Improved breast ultrasound tumor classification using dual-input CNN with GAP-guided attention loss
-
Published:2023
Issue:8
Volume:20
Page:15244-15264
-
ISSN:1551-0018
-
Container-title:Mathematical Biosciences and Engineering
-
language:
-
Short-container-title:MBE
Author:
Zou Xiao1, Zhai Jintao1, Qian Shengyou1, Li Ang1, Tian Feng1, Cao Xiaofei2, Wang Runmin2
Affiliation:
1. School of Physics and Electronics, Hunan Normal University, Changsha 410081, China 2. College of Information Science and Engineering, Hunan Normal University, Changsha 410081, China
Abstract
<abstract><p>Ultrasonography is a widely used medical imaging technique for detecting breast cancer. While manual diagnostic methods are subject to variability and time-consuming, computer-aided diagnostic (CAD) methods have proven to be more efficient. However, current CAD approaches neglect the impact of noise and artifacts on the accuracy of image analysis. To enhance the precision of breast ultrasound image analysis for identifying tissues, organs and lesions, we propose a novel approach for improved tumor classification through a dual-input model and global average pooling (GAP)-guided attention loss function. Our approach leverages a convolutional neural network with transformer architecture and modifies the single-input model for dual-input. This technique employs a fusion module and GAP operation-guided attention loss function simultaneously to supervise the extraction of effective features from the target region and mitigate the effect of information loss or redundancy on misclassification. Our proposed method has three key features: (i) ResNet and MobileViT are combined to enhance local and global information extraction. In addition, a dual-input channel is designed to include both attention images and original breast ultrasound images, mitigating the impact of noise and artifacts in ultrasound images. (ii) A fusion module and GAP operation-guided attention loss function are proposed to improve the fusion of dual-channel feature information, as well as supervise and constrain the weight of the attention mechanism on the fused focus region. (iii) Using the collected uterine fibroid ultrasound dataset to train ResNet18 and load the pre-trained weights, our experiments on the BUSI and BUSC public datasets demonstrate that the proposed method outperforms some state-of-the-art methods. The code will be publicly released at <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="https://github.com/425877/Improved-Breast-Ultrasound-Tumor-Classification">https://github.com/425877/Improved-Breast-Ultrasound-Tumor-Classification</ext-link>.</p></abstract>
Publisher
American Institute of Mathematical Sciences (AIMS)
Subject
Applied Mathematics,Computational Mathematics,General Agricultural and Biological Sciences,Modeling and Simulation,General Medicine
Reference59 articles.
1. N. Wu, J. Phang, J. Park, Y. Shen, Z. Huang, M. Zorin, Deep neural networks improve radiologists' performance in breast cancer screening, IEEE Trans. Med. Imaging, 39 (2019), 1184–1194. https://doi.org/10.1109/TMI.2019.2945514 2. D. M. van der Kolk, G. H. de Bock, B. K. Leegte, M. Schaapveld, M. J. Mourits, J. de Vries, et al., Penetrance of breast cancer, ovarian cancer and contralateral breast cancer in BRCA1 and BRCA2 families: high cancer incidence at older age, Breast Cancer Res. Treat., 124 (2010), 643–651. https://doi.org/10.1007/s10549-010-0805-3 3. Q. Xia, Y. Cheng, J. Hu, J. Huang, Y. Yu, H. Xie, et al., Differential diagnosis of breast cancer assisted by s-detect artificial intelligence system, Math. Biosci. Eng., 18 (2021), 3680–3689. https://doi.org/10.3934/mbe.2021184 4. S. Williamson, K. Vijayakumar, V. J. Kadam, Predicting breast cancer biopsy outcomes from bi-rads findings using random forests with chi-square and mi features, Multimedia Tools Appl., 81 (2022), 36869–36889. https://doi.org/10.1007/s11042-021-11114-5 5. D. J. Gavaghan, J. P. Whiteley, S. J. Chapman, J. M. Brady, P. Pathmanathan, Predicting tumor location by modeling the deformation of the breast, IEEE Trans. Biomed. Eng., 55 (2008), 2471–2480. https://doi.org/10.1109/TBME.2008.925714
|
|