Fully automated MRI-based convolutional neural network for noninvasive diagnosis of cirrhosis
Abstract Objectives To develop and externally validate a fully automated diagnostic convolutional neural network (CNN) model for cirrhosis based on liver MRI and serum biomarkers. Methods This multicenter retrospective study included consecutive patients receiving pathological evaluation of liver fi...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-12-01
|
| Series: | Insights into Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13244-024-01872-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850110031270248448 |
|---|---|
| author | Tianying Zheng Yajing Zhu Yidi Chen Shengshi Mai Lixin Xu Hanyu Jiang Ting Duan Yuanan Wu Yali Qu Yinan Chen Bin Song |
| author_facet | Tianying Zheng Yajing Zhu Yidi Chen Shengshi Mai Lixin Xu Hanyu Jiang Ting Duan Yuanan Wu Yali Qu Yinan Chen Bin Song |
| author_sort | Tianying Zheng |
| collection | DOAJ |
| description | Abstract Objectives To develop and externally validate a fully automated diagnostic convolutional neural network (CNN) model for cirrhosis based on liver MRI and serum biomarkers. Methods This multicenter retrospective study included consecutive patients receiving pathological evaluation of liver fibrosis stage and contrast-enhanced liver MRI between March 2010 and January 2024. On the training dataset, an MRI-based CNN model was constructed for cirrhosis against pathology, and then a combined model was developed integrating the CNN model and serum biomarkers. On the testing datasets, the area under the receiver operating characteristic curve (AUC) was computed to compare the diagnostic performance of the combined model with that of aminotransferase-to-platelet ratio index (APRI), fibrosis-4 index (FIB-4), and radiologists. The influence of potential confounders on the diagnostic performance was evaluated by subgroup analyses. Results A total of 1315 patients (median age, 54 years; 1065 men; training, n = 840) were included, 855 (65%) with pathological cirrhosis. The CNN model was constructed on pre-contrast T1- and T2-weighted imaging, and the combined model was developed integrating the CNN model, age, and eight serum biomarkers. On the external testing dataset, the combined model achieved an AUC of 0.86, which outperformed FIB-4, APRI and two radiologists (AUC: 0.67 to 0.73, all p < 0.05). Subgroup analyses revealed comparable diagnostic performances of the combined model in patients with different sizes of focal liver lesions. Conclusion Based on pre-contrast T1- and T2-weighted imaging, age, and serum biomarkers, the combined model allowed diagnosis of cirrhosis with moderate accuracy, independent of the size of focal liver lesions. Critical relevance statement The fully automated convolutional neural network model utilizing pre-contrast MR imaging, age and serum biomarkers demonstrated moderate accuracy, outperforming FIB-4, APRI, and radiologists, independent of size of focal liver lesions, potentially facilitating noninvasive diagnosis of cirrhosis pending further validation. Key Points 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. Graphical Abstract |
| format | Article |
| id | doaj-art-c8891e2c83c74764aa08eb3490ffda14 |
| institution | OA Journals |
| issn | 1869-4101 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Insights into Imaging |
| spelling | doaj-art-c8891e2c83c74764aa08eb3490ffda142025-08-20T02:37:55ZengSpringerOpenInsights into Imaging1869-41012024-12-0115111310.1186/s13244-024-01872-9Fully automated MRI-based convolutional neural network for noninvasive diagnosis of cirrhosisTianying Zheng0Yajing Zhu1Yidi Chen2Shengshi Mai3Lixin Xu4Hanyu Jiang5Ting Duan6Yuanan Wu7Yali Qu8Yinan Chen9Bin Song10Department of Radiology, West China Hospital, Sichuan UniversitySenseTime ResearchDepartment of Radiology, West China Hospital, Sichuan UniversityDepartment of Radiology, Sanya People’s HospitalSenseTime ResearchDepartment of Radiology, West China Hospital, Sichuan UniversityDepartment of Radiology, West China Hospital, Sichuan UniversityDepartment of Radiology, West China Hospital, Sichuan UniversityDepartment of Radiology, West China Hospital, Sichuan UniversitySenseTime ResearchDepartment of Radiology, West China Hospital, Sichuan UniversityAbstract Objectives To develop and externally validate a fully automated diagnostic convolutional neural network (CNN) model for