk of postoperative failure accurately to achieve anatomical closure. This study aimed to construct a predictive model for the anatomical outcome of FTMH after [...] Read more.

Full-thickness macular hole (FTMH) leads to central vision loss. It is essential to identify patients with FTMH at high risk of postoperative failure accurately to achieve anatomical closure. This study aimed to construct a predictive model for the anatomical outcome of FTMH after surgery. A retrospective study was performed, analyzing 200 eyes from 197 patients diagnosed with FTMH. Radiomics features were extracted from optical coherence tomography (OCT) images. Logistic regression, support vector machine (SVM), and backpropagation neural network (BPNN) classifiers were trained and evaluated. Decision curve analysis and survival analysis were performed to assess the clinical implications. Sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC) were calculated to assess the model effectiveness. In the training set, the AUC values were 0.998, 0.988, and 0.995, respectively. In the test set, the AUC values were 0.941, 0.943, and 0.968, respectively. The OCT-omics scores were significantly higher in the “Open” group than in the “Closed” group and were positively correlated with the minimum diameter (MIN) and base diameter (BASE) of FTMH. Therefore, in this study, we developed a model with robust discriminative ability to predict the postoperative anatomical outcome of FTMH. Full article

(This article belongs to the Special Issue Recent Progress of Deep Learning in Healthcare)

► Show Figures

Graphical abstract

15 pages, 4294 KiB

Open AccessArticle

Comparing Isolated Thumb Force Generation, Wrist Rotation, and Clinical Measurements in Healthy and Osteoarthritic Individuals before and after Surgery

by Nicole Arnold, Adam Chrzan, Kevin Chan, Daniel Hess, Levi Hinkleman, Stephen Duquette, John Kelpin and Tamara Reid Bush

Bioengineering 2024, 11(9), 948; https://doi.org/10.3390/bioengineering11090948 - 22 Sep 2024

Abstract

Thumb carpometacarpal (CMC) osteoarthritis (OA) is caused by the degeneration of joint surfaces at the base of the thumb. If conservative treatments have failed, surgery may be needed to improve symptoms. Typically, standard clinical tools, such as the pinch gauge, are used to [...] Read more.

Thumb carpometacarpal (CMC) osteoarthritis (OA) is caused by the degeneration of joint surfaces at the base of the thumb. If conservative treatments have failed, surgery may be needed to improve symptoms. Typically, standard clinical tools, such as the pinch gauge, are used to measure thumb force. However, these devices have utilized multiple digits and do not represent forces specifically generated by the thumb. Therefore, different devices are necessary to accurately measure isolated thumb force. The primary objective was to research the effect of thumb force after ligament reconstruction with tendon interposition surgery. To accomplish this, several sub-objectives were implemented: (1) create a testing device to collect isolated thumb forces, (2) collect a normative thumb force data set of males and females to compare the impact of aging and surgery, (3) collect and compare clinical data to see if these data sets matched isolated thumb forces, (4) determine the effect of wrist position on isolated thumb force data in different wrist positions, and (5) collect thumb force in directions that mimic daily activities, a directional force downward (push) and inward (pull). On average, older participants generated statistically larger forces than younger participants. Additionally, only 50% of CMC OA participants showed greater than 5 N of improvement at 6-months post-surgery compared to pre-surgery, but did not reach healthy force levels. When evaluating wrist rotation, OA participants’ push and pull decreased by 8 N and 7 N in the horizontal wrist position, and their push and pull increased by 2 N and 5 N in the vertical wrist position. Evaluation and results with standard clinical tools showed different post-surgery trends than isolated force data, which suggested the clinical approach has mixed results and may be under- or over-estimating the recovery process. These data sets allow surgeons and hand therapists to identify changes in isolated thumb force generation to create specialized therapies and treatment options, which is an improvement upon current clinical measurement tools. Full article

(This article belongs to the Section Biomechanics and Sports Medicine)

► Show Figures

Figure 1

23 pages, 6104 KiB

Open AccessArticle

Mesenchymal Stem Cell-Conditioned Media-Loaded Microparticles Enhance Acute Patency in Silk-Based Vascular Grafts

by Katherine L. Lorentz, Ande X. Marini, Liza A. Bruk, Prerak Gupta, Biman B. Mandal, Morgan V. DiLeo, Justin S. Weinbaum, Steven R. Little and David A. Vorp

Bioengineering 2024, 11(9), 947; https://doi.org/10.3390/bioengineering11090947 - 21 Sep 2024

Abstract

Coronary artery disease leads to over 360,000 deaths annually in the United States, and off-the-shelf bypass graft options are currently limited and/or have high failure rates. Tissue-engineered vascular grafts (TEVGs) present an attractive option, though the promising mesenchymal stem cell (MSC)-based implants face [...] Read more.

Coronary artery disease leads to over 360,000 deaths annually in the United States, and off-the-shelf bypass graft options are currently limited and/or have high failure rates. Tissue-engineered vascular grafts (TEVGs) present an attractive option, though the promising mesenchymal stem cell (MSC)-based implants face uncertain regulatory pathways. In this study, “artificial MSCs” (ArtMSCs) were fabricated by encapsulating MSC-conditioned media (CM) in poly(lactic-co-glycolic acid) microparticles. ArtMSCs and control microparticles (Blank-MPs) were incubated over 7 days to assess the release of total protein and the vascular endothelial growth factor (VEGF-A); releasates were also assessed for cytotoxicity and promotion of smooth muscle cell (SMC) proliferation. Each MP type was loaded in previously published “lyogel” silk scaffolds and implanted as interposition grafts in Lewis rats for 1 or 8 weeks. Explanted grafts were assessed for patency and cell content. ArtMSCs had a burst release of protein and VEGF-A. CM increased proliferation in SMCs, but not after encapsulation. TEVG explants after 1 week had significantly higher patency rates with ArtMSCs compared to Blank-MPs, but similar to unseeded lyogel grafts. ArtMSC explants had lower numbers of infiltrating macrophages compared to Blank-MP explants, suggesting a modulation of inflammatory response by the ArtMSCs. TEVG explants after 8 weeks showed no significant difference in patency among the three groups. The ArtMSC explants showed higher numbers of SMCs and endothelial cells within the neotissue layer of the graft compared to Blank-MP explants. In sum, while the ArtMSCs had positive effects acutely, efficacy was lost in the longer term; therefore, further optimization is needed. Full article

(This article belongs to the Section Regenerative Engineering)

► Show Figures

Graphical abstract

28 pages, 6469 KiB

Open AccessArticle

A 3D Epithelial–Mesenchymal Co-Culture Model of the Airway Wall Using Native Lung Extracellular Matrix

by Roderick H. J. de Hilster, Marjan A. Reinders-Luinge, Annemarie Schuil, Theo Borghuis, Martin C. Harmsen, Janette K. Burgess and Machteld N. Hylkema

Bioengineering 2024, 11(9), 946; https://doi.org/10.3390/bioengineering11090946 - 21 Sep 2024

Abstract

Chronic obstructive pulmonary disease (COPD) is a chronic lung disease characterized by ongoing inflammation, impaired tissue repair, and aberrant interplay between airway epithelium and fibroblasts, resulting in an altered extracellular matrix (ECM) composition. The ECM is the three-dimensional (3D) scaffold that provides mechanical [...] Read more.

