Judgment of benign and early malignant colorectal tumors from ultrasound images with deep multi-View fusion. (March 2022)

• Record Type: Journal Article
• Authors: Song, Dan; Zhang, Zheqi; Li, Wenhui; Yuan, Lijun; Zhang, Wenshu
• Is Part Of: Computer methods and programs in biomedicine. Volume 215(2022)
• Publication Date: 2022-03
• Subjects: Colorectal cancer -- Deep neural networks -- Endorectal ultrasound -- Computer-aided diagnosis -- Multi-view fusion; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106634
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A computer-aided diagnosis system is proposed based on deep neural network for judging benign and early malignant colorectal tumors. The computer-aided diagnosis system proposed is the first one based on endorectal ultrasound images, and the first to adopt a multi-view fusion mechanism. The first multi-view endorectal ultrasound image dataset is constructed. A new form of center loss was designed to optimize the model and achieves good results. The performance of the proposed algorithm surpasses both expert diagnosis results and comparison methods. Abstract: Background and objective: Colorectal cancer (CRC) is currently one of the main cancers world-wide, with a high incidence in the elderly. In the diagnosis of CRC, endorectal ultrasound plays an important role in judging benign and early malignant tumors. However, malignant tumors in the early-stage are not easy to identify visually and experts usually seek help from multi-view images, which increases the workload and also exists a certain probability of misdiagnosis. In recent years, with the widespread use of deep learning methods in the analysis of medical images, it becomes necessary to design an effective computer-aided diagnosis (CAD) system of CRC based on multi-view endorectal ultrasound images. Method: In this study, we proposed a CAD system for judging benign and early malignant colorectal tumors, and constructed the first multi-view ultrasound image dataset of CRC to validate our algorithm. Our system is an end-to-end model based on a deep neural network (DNN) which includes a feature extraction module based on dense blocks, a multi-view fusion module, and a Multi-Layer Perception-based classifier. A center loss was used for the first time in CAD tasks, to optimize our model. Result: On the constructed dataset, the proposed system surpasses expert diagnosis in accuracy, sensitivity, specificity, and F1-score. Compared with the popular deep classification networks and other CAD methods, the algorithm has reached the best performance. Comparative experiments using different feature extraction methods, different view fusion strategies, and different classifiers verify the effectiveness of each part of the algorithm. Conclusion: We propose a CAD system for judging benign and early malignant colorectal tumors based on DNN, which combines information of ultrasound images from different views for comprehension. On the first CRC multi-view ultrasound image dataset which we constructed, our method outperforms expert diagnosis results and all other methods, and the effectiveness of each part of the system has been verified. Our system has application value in future medical practice on early diagnosis of CRC.