cirrhosis based on liver MRI and serum biomarkers. Methods This multicenter retrospective study included consecutive patients receiving pathological evaluation of liver fibrosis stage and contrast-enhanced liver MRI between March 2010 and January 2024. On the training dataset, an MRI-based CNN model was constructed for cirrhosis against pathology, and then a combined model was developed integrating the CNN model and serum biomarkers. On the testing datasets, the area under the receiver operating characteristic curve (AUC) was computed to compare the diagnostic performance of the combined model with that of aminotransferase-to-platelet ratio index (APRI), fibrosis-4 index (FIB-4), and radiologists. The influence of potential confounders on the diagnostic performance was evaluated by subgroup analyses. Results A total of 1315 patients (median age, 54 years; 1065 men; training, n = 840) were included, 855 (65%) with pathological cirrhosis. The CNN model was constructed on pre-contrast T1- and T2-weighted imaging, and the combined model was developed integrating the CNN model, age, and eight serum biomarkers. On the external testing dataset, the combined model achieved an AUC of 0.86, which outperformed FIB-4, APRI and two radiologists (AUC: 0.67 to 0.73, all p < 0.05). Subgroup analyses revealed comparable diagnostic performances of the combined model in patients with different sizes of focal liver lesions. Conclusion Based on pre-contrast T1- and T2-weighted imaging, age, and serum biomarkers, the combined model allowed diagnosis of cirrhosis with moderate accuracy, independent of the size of focal liver lesions. Critical relevance statement The fully automated convolutional neural network model utilizing pre-contrast MR imaging, age and serum biomarkers demonstrated moderate accuracy, outperforming FIB-4, APRI, and radiologists, independent of size of focal liver lesions, potentially facilitating noninvasive diagnosis of cirrhosis pending further validation. Key Points 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. Graphical Abstracthttps://doi.org/10.1186/s13244-024-01872-9Deep learningLiver cirrhosisMagnetic resonance imagingNeural networksComputer |
| spellingShingle | Tianying Zheng Yajing Zhu Yidi Chen Shengshi Mai Lixin Xu Hanyu Jiang Ting Duan Yuanan Wu Yali Qu Yinan Chen Bin Song Fully automated MRI-based convolutional neural network for noninvasive diagnosis of cirrhosis Insights into Imaging Deep learning Liver cirrhosis Magnetic resonance imaging Neural networks Computer |
| title | Fully automated MRI-based convolutional neural network for noninvasive diagnosis of cirrhosis |
| title_full | Fully automated MRI-based convolutional neural network for noninvasive diagnosis of cirrhosis |
| title_fullStr | Fully automated MRI-based convolutional neural network for noninvasive diagnosis of cirrhosis |
| title_full_unstemmed | Fully automated MRI-based convolutional neural network for noninvasive diagnosis of cirrhosis |
| title_short | Fully automated MRI-based convolutional neural network for noninvasive diagnosis of cirrhosis |
| title_sort | fully automated mri based convolutional neural network for noninvasive diagnosis of cirrhosis |
| topic | Deep learning Liver cirrhosis Magnetic resonance imaging Neural networks Computer |
| url | https://doi.org/10.1186/s13244-024-01872-9 |
| work_keys_str_mv | AT tianyingzheng fullyautomatedmribasedconvolutionalneuralnetworkfornoninvasivediagnosisofcirrhosis AT yajingzhu fullyautomatedmribasedconvolutionalneuralnetworkfornoninvasivediagnosisofcirrhosis AT yidichen fullyautomatedmribasedconvolutionalneuralnetworkfornoninvasivediagnosisofcirrhosis AT shengshimai fullyautomatedmribasedconvolutionalneuralnetworkfornoninvasivediagnosisofcirrhosis AT lixinxu fullyautomatedmribasedconvolutionalneuralnetworkfornoninvasivediagnosisofcirrhosis AT hanyujiang fullyautomatedmribasedconvolutionalneuralnetworkfornoninvasivediagnosisofcirrhosis AT tingduan fullyautomatedmribasedconvolutionalneuralnetworkfornoninvasivediagnosisofcirrhosis AT yuananwu fullyautomatedmribasedconvolutionalneuralnetworkfornoninvasivediagnosisofcirrhosis AT yaliqu fullyautomatedmribasedconvolutionalneuralnetworkfornoninvasivediagnosisofcirrhosis AT yinanchen fullyautomatedmribasedconvolutionalneuralnetworkfornoninvasivediagnosisofcirrhosis AT binsong fullyautomatedmribasedconvolutionalneuralnetworkfornoninvasivediagnosisofcirrhosis |