Radiomics in stratification of pancreatic cystic lesions: Machine learning in action

Vipin Dalal, Joseph Carmicheal, Amaninder Dhaliwal, Maneesh Jain, Sukhwinder Kaur, Surinder K. Batra

Research output: Contribution to journalShort survey

Abstract

Pancreatic cystic lesions (PCLs) are well-known precursors of pancreatic cancer. Their diagnosis can be challenging as their behavior varies from benign to malignant disease. Precise and timely management of malignant pancreatic cysts might prevent transformation to pancreatic cancer. However, the current consensus guidelines, which rely on standard imaging features to predict cyst malignancy potential, are conflicting and unclear. This has led to an increased interest in radiomics, a high-throughput extraction of comprehensible data from standard of care images. Radiomics can be used as a diagnostic and prognostic tool in personalized medicine. It utilizes quantitative image analysis to extract features in conjunction with machine learning and artificial intelligence (AI) methods like support vector machines, random forest, and convolutional neural network for feature selection and classification. Selected features can then serve as imaging biomarkers to predict high-risk PCLs. Radiomics studies conducted heretofore on PCLs have shown promising results. This cost-effective approach would help us to differentiate benign PCLs from malignant ones and potentially guide clinical decision-making leading to better utilization of healthcare resources. In this review, we discuss the process of radiomics, its myriad applications such as diagnosis, prognosis, and prediction of therapy response. We also discuss the outcomes of studies involving radiomic analysis of PCLs and pancreatic cancer, and challenges associated with this novel field along with possible solutions. Although these studies highlight the potential benefit of radiomics in the prevention and optimal treatment of pancreatic cancer, further studies are warranted before incorporating radiomics into the clinical decision support system.

Original languageEnglish (US)
Pages (from-to)228-237
Number of pages10
JournalCancer Letters
Volume469
DOIs
StatePublished - Jan 28 2020

Fingerprint

Pancreatic Neoplasms
Artificial Intelligence
Clinical Decision Support Systems
Pancreatic Cyst
Precision Medicine
Standard of Care
Cysts
Biomarkers
Outcome Assessment (Health Care)
Guidelines
Delivery of Health Care
Costs and Cost Analysis
Machine Learning
Therapeutics
Neoplasms

Keywords

  • Machine learning
  • Pancreatic cancer
  • Pancreatic cystic lesions
  • Radiomics
  • Radiomics in pancreatic cancer

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Cite this

Radiomics in stratification of pancreatic cystic lesions : Machine learning in action. / Dalal, Vipin; Carmicheal, Joseph; Dhaliwal, Amaninder; Jain, Maneesh; Kaur, Sukhwinder; Batra, Surinder K.

In: Cancer Letters, Vol. 469, 28.01.2020, p. 228-237.

Research output: Contribution to journalShort survey

@article{0d2494ab91ac4ef584ecf8f9823d66ea,
title = "Radiomics in stratification of pancreatic cystic lesions: Machine learning in action",
abstract = "Pancreatic cystic lesions (PCLs) are well-known precursors of pancreatic cancer. Their diagnosis can be challenging as their behavior varies from benign to malignant disease. Precise and timely management of malignant pancreatic cysts might prevent transformation to pancreatic cancer. However, the current consensus guidelines, which rely on standard imaging features to predict cyst malignancy potential, are conflicting and unclear. This has led to an increased interest in radiomics, a high-throughput extraction of comprehensible data from standard of care images. Radiomics can be used as a diagnostic and prognostic tool in personalized medicine. It utilizes quantitative image analysis to extract features in conjunction with machine learning and artificial intelligence (AI) methods like support vector machines, random forest, and convolutional neural network for feature selection and classification. Selected features can then serve as imaging biomarkers to predict high-risk PCLs. Radiomics studies conducted heretofore on PCLs have shown promising results. This cost-effective approach would help us to differentiate benign PCLs from malignant ones and potentially guide clinical decision-making leading to better utilization of healthcare resources. In this review, we discuss the process of radiomics, its myriad applications such as diagnosis, prognosis, and prediction of therapy response. We also discuss the outcomes of studies involving radiomic analysis of PCLs and pancreatic cancer, and challenges associated with this novel field along with possible solutions. Although these studies highlight the potential benefit of radiomics in the prevention and optimal treatment of pancreatic cancer, further studies are warranted before incorporating radiomics into the clinical decision support system.",
keywords = "Machine learning, Pancreatic cancer, Pancreatic cystic lesions, Radiomics, Radiomics in pancreatic cancer",
author = "Vipin Dalal and Joseph Carmicheal and Amaninder Dhaliwal and Maneesh Jain and Sukhwinder Kaur and Batra, {Surinder K.}",
year = "2020",
month = "1",
day = "28",
doi = "10.1016/j.canlet.2019.10.023",
language = "English (US)",
volume = "469",
pages = "228--237",
journal = "Cancer Letters",
issn = "0304-3835",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Radiomics in stratification of pancreatic cystic lesions