Chronic obstructive pulmonary disease (COPD) is a chronic lung disease characterized by ongoing inflammation, impaired tissue repair, and aberrant interplay between airway epithelium and fibroblasts, resulting in an altered extracellular matrix (ECM) composition. The ECM is the three-dimensional (3D) scaffold that provides mechanical support and biochemical signals to cells, now recognized not only as a consequence but as a potential driver of disease progression. To elucidate how the ECM influences pathophysiological changes occurring in COPD, in vitro models are needed that incorporate the ECM. ECM hydrogels are a novel experimental tool for incorporating the ECM in experimental setups. We developed an airway wall model by combining lung-derived ECM hydrogels with a co-culture of primary human fibroblasts and epithelial cells at an air–liquid interface. Collagen IV and a mixture of collagen I, fibronectin, and bovine serum albumin were used as basement membrane-mimicking coatings. The model was initially assembled using porcine lung-derived ECM hydrogels and subsequently with COPD and non-COPD human lung-derived ECM hydrogels. The resulting 3D construct exhibited considerable contraction and supported co-culture, resulting in a differentiated epithelial layer. This multi-component 3D model allows the investigation of remodelling mechanisms, exploring ECM involvement in cellular crosstalk, and holds promise as a model for drug discovery studies exploring ECM involvement in cellular interactions. Full article

(This article belongs to the Section Regenerative Engineering)

► Show Figures

Graphical abstract

24 pages, 13091 KiB

Open AccessArticle

EfficientUNetViT: Efficient Breast Tumor Segmentation Utilizing UNet Architecture and Pretrained Vision Transformer

by Shokofeh Anari, Gabriel Gomes de Oliveira, Ramin Ranjbarzadeh, Angela Maria Alves, Gabriel Caumo Vaz and Malika Bendechache

Bioengineering 2024, 11(9), 945; https://doi.org/10.3390/bioengineering11090945 - 21 Sep 2024

Abstract

This study introduces a sophisticated neural network structure for segmenting breast tumors. It achieves this by combining a pretrained Vision Transformer (ViT) model with a UNet framework. The UNet architecture, commonly employed for biomedical image segmentation, is further enhanced with depthwise separable convolutional [...] Read more.

This study introduces a sophisticated neural network structure for segmenting breast tumors. It achieves this by combining a pretrained Vision Transformer (ViT) model with a UNet framework. The UNet architecture, commonly employed for biomedical image segmentation, is further enhanced with depthwise separable convolutional blocks to decrease computational complexity and parameter count, resulting in better efficiency and less overfitting. The ViT, renowned for its robust feature extraction capabilities utilizing self-attention processes, efficiently captures the overall context within images, surpassing the performance of conventional convolutional networks. By using a pretrained ViT as the encoder in our UNet model, we take advantage of its extensive feature representations acquired from extensive datasets, resulting in a major enhancement in the model’s ability to generalize and train efficiently. The suggested model has exceptional performance in segmenting breast cancers from medical images, highlighting the advantages of integrating transformer-based encoders with efficient UNet topologies. This hybrid methodology emphasizes the capabilities of transformers in the field of medical image processing and establishes a new standard for accuracy and efficiency in activities related to tumor segmentation. Full article

(This article belongs to the Special Issue Applications of Large Language Models in Medical and Biomedical Data Processing)

► Show Figures

Figure 1

15 pages, 1822 KiB

Open AccessArticle

Improvement in Image Quality of Low-Dose CT of Canines with Generative Adversarial Network of Anti-Aliasing Generator and Multi-Scale Discriminator

by Yuseong Son, Sihyeon Jeong, Youngtaek Hong, Jina Lee, Byunghwan Jeon, Hyunji Choi, Jaehwan Kim and Hackjoon Shim

Bioengineering 2024, 11(9), 944; https://doi.org/10.3390/bioengineering11090944 - 20 Sep 2024

Abstract

Computed tomography (CT) imaging is vital for diagnosing and monitoring diseases in both humans and animals, yet radiation exposure remains a significant concern, especially in animal imaging. Low-dose CT (LDCT) minimizes radiation exposure but often compromises image quality due to a reduced signal-to-noise [...] Read more.

Computed tomography (CT) imaging is vital for diagnosing and monitoring diseases in both humans and animals, yet radiation exposure remains a significant concern, especially in animal imaging. Low-dose CT (LDCT) minimizes radiation exposure but often compromises image quality due to a reduced signal-to-noise ratio (SNR). Recent advancements in deep learning, particularly with CycleGAN, offer promising solutions for denoising LDCT images, though challenges in preserving anatomical detail and image sharpness persist. This study introduces a novel framework tailored for animal LDCT imaging, integrating deep learning techniques within the CycleGAN architecture. Key components include BlurPool for mitigating high-resolution image distortion, PixelShuffle for enhancing expressiveness, hierarchical feature synthesis (HFS) networks for feature retention, and spatial channel squeeze excitation (scSE) blocks for contrast reproduction. Additionally, a multi-scale discriminator enhances detail assessment, supporting effective adversarial learning. Rigorous experimentation on veterinary CT images demonstrates our framework’s superiority over traditional denoising methods, achieving significant improvements in noise reduction, contrast enhancement, and anatomical structure preservation. Extensive evaluations show that our method achieves a precision of 0.93 and a recall of 0.94. This validates our approach’s efficacy, highlighting its potential to enhance diagnostic accuracy in veterinary imaging. We confirm the scSE method’s critical role in optimizing performance, and robustness to input variations underscores its practical utility. Full article

(This article belongs to the Special Issue Applications of Computational Modeling in Biomedical Image and Signal Processing)

► Show Figures

Graphical abstract

15 pages, 1570 KiB

Open AccessArticle

Machine Learning-Driven Prediction of Brain Age for Alzheimer’s Risk: APOE4 Genotype and Gender Effects

by Carter Woods, Xin Xing, Subash Khanal and Ai-Ling Lin

Bioengineering 2024, 11(9), 943; https://doi.org/10.3390/bioengineering11090943 - 20 Sep 2024

Abstract

Background: Alzheimer’s disease (AD) is a leading cause of dementia, and it is significantly influenced by the apolipoprotein E4 (APOE4) gene and gender. This study aimed to use machine learning (ML) algorithms to predict brain age and assess AD risk by considering the [...] Read more.

