Machine learning based on gadoxetic acid-enhanced MRI for differentiating atypical intrahepatic mass-forming cholangiocarcinoma from poorly differentiated hepatocellular carcinoma.
Purpose: The study was to develop a Gd-EOB-DTPA-enhanced MRI radiomics model for differentiating atypical intrahepatic mass-forming cholangiocarcinoma (aIMCC) from poorly differentiated hepatocellular carcinoma (pHCC). Materials and methods: A total of 134 patients (51 aIMCC and 83 pHCC) who underwe...
| Publicado en: | Abdominal Radiology Vol. 48; no. 8; pp. 2525 - 2537 |
|---|---|
| Autores principales: | , , , , , , , , |
| Formato: | Journal Article |
| Publicado: |
Springer Nature
Aug2023
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=164801541&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 164801541 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 2366004X JT14 jtl: Abdominal Radiology issn: 2366004X maglogo: N pubinfo: dt: Aug2023 vid: 48 iid: 8 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 164801541 163649281 10.1007/s00261-023-03870-9 164801541 ppf: 2525 ppct: 12 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Machine learning based on gadoxetic acid-enhanced MRI for differentiating atypical intrahepatic mass-forming cholangiocarcinoma from poorly differentiated hepatocellular carcinoma. aug: au: Chen, Xiang Chen, Ying Chen, Haobo Zhu, Jingfen Huang, Renjun Xie, Junjian Zhang, Tao Xie, An Li, Yonggang affil: Department of Radiology, the First Affiliated Hospital of Soochow University, 215000, Suzhou, Jiangsu, People's Republic of China sug: ab: Purpose: The study was to develop a Gd-EOB-DTPA-enhanced MRI radiomics model for differentiating atypical intrahepatic mass-forming cholangiocarcinoma (aIMCC) from poorly differentiated hepatocellular carcinoma (pHCC). Materials and methods: A total of 134 patients (51 aIMCC and 83 pHCC) who underwent Gadoxetic acid-enhanced MRI between March 2016 and March 2022 were enrolled in this study and then randomly assigned to the training and validation cohorts by 7:3 (93 patients and 41 patients, respectively). The radiomics features were extracted from the hepatobiliary phase of Gadoxetic acid-enhanced MRI. In the training cohort, the SelectKBest and the least absolute shrinkage and selection operator (LASSO) were used to select the radiomics features. The clinical, radiomics, and clinical-radiomics model were established using four machine learning algorithms. The performance of the model was evaluated by the receiver operating characteristic (ROC) curve. Comparison of the radiomics and clinical-radiomics model was done by the Delong test. The clinical usefulness of the model was evaluated using decision curve analysis (DCA). Results: In 1132 extracted radiomic features, 15 were selected to develop radiomics signature. For identifying aIMCC and pHCC, the radiomics model constructed by random forest algorithm showed the high performance (AUC = 0.90) in the training cohort. The performance of the clinical-radiomics model (AUC = 0.89) was not significantly different (P = 0.88) from that of the radiomics model constructed by random forest algorithm (AUC = 0.86) in the validation cohort. DCA demonstrated that the clinical-radiomics model constructed by random forest algorithm had a high net clinical benefit. Conclusion: The clinical-radiomics model is an effective tool to distinguish aIMCC from pHCC and may provide additional value for the development of treatment plans. pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|