Search Results (1,729)

Background/Objectives: To report the cosmetic, clinical, and visual outcomes of a combined surgical approach for treating a corneal/limbal dermoid using excision and a three-layered amniotic membrane graft with fibrin glue. Methods: An 18-year-old female presented with impaired vision and ocular discomfort caused by a prominent dome-shaped limbal congenital dermoid on the inferotemporal cornea, resulting in a significant aesthetic concern. A full assessment, including refraction, best-corrected visual acuity (BCVA), corneal topography, aberrometry and anterior segment OCT (AS-OCT) was conducted to plan the surgical approach. The dermoid was excised under peribulbar anaesthesia using manual lamellar dissection, followed by the application of 0.02% Mitomycin C and a multilayered amniotic membrane graft with fibrin glue. A bandage contact lens was applied and removed after three weeks, with postoperative treatment including topical antibiotics and steroids. Follow-ups were conducted on day 1, at 1 week, 3 weeks, 2 months, 6 months, 1 year, and 2 years. Results: Histopathological examination confirmed the mesoblastic nature of the lesion. Significant improvements in BCVA and ocular symptoms were observed. Corneal topography showed ocular surface regularization with reduction of high order aberrations and point spread function. AS-OCT showed complete integration of the amniotic membrane, with full epithelial coverage of the defect. The healing process was uneventful and the ocular surface remained stable throughout the entire follow-up, without complications or recurrence. Conclusions: This approach of dermoid excision, multilayered amniotic membrane and fibrin glue restored vision effectively, with notable improvements in ocular surface and cosmetic outcomes, without recurrence over two years. Full article

Due to the labor-intensive manual annotations for nuclei segmentation, point-supervised segmentation based on nuclei coordinate supervision has gained recognition in recent years. Despite great progress, two challenges hinder the performance of weakly supervised nuclei segmentation methods: (1) The stable and effective segmentation of adjacent cell nuclei remains an unresolved challenge. (2) Existing approaches rely solely on initial pseudo-labels generated from point annotations for training, and inaccurate labels may lead the model to assimilate a considerable amount of noise information, thereby diminishing performance. To address these issues, we propose a method based on center-point prediction and pseudo-label updating for precise nuclei segmentation. First, we devise a Gaussian kernel mechanism that employs multi-scale Gaussian masks for multi-branch center-point prediction. The generated center points are utilized by the segmentation module to facilitate the effective separation of adjacent nuclei. Next, we introduce a point-guided attention mechanism that concentrates the segmentation module’s attention around authentic point labels, reducing the noise impact caused by pseudo-labels. Finally, a label updating mechanism based on the exponential moving average (EMA) and k-means clustering is introduced to enhance the quality of pseudo-labels. The experimental results on three public datasets demonstrate that our approach has achieved state-of-the-art performance across multiple metrics. This method can significantly reduce annotation costs and reliance on clinical experts, facilitating large-scale dataset training and promoting the adoption of automated analysis in clinical applications. Full article

The purpose was to contribute to the validation of the TFPI, a new tool to assess the phonetic development of Italian-speaking children aged 18–47 months. Since currently, norm-referenced instruments for Italian are lacking, the TFPI would fill this gap. We recruited 52 monolingual children aged 24–47 months with typical development. They were administered the complete TFPI, i.e., a naming task and repetition task; however, only their performances from the naming task were analyzed. The sessions were audio-recorded, in order to be later segmented and annotated in Praat, then manually transcribed with IPA. These data were then imported into Phon, an extremely suitable software for conducting analyses of phonological and speech data. We compiled the Phonetic Inventory (PhI) and calculated the Percentage of Consonants Correct (PCC) for each child, taking into consideration the allophones of Italian, in order to not compute them as errors. Both the PhI and the PCC improve with age, while intersubjective variability progressively decreases. Additionally, we investigated the age of the acquisition of each phone, since this domain lacks robust scientific data. Finally, our results align with previous findings, which proves the reliability and validity of the TFPI, and provides new information about the PCC, for which there are no reference values for the Italian language. Full article

