Personalized Breast Cancer Treatments Using Artificial Intelligence in Radiomics and Pathomics

William T. Tran, Katarzyna Jerzak, Fang I. Lu, Jonathan H. Klein, Sami Tabbarah, Andrew Lagree, Tina Wu, Ivan Rosado-Mendez, E. Law, Khadijeh Saednia, Ali Sadeghi-Naini

Research output: Contribution to journalComment/debate

Abstract

Progress in computing power and advances in medical imaging over recent decades have culminated in new opportunities for artificial intelligence (AI), computer vision, and using radiomics to facilitate clinical decision-making. These opportunities are growing in medical specialties, such as radiology, pathology, and oncology. As medical imaging and pathology are becoming increasingly digitized, it is recently recognized that harnessing data from digital images can yield parameters that reflect the underlying biology and physiology of various malignancies. This greater understanding of the behaviour of cancer can potentially improve on therapeutic strategies. In addition, the use of AI is particularly appealing in oncology to facilitate the detection of malignancies, to predict the likelihood of tumor response to treatments, and to prognosticate the patients' risk of cancer-related mortality. AI will be critical for identifying candidate biomarkers from digital imaging and developing robust and reliable predictive models. These models will be used to personalize oncologic treatment strategies, and identify confounding variables that are related to the complex biology of tumors and diversity of patient-related factors (ie, mining “big data”). This commentary describes the growing body of work focussed on AI for precision oncology. Advances in AI-driven computer vision and machine learning are opening new pathways that can potentially impact patient outcomes through response-guided adaptive treatments and targeted therapies based on radiomic and pathomic analysis.

Original languageEnglish (US)
JournalJournal of Medical Imaging and Radiation Sciences
DOIs
StateAccepted/In press - Jan 1 2019

Fingerprint

Artificial Intelligence
Breast Neoplasms
Neoplasms
Diagnostic Imaging
Therapeutics
Pathology
Confounding Factors (Epidemiology)
Data Mining
Radiology
Biomarkers
Medicine
Mortality

Keywords

  • Breast cancer
  • digital pathology
  • informatics
  • pathology
  • pathomics
  • radiomics

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging

Cite this

Personalized Breast Cancer Treatments Using Artificial Intelligence in Radiomics and Pathomics. / Tran, William T.; Jerzak, Katarzyna; Lu, Fang I.; Klein, Jonathan H.; Tabbarah, Sami; Lagree, Andrew; Wu, Tina; Rosado-Mendez, Ivan; Law, E.; Saednia, Khadijeh; Sadeghi-Naini, Ali.

In: Journal of Medical Imaging and Radiation Sciences, 01.01.2019.

Research output: Contribution to journalComment/debate

Tran, William T. ; Jerzak, Katarzyna ; Lu, Fang I. ; Klein, Jonathan H. ; Tabbarah, Sami ; Lagree, Andrew ; Wu, Tina ; Rosado-Mendez, Ivan ; Law, E. ; Saednia, Khadijeh ; Sadeghi-Naini, Ali. / Personalized Breast Cancer Treatments Using Artificial Intelligence in Radiomics and Pathomics. In: Journal of Medical Imaging and Radiation Sciences. 2019.
@article{6f5b145fb95f46e19c6c51ab17c8d774,
title = "Personalized Breast Cancer Treatments Using Artificial Intelligence in Radiomics and Pathomics",
abstract = "Progress in computing power and advances in medical imaging over recent decades have culminated in new opportunities for artificial intelligence (AI), computer vision, and using radiomics to facilitate clinical decision-making. These opportunities are growing in medical specialties, such as radiology, pathology, and oncology. As medical imaging and pathology are becoming increasingly digitized, it is recently recognized that harnessing data from digital images can yield parameters that reflect the underlying biology and physiology of various malignancies. This greater understanding of the behaviour of cancer can potentially improve on therapeutic strategies. In addition, the use of AI is particularly appealing in oncology to facilitate the detection of malignancies, to predict the likelihood of tumor response to treatments, and to prognosticate the patients' risk of cancer-related mortality. AI will be critical for identifying candidate biomarkers from digital imaging and developing robust and reliable predictive models. These models will be used to personalize oncologic treatment strategies, and identify confounding variables that are related to the complex biology of tumors and diversity of patient-related factors (ie, mining “big data”). This commentary describes the growing body of work focussed on AI for precision oncology. Advances in AI-driven computer vision and machine learning are opening new pathways that can potentially impact patient outcomes through response-guided adaptive treatments and targeted therapies based on radiomic and pathomic analysis.",
keywords = "Breast cancer, digital pathology, informatics, pathology, pathomics, radiomics",
author = "Tran, {William T.} and Katarzyna Jerzak and Lu, {Fang I.} and Klein, {Jonathan H.} and Sami Tabbarah and Andrew Lagree and Tina Wu and Ivan Rosado-Mendez and E. Law and Khadijeh Saednia and Ali Sadeghi-Naini",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.jmir.2019.07.010",
language = "English (US)",
journal = "Journal of Medical Imaging and Radiation Sciences",
issn = "1939-8654",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Personalized Breast Cancer Treatments Using Artificial Intelligence in Radiomics and Pathomics

