{Reference Type}: Journal Article
{Title}: Deep learning applied to breast imaging classification and segmentation with human expert intervention.
{Author}: Wilding R;Sheraton VM;Soto L;Chotai N;Tan EY;
{Journal}: J Ultrasound
{Volume}: 25
{Issue}: 3
{Year}: Sep 2022
暂无{DOI}: 10.1007/s40477-021-00642-3
{Abstract}: <B>OBJECTIVE: </B>Automatic classification and segmentation of tumors in breast ultrasound images enables better diagnosis and planning treatment strategies for breast cancer patients.<BR><B>METHODS: </B>We collected 953 breast ultrasound images from two open-source datasets and classified them with help of an expert radiologist according to BI-RADS criteria. The data was split into normal, benign and malignant classes. We then used machine learning to develop classification and segmentation algorithms.<BR><B>RESULTS: </B>We found 3.92% of the images across the open-source datasets had erroneous classifications. Post-radiologist intervention, three algorithms were developed based on the classification categories. Classification algorithms distinguished images with healthy breast tissue from those with abnormal tissue with 96% accuracy, and distinguished benign from malignant images with 85% accuracy. Both algorithms generated robust F1 and AUROC metrics. Finally, the masses within images were segmented with an 80.31% DICE score.<BR><B>CONCLUSIONS: </B>Our work illustrates the potential of deep learning algorithms to improve the accuracy of breast ultrasound assessments and to facilitate automated assessments.