Abstract
To improve the automatic segmentation accuracy of breast masses in digital breast tomosynthesis (DBT) images, we propose a DBT mass automatic segmentation algorithm by using a U-Net architecture. Firstly, to suppress the background tissue noise and enhance the contrast of the mass candidate regions, after the top-hat transform of DBT images, a constraint matrix is constructed and multiplied with the DBT image. Secondly, an efficient U-Net neural network is built and image patches are extracted before data augmentation to establish the training dataset to train the U-Net model. And then the presegmentation of the DBT tumors is implemented, which initially classifies per pixel into two different types of labels. Finally, all regions smaller than 50 voxels considered as false positives are removed, and the median filter smoothes the mass boundaries to obtain the final segmentation results. The proposed method can effectively improve the performance in the automatic segmentation of the masses in DBT images. Using the detection Accuracy (Acc), Sensitivity (Sen), Specificity (Spe), and area under the curve (AUC) as evaluation indexes, the Acc, Sen, Spe, and AUC for DBT mass segmentation in the entire experimental dataset is 0.871, 0.869, 0.882, and 0.859, respectively. Our proposed U-Net-based DBT mass automatic segmentation system obtains promising results, which is superior to some classical architectures, and may be expected to have clinical application prospects.
Highlights
Breast cancer is the most common malignant tumor of breast epithelial tissue in women, which seriously threatens the physical and mental health of patients [1]
To assess the segmentation performance of our proposed method based on U-Net, we evaluated the overlap between the proposed Digital breast tomosynthesis (DBT) mass labels and the ground truth (GT)
We can see that when the U-Net model is trained on the DBT images comes from the same hospital and tested on the DBT images comes from the same hospital, the maximum probability achieves best accuracy, which highlights the importance of a good voting scheme, namely, maximum probability
Summary
Breast cancer is the most common malignant tumor of breast epithelial tissue in women, which seriously threatens the physical and mental health of patients [1]. Digital breast tomosynthesis (DBT) is a new 3D tomography method for breast cancer screening. It can reconstruct a small amount of low-dose mammographic images from a limited angle into three-dimensional mammographic images and can better detect some small hidden lesions [4]. If the computer can automatically detect breast masses in DBT images, it can reduce the review time for radiologists and effectively reduce the misjudgment caused by excessive fatigue. Erefore, automatic segmentation of breast masses in DBT images is of great clinical value in assistant screening, early diagnosis, and preoperative localization of breast cancer [8,9,10] If the computer can automatically detect breast masses in DBT images, it can reduce the review time for radiologists and effectively reduce the misjudgment caused by excessive fatigue. erefore, automatic segmentation of breast masses in DBT images is of great clinical value in assistant screening, early diagnosis, and preoperative localization of breast cancer [8,9,10]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Computational and Mathematical Methods in Medicine
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