The application of cyclones can be traced back to 100 years ago. Salt, an important carrier of energy exchange in the human body, is one of the essential substances. Currently, salt surface impurities are mostly removed manually, resulting in low sorting efficiency. Cyclones, as important physical separation equipment, are widely used in separating different substances. This paper focuses on using cyclones for salt decontamination. However, due to the limitations of the cyclone’s structure, ensuring grading accuracy is challenging. The flow field, as the main power source in the cyclone grading process, significantly impacts the grading effect. The overflow pipe, where fine particles exit, has a significant effect on the internal flow field. To explore the impact of the overflow pipe structure on the cyclone’s internal flow field, five overflow pipe structures were designed and numerically analyzed. The results indicate that the improved overflow tube structure has higher static pressure than the conventional linear structure. Type 2 (Parabolic) has the highest tangential velocity, which is 27.7 percentage points higher than that of the conventional cyclone, while Type 3 (hyperbola) has the lowest axial velocity(minimum value is only 0.3 m/s) and turbulence intensity(minimum value of the cone segment is only 0.2), resulting in longer particle residence time in the cyclone for better separation. Additionally, vortices are effectively avoided, improving the stability of the flow field to some extent. The obtained data provide a theoretical basis and support for the structural design of new cyclones. Full article

In response to the structural changes of tomato seedlings, traditional image techniques are difficult to accurately quantify key morphological parameters, such as leaf area, internode length, and mutual occlusion between organs. Therefore, this paper proposes a tomato point cloud stem and leaf segmentation framework based on Elite Strategy-based Improved Red-billed Blue Magpie Optimization (ES-RBMO) Algorithm. The framework uses a four-layer Convolutional Neural Network (CNN) for stem and leaf segmentation by incorporating an improved swarm intelligence algorithm with an accuracy of 0.965. Four key phenotypic parameters of the plant were extracted. The phenotypic parameters of plant height, stem thickness, leaf area and leaf inclination were analyzed by comparing the values extracted by manual measurements with the values extracted by the 3D point cloud technique. The results showed that the coefficients of determination (R²) for these parameters were 0.932, 0.741, 0.938 and 0.935, respectively, indicating high correlation. The root mean square error (RMSE) was 0.511, 0.135, 0.989 and 3.628, reflecting the level of error between the measured and extracted values. The absolute percentage errors (APE) were 1.970, 4.299, 4.365 and 5.531, which further quantified the measurement accuracy. In this study, an efficient and adaptive intelligent optimization framework was constructed, which is capable of optimizing data processing strategies to achieve efficient and accurate processing of tomato point cloud data. This study provides a new technical tool for plant phenotyping and helps to improve the intelligent management in agricultural production. Full article

In the domain of food science, apple grading holds significant research value and application potential. Currently, apple grading predominantly relies on manual methods, which present challenges such as low production efficiency and high subjectivity. This study marks the first integration of advanced computer vision, image processing, and machine learning technologies to design an innovative automated apple grading system. The system aims to reduce human interference and enhance grading efficiency and accuracy. A lightweight detection algorithm, FDNet-p, was developed to capture stem features, and a strategy for auxiliary positioning was designed for image acquisition. An improved DPC-AWKNN segmentation algorithm is proposed for segmenting the apple body. Image processing techniques are employed to extract apple features, such as color, shape, and diameter, culminating in the development of an intelligent apple grading model using the GBDT algorithm. Experimental results demonstrate that, in stem detection tasks, the lightweight FDNet-p model exhibits superior performance compared to various detection models, achieving an [email protected] of 96.6%, with a GFLOPs of 3.4 and a model size of just 2.5 MB. In apple grading experiments, the GBDT grading model achieved the best comprehensive performance among classification models, with weighted Jacard Score, Precision, Recall, and F1 Score values of 0.9506, 0.9196, 0.9683, and 0.9513, respectively. The proposed stem detection and apple body classification models provide innovative solutions for detection and classification tasks in automated fruit grading, offering a comprehensive and replicable research framework for standardizing image processing and feature extraction for apples and similar spherical fruit bodies. Full article