AU - Tran, William T.

AU - Jerzak, Katarzyna

AU - Lu, Fang I.

AU - Klein, Jonathan H.

AU - Tabbarah, Sami

AU - Lagree, Andrew

AU - Wu, Tina

AU - Rosado-Mendez, Ivan

AU - Law, E.

AU - Saednia, Khadijeh

AU - Sadeghi-Naini, Ali

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Progress in computing power and advances in medical imaging over recent decades have culminated in new opportunities for artificial intelligence (AI), computer vision, and using radiomics to facilitate clinical decision-making. These opportunities are growing in medical specialties, such as radiology, pathology, and oncology. As medical imaging and pathology are becoming increasingly digitized, it is recently recognized that harnessing data from digital images can yield parameters that reflect the underlying biology and physiology of various malignancies. This greater understanding of the behaviour of cancer can potentially improve on therapeutic strategies. In addition, the use of AI is particularly appealing in oncology to facilitate the detection of malignancies, to predict the likelihood of tumor response to treatments, and to prognosticate the patients' risk of cancer-related mortality. AI will be critical for identifying candidate biomarkers from digital imaging and developing robust and reliable predictive models. These models will be used to personalize oncologic treatment strategies, and identify confounding variables that are related to the complex biology of tumors and diversity of patient-related factors (ie, mining “big data”). This commentary describes the growing body of work focussed on AI for precision oncology. Advances in AI-driven computer vision and machine learning are opening new pathways that can potentially impact patient outcomes through response-guided adaptive treatments and targeted therapies based on radiomic and pathomic analysis.

AB - Progress in computing power and advances in medical imaging over recent decades have culminated in new opportunities for artificial intelligence (AI), computer vision, and using radiomics to facilitate clinical decision-making. These opportunities are growing in medical specialties, such as radiology, pathology, and oncology. As medical imaging and pathology are becoming increasingly digitized, it is recently recognized that harnessing data from digital images can yield parameters that reflect the underlying biology and physiology of various malignancies. This greater understanding of the behaviour of cancer can potentially improve on therapeutic strategies. In addition, the use of AI is particularly appealing in oncology to facilitate the detection of malignancies, to predict the likelihood of tumor response to treatments, and to prognosticate the patients' risk of cancer-related mortality. AI will be critical for identifying candidate biomarkers from digital imaging and developing robust and reliable predictive models. These models will be used to personalize oncologic treatment strategies, and identify confounding variables that are related to the complex biology of tumors and diversity of patient-related factors (ie, mining “big data”). This commentary describes the growing body of work focussed on AI for precision oncology. Advances in AI-driven computer vision and machine learning are opening new pathways that can potentially impact patient outcomes through response-guided adaptive treatments and targeted therapies based on radiomic and pathomic analysis.

KW - Breast cancer

KW - digital pathology

KW - informatics

KW - pathology

KW - pathomics

KW - radiomics

UR - http://www.scopus.com/inward/record.url?scp=85070873274&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070873274&partnerID=8YFLogxK

U2 - 10.1016/j.jmir.2019.07.010

DO - 10.1016/j.jmir.2019.07.010

M3 - Comment/debate

JO - Journal of Medical Imaging and Radiation Sciences

JF - Journal of Medical Imaging and Radiation Sciences

SN - 1939-8654

ER -