Background: Alzheimer’s disease (AD) is a leading cause of dementia, and it is significantly influenced by the apolipoprotein E4 (APOE4) gene and gender. This study aimed to use machine learning (ML) algorithms to predict brain age and assess AD risk by considering the effects of the APOE4 genotype and gender. Methods: We collected brain volumetric MRI data and medical records from 1100 cognitively unimpaired individuals and 602 patients with AD. We applied three ML regression models—XGBoost, random forest (RF), and linear regression (LR)—to predict brain age. Additionally, we introduced two novel metrics, brain age difference (BAD) and integrated difference (ID), to evaluate the models’ performances and analyze the influences of the APOE4 genotype and gender on brain aging. Results: Patients with AD displayed significantly older brain ages compared to their chronological ages, with BADs ranging from 6.5 to 10 years. The RF model outperformed both XGBoost and LR in terms of accuracy, delivering higher ID values and more precise predictions. Comparing the APOE4 carriers with noncarriers, the models showed enhanced ID values and consistent brain age predictions, improving the overall performance. Gender-specific analyses indicated slight enhancements, with the models performing equally well for both genders. Conclusions: This study demonstrates that robust ML models for brain age prediction can play a crucial role in the early detection of AD risk through MRI brain structural imaging. The significant impact of the APOE4 genotype on brain aging and AD risk is also emphasized. These findings highlight the potential of ML models in assessing AD risk and suggest that utilizing AI for AD identification could enable earlier preventative interventions. Full article

(This article belongs to the Special Issue Recent Advances in Biomedical Imaging: 2nd Edition)

► Show Figures

Graphical abstract

19 pages, 2463 KiB

Open AccessArticle

AI-Powered Telemedicine for Automatic Scoring of Neuromuscular Examinations

by Quentin Lesport, Davis Palmie, Gülşen Öztosun, Henry J. Kaminski and Marc Garbey

Bioengineering 2024, 11(9), 942; https://doi.org/10.3390/bioengineering11090942 - 20 Sep 2024

Abstract

Telemedicine is now being used more frequently to evaluate patients with myasthenia gravis (MG). Assessing this condition involves clinical outcome measures, such as the standardized MG-ADL scale or the more complex MG-CE score obtained during clinical exams. However, human subjectivity limits the reliability [...] Read more.

Telemedicine is now being used more frequently to evaluate patients with myasthenia gravis (MG). Assessing this condition involves clinical outcome measures, such as the standardized MG-ADL scale or the more complex MG-CE score obtained during clinical exams. However, human subjectivity limits the reliability of these examinations. We propose a set of AI-powered digital tools to improve scoring efficiency and quality using computer vision, deep learning, and natural language processing. This paper focuses on automating a standard telemedicine video by segmenting it into clips corresponding to the MG-CE assessment. This AI-powered solution offers a quantitative assessment of neurological deficits, improving upon subjective evaluations prone to examiner variability. It has the potential to enhance efficiency, patient participation in MG clinical trials, and broader applicability to various neurological diseases. Full article

(This article belongs to the Special Issue Artificial Intelligence in Medical Image Processing and Segmentation, 2nd Edition)

► Show Figures

Figure 1

21 pages, 11958 KiB

Open AccessArticle

Deep Learning-Based Fine-Tuning Approach of Coarse Registration for Ear–Nose–Throat (ENT) Surgical Navigation Systems

by Dongjun Lee, Ahnryul Choi and Joung Hwan Mun

Bioengineering 2024, 11(9), 941; https://doi.org/10.3390/bioengineering11090941 - 20 Sep 2024

Abstract

Accurate registration between medical images and patient anatomy is crucial for surgical navigation systems in minimally invasive surgeries. This study introduces a novel deep learning-based refinement step to enhance the accuracy of surface registration without disrupting established workflows. The proposed method integrates a [...] Read more.

Accurate registration between medical images and patient anatomy is crucial for surgical navigation systems in minimally invasive surgeries. This study introduces a novel deep learning-based refinement step to enhance the accuracy of surface registration without disrupting established workflows. The proposed method integrates a machine learning model between conventional coarse registration and ICP fine registration. A deep-learning model was trained using simulated anatomical landmarks with introduced localization errors. The model architecture features global feature-based learning, an iterative prediction structure, and independent processing of rotational and translational components. Validation with silicon-masked head phantoms and CT imaging compared the proposed method to both conventional registration and a recent deep-learning approach. The results demonstrated significant improvements in target registration error (TRE) across different facial regions and depths. The average TRE for the proposed method (1.58 ± 0.52 mm) was significantly lower than that of the conventional (2.37 ± 1.14 mm) and previous deep-learning (2.29 ± 0.95 mm) approaches (p < 0.01). The method showed a consistent performance across various facial regions and enhanced registration accuracy for deeper areas. This advancement could significantly enhance precision and safety in minimally invasive surgical procedures. Full article

(This article belongs to the Special Issue Optical Imaging for Biomedical Applications)

► Show Figures

Graphical abstract

12 pages, 5572 KiB

Open AccessArticle

Segment Anything in Optical Coherence Tomography: SAM 2 for Volumetric Segmentation of Retinal Biomarkers

by Mikhail Kulyabin, Aleksei Zhdanov, Andrey Pershin, Gleb Sokolov, Anastasia Nikiforova, Mikhail Ronkin, Vasilii Borisov and Andreas Maier

Bioengineering 2024, 11(9), 940; https://doi.org/10.3390/bioengineering11090940 - 19 Sep 2024

Abstract

Optical coherence tomography (OCT) is a non-invasive imaging technique widely used in ophthalmology for visualizing retinal layers, aiding in the early detection and monitoring of retinal diseases. OCT is useful for detecting diseases such as age-related macular degeneration (AMD) and diabetic macular edema [...] Read more.

Optical coherence tomography (OCT) is a non-invasive imaging technique widely used in ophthalmology for visualizing retinal layers, aiding in the early detection and monitoring of retinal diseases. OCT is useful for detecting diseases such as age-related macular degeneration (AMD) and diabetic macular edema (DME), which affect millions of people globally. Over the past decade, the area of application of artificial intelligence (AI), particularly deep learning (DL), has significantly increased. The number of medical applications is also rising, with solutions from other domains being increasingly applied to OCT. The segmentation of biomarkers is an essential problem that can enhance the quality of retinal disease diagnostics. For 3D OCT scans, AI is beneficial since manual segmentation is very labor-intensive. In this paper, we employ the new SAM 2 and MedSAM 2 for the segmentation of OCT volumes for two open-source datasets, comparing their performance with the traditional U-Net. The model achieved an overall Dice score of 0.913 and 0.902 for macular holes (MH) and intraretinal cysts (IRC) on OIMHS and 0.888 and 0.909 for intraretinal fluid (IRF) and pigment epithelial detachment (PED) on the AROI dataset, respectively. Full article

(This article belongs to the Special Issue AI in OCT (Optical Coherence Tomography) Image Analysis)

► Show Figures

Figure 1

11 pages, 1116 KiB

Open AccessArticle

Visual Outcomes and Patient Satisfaction of Enhanced Monofocal Intraocular Lens in Phacovitrectomy for Idiopathic Epiretinal Membrane

by Ji Youn Choi, Yeo Kyoung Won, Soo Jin Lee, Se Woong Kang and Dong Hui Lim

Bioengineering 2024, 11(9), 939; https://doi.org/10.3390/bioengineering11090939 - 19 Sep 2024

Abstract

Background: To evaluate the clinical outcomes and patient satisfaction after implantation of an enhanced monofocal intraocular lens (TECNIS Eyhance ICB00) in patients with idiopathic epiretinal membrane (ERM) who underwent cataract surgery with pars plana vitrectomy (PPV). Methods: This is a single-center, retrospective, comparative [...] Read more.