T2 - Machine learning in action

AU - Dalal, Vipin

AU - Carmicheal, Joseph

AU - Dhaliwal, Amaninder

AU - Jain, Maneesh

AU - Kaur, Sukhwinder

AU - Batra, Surinder K.

PY - 2020/1/28

Y1 - 2020/1/28

N2 - Pancreatic cystic lesions (PCLs) are well-known precursors of pancreatic cancer. Their diagnosis can be challenging as their behavior varies from benign to malignant disease. Precise and timely management of malignant pancreatic cysts might prevent transformation to pancreatic cancer. However, the current consensus guidelines, which rely on standard imaging features to predict cyst malignancy potential, are conflicting and unclear. This has led to an increased interest in radiomics, a high-throughput extraction of comprehensible data from standard of care images. Radiomics can be used as a diagnostic and prognostic tool in personalized medicine. It utilizes quantitative image analysis to extract features in conjunction with machine learning and artificial intelligence (AI) methods like support vector machines, random forest, and convolutional neural network for feature selection and classification. Selected features can then serve as imaging biomarkers to predict high-risk PCLs. Radiomics studies conducted heretofore on PCLs have shown promising results. This cost-effective approach would help us to differentiate benign PCLs from malignant ones and potentially guide clinical decision-making leading to better utilization of healthcare resources. In this review, we discuss the process of radiomics, its myriad applications such as diagnosis, prognosis, and prediction of therapy response. We also discuss the outcomes of studies involving radiomic analysis of PCLs and pancreatic cancer, and challenges associated with this novel field along with possible solutions. Although these studies highlight the potential benefit of radiomics in the prevention and optimal treatment of pancreatic cancer, further studies are warranted before incorporating radiomics into the clinical decision support system.

AB - Pancreatic cystic lesions (PCLs) are well-known precursors of pancreatic cancer. Their diagnosis can be challenging as their behavior varies from benign to malignant disease. Precise and timely management of malignant pancreatic cysts might prevent transformation to pancreatic cancer. However, the current consensus guidelines, which rely on standard imaging features to predict cyst malignancy potential, are conflicting and unclear. This has led to an increased interest in radiomics, a high-throughput extraction of comprehensible data from standard of care images. Radiomics can be used as a diagnostic and prognostic tool in personalized medicine. It utilizes quantitative image analysis to extract features in conjunction with machine learning and artificial intelligence (AI) methods like support vector machines, random forest, and convolutional neural network for feature selection and classification. Selected features can then serve as imaging biomarkers to predict high-risk PCLs. Radiomics studies conducted heretofore on PCLs have shown promising results. This cost-effective approach would help us to differentiate benign PCLs from malignant ones and potentially guide clinical decision-making leading to better utilization of healthcare resources. In this review, we discuss the process of radiomics, its myriad applications such as diagnosis, prognosis, and prediction of therapy response. We also discuss the outcomes of studies involving radiomic analysis of PCLs and pancreatic cancer, and challenges associated with this novel field along with possible solutions. Although these studies highlight the potential benefit of radiomics in the prevention and optimal treatment of pancreatic cancer, further studies are warranted before incorporating radiomics into the clinical decision support system.

KW - Machine learning

KW - Pancreatic cancer

KW - Pancreatic cystic lesions

KW - Radiomics

KW - Radiomics in pancreatic cancer

UR - http://www.scopus.com/inward/record.url?scp=85075371690&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075371690&partnerID=8YFLogxK

U2 - 10.1016/j.canlet.2019.10.023

DO - 10.1016/j.canlet.2019.10.023

M3 - Short survey

C2 - 31629933

AN - SCOPUS:85075371690

VL - 469

SP - 228

EP - 237

JO - Cancer Letters

JF - Cancer Letters

SN - 0304-3835

ER -