A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features

British Journal of Cancer
Ashirbani SahaMaciej A Mazurowski

Abstract

Recent studies showed preliminary data on associations of MRI-based imaging phenotypes of breast tumours with breast cancer molecular, genomic, and related characteristics. In this study, we present a comprehensive analysis of this relationship. We analysed a set of 922 patients with invasive breast cancer and pre-operative MRI. The MRIs were analysed by a computer algorithm to extract 529 features of the tumour and the surrounding tissue. Machine-learning-based models based on the imaging features were trained using a portion of the data (461 patients) to predict the following molecular, genomic, and proliferation characteristics: tumour surrogate molecular subtype, oestrogen receptor, progesterone receptor and human epidermal growth factor status, as well as a tumour proliferation marker (Ki-67). Trained models were evaluated on the set of the remaining 461 patients. Multivariate models were predictive of Luminal A subtype with AUC = 0.697 (95% CI: 0.647-0.746, p < .0001), triple negative breast cancer with AUC = 0.654 (95% CI: 0.589-0.727, p < .0001), ER status with AUC = 0.649 (95% CI: 0.591-0.705, p < .001), and PR status with AUC = 0.622 (95% CI: 0.569-0.674, p < .0001). Associations between individual features and subtyp...Continue Reading

References

May 14, 2009·Journal of the National Cancer Institute·Maggie C U CheangTorsten O Nielsen
Apr 10, 2010·IEEE Transactions on Medical Imaging·Nicholas J TustisonJames C Gee
Mar 14, 2012·European Radiology·Laura MartincichFilippo Montemurro
Aug 24, 2012·AJR. American Journal of Roentgenology·Shota YamamotoMichael D Kuo
Nov 21, 2012·Annals of Oncology : Official Journal of the European Society for Medical Oncology·S GuiuJ S Reis-Filho
Sep 11, 2013·The Breast Journal·Janice S SungElizabeth A Morris
Jan 10, 2014·Breast Cancer : the Journal of the Japanese Breast Cancer Society·Ken YamaguchiHiroyuki Irie
Mar 12, 2015·Journal of Magnetic Resonance Imaging : JMRI·Eric Blaschke, Hiroyuki Abe
May 23, 2015·AJR. American Journal of Roentgenology·Richard HaRalph Wynn
Aug 8, 2015·Journal of the American College of Radiology : JACR·Maciej A Mazurowski
Oct 16, 2018·Expert Systems with Applications·Ashirbani SahaMaciej A Mazurowski
Dec 1, 2012·Annals of Oncology : Official Journal of the European Society for Medical Oncology·S GuiuJ S Reis-Filho

❮ Previous
Next ❯

Citations

Jan 24, 2019·Journal of Magnetic Resonance Imaging : JMRI·Maciej A MazurowskiP Kelly Marcom
Apr 30, 2020·Technology in Cancer Research & Treatment·Dong-Man YeTao Yu
Jul 6, 2019·Journal of Magnetic Resonance Imaging : JMRI·Beatriu ReigLinda Moy
Feb 21, 2019·European Radiology·Axel MeinekeJohannes Boos
May 3, 2019·Abdominal Radiology·Zuhir BodalalRegina Beets-Tan
Aug 10, 2019·British Journal of Cancer·Niels Halama
May 7, 2020·Seminars in Cancer Biology·Allegra ContiNicola Toschi
Jan 1, 2021·Biomedicine & Pharmacotherapy = Biomédecine & Pharmacothérapie·Zhen LiuYi Qi
Dec 19, 2020·Diagnostics·Giuliana MoffaFederica Pediconi
May 3, 2019·Computers in Biology and Medicine·Zhe ZhuMaciej A Mazurowski
Apr 28, 2021·Clinical Radiology·H M C Cheung, D Rubin
Mar 31, 2021·Physics in Medicine and Biology·Mingkuan JiangTao Yu
Dec 11, 2019·Academic Radiology·Lars J Grimm, Maciej A Mazurowski
Jan 21, 2022·European Radiology·Yana QiMingyong Han

❮ Previous
Next ❯

Methods Mentioned

BETA
feature extraction

Software Mentioned

R
MATLAB

Related Concepts

Related Feeds

Breast Cancer Triple-N

Breast cancer cells have receptors for estrogen, progesterone, HER2 receptors (also called ERBB2). Triple-negative breast cancers do not have any of these receptors. Here are the latest discoveries pertaining to triple-negative breast cancers.

Cancer Genomics (Keystone)

Cancer genomics approaches employ high-throughput technologies to identify the complete catalog of somatic alterations that characterize the genome, transcriptome and epigenome of cohorts of tumor samples. Discover the latest research using such technologies in this feed.