Background: To evaluate the clinical outcomes and patient satisfaction after implantation of an enhanced monofocal intraocular lens (TECNIS Eyhance ICB00) in patients with idiopathic epiretinal membrane (ERM) who underwent cataract surgery with pars plana vitrectomy (PPV). Methods: This is a single-center, retrospective, comparative study. In total, 61 eyes of 61 patients with idiopathic ERM and cataracts were included. We measured the uncorrected near and intermediate visual acuity (UNVA and UIVA), uncorrected and corrected distance visual acuity (UDVA and CDVA), central macular thickness, defocus curves, and contrast sensitivity 3–6 months after the surgery. Overall patient satisfaction was assessed using a questionnaire at the 1-month follow-up visit. Results: The ICB00 group showed better near and intermediate visual acuity than the monofocal group (TECNIS ZCB00); however, no statistically significant differences were found between the groups. The ICB00 group exhibited wider defocus curves at near to far distances (−3.0 to +2.0 D) than the ZCB00 group. There were no significant differences in the results of the contrast sensitivity test, dysphotopsia, spectacle dependence, or patient satisfaction between the two groups. Conclusions: In combined PPV and cataract surgery for ERM patients, ICB00 resulted in good visual acuity with a smoother defocus curve compared to the ZCB00 group. Full article

(This article belongs to the Special Issue Recent Advances and Trends in Ophthalmic Diseases Treatment)

► Show Figures

Graphical abstract

11 pages, 2497 KiB

Open AccessArticle

Patient-Reported Outcome Measures and Biomechanical Variables That May Be Related to Knee Functions Following Total Knee Arthroplasty

by Hannah Seymour, Fangjian Chen and Naiquan (Nigel) Zheng

Bioengineering 2024, 11(9), 938; https://doi.org/10.3390/bioengineering11090938 - 19 Sep 2024

Abstract

Total knee arthroplasty (TKA) is a commonly performed surgery aimed at alleviating pain and improving functionality. However, patients often face uncertainties in selecting the timing, location, and type of TKA implant that best meets their needs. This study aims to comprehensively compare various [...] Read more.

Total knee arthroplasty (TKA) is a commonly performed surgery aimed at alleviating pain and improving functionality. However, patients often face uncertainties in selecting the timing, location, and type of TKA implant that best meets their needs. This study aims to comprehensively compare various variables, explore trends, and identify factors potentially influencing TKA outcomes. A cohort of 40 TKA subjects received either unilateral posterior stabilized (Persona) TKA or bi-cruciate stabilized (Journey II) TKA. Additionally, 20 healthy controls matched for age, gender, and BMI were included. Participants underwent patient-reported outcome assessments, range of motion evaluations, balance assessments, proprioception tests, and biomechanical analyses. These analyses covered motion, loading, and electromyography during five daily activities and two clinical tests. Multifactor ANOVA was utilized to compare 283 variables and assess their impact on TKA outcomes. A knee biomechanics index was formulated to evaluate deviations from healthy norms. Significant differences were observed in EMG varus/valgus rotation during both ramp-up and ramp-down phases between the two implant groups. Although significant improvements were noted post-TKA for both implants, the results remained below those of the control group. Gender, age, and BMI exhibited noticeable effects on TKA outcomes across several biomechanical variables and demonstrated significant disparities compared to the controls. Full article

(This article belongs to the Section Biomedical Engineering and Biomaterials)

► Show Figures

Figure 1

37 pages, 3190 KiB

Open AccessReview

Toward Digital Periodontal Health: Recent Advances and Future Perspectives

by Fatemeh Soheili, Niloufar Delfan, Negin Masoudifar, Shahin Ebrahimni, Behzad Moshiri, Michael Glogauer and Ebrahim Ghafar-Zadeh

Bioengineering 2024, 11(9), 937; https://doi.org/10.3390/bioengineering11090937 - 18 Sep 2024

Abstract

Periodontal diseases, ranging from gingivitis to periodontitis, are prevalent oral diseases affecting over 50% of the global population. These diseases arise from infections and inflammation of the gums and supporting bones, significantly impacting oral health. The established link between periodontal diseases and systemic [...] Read more.

Periodontal diseases, ranging from gingivitis to periodontitis, are prevalent oral diseases affecting over 50% of the global population. These diseases arise from infections and inflammation of the gums and supporting bones, significantly impacting oral health. The established link between periodontal diseases and systemic diseases, such as cardiovascular diseases, underscores their importance as a public health concern. Consequently, the early detection and prevention of periodontal diseases have become critical objectives in healthcare, particularly through the integration of advanced artificial intelligence (AI) technologies. This paper aims to bridge the gap between clinical practices and cutting-edge technologies by providing a comprehensive review of current research. We examine the identification of causative factors, disease progression, and the role of AI in enhancing early detection and treatment. Our goal is to underscore the importance of early intervention in improving patient outcomes and to stimulate further interest among researchers, bioengineers, and AI specialists in the ongoing exploration of AI applications in periodontal disease diagnosis. Full article

► Show Figures

Figure 1

20 pages, 284 KiB

Open AccessReview

The Use of Artificial Intelligence in Caries Detection: A Review

by Khalifa S. Al-Khalifa, Walaa Magdy Ahmed, Amr Ahmed Azhari, Masoumah Qaw, Rasha Alsheikh, Fatema Alqudaihi and Amal Alfaraj

Bioengineering 2024, 11(9), 936; https://doi.org/10.3390/bioengineering11090936 - 18 Sep 2024

Abstract

Advancements in artificial intelligence (AI) have significantly impacted the field of dentistry, particularly in diagnostic imaging for caries detection. This review critically examines the current state of AI applications in caries detection, focusing on the performance and accuracy of various AI techniques. We [...] Read more.

