Machine Learning for Hepatocellular Carcinoma Segmentation at MRI: Radiology In Training

Alex G Raman; Craig Jones; Clifford R Weiss

doi:10.1148/radiol.212386

Machine Learning for Hepatocellular Carcinoma Segmentation at MRI: Radiology In Training

Radiology. 2022 Sep;304(3):509-515. doi: 10.1148/radiol.212386. Epub 2022 May 10.

Authors

Alex G Raman¹, Craig Jones¹, Clifford R Weiss¹

Affiliation

¹ From the Western University of Health Sciences, College of Osteopathic Medicine of the Pacific, 309 E 2nd St, Pomona, CA 91766 (A.G.R.); Department of Computer Science, Malone Center for Engineering in Healthcare, Johns Hopkins University, Balrimore, Md (C.J.); and Department of Radiology and Radiologic Science, Division of Interventional Radiology, Johns Hopkins Hospital, Baltimore, MD (C.R.W.).

PMID: 35536132
DOI: 10.1148/radiol.212386

Abstract

A 68-year-old woman with a history of hepatocellular carcinoma underwent conventional transarterial chemoembolization. Manual tumor segmentation on images, which can be used to assess disease progression, is time consuming and may suffer from interobserver reliability issues. The authors present a how-to guide to develop machine learning algorithms for fully automatic segmentation of hepatocellular carcinoma and other tumors for lesion tracking over time.

Publication types

Case Reports
Review

MeSH terms

Aged
Carcinoma, Hepatocellular* / diagnostic imaging
Carcinoma, Hepatocellular* / pathology
Carcinoma, Hepatocellular* / therapy
Chemoembolization, Therapeutic* / methods
Female
Humans
Liver Neoplasms* / diagnostic imaging
Liver Neoplasms* / pathology
Liver Neoplasms* / therapy
Machine Learning
Magnetic Resonance Imaging / methods
Radiology*
Reproducibility of Results