MRI-based deep learning radiomics to differentiate dual-phenotype hepatocellular carcinoma from HCC and intrahepatic cholangiocarcinoma: a multicenter study
Abstract Objectives To develop and validate radiomics and deep learning models based on contrast-enhanced MRI (CE-MRI) for differentiating dual-phenotype hepatocellular carcinoma (DPHCC) from HCC and intrahepatic cholangiocarcinoma (ICC). Methods Our study consisted of 381 patients from four centers...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Insights into Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13244-025-01904-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571611804336128 |
|---|---|
| author | Qian Wu Tao Zhang Fan Xu Lixiu Cao Wenhao Gu Wenjing Zhu Yanfen Fan Ximing Wang Chunhong Hu Yixing Yu |
| author_facet | Qian Wu Tao Zhang Fan Xu Lixiu Cao Wenhao Gu Wenjing Zhu Yanfen Fan Ximing Wang Chunhong Hu Yixing Yu |
| author_sort | Qian Wu |
| collection | DOAJ |
| description | Abstract Objectives To develop and validate radiomics and deep learning models based on contrast-enhanced MRI (CE-MRI) for differentiating dual-phenotype hepatocellular carcinoma (DPHCC) from HCC and intrahepatic cholangiocarcinoma (ICC). Methods Our study consisted of 381 patients from four centers with 138 HCCs, 122 DPHCCs, and 121 ICCs (244 for training and 62 for internal tests, centers 1 and 2; 75 for external tests, centers 3 and 4). Radiomics, deep transfer learning (DTL), and fusion models based on CE-MRI were established for differential diagnosis, respectively, and their diagnostic performances were compared using the confusion matrix and area under the receiver operating characteristic (ROC) curve (AUC). Results The radiomics model demonstrated competent diagnostic performance, with a macro-AUC exceeding 0.9, and both accuracy and F1-score above 0.75 in the internal and external validation sets. Notably, the vgg19-combined model outperformed the radiomics and other DTL models. The fusion model based on vgg19 further improved diagnostic performance, achieving a macro-AUC of 0.990 (95% CI: 0.965–1.000), an accuracy of 0.935, and an F1-score of 0.937 in the internal test set. In the external test set, it similarly performed well, with a macro-AUC of 0.988 (95% CI: 0.964–1.000), accuracy of 0.875, and an F1-score of 0.885. Conclusions Both the radiomics and the DTL models were able to differentiate DPHCC from HCC and ICC before surgery. The fusion models showed better diagnostic accuracy, which has important value in clinical application. Critical relevance statement MRI-based deep learning radiomics were able to differentiate DPHCC from HCC and ICC preoperatively, aiding clinicians in the identification and targeted treatment of these malignant hepatic tumors. Key Points Fusion models may yield an incremental value over radiomics models in differential diagnosis. Radiomics and deep learning effectively differentiate the three types of malignant hepatic tumors. The fusion models may enhance clinical decision-making for malignant hepatic tumors. Graphical Abstract |
| format | Article |
| id | doaj-art-bcdb80f47c1c486fb82fdc7c84174a90 |
| institution | Kabale University |
| issn | 1869-4101 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Insights into Imaging |
| spelling | doaj-art-bcdb80f47c1c486fb82fdc7c84174a902025-02-02T12:27:52ZengSpringerOpenInsights into Imaging1869-41012025-01-0116111510.1186/s13244-025-01904-yMRI-based deep learning radiomics to differentiate dual-phenotype hepatocellular carcinoma from HCC and intrahepatic cholangiocarcinoma: a multicenter studyQian Wu0Tao Zhang1Fan Xu2Lixiu Cao3Wenhao Gu4Wenjing Zhu5Yanfen Fan6Ximing Wang7Chunhong Hu8Yixing Yu9Department of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, Affiliated Nantong Hospital 3 of Nantong UniversityCancer Center, Zhongshan Hospital, Fudan UniversityDepartment of Nuclear Medical Imaging, Tangshan People’s HospitalThe First People’s Hospital of TaicangDepartment of Radiology, Affiliated Nantong Hospital 3 of Nantong UniversityDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityAbstract Objectives To develop and validate radiomics and deep learning models based on contrast-enhanced MRI (CE-MRI) for differentiating dual-phenotype hepatocellular carcinoma (DPHCC) from HCC and intrahepatic cholangiocarcinoma (ICC). Methods Our study consisted of 381 patients from four centers with 138 HCCs, 122 DPHCCs, and 121 ICCs (244 for training and 62 for internal tests, centers 1 and 2; 75 for external tests, centers 3 and 4). Radiomics, deep transfer learning (DTL), and fusion models based on CE-MRI were established for differential diagnosis, respectively, and their diagnostic performances were