Fully automated MRI-based convolutional neural network for noninvasive diagnosis of cirrhosis
This fully automated convolutional neural network (CNN) model, using pre-contrast MRI, age, and serum biomarkers, diagnoses cirrhosis. The CNN model demonstrated an external testing dataset AUC of 0.86, independent of the size of focal liver lesions. The CNN model outperformed aminotransferase-to-platelet ratio index, fibrosis-4 index, and radiologists, potentially facilitating noninvasive diagnosis of cirrhosis.
Authors
- Yuanan Wu (ORCID: https://orcid.org/0000-0003-4513-1357)
- Yajing Zhu (ORCID: https://orcid.org/0000-0001-8035-2337)
- Shengshi Mai
- Hanyu Jiang (ORCID: https://orcid.org/0000-0002-7726-1618)
- Yali Qu (ORCID: https://orcid.org/0000-0002-9636-4786)
- Bin Song (ORCID: https://orcid.org/0000-0002-7269-2101)
- Lixin Xu (ORCID: https://orcid.org/0000-0003-2208-018X)
- Ting Duan (ORCID: https://orcid.org/0000-0001-6694-4520)
- Yinan Chen (ORCID: https://orcid.org/0000-0001-8488-9246)
- Yidi Chen (ORCID: https://orcid.org/0000-0001-6293-4624)
- Tianying Zheng
Institutions
- Sichuan University (CN)
- West China Hospital of Sichuan University (CN)
- Sensimetrics Corporation (US)
- Group Sense (China) (CN)
- Sanya Central Hospital (CN)
- Xiangnan University (CN)
Publication Details
- Journal
- Insights into Imaging
- Published
- 2024-12-12
- DOI
- https://doi.org/10.1186/s13244-024-01872-9
- Citations
- 2
- Primary Topic
- Liver Disease Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.77
Funders
- National Natural Science Foundation of China
- Department of Science and Technology of Sichuan Province
- Sichuan University
- Chengdu Science and Technology Bureau
- Natural Science Foundation of Sichuan Province
- National Health Commission of the People's Republic of China