The value of convolutional neural networks-based deep learning model in differential diagnosis of space-occupying brain diseases

Frontiers in Neurology

Neurology

Jing Han¹  Xiuling Miao²  Jianguo Liu²  Yuxin Li³  Chenjing Sun³  Xinnan Li³  Yaming Wang⁴  Qingjun Wang⁵  Tianyu Shao⁶  Junhai Wen⁶ 

[1] Department of Neurology, School of Medicine, South China University of Technology, Guangzhou, China;Department of Neurology, School of Medicine, South China University of Technology, Guangzhou, China;Department of Neurology, The Sixth Medical Center of PLA General Hospital of Beijing, Beijing, China;Department of Neurology, The Sixth Medical Center of PLA General Hospital of Beijing, Beijing, China;Department of Neurosurgery, Xuanwu Hospital, Capital Medical University, Beijing, China;Department of Radiology, The Sixth Medical Center of PLA General Hospital of Beijing, Beijing, China;School of Life Science, Beijing Institute of Technology, Beijing, China;

关键词: convolutional neural network;    space-occupying brain lesions;    diagnosis;    differential;    magnetic resonance imaging;    tumefactive demyelinating lesions;   

DOI  :  10.3389/fneur.2023.1107957

 received in 2022-11-25, accepted in 2023-01-16,  发布年份 2023

来源: Frontiers

【 摘 要 】

ObjectivesIt is still a challenge to differentiate space-occupying brain lesions such as tumefactive demyelinating lesions (TDLs), tumefactive primary angiitis of the central nervous system (TPACNS), primary central nervous system lymphoma (PCNSL), and brain gliomas. Convolutional neural networks (CNNs) have been used to analyze complex medical data and have proven transformative for image-based applications. It can quickly acquire diseases' radiographic features and correct doctors' diagnostic bias to improve diagnostic efficiency and accuracy. The study aimed to assess the value of CNN-based deep learning model in the differential diagnosis of space-occupying brain diseases on MRI.MethodsWe retrospectively analyzed clinical and MRI data from 480 patients with TDLs (n = 116), TPACNS (n = 64), PCNSL (n = 150), and brain gliomas (n = 150). The patients were randomly assigned to training (n = 240), testing (n = 73), calibration (n = 96), and validation (n = 71) groups. And a CNN-implemented deep learning model guided by clinical experts was developed to identify the contrast-enhanced T1-weighted sequence lesions of these four diseases. We utilized accuracy, sensitivity, specificity, and area under the curve (AUC) to evaluate the performance of the CNN model. The model's performance was then compared to the neuroradiologists' diagnosis.ResultsThe CNN model had a total accuracy of 87% which was higher than senior neuroradiologists (74%), and the AUC of TDLs, PCNSL, TPACNS and gliomas were 0.92, 0.92, 0.89 and 0.88, respectively.ConclusionThe CNN model can accurately identify specific radiographic features of TDLs, TPACNS, PCNSL, and gliomas. It has the potential to be an effective auxiliary diagnostic tool in the clinic, assisting inexperienced clinicians in reducing diagnostic bias and improving diagnostic efficiency.

【 授权许可】

Unknown   
Copyright © 2023 Miao, Shao, Wang, Wang, Han, Li, Li, Sun, Wen and Liu.