A deep supervised transformer U‐shaped full‐resolution residual network for the segmentation of breast ultrasound image
Authors:
- 10 October 2023
- journal article
- research article
- Published by Wiley in Medical Physics
- Vol. 50 (12) , 7513-7524
Abstract
Purpose: Breast ultrasound (BUS) is an important breast imaging tool. Automatic BUS image segmentation can measure the breast tumor size objectively and reduce doctors’ workload. In this article, we proposed a deep supervised transformer U‐shaped full‐resolution residual network (DSTransUFRRN) to segment BUS images.Methods: In the proposed method, a full‐resolution residual stream and a deep supervision mechanism were introduced into TransU‐Net. The residual stream can keep full resolution features from different levels and enhance features fusion. Then, the deep supervision can suppress gradient dispersion. Moreover, the transformer module can suppress irrelevant features and improve feature extraction process. Two datasets (dataset A and B) were used for training and evaluation. The dataset A included 980 BUS image samples and the dataset B had 163 BUS image samples.Results: Cross‐validation was conducted. For the dataset A, the proposed DSTransUFRRN achieved significantly higher Dice (91.04 ± 0.86%) than all compared methods (p < 0.05). For the dataset B, the Dice was lower than that for the dataset A due to the small number of samples, but the Dice of DSTransUFRRN (88.15% ± 2.11%) was significantly higher than that of other compared methods (p < 0.05).Conclusions: In this study, we proposed DSTransUFRRN for BUS image segmentation. The proposed methods achieved significantly higher accuracy than the compared previous methods.Keywords
This publication has 26 references indexed in Scilit:
- Adjunctive ultrasonography for breast cancer screening – Authors' replyThe Lancet, 2016
- Semi-automatic Breast Ultrasound Image Segmentation Based on Mean Shift and Graph CutsUltrasonic Imaging, 2014
- Tumor detection in automated breast ultrasound images using quantitative tissue clusteringMedical Physics, 2014
- Optimization of breast lesion segmentation in texture feature space approachMedical Engineering & Physics, 2013
- A robust graph-based segmentation method for breast tumors in ultrasound imagesUltrasonics, 2012
- Development of a fully automatic scheme for detection of masses in whole breast ultrasound imagesMedical Physics, 2007
- Performance of computer-aided diagnosis in the interpretation of lesions on breast sonographyAcademic Radiology, 2004
- Comparison of the Performance of Screening Mammography, Physical Examination, and Breast US and Evaluation of Factors that Influence Them: An Analysis of 27,825 Patient EvaluationsRadiology, 2002
- Computerized lesion detection on breast ultrasoundMedical Physics, 2002
- Computerized diagnosis of breast lesions on ultrasoundMedical Physics, 2002