Phenotypic analysis of mature soybeans is a critical aspect of soybean breeding. However, manually obtaining phenotypic parameters not only is time-consuming and labor intensive but also lacks objectivity. Therefore, there is an urgent need for a rapid, accurate, and efficient method to collect the phenotypic parameters of soybeans. This study develops a novel pipeline for acquiring the phenotypic traits of mature soybeans based on three-dimensional (3D) point clouds. First, soybean point clouds are obtained using a multi-view stereo 3D reconstruction method, followed by preprocessing to construct a dataset. Second, a deep learning-based network, PVSegNet (Point Voxel Segmentation Network), is proposed specifically for segmenting soybean pods and stems. This network enhances feature extraction capabilities through the integration of point cloud and voxel convolution, as well as an orientation-encoding (OE) module. Finally, phenotypic parameters such as stem diameter, pod length, and pod width are extracted and validated against manual measurements. Experimental results demonstrate that the average Intersection over Union (IoU) for semantic segmentation is 92.10%, with a precision of 96.38%, recall of 95.41%, and F1-score of 95.87%. For instance segmentation, the network achieves an average precision (AP@50) of 83.47% and an average recall (AR@50) of 87.07%. These results indicate the feasibility of the network for the instance segmentation of pods and stems. In the extraction of plant parameters, the predicted values of pod width, pod length, and stem diameter obtained through the phenotypic extraction method exhibit coefficients of determination (R2) of 0.9489, 0.9182, and 0.9209, respectively, with manual measurements. This demonstrates that our method can significantly improve efficiency and accuracy, contributing to the application of automated 3D point cloud analysis technology in soybean breeding. Full article

Mastoidectomy is critical in acoustic neuroma surgery, where precise planning of the bone milling area is essential for surgical navigation. The complexity of representing the irregular volumetric area and the presence of high-risk structures (e.g., blood vessels and nerves) complicate this task. In order to determine the bone area to mill using preoperative CT images automatically, we propose an automated planning method using evolutionary multi-objective optimization for safer and more efficient milling plans. High-resolution segmentation of the adjacent risk structures is performed on preoperative CT images with a template-based approach. The maximum milling area is defined based on constraints from the risk structures and tool dimensions. Deformation fields are used to simplify the volumetric area into limited continuous parameters suitable for optimization. Finally, a multi-objective optimization algorithm is used to achieve a Pareto-optimal design. Compared with manual planning on six volumes, our method reduced the potential damage to the scala vestibuli by 29.8%, improved the milling boundary smoothness by 78.3%, and increased target accessibility by 26.4%. Assessment by surgeons confirmed the clinical feasibility of the generated plans. In summary, this study presents a parameterization approach to irregular volumetric regions, enabling automated milling area planning through optimization techniques that ensure safety and feasibility. This method is also adaptable to various volumetric planning scenarios. Full article

Monitoring river ice is crucial for planning safe navigation routes, with ice–water classification being one of the most important tasks in ice mapping. While high-resolutions satellite imagery, such as synthetic aperture radar (SAR), is well-suited to this task, manual interpretation of these data is challenging due to the large data volume. Machine learning approaches are suitable methods to overcome this; however, training the models might not be time-effective when the desired result is a narrow structure, such as a river, within a large image. To address this issue, we proposed a model incorporating a graph neural network (GNN), called learnable weights graph convolution network (LWGCN). Focusing on the winters of 2017–2021 with emphasis on the Beauharnois Canal and Lake St Lawrence regions of the Saint Lawrence River. The model first converts the SAR image into graph-structured data using simple linear iterative clustering (SLIC) to segment the SAR image, then connecting the centers of each superpixel to form graph-structured data. For the training model, the LWGCN learns the weights on each edge to determine the relationship between ice and water. By using the graph-structured data as input, the proposed model training time is eight times faster, compared to a convolution neural network (CNN) model. Our findings also indicate that the LWGCN model can significantly enhance the accuracy of ice and water classification in SAR imagery. Full article

