2023
Chen, Jianan; Cheung, Helen M C; Karanicolas, Paul J; Coburn, Natalie G; Martel, Guillaume; Lee, Albert; Patel, Chirag; Milot, Laurent; Martel, Anne L
A radiomic biomarker for prognosis of resected colorectal cancer liver metastases generalizes across MRI contrast agents Journal Article
In: Frontiers in Oncology, vol. 13, pp. 898854, 2023, ISSN: 2234-943X.
Abstract | Links | BibTeX | Tags: colorectal cancer, contrast agents, liver, metastasis, MRI, radiomics
@article{Chen2023,
title = {A radiomic biomarker for prognosis of resected colorectal cancer liver metastases generalizes across MRI contrast agents},
author = {Jianan Chen and Helen M C Cheung and Paul J Karanicolas and Natalie G Coburn and Guillaume Martel and Albert Lee and Chirag Patel and Laurent Milot and Anne L Martel},
url = {http://www.ncbi.nlm.nih.gov/pubmed/36816920 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC9932499 https://www.frontiersin.org/articles/10.3389/fonc.2023.898854/full},
doi = {10.3389/fonc.2023.898854},
issn = {2234-943X},
year = {2023},
date = {2023-02-01},
journal = {Frontiers in Oncology},
volume = {13},
pages = {898854},
abstract = {INTRODUCTION Contrast-enhanced MRI is routinely performed as part of preoperative work-up for patients with Colorectal Cancer Liver Metastases (CRLM). Radiomic biomarkers depicting the characteristics of CRLMs in MRI have been associated with overall survival (OS) of patients, but the reproducibility and clinical applicability of these biomarkers are limited due to the variations in MRI protocols between hospitals. METHODS In this work, we propose a generalizable radiomic model for predicting OS of CRLM patients who received preoperative chemotherapy and delayed-phase contrast enhanced (DPCE) MRIs prior to hepatic resection. This retrospective two-center study included three DPCE MRI cohorts (n=221) collected between January 2006 and December 2012. A 10-minute delayed Gd-DO3A-butrol enhanced MRI discovery cohort was used to select features based on robustness across contrast agents, correlation with OS and pairwise Pearson correlation, and to train a logistic regression model that predicts 3-year OS. RESULTS The model was evaluated on a 10-minute delayed Gd-DO3A-butrol enhanced MRI validation cohort (n=121), a 20-minute delayed Gd-EOB-DTPA (n=72) cohort from the same institute, and a 5-minute delayed Gd-DTPA cohort (n=28) from an independent institute. Two features were selected: minor axis length and dependence variance. The radiomic signature model stratified high-risk and low-risk CRLM groups in the Gd-DO3Abutrol (HR = 6.29},
keywords = {colorectal cancer, contrast agents, liver, metastasis, MRI, radiomics},
pubstate = {published},
tppubtype = {article}
}
2019
Chen, Jianan; Milot, Laurent; Cheung, Helen M C; Martel, Anne L.
Unsupervised Clustering of Quantitative Imaging Phenotypes Using Autoencoder and Gaussian Mixture Model Book Section
In: MICCAI . International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 575–582, Shenzhen, China, 2019.
Abstract | Links | BibTeX | Tags: MRI, probabilistic generative modeling, radiomics, unsupervised clustering
@incollection{Chen2019b,
title = {Unsupervised Clustering of Quantitative Imaging Phenotypes Using Autoencoder and Gaussian Mixture Model},
author = {Jianan Chen and Laurent Milot and Helen M C Cheung and Anne L. Martel},
url = {http://link.springer.com/10.1007/978-3-030-32251-9_63},
doi = {10.1007/978-3-030-32251-9_63},
year = {2019},
date = {2019-01-01},
urldate = {2019-01-01},
booktitle = {MICCAI . International Conference on Medical Image Computing and Computer-Assisted Intervention},
pages = {575–582},
address = {Shenzhen, China},
abstract = {Quantitative medical image computing (radiomics) has been widely applied to build prediction models from medical images. However, overfitting is a significant issue in conventional radiomics, where a large number of radiomic features are directly used to train and test models that predict genotypes or clinical outcomes. In order to tackle this problem, we propose an unsupervised learning pipeline composed of an autoencoder for representation learning of radiomic features and a Gaussian mixture model based on minimum message length criterion for clustering. By incorporating probabilistic modeling, disease heterogeneity has been taken into account. The performance of the proposed pipeline was evaluated on an institutional MRI cohort of 108 patients with colorectal cancer liver metastases. Our approach is capable of automatically selecting the optimal number of clusters and assigns patients into clusters (imaging subtypes) with significantly different survival rates. Our method outperforms other unsupervised clustering methods that have been used for radiomics analysis and has comparable performance to a state-of-the-art imaging biomarker.},
keywords = {MRI, probabilistic generative modeling, radiomics, unsupervised clustering},
pubstate = {published},
tppubtype = {incollection}
}