A Small Intestinal Stromal Tumor Detection Method Based on an Attention Balance Feature Pyramid
Author:
Xie Fei12, Ju Jianguo3, Zhang Tongtong3, Wang Hexu1, Liu Jindong3, Wang Juan1, Zhou Yang3, Zhao Xuesong4
Affiliation:
1. Xi’an Key Laboratory of Human–Machine Integration and Control Technology for Intelligent Rehabilitation, Xijing University, Xi’an 710123, China 2. School of AOAIR, Xidian University, Xi’an 710075, China 3. School of Information Science and Technology, Northwest University, Xi’an 710126, China 4. Departments of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China
Abstract
Small intestinal stromal tumor (SIST) is a common gastrointestinal tumor. Currently, SIST diagnosis relies on clinical radiologists reviewing CT images from medical imaging sensors. However, this method is inefficient and greatly affected by subjective factors. The automatic detection method for stromal tumors based on computer vision technology can better solve these problems. However, in CT images, SIST have different shapes and sizes, blurred edge texture, and little difference from surrounding normal tissues, which to a large extent challenges the use of computer vision technology for the automatic detection of stromal tumors. Furthermore, there are the following issues in the research on the detection and recognition of SIST. After analyzing mainstream target detection models on SIST data, it was discovered that there is an imbalance in the features at different levels during the feature fusion stage of the network model. Therefore, this paper proposes an algorithm, based on the attention balance feature pyramid (ABFP), for detecting SIST with unbalanced feature fusion in the target detection model. By combining weighted multi-level feature maps from the backbone network, the algorithm creates a balanced semantic feature map. Spatial attention and channel attention modules are then introduced to enhance this map. In the feature fusion stage, the algorithm scales the enhanced balanced semantic feature map to the size of each level feature map and enhances the original feature information with the original feature map, effectively addressing the imbalance between deep and shallow features. Consequently, the SIST detection model’s detection performance is significantly improved, and the method is highly versatile. Experimental results show that the ABFP method can enhance traditional target detection methods, and is compatible with various models and feature fusion strategies.
Funder
National Key R&D program of China National Natural Science Foundation of China Key Research and Development Program of Shaanxi Young Science and Technology Nova of Shaanxi Province Key R & D programs of Shaanxi Province Qin Chuangyuan project National Defense Science and Technology Key Laboratory Qinchuangyuan Scientist and Engineer National Key R & D program of China Shaanxi Association for Science and Technology
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference31 articles.
1. Gheorghe, G., Bacalbasa, N., Ceobanu, G., Ilie, M., Enache, V., Constantinescu, G., Bungau, S., and Diaconu, C.C. (2021). Gastrointestinal stromal tumors—A mini review. J. Pers. Med., 11. 2. Gastrointestinal stromal tumours;Blay;Nat. Rev. Dis. Prim.,2021 3. Yang, D., Zhang, S., Yan, Z., Tan, C., Li, K., and Metaxas, D. (2015, January 16–19). Automated anatomical landmark detection on distal femur surface using convolutional neural network. Proceedings of the 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), New York, NY, USA. 4. De Vos, B.D., Wolterink, J.M., De Jong, P.A., Viergever, M.A., and Išgum, I. (2016, January 17–21). 2D image classification for 3D anatomy localization: Employing deep convolutional neural networks. Proceedings of the Medical Imaging 2016: Image Processing Conference, Athens, Greece. 5. Multi-modal vertebrae recognition using transformed deep convolution network;Cai;Comput. Med. Imaging Graph.,2016
|
|