Manual labeling of lesions in medical image analysis presents a significant challenge due to its labor-intensive and inefficient nature, which ultimately strains essential medical resources and impedes the advancement of computer-aided diagnosis. This paper introduces a novel medical image-segmentation framework named Efficient Generative-Adversarial U-Net (EGAUNet), designed to facilitate rapid and accurate multi-organ labeling. To enhance the model’s capability to comprehend spatial information, we propose the Global Spatial-Channel Attention Mechanism (GSCA). This mechanism enables the model to concentrate more effectively on regions of interest. Additionally, we have integrated Efficient Mapping Convolutional Blocks (EMCB) into the feature-learning process, allowing for the extraction of multi-scale spatial information and the adjustment of feature map channels through optimized weight values. Moreover, the proposed framework progressively enhances its performance by utilizing a generative-adversarial learning strategy, which contributes to improvements in segmentation accuracy. Consequently, EGAUNet demonstrates exemplary segmentation performance on public multi-organ datasets while maintaining high efficiency. For instance, in evaluations on the CHAOS T2SPIR dataset, EGAUNet achieves approximately 2% higher performance on the Jaccard metric, 1% higher on the Dice metric, and nearly 3% higher on the precision metric in comparison to advanced networks such as Swin-Unet and TransUnet. Full article

Background/Objectives: Accurate and reproducible spleen volume measurements are essential for assessing treatment response and disease progression in myelofibrosis. This study evaluates techniques for measuring spleen volume on abdominal MRI. Methods: In 20 patients with bone marrow biopsy-proven myelofibrosis, 5 observers independently measured spleen volume on 3 abdominal MRI pulse sequences, 3D-spoiled gradient echo T1, axial single-shot fast spin echo (SSFSE) T2, and coronal SSFSE T2, using ellipsoidal approximation, manual contouring, and 3D nnU-Net model-assisted contouring comparing coefficients of variation. Changes in spleen volume were compared to all information to assess which measurement technique tracked disease progression with the greatest accuracy. Results: The coefficient of variation in spleen volume measurements averaging over 3 sequences was significantly lower for model-assisted contouring, 1.6% and manual contouring, 3.5%, compared to ellipsoidal estimation from 3 dimensions measured on axial and coronal T2 images, 15, p < 0.001. In 4 subjects with divergent treatment response predictions, model-assisted contouring was consistent with all information while ellipsoidal estimation was not. Manual contouring tracked similarly to model-assisted contouring but required more operator time. Conclusions: Model-assisted segmentations provide efficient and more reproducible spleen volume measurements compared to estimates of spleen volume from ellipsoidal approximations and improve objective determinations of clinical trial enrollment eligibility based upon spleen volume as well as assessments of treatment response. Full article

Malaria remains a global health concern, with 249 million cases and 608,000 deaths being reported by the WHO in 2022. Traditional diagnostic methods often struggle with inconsistent stain quality, lighting variations, and limited resources in endemic regions, making manual detection time-intensive and error-prone. This study introduces an automated system for analyzing Romanowsky-stained thick blood smears, focusing on image quality evaluation, leukocyte detection, and malaria parasite classification. Using a dataset of 1000 clinically diagnosed images, we applied feature extraction techniques, including histogram bins and texture analysis with the gray level co-occurrence matrix (GLCM), alongside support vector machines (SVMs), for image quality assessment. Leukocyte detection employed optimal thresholding segmentation utility (OTSU) thresholding, binary masking, and erosion, followed by the connected components algorithm. Parasite detection used high-intensity region selection and adaptive bounding boxes, followed by a custom convolutional neural network (CNN) for candidate identification. A second CNN classified parasites into trophozoites, schizonts, and gametocytes. The system achieved an F1-score of 95% for image quality evaluation, 88.92% for leukocyte detection, and 82.10% for parasite detection. The F1-score—a metric balancing precision (correctly identified positives) and recall (correctly detected instances out of actual positives)—is especially valuable for assessing models on imbalanced datasets. In parasite stage classification, CNN achieved F1-scores of 85% for trophozoites, 88% for schizonts, and 83% for gametocytes. This study introduces a robust and scalable automated system that addresses critical challenges in malaria diagnosis by integrating advanced image quality assessment and deep learning techniques for parasite detection and classification. This system’s adaptability to low-resource settings underscores its potential to improve malaria diagnostics globally. Full article