Advancements in artificial intelligence (AI) have significantly impacted the field of dentistry, particularly in diagnostic imaging for caries detection. This review critically examines the current state of AI applications in caries detection, focusing on the performance and accuracy of various AI techniques. We evaluated 40 studies from the past 23 years, carefully selected for their relevance and quality. Our analysis highlights the potential of AI, especially convolutional neural networks (CNNs), to improve diagnostic accuracy and efficiency in detecting dental caries. The findings underscore the transformative potential of AI in clinical dental practice. Full article

(This article belongs to the Section Biosignal Processing)

21 pages, 2810 KiB

Open AccessArticle

Pretreatment of Vine Shoot Biomass by Choline Chloride-Based Deep Eutectic Solvents to Promote Biomass Fractionation and Enhance Sugar Production

by Raquel Cañadas, Aleta Duque, Alberto Bahíllo, Raquel Iglesias and Paloma Manzanares

Bioengineering 2024, 11(9), 935; https://doi.org/10.3390/bioengineering11090935 - 18 Sep 2024

Abstract

Vine shoots hold promise as a biomass source for fermentable sugars with efficient fractionation and conversion processes. The study explores vine shoots as a biomass source for fermentable sugars through pretreatment with two deep eutectic solvents mixtures: choline chloride:lactic acid 1:5 (ChCl:LA) and [...] Read more.

Vine shoots hold promise as a biomass source for fermentable sugars with efficient fractionation and conversion processes. The study explores vine shoots as a biomass source for fermentable sugars through pretreatment with two deep eutectic solvents mixtures: choline chloride:lactic acid 1:5 (ChCl:LA) and choline chloride:ethylene glycol 1:2 (ChCl:EG). Pretreatment conditions, such as temperature/time, solid/liquid ratio, and biomass particle size, were studied. Chemical composition, recovery yields, delignification extent, and carbohydrate conversion were evaluated, including the influence of washing solvents. Temperature and particle size notably affected hemicellulose and lignin dissolution, especially with ChCl:LA. Pretreatment yielded enriched cellulose substrates, with high carbohydrate conversion rates up to 75.2% for cellulose and 99.9% for xylan with ChCl:LA, and 54.6% for cellulose and 60.2% for xylan with ChCl:EG. A 50% acetone/water mixture increased the delignification ratios to 31.5%. The results underscore the potential of this pretreatment for vine shoot fractionation, particularly at 30% solid load, while acknowledging the need for further process enhancement. Full article

(This article belongs to the Special Issue From Residues to Bio-Based Products through Bioprocess Engineering)

► Show Figures

Graphical abstract

18 pages, 14036 KiB

Open AccessArticle

Tailoring Plasmonic Nanoheaters Size for Enhanced Theranostic Agent Performance

by Túlio de L. Pedrosa, Gabrielli M. F. de Oliveira, Arthur C. M. V. Pereira, Mariana J. B. da S. Crispim, Luzia A. da Silva, Marcilene S. da Silva, Ivone A. de Souza, Ana M. M. de A. Melo, Anderson S. L. Gomes and Renato E. de Araujo

Bioengineering 2024, 11(9), 934; https://doi.org/10.3390/bioengineering11090934 - 18 Sep 2024

Abstract

The introduction of optimized nanoheaters, which function as theranostic agents integrating both diagnostic and therapeutic processes, holds significant promise in the medical field. Therefore, developing strategies for selecting and utilizing optimized plasmonic nanoheaters is crucial for the effective use of nanostructured biomedical agents. [...] Read more.

The introduction of optimized nanoheaters, which function as theranostic agents integrating both diagnostic and therapeutic processes, holds significant promise in the medical field. Therefore, developing strategies for selecting and utilizing optimized plasmonic nanoheaters is crucial for the effective use of nanostructured biomedical agents. This work elucidates the use of the Joule number (

J_{o}

) as a figure of merit to identify high-performance plasmonic theranostic agents. A framework for optimizing metallic nanoparticles for heat generation was established, uncovering the size dependence of plasmonic nanoparticles optical heating. Gold nanospheres (AuNSs) with a diameter of 50 nm and gold nanorods (AuNRs) with dimensions of

41 \times 10

nm were identified as effective nanoheaters for visible (530 nm) and infrared (808 nm) excitation. Notably, AuNRs achieve higher

J_{o}

values than AuNSs, even when accounting for the possible orientations of the nanorods. Theoretical results estimate that

41 \times 10

nm gold nanorods have an average Joule number of 80, which is significantly higher compared to larger rods. The photothermal performance of optimal and suboptimal nanostructures was evaluated using photoacoustic imaging and photothermal therapy procedures. The photoacoustic images indicate that, despite having larger absorption cross-sections, the large nanoparticle volume of bigger particles leads to less efficient conversion of light into heat, which suggests that the use of optimized nanoparticles promotes higher contrast, benefiting photoacoustic-based procedures in diagnostic applications. The photothermal therapy procedure was performed on S180-bearing mice inoculated with

41 \times 10

nm and

90 \times 25

nm PEGylated AuNRs. Five minutes of laser irradiation of tumor tissue with

41 \times 10

nm produced an approximately 9.5% greater temperature rise than using

90 \times 25

AuNRs in the therapy trials. Optimizing metallic nanoparticles for heat generation may reduce the concentration of the nanoheaters used or decrease the light fluence for bioscience applications, paving the way for the development of more economical theranostic agents. Full article

(This article belongs to the Special Issue Recent Advances in Optical Imaging and Machine Learning in Biomedicine)

► Show Figures

Figure 1

30 pages, 808 KiB

Open AccessReview

Artifact Management for Cerebral Near-Infrared Spectroscopy Signals: A Systematic Scoping Review

by Tobias Bergmann, Nuray Vakitbilir, Alwyn Gomez, Abrar Islam, Kevin Y. Stein, Amanjyot Singh Sainbhi, Logan Froese and Frederick A. Zeiler

Bioengineering 2024, 11(9), 933; https://doi.org/10.3390/bioengineering11090933 - 18 Sep 2024

Abstract

Artifacts induced during patient monitoring are a main limitation for near-infrared spectroscopy (NIRS) as a non-invasive method of cerebral hemodynamic monitoring. There currently does not exist a robust “gold-standard” method for artifact management for these signals. The objective of this review is to [...] Read more.

