Format

Send to

Choose Destination
J Vasc Interv Radiol. 2018 Jun;29(6):850-857.e1. doi: 10.1016/j.jvir.2018.01.769. Epub 2018 Mar 14.

Predicting Treatment Response to Intra-arterial Therapies for Hepatocellular Carcinoma with the Use of Supervised Machine Learning-An Artificial Intelligence Concept.

Author information

1
Department of Radiology and Biomedical Imaging, Yale School of Medicine, 333 Cedar Street, New Haven, CT 06520.
2
Department of Radiology and Biomedical Imaging, Yale School of Medicine, 333 Cedar Street, New Haven, CT 06520; Department of Diagnostic and Interventional Radiology, Universitätsmedizin Charité Berlin, Berlin, Germany.
3
Department of Biomedical Engineering, Yale School of Engineering and Applied Science, New Haven, Connecticut.
4
Philips Research North America, Cambridge, Massachusetts.
5
Prescience Labs, Westport, Connecticut.
6
Department of Radiology and Biomedical Imaging, Yale School of Medicine, 333 Cedar Street, New Haven, CT 06520. Electronic address: julius.chapiro@yale.edu.

Abstract

PURPOSE:

To use magnetic resonance (MR) imaging and clinical patient data to create an artificial intelligence (AI) framework for the prediction of therapeutic outcomes of transarterial chemoembolization by applying machine learning (ML) techniques.

MATERIALS AND METHODS:

This study included 36 patients with hepatocellular carcinoma (HCC) treated with transarterial chemoembolization. The cohort (age 62 ± 8.9 years; 31 men; 13 white; 24 Eastern Cooperative Oncology Group performance status 0, 10 status 1, 2 status 2; 31 Child-Pugh stage A, 4 stage B, 1 stage C; 1 Barcelona Clinic Liver Cancer stage 0, 12 stage A, 10 stage B, 13 stage C; tumor size 5.2 ± 3.0 cm; number of tumors 2.6 ± 1.1; and 30 conventional transarterial chemoembolization, 6 with drug-eluting embolic agents). MR imaging was obtained before and 1 month after transarterial chemoembolization. Image-based tumor response to transarterial chemoembolization was assessed with the use of the 3D quantitative European Association for the Study of the Liver (qEASL) criterion. Clinical information, baseline imaging, and therapeutic features were used to train logistic regression (LR) and random forest (RF) models to predict patients as treatment responders or nonresponders under the qEASL response criterion. The performance of each model was validated using leave-one-out cross-validation.

RESULTS:

Both LR and RF models predicted transarterial chemoembolization treatment response with an overall accuracy of 78% (sensitivity 62.5%, specificity 82.1%, positive predictive value 50.0%, negative predictive value 88.5%). The strongest predictors of treatment response included a clinical variable (presence of cirrhosis) and an imaging variable (relative tumor signal intensity >27.0).

CONCLUSIONS:

Transarterial chemoembolization outcomes in patients with HCC may be predicted before procedures by combining clinical patient data and baseline MR imaging with the use of AI and ML techniques.

PMID:
29548875
PMCID:
PMC5970021
DOI:
10.1016/j.jvir.2018.01.769
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Elsevier Science Icon for PubMed Central
Loading ...
Support Center