Improved FCOS for Detecting the Breast Cancers

• Published in: Current medical imaging reviews
• Main Authors: Wang, Yingni, Lin, Xiaona, Zhang, Xuesheng, Ye, Qingyu, Zhou, Haiying, Zhang, Renrong, Ge, Shuang, Sun, Desheng, Yuan, Kehong
• Format: Journal Article
• Language: English
• Published: United Arab Emirates 01.01.2022
• Subjects: FCOS; deformable spatial attention; Object detection algorithm; non-local module; breast cancers
• ISSN: 1573-4056
• DOI: 10.2174/1573405618666220420091649

Breast cancer ranks first among cancers affecting women's health. Our goal is to develop a fast, high-precision, and fully automated breast cancer detection algorithm to improve the early detection rate of breast cancer. We compare different object detection algorithms including anchor-based and anchor-free object detection algorithms for detecting breast lesions. Finally, we find that the Fully Convolutional One-Stage Object Detection (FCOS) showed the best performance in the detection of breast lesions, which is an anchor-free algorithm. 1) Considering that the detection of breast lesions requires the context information of the ultrasound images, we introduce the non-local technique, which models long-range dependency between pixels to the FCOS algorithm, providing the global context information for the detection of the breast lesions. 2) The variety of shape and size of breast lesions makes detection difficult. We propose a new deformable spatial attention (DSA) module and add it to the FCOS algorithm. The detection performance of the original FCOS is that the average precision (AP) for benign lesions is 0.818, and for malignant lesions is 0.888. The FCOS with non-local module improves the performance of the breast detection, the AP of benign lesions was 0.819 and that of malignant lesions was 0.894. Combining the DSA module with the FCOS improves the performance of breast detection, the AP for benign lesions malignant lesions is 0.840 and 0.899, respectively. We propose two methods to improve the FCOS algorithm from different perspectives to improve its performance in detecting breast lesions. We find that FCOS combined with DSA is beneficial to improve the localization and classification of breast tumors and can provide auxiliary diagnostic advice for ultrasound physicians, which has certain clinical application value.