compared using the confusion matrix and area under the receiver operating characteristic (ROC) curve (AUC). Results The radiomics model demonstrated competent diagnostic performance, with a macro-AUC exceeding 0.9, and both accuracy and F1-score above 0.75 in the internal and external validation sets. Notably, the vgg19-combined model outperformed the radiomics and other DTL models. The fusion model based on vgg19 further improved diagnostic performance, achieving a macro-AUC of 0.990 (95% CI: 0.965–1.000), an accuracy of 0.935, and an F1-score of 0.937 in the internal test set. In the external test set, it similarly performed well, with a macro-AUC of 0.988 (95% CI: 0.964–1.000), accuracy of 0.875, and an F1-score of 0.885. Conclusions Both the radiomics and the DTL models were able to differentiate DPHCC from HCC and ICC before surgery. The fusion models showed better diagnostic accuracy, which has important value in clinical application. Critical relevance statement MRI-based deep learning radiomics were able to differentiate DPHCC from HCC and ICC preoperatively, aiding clinicians in the identification and targeted treatment of these malignant hepatic tumors. Key Points Fusion models may yield an incremental value over radiomics models in differential diagnosis. Radiomics and deep learning effectively differentiate the three types of malignant hepatic tumors. The fusion models may enhance clinical decision-making for malignant hepatic tumors. Graphical Abstracthttps://doi.org/10.1186/s13244-025-01904-yLiver cancerMagnetic resonance imagingRadiomicsDeep learningDifferential diagnosis |
| spellingShingle | Qian Wu Tao Zhang Fan Xu Lixiu Cao Wenhao Gu Wenjing Zhu Yanfen Fan Ximing Wang Chunhong Hu Yixing Yu MRI-based deep learning radiomics to differentiate dual-phenotype hepatocellular carcinoma from HCC and intrahepatic cholangiocarcinoma: a multicenter study Insights into Imaging Liver cancer Magnetic resonance imaging Radiomics Deep learning Differential diagnosis |
| title | MRI-based deep learning radiomics to differentiate dual-phenotype hepatocellular carcinoma from HCC and intrahepatic cholangiocarcinoma: a multicenter study |
| title_full | MRI-based deep learning radiomics to differentiate dual-phenotype hepatocellular carcinoma from HCC and intrahepatic cholangiocarcinoma: a multicenter study |
| title_fullStr | MRI-based deep learning radiomics to differentiate dual-phenotype hepatocellular carcinoma from HCC and intrahepatic cholangiocarcinoma: a multicenter study |
| title_full_unstemmed | MRI-based deep learning radiomics to differentiate dual-phenotype hepatocellular carcinoma from HCC and intrahepatic cholangiocarcinoma: a multicenter study |
| title_short | MRI-based deep learning radiomics to differentiate dual-phenotype hepatocellular carcinoma from HCC and intrahepatic cholangiocarcinoma: a multicenter study |
| title_sort | mri based deep learning radiomics to differentiate dual phenotype hepatocellular carcinoma from hcc and intrahepatic cholangiocarcinoma a multicenter study |
| topic | Liver cancer Magnetic resonance imaging Radiomics Deep learning Differential diagnosis |
| url | https://doi.org/10.1186/s13244-025-01904-y |
| work_keys_str_mv | AT qianwu mribaseddeeplearningradiomicstodifferentiatedualphenotypehepatocellularcarcinomafromhccandintrahepaticcholangiocarcinomaamulticenterstudy AT taozhang mribaseddeeplearningradiomicstodifferentiatedualphenotypehepatocellularcarcinomafromhccandintrahepaticcholangiocarcinomaamulticenterstudy AT fanxu mribaseddeeplearningradiomicstodifferentiatedualphenotypehepatocellularcarcinomafromhccandintrahepaticcholangiocarcinomaamulticenterstudy AT lixiucao mribaseddeeplearningradiomicstodifferentiatedualphenotypehepatocellularcarcinomafromhccandintrahepaticcholangiocarcinomaamulticenterstudy AT wenhaogu mribaseddeeplearningradiomicstodifferentiatedualphenotypehepatocellularcarcinomafromhccandintrahepaticcholangiocarcinomaamulticenterstudy AT wenjingzhu mribaseddeeplearningradiomicstodifferentiatedualphenotypehepatocellularcarcinomafromhccandintrahepaticcholangiocarcinomaamulticenterstudy AT yanfenfan mribaseddeeplearningradiomicstodifferentiatedualphenotypehepatocellularcarcinomafromhccandintrahepaticcholangiocarcinomaamulticenterstudy AT ximingwang mribaseddeeplearningradiomicstodifferentiatedualphenotypehepatocellularcarcinomafromhccandintrahepaticcholangiocarcinomaamulticenterstudy AT chunhonghu mribaseddeeplearningradiomicstodifferentiatedualphenotypehepatocellularcarcinomafromhccandintrahepaticcholangiocarcinomaamulticenterstudy AT yixingyu mribaseddeeplearningradiomicstodifferentiatedualphenotypehepatocellularcarcinomafromhccandintrahepaticcholangiocarcinomaamulticenterstudy |