3-D Res-CapsNet convolutional neural network on automated breast ultrasound tumor diagnosis. Issue 138 (May 2021)

• Record Type: Journal Article
• Authors: Xiang, Huiling; Huang, Yao-Sian; Lee, Chu-Hsuan; Chang Chien, Ting-Yin; Lee, Cheng-Kuang; Liu, Lixian; Li, Anhua; Lin, Xi; Chang, Ruey-Feng
• Is Part Of: European journal of radiology. Issue 138(2021)
• Publication Date: 2021-05
• Subjects: ABUS automated breast ultrasound -- HHUS handheld ultrasound -- CADx computer-aided diagnosis -- CNN convolutional neural network -- ResBlock residual block -- CapsNet capsule network -- VOI volume of interest -- AUC area under the curve; Breast neoplasms -- Automated breast ultrasound -- Computer-assisted image interpretation -- Convolutional neural networks; Medical radiology -- Periodicals; Radiology -- Periodicals; Radiologie médicale -- Périodiques; Medical radiology; Periodicals; 616.075705
• DOI: 10.1016/j.ejrad.2021.109608
• Languages: English
• ISSNs: 0720-048X

Abstract

Highlights: Providing a CNN-based computer-aided tumor classification (CADx), 3-D Res-CapsNet model, for automatic breast ultrasound. Our CADx uses the residual block, the capsule neural structure, and the group normalization to achieve higher accuracy. The accuracy and specificity of our CADx in non-mass tumor are 81.6 % and 86.7 % which are higher than two junior readers. Abstract: Purpose: We propose a 3-D tumor computer-aided diagnosis (CADx) system with U-net and a residual-capsule neural network (Res-CapsNet) for ABUS images and provide a reference for early tumor diagnosis, especially non-mass lesions. Methods: A total of 396 patients with 444 tumors (226 malignant and 218 benign) were retrospectively enrolled from Sun Yat-sen University Cancer Center. In our CADx, preprocessing was performed first to crop and resize the tumor volumes of interest (VOIs). Then, a 3-D U-net and postprocessing were applied to the VOIs to obtain tumor masks. Finally, a 3-D Res-CapsNet classification model was executed with the VOIs and the corresponding masks to diagnose the tumors. Finally, the diagnostic performance, including accuracy, sensitivity, specificity, and area under the curve (AUC), was compared with other classification models and among three readers with different years of experience in ABUS review. Results: For all tumors, the accuracy, sensitivity, specificity, and AUC of the proposed CADx were 84.9 %, 87.2 %, 82.6 %, and 0.9122, respectively, outperforming other models and junior reader. Next, the tumors were subdivided into mass and non-mass tumors to validate the system performance. For mass tumors, our CADx achieved an accuracy, sensitivity, specificity, and AUC of 85.2 %, 88.2 %, 82.3 %, and 0.9147, respectively, which was higher than that of other models and junior reader. For non-mass tumors, our CADx achieved an accuracy, sensitivity, specificity, and AUC of 81.6 %, 78.3 %, 86.7 %, and 0.8654, respectively, outperforming the two readers. Conclusion: The proposed CADx with 3-D U-net and 3-D Res-CapsNet models has the potential to reduce misdiagnosis, especially for non-mass lesions.