KEYWORDS: Histograms, Tumor growth modeling, Image classification, Breast cancer, Feature extraction, Breast, Data modeling, Image restoration, Deep learning, Education and training
SignificanceUltrasound (US)-guided diffuse optical tomography (DOT) has demonstrated great potential for breast cancer diagnosis in which real-time or near real-time diagnosis with high accuracy is desired.AimWe aim to use US-guided DOT to achieve an automated, fast, and accurate classification of breast lesions.ApproachWe propose a two-stage classification strategy with deep learning. In the first stage, US images and histograms created from DOT perturbation measurements are combined to predict benign lesions. Then the non-benign suspicious lesions are passed through to the second stage, which combine US image features, DOT histogram features, and 3D DOT reconstructed images for final diagnosis.ResultsThe first stage alone identified 73.0% of benign cases without image reconstruction. In distinguishing between benign and malignant breast lesions in patient data, the two-stage classification approach achieved an area under the receiver operating characteristic curve of 0.946, outperforming the diagnoses of all single-modality models and of a single-stage classification model that combines all US images, DOT histogram, and imaging features.ConclusionsThe proposed two-stage classification strategy achieves better classification accuracy than single-modality-only models and a single-stage classification model that combines all features. It can potentially distinguish breast cancers from benign lesions in near real-time.
Ultrasound (US)-guided diffuse optical tomography (DOT) has demonstrated success in breast cancer diagnosis. However, DOT data pre-processing and reconstruction still require some level of manual operation, for example, contralateral reference selection and data cleaning. In this study, we introduce an automated data pre-processing and reconstruction pipeline to accelerate the DOT clinical translation. The pipeline has integrated several data pre-processing modules and reconstruction methods that are adapted to data. The pipeline is implemented using a graphical user interface. Initial testing has shown that it can automate DOT right after the data acquisition and provides an accurate diagnostic score on cancer vs. benign probability.
Ultrasound (US)-guided diffuse optical tomography (DOT) has demonstrated potential for breast cancer diagnosis. Previous diagnostic strategies all require image reconstruction, which hindered real-time diagnosis. In this study, we propose a deep learning approach to combine DOT frequency-domain measurement data and co-registered US images to classify breast lesions. The combined deep learning model achieved an AUC of 0.886 in distinguishing between benign and malignant breast lesions in patient data without reconstructing images.
Significance: “Difference imaging,” which reconstructs target optical properties using measurements with and without target information, is often used in diffuse optical tomography (DOT) in vivo imaging. However, taking additional reference measurements is time consuming, and mismatches between the target medium and the reference medium can cause inaccurate reconstruction.Aim: We aim to streamline the data acquisition and mitigate the mismatch problems in DOT difference imaging using a deep learning-based approach to generate data from target measurements only.Approach: We train an artificial neural network to output data for difference imaging from target measurements only. The model is trained and validated on simulation data and tested with simulations, phantom experiments, and clinical data from 56 patients with breast lesions.Results: The proposed method has comparable performance to the traditional approach using measurements without mismatch between the target side and the reference side, and it outperforms the traditional approach using measurements when there is a mismatch. It also improves the target-to-artifact ratio and lesion localization in patient data.Conclusions: The proposed method can simplify the data acquisition procedure, mitigate mismatch problems, and improve reconstructed image quality in DOT difference imaging.
Significance: In general, image reconstruction methods used in diffuse optical tomography (DOT) are based on diffusion approximation, and they consider the breast tissue as a homogenous, semi-infinite medium. However, the semi-infinite medium assumption used in DOT reconstruction is not valid when the chest wall is underneath the breast tissue.
Aim: We aim to reduce the chest wall’s effect on the estimated average optical properties of breast tissue and obtain accurate forward model for DOT reconstruction.
Approach: We propose a deep learning-based neural network approach where a convolution neural network (CNN) is trained to simultaneously obtain accurate optical property values for both the breast tissue and the chest wall.
Results: The CNN model shows great promise in reducing errors in estimating the optical properties of the breast tissue in the presence of a shallow chest wall. For patient data, the CNN model predicted the breast tissue optical absorption coefficient, which was independent of chest wall depth.
Conclusions: Our proposed method can be readily used in DOT and diffuse spectroscopy measurements to improve the accuracy of estimated tissue optical properties.
Ultrasound (US)-guided diffuse optical tomography (DOT) has demonstrated potential value for screening and treatment monitoring of breast cancers. However, in clinical cases, the chest wall, bad probe-tissue contact, and tissue heterogeneity can create image artifacts, causing misinterpretation of lesion images. In the current work, realistic and flexible threedimensional numerical breast phantoms were generated using the Virtual Imaging Clinical Trials for Regulatory Evaluation (VICTRE) tools developed by U.S. Food and Drug Administration (FDA). By selecting physical attributes and tissue optical properties, the VICTRE breast phantoms were, for the first time, adopted in DOT for in silico studies. Monte Carlo simulations were conducted to generate the forward data. Edge artifacts (hot spots on the edge of the regions of interests) were found on the reconstructed images when there was a mismatch between the lesion-side breast and the contralateral reference-side breast. We propose a fully automated, connected components analysis-based algorithm that can remove these edge artifacts and improve lesion reconstruction.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.