Improving B-mode ultrasound diagnostic performance for focal liver lesions using deep learning: A multicentre study
| Autor: | Wenjia Cai, Li-na Tang, Jin-tang Liao, Hui-ping Zhang, Yao Zhang, Jie Yu, Jingwei Wei, Xiaohan Hao, Rongqin Zheng, Wen Cheng, Yan-Chun Luo, Jun-qing Xi, Yu Song, Zhiyu Han, Yilin Yang, Jin-yu Wu, Qi Yang, Ping Liang, Tian'an Jiang, Pei Zhou, Jie Tian, Xiang Jing, Fangyi Liu, Jianping Dou, Xiaoling Yu, Dexing Kong, Zhigang Cheng |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
medicine.medical_specialty Enhanced ct CONTRAST ENHANCED MRI lcsh:Medicine Convolutional neural network General Biochemistry Genetics and Molecular Biology 03 medical and health sciences 0302 clinical medicine Ultrasound Diagnosis medicine lcsh:R5-920 medicine.diagnostic_test B mode ultrasound business.industry lcsh:R External validation Magnetic resonance imaging General Medicine medicine.disease 030104 developmental biology 030220 oncology & carcinogenesis Cohort Focal liver lesions Radiology lcsh:Medicine (General) business Liver cancer |
| Zdroj: | EBioMedicine, Vol 56, Iss, Pp 102777-(2020) |
| ISSN: | 2352-3964 |
| DOI: | 10.1016/j.ebiom.2020.102777 |
| Popis: | Background The diagnosis performance of B-mode ultrasound (US) for focal liver lesions (FLLs) is relatively limited. We aimed to develop a deep convolutional neural network of US (DCNN-US) for aiding radiologists in classification of malignant from benign FLLs. Materials and methods This study was conducted in 13 hospitals and finally 2143 patients with 24,343 US images were enrolled. Patients who had non-cystic FLLs with pathological results were enrolled. The FLLs from 11 hospitals were randomly divided into training and internal validations (IV) cohorts with a 4:1 ratio for developing and evaluating DCNN-US. Diagnostic performance of the model was verified using external validation (EV) cohort from another two hospitals. The diagnosis value of DCNN-US was compared with that of contrast enhanced computed tomography (CT)/magnetic resonance image (MRI) and 236 radiologists, respectively. Findings The AUC of ModelLBC for FLLs was 0.924 (95% CI: 0.889–0.959) in the EV cohort. The diagnostic sensitivity and specificity of ModelLBC were superior to 15-year skilled radiologists (86.5% vs 76.1%, p = 0.0084 and 85.5% vs 76.9%, p = 0.0051, respectively). Accuracy of ModelLBC was comparable to that of contrast enhanced CT (both 84.7%) but inferior to contrast enhanced MRI (87.9%) for lesions detected by US. Interpretation DCNN-US with high sensitivity and specificity in diagnosing FLLs shows its potential to assist less-experienced radiologists in improving their performance and lowering their dependence on sectional imaging in liver cancer diagnosis. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|