Artifacts induced during patient monitoring are a main limitation for near-infrared spectroscopy (NIRS) as a non-invasive method of cerebral hemodynamic monitoring. There currently does not exist a robust “gold-standard” method for artifact management for these signals. The objective of this review is to comprehensively examine the literature on existing artifact management methods for cerebral NIRS signals recorded in animals and humans. A search of five databases was conducted based on the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. The search yielded 806 unique results. There were 19 articles from these results that were included in this review based on the inclusion/exclusion criteria. There were an additional 36 articles identified in the references of select articles that were also included. The methods outlined in these articles were grouped under two major categories: (1) motion and other disconnection artifact removal methods; (2) data quality improvement and physiological/other noise artifact filtering methods. These were sub-categorized by method type. It proved difficult to quantitatively compare the methods due to the heterogeneity of the effectiveness metrics and definitions of artifacts. The limitations evident in the existing literature justify the need for more comprehensive comparisons of artifact management. This review provides insights into the available methods for artifact management in cerebral NIRS and justification for a homogenous method to quantify the effectiveness of artifact management methods. This builds upon the work of two existing reviews that have been conducted on this topic; however, the scope is extended to all artifact types and all NIRS recording types. Future work by our lab in cerebral NIRS artifact management will lie in a layered artifact management method that will employ different techniques covered in this review (including dynamic thresholding, autoregressive-based methods, and wavelet-based methods) amongst others to remove varying artifact types. Full article

(This article belongs to the Section Biosignal Processing)

► Show Figures

Figure 1

26 pages, 2887 KiB

Open AccessArticle

Implicit Is Not Enough: Explicitly Enforcing Anatomical Priors inside Landmark Localization Models

by Simon Johannes Joham, Arnela Hadzic and Martin Urschler

Bioengineering 2024, 11(9), 932; https://doi.org/10.3390/bioengineering11090932 - 17 Sep 2024

Abstract

The task of localizing distinct anatomical structures in medical image data is an essential prerequisite for several medical applications, such as treatment planning in orthodontics, bone-age estimation, or initialization of segmentation methods in automated image analysis tools. Currently, Anatomical Landmark Localization (ALL) is [...] Read more.

The task of localizing distinct anatomical structures in medical image data is an essential prerequisite for several medical applications, such as treatment planning in orthodontics, bone-age estimation, or initialization of segmentation methods in automated image analysis tools. Currently, Anatomical Landmark Localization (ALL) is mainly solved by deep-learning methods, which cannot guarantee robust ALL predictions; there may always be outlier predictions that are far from their ground truth locations due to out-of-distribution inputs. However, these localization outliers are detrimental to the performance of subsequent medical applications that rely on ALL results. The current ALL literature relies heavily on implicit anatomical constraints built into the loss function and network architecture to reduce the risk of anatomically infeasible predictions. However, we argue that in medical imaging, where images are generally acquired in a controlled environment, we should use stronger explicit anatomical constraints to reduce the number of outliers as much as possible. Therefore, we propose the end-to-end trainable Global Anatomical Feasibility Filter and Analysis (GAFFA) method, which uses prior anatomical knowledge estimated from data to explicitly enforce anatomical constraints. GAFFA refines the initial localization results of a U-Net by approximately solving a Markov Random Field (MRF) with a single iteration of the sum-product algorithm in a differentiable manner. Our experiments demonstrate that GAFFA outperforms all other landmark refinement methods investigated in our framework. Moreover, we show that GAFFA is more robust to large outliers than state-of-the-art methods on the studied X-ray hand dataset. We further motivate this claim by visualizing the anatomical constraints used in GAFFA as spatial energy heatmaps, which allowed us to find an annotation error in the hand dataset not previously discussed in the literature. Full article

(This article belongs to the Special Issue Machine Learning-Aided Medical Image Analysis)

► Show Figures

Graphical abstract

20 pages, 4007 KiB

Open AccessArticle

Encapsulation of Inositol Hexakisphosphate with Chitosan via Gelation to Facilitate Cellular Delivery and Programmed Cell Death in Human Breast Cancer Cells

by Ilham H. Kadhim, Adeolu S. Oluremi, Bijay P. Chhetri, Anindya Ghosh and Nawab Ali

Bioengineering 2024, 11(9), 931; https://doi.org/10.3390/bioengineering11090931 - 17 Sep 2024

Abstract

Inositol hexakisphosphate (InsP₆) is the most abundant inositol polyphosphate both in plant and animal cells. Exogenous InsP₆ is known to inhibit cell proliferation and induce apoptosis in cancerous cells. However, cellular entry of exogenous InsP₆ is hindered due to [...] Read more.

Inositol hexakisphosphate (InsP₆) is the most abundant inositol polyphosphate both in plant and animal cells. Exogenous InsP₆ is known to inhibit cell proliferation and induce apoptosis in cancerous cells. However, cellular entry of exogenous InsP₆ is hindered due to the presence of highly negative charge on this molecule. Therefore, to enhance the cellular delivery of InsP₆ in cancerous cells, InsP₆ was encapsulated by chitosan (CS), a natural polysaccharide, via the ionic gelation method. Our hypothesis is that encapsulated InsP₆ will enter the cell more efficiently to trigger its apoptotic effects. The incorporation of InsP₆ into CS was optimized by varying the ratios of the two and confirmed by InsP₆ analysis via polyacrylamide gel electrophoresis (PAGE) and atomic absorption spectrophotometry (AAS). The complex was further characterized by Scanning Electron Microscopy (SEM) and Fourier Transform Infrared Spectroscopy (FTIR) for physicochemical changes. The data indicated morphological changes and changes in the spectral properties of the complex upon encapsulation. The encapsulated InsP₆ enters human breast cancer MCF-7 cells more efficiently than free InsP₆ and triggers apoptosis via a mechanism involving the production of reactive oxygen species (ROS). This work has potential for developing cancer therapeutic applications utilizing natural compounds that are likely to overcome the severe toxic effects associated with synthetic chemotherapeutic drugs. Full article

(This article belongs to the Special Issue Advances in Hydrogels for Tissue Engineering Applications)

► Show Figures

Graphical abstract

21 pages, 2548 KiB

Open AccessArticle

ABNet: AI-Empowered Abnormal Action Recognition Method for Laboratory Mouse Behavior

by Yuming Chen, Chaopeng Guo, Yue Han, Shuang Hao and Jie Song

Bioengineering 2024, 11(9), 930; https://doi.org/10.3390/bioengineering11090930 - 17 Sep 2024

Abstract

The automatic recognition and quantitative analysis of abnormal behavior in mice play a crucial role in behavioral observation experiments in neuroscience, pharmacology, and toxicology. Due to the challenging definition of abnormal behavior and difficulty in collecting training samples, directly applying behavior recognition methods [...] Read more.

