Comparison of MRI and CT based deep learning radiomics analyses and their combination for diagnosing intrahepatic cholangiocarcinoma.

Journal: Scientific reports
PMID:

Abstract

Intrahepatic cholangiocarcinoma (iCCA) and other subtypes of primary liver cancer (PLC) have overlapping clinical manifestations and radiological characteristics. The objective of this study was to evaluate the efficacy of deep learning (DL) radiomics analysis, performed using computed tomography (CT) and magnetic resonance imaging (MRI), in diagnosing iCCA within PLC. 178 pathologically confirmed PLC patients (training cohort: test cohort = 124: 54) who underwent both CT and MRI examinations was enrolled. Univariate and multivariate analysis was used to identify the significant factors of radiological findings for diagnosing iCCA. DL radiomics analysis was applied to CT and MRI images, respectively. We constructed and evaluated six distinct models: CT DL radiomics (DLRS), CT radiological (R), CT DL radiomics-radiological (DLRR), MRI DL radiomics (DLRS), MRI radiological (R) and MRI DL radiomics-radiological (DLRR). To further explore the diagnostic and predictive value of a cross-modal approach, we developed a fused model that combined DLRR and DLRR. Receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were employed to compare the performance of different models. MRI-based models demonstrated a superior predictive performance than CT-based models in test cohort (AUCs of MRI vs. CT: DLRR, 0.923 vs. 0.880, P = 0.521; DLRS, 0.875 vs. 0.867, P = 0.922; R, 0.859 vs. 0.840, P = 0.808). The CT-MRI cross-modal model yielded the highest AUC of 0.994 and 0.937 in training and test cohorts, respectively. CT- and MRI-based DL radiomics analyses exhibited good performance in diagnosing iCCA, and the CT-MRI cross-modal model may have significant clinical implications on detection of liver malignancies.

Authors

  • Ming Cheng
  • Hanyue Zhang
    Department of Medical Psychology, Nanjing Brain Hospital, Jiangsu, China.
  • Yimin Guo
    Department of Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China.
  • Peijie Lyu
    Department of Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan Province, China; Department of Radiology, Duke University Medical Center, Durham, NC, USA. Electronic address: lvpeijie2@163.com.
  • Jing Yan
    Department of Neurology, Shanghai Pudong New Area People's Hospital, Shanghai, China.
  • Yin Liu
    School of Chemistry and Chemical Engineering, Shandong University, Jinan, China.
  • Pan Liang
    Department of Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
  • Zhigang Ren
    Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China.
  • Jianbo Gao
    Department of Radiology, the First Affiliated Hospital of Zhengzhou University, No. 1, East Jianshe Road, Zhengzhou, 450052, Henan, China. gaojianbo_cancer@163.com.