Tea is a significant cash crop grown widely around the world. Currently, tea plucking predominantly relies on manual work. However, due to the aging population and increasing labor costs, machine plucking has become an important trend in the tea industry. The determination of the plucking position and plucking posture is a critical prerequisite for machine plucking tea leaves. In order to improve the accuracy and efficiency of machine plucking tea leaves, a method is presented in this paper to determine the plucking point and plucking posture based on the instance segmentation deep learning network. In this study, tea images in the dataset were first labeled using the Labelme software (version 4.5.13), and then the LDS-YOLOv8-seg model was proposed to identify the tea bud region and plucking area. The plucking points and the central points of the tea bud’s bounding box were calculated and matched as pairs using the nearest point method (NPM) and the point in range method (PIRM) proposed in this study. Finally, the plucking posture was obtained according to the results of the feature points matching. The matching results on the test dataset show that the PIRM has superior performance, with a matching accuracy of 99.229% and an average matching time of 2.363 milliseconds. In addition, failure cases of feature points matching in the plucking posture determination process were also analyzed in this study. The test results show that the plucking position and posture determination method proposed in this paper is feasible for machine plucking tea. Full article

Neonatal mortality remains a critical global challenge, particularly in resource-limited settings with restricted access to advanced diagnostic tools. Early detection of life-threatening conditions like Sepsis and Respiratory Distress Syndrome (RDS), which significantly contribute to neonatal deaths, is crucial for timely interventions and improved survival rates. This study investigates the use of newborn cry sounds, specifically the expiratory segments (the most informative parts of cry signals) as non-invasive biomarkers for early disease diagnosis. We utilized an expanded and balanced cry dataset, applying Self-Supervised Learning (SSL) models—wav2vec 2.0, WavLM, and HuBERT—to extract feature representations directly from raw cry audio signals. This eliminates the need for manual feature extraction while effectively capturing complex patterns associated with sepsis and RDS. A classifier consisting of a single fully connected layer was placed on top of the SSL models to classify newborns into Healthy, Sepsis, or RDS groups. We fine-tuned the SSL models and classifiers by optimizing hyperparameters using two learning rate strategies: linear and annealing. Results demonstrate that the annealing strategy consistently outperformed the linear strategy, with wav2vec 2.0 achieving the highest accuracy of approximately 90% (89.76%). These findings highlight the potential of integrating this method into Newborn Cry Diagnosis Systems (NCDSs). Such systems could assist medical staff in identifying critically ill newborns, prioritizing care, and improving neonatal outcomes through timely interventions. Full article

Background: Hypoxic-ischemic brain injury (HIBI) is a feared complication post-cardiac arrest (CA). The timing of brain imaging remains a topic of ongoing debate. Early computed tomography (CT) scans can reveal acute intracranial pathologies but may have limited predictive value due to delayed manifestation of HIBI-related changes. Radiomics analyses present a promising approach to identifying subtle imaging markers, potentially aiding early HIBI detection. Methods: This study retrospectively assessed post-CA patients between 2016 and 2023 who received immediate brain CTs. Patients without acute intracranial pathology on initial scans and who underwent follow-up brain CTs within 14 days post-return of spontaneous circulation (ROSC) were included. Image segmentation involved manual basalganglia segmentation and automated whole-brain segmentation. Radiomics features were calculated using Pyradiomics (v3.0.1) in 3DSlicer (v5.2.2). Feature selection involved reproducibility analysis via ICC and LASSO regression, retaining five features per segmentation method. A logistic regression model for each segmentation method underwent 5-fold cross-validation. Results were summarized with ROC analyses and average sensitivity and specificity. Results: A total of 83 patients (average age: 65 ± 13.3 years, 19 women) with CA and ROSC were included. Follow-up CT scans after 5.2 ± 2.9 days revealed brain edema in 47 patients. The model using manual segmentation achieved an average AUC of 0.76, sensitivity of 0.59, and specificity of 0.78. The automated segmentation model showed an average AUC of 0.66, sensitivity of 0.49, and specificity of 0.68. Conclusions: Radiomics, particularly focused on the basalganglia area in normal-appearing brain CTs after CA and ROSC, may enhance predictive insights for HIBI and the development of brain edema. Full article