The automatic recognition and quantitative analysis of abnormal behavior in mice play a crucial role in behavioral observation experiments in neuroscience, pharmacology, and toxicology. Due to the challenging definition of abnormal behavior and difficulty in collecting training samples, directly applying behavior recognition methods to identify abnormal behavior is often infeasible. This paper proposes ABNet, an AI-empowered abnormal action recognition approach for mice. ABNet utilizes an enhanced Spatio-Temporal Graph Convolutional Network (ST-GCN) as an encoder; ST-GCN combines graph convolution and temporal convolution to efficiently capture and analyze spatio-temporal dynamic features in graph-structured data, making it suitable for complex tasks such as action recognition and traffic prediction. ABNet trains the encoding network with normal behavior samples, then employs unsupervised clustering to identify abnormal behavior in mice. Compared to the original ST-GCN network, the method significantly enhances the capabilities of feature extraction and encoding. We conduct comprehensive experiments on the Kinetics-Skeleton dataset and the mouse behavior dataset to evaluate and validate the performance of ABNet in behavior recognition and abnormal motion detection. In the behavior recognition experiments conducted on the Kinetics-Skeleton dataset, ABNet achieves an accuracy of 32.7% for the top one and 55.2% for the top five. Moreover, in the abnormal behavior analysis experiments conducted on the mouse behavior dataset, ABNet achieves an average accuracy of 83.1%. Full article

(This article belongs to the Special Issue New Insights into Machine Learning and Biomedicine: Updates and Directions)

► Show Figures

Figure 1

10 pages, 8551 KiB

Open AccessArticle

Manufacturing Process Affects Coagulation Kinetics of Ortho-R, an Injectable Chitosan–Platelet-Rich Plasma Biomaterial for Tissue Repair

by Anik Chevrier and Marc Lavertu

Bioengineering 2024, 11(9), 929; https://doi.org/10.3390/bioengineering11090929 - 17 Sep 2024

Abstract

Ortho-R (ChitogenX Inc., Kirkland, QC, Canada) is an injectable combination drug–biologic product that is used as an adjunct to augment the standard of care for the surgical repair of soft tissues. The drug product comprises lyophilized chitosan, trehalose and calcium chloride, and it [...] Read more.

Ortho-R (ChitogenX Inc., Kirkland, QC, Canada) is an injectable combination drug–biologic product that is used as an adjunct to augment the standard of care for the surgical repair of soft tissues. The drug product comprises lyophilized chitosan, trehalose and calcium chloride, and it is dissolved in platelet-rich plasma (PRP), a blood-derived biologic, prior to injection at the surgical site where it will coagulate. The first step of the Ortho-R manufacturing process involves dissolving the chitosan in hydrochloric acid. The purpose of this study was to investigate the effect of increasing the amount of acid used to dissolve the chitosan on final drug product performance, more specifically, on the chitosan–PRP coagulation kinetics. Chitosans were solubilized in hydrochloric acid, with concentrations adjusted to obtain between 60% and 95% protonation of the chitosan amino groups. Freeze-dried Ortho-R was solubilized with PRP, and coagulation was assessed using thromboelastography (TEG). The clotted mixtures were observed with histology. Clot reaction time (TEG R) increased and clot maximal amplitude (TEG MA) decreased with protonation levels as pH decreased. Chitosan distribution was homogeneous in chitosan–PRP clots at the lowest protonation levels, but it accumulated toward the surface of the clots at the highest protonation levels as pH decreased. These changes in coagulation kinetics, clot strength and chitosan distribution induced by high protonation of the chitosan amino groups were partially reversed by adding sodium hydroxide to the dissolved chitosan component in order to decrease pH. Careful control of manufacturing processes is critical, and it is important to consider the impact of each manufacturing step on product performance. Full article

(This article belongs to the Special Issue Exploring the Versatility of Biopolymer Chitin and Chitosan)

► Show Figures

Figure 1

10 pages, 2484 KiB

Open AccessArticle

Thermal Evaluation of Bone Drilling: Assessing Drill Bits and Sequential Drilling

by Sihana Rugova and Marcus Abboud

Bioengineering 2024, 11(9), 928; https://doi.org/10.3390/bioengineering11090928 - 16 Sep 2024

Abstract

Sequential drilling is a common practice in dental implant surgery aimed at minimizing thermal damage to bone. This study evaluates the thermal effects of sequential drilling and assesses modifications to drilling protocols to manage heat generation. We utilized a custom drill press and [...] Read more.

Sequential drilling is a common practice in dental implant surgery aimed at minimizing thermal damage to bone. This study evaluates the thermal effects of sequential drilling and assesses modifications to drilling protocols to manage heat generation. We utilized a custom drill press and artificial bone models to test five drill bits under various protocols, including sequential drilling with different loads, spindle speeds, and peck drilling. Infrared thermography recorded temperature changes during the drilling process, with temperatures monitored at various depths around the osteotomy. The results reveal sequential drilling does not eliminate the thermal damage zone it creates (well over 70 °C). It creates harmful heat to surrounding bone that can spread up to 10 mm from the osteotomy. The first drill used in sequential drilling produces the highest temperatures (over 100 °C), and subsequent drill bits cannot remove the thermal trauma incurred; rather, they add to it. Modifying drill bit design and employing proper drilling techniques, such as reducing drilling RPM and load, can reduce thermal trauma by reducing friction. Inadequate management of heat can lead to prolonged recovery, increased patient discomfort, and potential long-term complications such as impaired bone-to-implant integration and chronic conditions like peri-implantitis. Ensuring healthy bone conditions is critical for successful implant outcomes. Full article

(This article belongs to the Special Issue Advanced Assessment of Medical Devices)

► Show Figures

Figure 1

13 pages, 3844 KiB

Open AccessArticle

Machine Learning Algorithm for Predicting Distant Metastasis of T1 and T2 Gallbladder Cancer Based on SEER Database

by Zhentian Guo, Zongming Zhang, Limin Liu, Yue Zhao, Zhuo Liu, Chong Zhang, Hui Qi, Jinqiu Feng, Peijie Yao and Haiming Yuan

Bioengineering 2024, 11(9), 927; https://doi.org/10.3390/bioengineering11090927 - 15 Sep 2024

Abstract

(1) Background: This study seeks to employ a machine learning (ML) algorithm to forecast the risk of distant metastasis (DM) in patients with T1 and T2 gallbladder cancer (GBC); (2) Methods: Data of patients diagnosed with T1 and T2 GBC was obtained from [...] Read more.

(1) Background: This study seeks to employ a machine learning (ML) algorithm to forecast the risk of distant metastasis (DM) in patients with T1 and T2 gallbladder cancer (GBC); (2) Methods: Data of patients diagnosed with T1 and T2 GBC was obtained from SEER, encompassing the period from 2004 to 2015, were utilized to apply seven ML algorithms. These algorithms were appraised by the area under the receiver operating characteristic curve (AUC) and other metrics; (3) Results: This study involved 4371 patients in total. Out of these patients, 764 (17.4%) cases progressed to develop DM. Utilizing a logistic regression (LR) model to identify independent risk factors for DM of gallbladder cancer (GBC). A nomogram has been developed to forecast DM in early T-stage gallbladder cancer patients. Through the evaluation of different models using relevant indicators, it was discovered that Random Forest (RF) exhibited the most outstanding predictive performance; (4) Conclusions: RF has demonstrated high accuracy in predicting DM in gallbladder cancer patients, assisting clinical physicians in enhancing the accuracy of diagnosis. This can be particularly valuable for improving patient outcomes and optimizing treatment strategies. We employ the RF algorithm to construct the corresponding web calculator. Full article

(This article belongs to the Section Biosignal Processing)

► Show Figures

Graphical abstract

18 pages, 3786 KiB

Open AccessArticle

Efficient Multi-View Graph Convolutional Network with Self-Attention for Multi-Class Motor Imagery Decoding

by Xiyue Tan, Dan Wang, Meng Xu, Jiaming Chen and Shuhan Wu

Bioengineering 2024, 11(9), 926; https://doi.org/10.3390/bioengineering11090926 - 15 Sep 2024

Abstract

Research on electroencephalogram-based motor imagery (MI-EEG) can identify the limbs of subjects that generate motor imagination by decoding EEG signals, which is an important issue in the field of brain–computer interface (BCI). Existing deep-learning-based classification methods have not been able to entirely employ [...] Read more.

