Literature DB >> 33728532

A radiomic-based model of different contrast-enhanced CT phase for differentiate intrahepatic cholangiocarcinoma from inflammatory mass with hepatolithiasis.

Beihui Xue1, Sunjie Wu1, Mingyue Zhang1, Junjie Hong1, Bole Liu1, Nina Xu1, Qiqiang Zeng2, Kun Tang1, Xiangwu Zheng3.   

Abstract

BACKGROUND: Intrahepatic cholangiocarcinoma (ICC) is hard to distinguish from inflammatory mass (IM) complicated with hepatolithiasis in clinical practice preoperatively. This study looked to develop and confirm the radiomics models to make a distinction between ICC with hepatolithiasis from IM and to compare the results of different contrast-enhanced computed tomography (CT) phase.
METHODS: The models were developed in a training cohort of 110 patients from January 2005 to June 2020. Radiomics features were extracted from both arterial phase and portal venous phase contrast-enhanced computed tomography (CT) scans. The radiomics scores based on radiomics features, were built by logistic regression after using the least absolute shrinkage and selection operator (LASSO) method. The rad-scores of two contrast -enhanced CT phases and clinical features were incorporated into a novel model. The performance of the models were determined by theirs discrimination, calibration, and clinical usefulness. The models were externally validated in 35 consecutive patients.
RESULTS: The radiomics signature comprised two features in arterial phase (training cohort, AUC = 0.809, sensitivity 0.700, specificity 0.848, and accuracy 0.774;validation cohort, AUC = 0.790, sensitivity 0.714, specificity 0.800, and accuracy 0.757) and three related features in portal venous phase (training cohort, AUC = 0.801, sensitivity 0.800, specificity 0.717, and accuracy 0.759; validation cohort, AUC = 0.830, sensitivity 0.700, specificity 0.750, and accuracy 0.775) showed significant association with ICC in both cohorts (P < 0.05).We also developed a model only based on clinical variables (training cohort, AUC = 0.778, sensitivity 0.567, specificity 0.891, and accuracy 0.729; validation cohort, AUC = 0.788, sensitivity 0.571, specificity 0.950, and accuracy 0.761). The radiomics-based model contained rad-score of two phases and two clinical factors (CEA and CA19-9) showed the best performance (training cohort, AUC = 0.864, sensitivity 0.867, specificity 0.804, and accuracy 0.836; validation cohort, AUC = 0.843, sensitivity 0.643, specificity 0.980, and accuracy 0.821).
CONCLUSIONS: Our radiomics-based models provided a diagnostic tool for differentiate intrahepatic cholangiocarcinoma (ICC) from inflammatory mass (IM) with hepatolithiasis both in arterial phase and portal venous phase. To go a step further, the diagnostic accuracy will improved by a clinico-radiologic model.
© 2021. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Entities:  

Keywords:  Hepatolithiasis; Inflammatory mass(IM); Intrahepatic cholangiocarcinoma (ICC); Radiomics

Mesh:

Year:  2021        PMID: 33728532     DOI: 10.1007/s00261-021-03027-6

Source DB:  PubMed          Journal:  Abdom Radiol (NY)


  3 in total

1.  Factors predicting concurrent cholangiocarcinomas associated with hepatolithiasis.

Authors:  Y-T Kim; J S Byun; J Kim; Y H Jang; W J Lee; J K Ryu; S W Kim; Y B Yoon; C Y Kim
Journal:  Hepatogastroenterology       Date:  2003 Jan-Feb

2.  Intrahepatic stones associated with cholangiocarcinoma.

Authors:  M F Chen; Y Y Jan; C S Wang; L B Jeng; T L Hwang; S C Chen
Journal:  Am J Gastroenterol       Date:  1989-04       Impact factor: 10.864

3.  Clinical Significance of Preoperative Serum CEA, CA125, and CA19-9 Levels in Predicting the Resectability of Cholangiocarcinoma.

Authors:  Tianyi Fang; Hao Wang; Yunfu Cui; Zhidong Wang; Yufu Wang; Xuan Lin
Journal:  Dis Markers       Date:  2019-02-04       Impact factor: 3.464

  3 in total
  3 in total

Review 1.  Radiomics of Biliary Tumors: A Systematic Review of Current Evidence.

Authors:  Francesco Fiz; Visala S Jayakody Arachchige; Matteo Gionso; Ilaria Pecorella; Apoorva Selvam; Dakota Russell Wheeler; Martina Sollini; Luca Viganò
Journal:  Diagnostics (Basel)       Date:  2022-03-28

2.  Development and Validation of a Radiomics Nomogram for Differentiating Pulmonary Cryptococcosis and Lung Adenocarcinoma in Solitary Pulmonary Solid Nodule.

Authors:  Jiabi Zhao; Lin Sun; Ke Sun; Tingting Wang; Bin Wang; Yang Yang; Chunyan Wu; Xiwen Sun
Journal:  Front Oncol       Date:  2021-11-09       Impact factor: 6.244

3.  An update on radiomics techniques in primary liver cancers.

Authors:  Vincenza Granata; Roberta Fusco; Sergio Venazio Setola; Igino Simonetti; Diletta Cozzi; Giulia Grazzini; Francesca Grassi; Andrea Belli; Vittorio Miele; Francesco Izzo; Antonella Petrillo
Journal:  Infect Agent Cancer       Date:  2022-03-04       Impact factor: 2.965

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.