A meta-fusion RCNN network for endoscopic visual bladder lesions intelligent detection. (December 2022)

• Record Type: Journal Article
• Authors: Lin, Jie; Pan, Yulong; Xu, Jiajun; Bao, Yige; Zhuo, Hui
• Is Part Of: Computerized medical imaging and graphics. Volume 102(2022)
• Publication Date: 2022-12
• Subjects: Meta learning -- Fusion network -- Endoscopic visual detection -- Bladder lesions detection; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2022.102138
• Languages: English
• ISSNs: 0895-6111

Abstract

Abstract: This study investigates a visual object detection technology in order to help doctors diagnose bladder lesions with endoscopy. A new object detection approach based on deep learning is presented, which derived from the cascade R-CNN and extended the ability of network for adapting insufficient endoscopic lesions samples when training a deep neural network. We propose a feature adaptive fusion model to increase the network's mobility and reduce the possibility of overfitting problems, and use task adaptation meta-learning approach to train the feature fusion process of the entire model and the target network update process in order to complete the task-adaptive classification and detection. The new model has been evaluated on the challenging object detection data set Pascal VOC and its converted format of Microsoft COCO, and the results show that the performance of our proposed method is superior to the original method. Therefore, we apply the proposed method to a custom bladder lesions data set to solve the auxiliary detection problem in the intelligent diagnosis of bladder lesions and demonstrated the effectiveness. Highlights: Proposed an efficient computer vision-based bladder lesions detection technology. Proposed an adaptive fusion network to form the target domain from source domains. Proposed a meta-learning method to resolve the model overfitting problem.