Research on electroencephalogram-based motor imagery (MI-EEG) can identify the limbs of subjects that generate motor imagination by decoding EEG signals, which is an important issue in the field of brain–computer interface (BCI). Existing deep-learning-based classification methods have not been able to entirely employ the topological information among brain regions, and thus, the classification performance needs further improving. In this paper, we propose a multi-view graph convolutional attention network (MGCANet) with residual learning structure for multi-class MI decoding. Specifically, we design a multi-view graph convolution spatial feature extraction method based on the topological relationship of brain regions to achieve more comprehensive information aggregation. During the modeling, we build an adaptive weight fusion (Awf) module to adaptively merge feature from different brain views to improve classification accuracy. In addition, the self-attention mechanism is introduced for feature selection to expand the receptive field of EEG signals to global dependence and enhance the expression of important features. The proposed model is experimentally evaluated on two public MI datasets and achieved a mean accuracy of 78.26% (BCIC IV 2a dataset) and 73.68% (OpenBMI dataset), which significantly outperforms representative comparative methods in classification accuracy. Comprehensive experiment results verify the effectiveness of our proposed method, which can provide novel perspectives for MI decoding. Full article

(This article belongs to the Section Biosignal Processing)

► Show Figures

Figure 1

5 pages, 154 KiB

Open AccessEditorial

Advanced Engineering Technology in Orthopedic Research

by Rongshan Cheng, Huizhi Wang and Cheng-Kung Cheng

Bioengineering 2024, 11(9), 925; https://doi.org/10.3390/bioengineering11090925 - 15 Sep 2024

Abstract

Musculoskeletal injuries are increasing in conjunction with the aging of populations and the rising frequency of exercise [...] Full article

(This article belongs to the Special Issue Advanced Engineering Technology in Orthopaedic Research)

18 pages, 3680 KiB

Open AccessArticle

Innovative PEEK in Dentistry of Enhanced Adhesion and Sustainability through AI-Driven Surface Treatments

by Mattew A. Olawumi, Francis T. Omigbodun, Bankole I. Oladapo, Temitope Olumide Olugbade and David B. Olawade

Bioengineering 2024, 11(9), 924; https://doi.org/10.3390/bioengineering11090924 - 14 Sep 2024

Abstract

This research investigates using Polyether ether ketone (PEEK) in dental prosthetics, focusing on enhancing the mechanical properties, adhesion capabilities, and environmental sustainability through AI-driven data analysis and advanced surface treatments. The objectives include improving PEEK’s adhesion to dental types of cement, assessing its [...] Read more.

This research investigates using Polyether ether ketone (PEEK) in dental prosthetics, focusing on enhancing the mechanical properties, adhesion capabilities, and environmental sustainability through AI-driven data analysis and advanced surface treatments. The objectives include improving PEEK’s adhesion to dental types of cement, assessing its biocompatibility, and evaluating its environmental impact compared to traditional materials. The methodologies employed involve surface treatments such as plasma treatment and chemical etching, mechanical testing under ASTM standards, biocompatibility assessments, and lifecycle analysis. AI models predict and optimize mechanical properties based on extensive data. Significant findings indicate that surface-treated PEEK exhibits superior adhesion properties, maintaining robust mechanical integrity with no cytotoxic effects and supporting its use in direct contact with human tissues. Lifecycle analysis suggests PEEK offers a reduced environmental footprint due to lower energy-intensive production processes and recyclability. AI-driven analysis further enhances the material’s performance prediction and optimization, ensuring better clinical outcomes. The study concludes that with improved surface treatments and AI optimization, PEEK is a promising alternative to conventional dental materials, combining enhanced performance with environmental sustainability, paving the way for broader acceptance in dental applications. Full article

(This article belongs to the Special Issue Advanced Manufacturing and Biomaterials for Tissue Engineering and Regenerative Medicine)

► Show Figures

Figure 1

12 pages, 1292 KiB

Open AccessArticle

Clinical Investigation of Bioelectric Toothbrush for Dentin Hypersensitivity Management: A Randomized Double-Blind Study

by Hyun-Kyung Kang, Yu-Rin Kim, Ji-Young Lee, Da-Jeong Kim and Young-Wook Kim

Bioengineering 2024, 11(9), 923; https://doi.org/10.3390/bioengineering11090923 - 14 Sep 2024

Abstract

Background: The objective of this study was to evaluate how effectively the bioelectric toothbrush can alleviate dentin hypersensitivity (DHS) by using electrostatic forces to remove biofilm from the tooth surface. Methods: This study divided inpatients of a preventative dental clinic between March and [...] Read more.

Background: The objective of this study was to evaluate how effectively the bioelectric toothbrush can alleviate dentin hypersensitivity (DHS) by using electrostatic forces to remove biofilm from the tooth surface. Methods: This study divided inpatients of a preventative dental clinic between March and October 2023 into the following two groups: a bioelectric toothbrush group (BET, n = 25) and a non-bioelectric toothbrush group (NBET, n = 18) as a control group. This was a randomized double-blind, placebo-controlled trial study. A survey, the number of hypersensitive teeth, the O’Leary index, the visual analogue scale (VAS), and the Schiff Cold Air Sensitivity Scale (SCASS) were also investigated. Results: When fluoride toothpaste was applied with a bioelectric toothbrush, the subjects’ VAS and SCASS scores reflecting symptoms of hyperesthesia significantly decreased over time, as did the number of hypersensitive teeth and the O’Leary index. Moreover, the bioelectric toothbrush was confirmed to be effective in removing dental plaque. Conclusions: Dental clinics must actively promote bioelectric toothbrushes and fluoride toothpaste for patients suffering from hyperesthesia and pain. Furthermore, these items can be suggested as preventative oral care products to patients with potential hyperesthesia. Full article

(This article belongs to the Section Biomedical Engineering and Biomaterials)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Bioengineering, Volume 11, Issue 9 (September 2024) – 94 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI