Automatic Detection and Classification of Focal Liver Lesions Based on Deep Convolutional Neural Networks: A Preliminary Study

Frontiers in Oncology

Jian Wu³  Biwen Lei³  Wenzhe Wang³  Wenhao Ge⁵  Linshi Zhang⁵  Dongkai Zhou⁵  Yu Huang⁵  Jiarong Zhou⁵  Yingcai Yan⁵  Yuan Ding⁶  Weilin Wang⁶ 

[1] Clinical Medicine Innovation Center of Precision Diagnosis and Treatment for Hepatobiliary and Pancreatic Diseases of Zhejiang University, Hangzhou, China;Clinical Research Center of Hepatobiliary and Pancreatic Diseases of Zhejiang Province, Hangzhou, China;College of Computer Science and Technology, Zhejiang University, Hangzhou, China;Department of Hepatobiliary and Pancreatic Surgery, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China;Key Laboratory of Precision Diagnosis and Treatment for Hepatobiliary and Pancreatic Tumor of Zhejiang Province, Hangzhou, China;Research Center of Diagnosis and Treatment Technology for Hepatocellular Carcinoma of Zhejiang Province, Hangzhou, China;

关键词: deep learning;    focal liver lesions;    detection;    classification;    computed tomography;   

DOI  :  10.3389/fonc.2020.581210

来源: DOAJ

【 摘 要 】

With the increasing daily workload of physicians, computer-aided diagnosis (CAD) systems based on deep learning play an increasingly important role in pattern recognition of diagnostic medical images. In this paper, we propose a framework based on hierarchical convolutional neural networks (CNNs) for automatic detection and classification of focal liver lesions (FLLs) in multi-phasic computed tomography (CT). A total of 616 nodules, composed of three types of malignant lesions (hepatocellular carcinoma, intrahepatic cholangiocarcinoma, and metastasis) and benign lesions (hemangioma, focal nodular hyperplasia, and cyst), were randomly divided into training and test sets at an approximate ratio of 3:1. To evaluate the performance of our model, other commonly adopted CNN models and two physicians were included for comparison. Our model achieved the best results to detect FLLs, with an average test precision of 82.8%, recall of 93.4%, and F1-score of 87.8%. Our model initially classified FLLs into malignant and benign and then classified them into more detailed classes. For the binary and six-class classification, our model achieved average accuracy results of 82.5 and73.4%, respectively, which were better than the other three classification neural networks. Interestingly, the classification performance of the model was placed between a junior physician and a senior physician. Overall, this preliminary study demonstrates that our proposed multi-modality and multi-scale CNN structure can locate and classify FLLs accurately in a limited dataset, and would help inexperienced physicians to reach a diagnosis in clinical practice.

【 授权许可】

Unknown