A Lesion-Based Response Prediction Model Using Pretherapy PET/CT Image Features for Y90 Radioembolization to Hepatic Malignancies

Rahul Mehta, Kejia Cai, Nishant Kumar, Grace Knuttinen, Thomas M. Anderson, Hui Lu, Yang Lu

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

We present a probabilistic approach to identify patients with primary and secondary hepatic malignancies as responders or nonresponders to yttrium-90 radioembolization therapy. Recent advances in computer-aided detection have decreased false-negative and false-positive rates of perceived abnormalities; however, there is limited research in using similar concepts to predict treatment response. Our approach is driven by the goal of precision medicine to determine pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography imaging parameters to facilitate the identification of patients who would benefit most from yttrium-90 radioembolization therapy, while avoiding complex and costly procedures for those who would not. Our algorithm seeks to predict a patient’s response by discovering common co-occurring image patterns in the lesions of baseline fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography scans by extracting invariant shape and texture features. The extracted imaging features were represented as a distribution of each subject based on the bag-of-feature paradigm. The distribution was applied in a multinomial naive Bayes classifier to predict whether a patient would be a responder or nonresponder to yttrium-90 radioembolization therapy based on the imaging features of a pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography scan. Comprehensive published criteria were used to determine lesion-based clinical treatment response based on fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography imaging findings. Our results show that the model is able to predict a patient with liver cancer as a responder or nonresponder to yttrium-90 radioembolization therapy with a sensitivity of 0.791 using extracted invariant imaging features from the pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography test. The sensitivity increased to 0.821 when combining extracted invariant image features with variable features of tumor volume.

Original languageEnglish (US)
Pages (from-to)620-629
Number of pages10
JournalTechnology in Cancer Research and Treatment
Volume16
Issue number5
DOIs
StatePublished - Oct 1 2017
Externally publishedYes

Fingerprint

Fluorine
Yttrium
Liver
Glucose
Neoplasms
Therapeutics
Precision Medicine
Liver Neoplasms
Tumor Burden
Positron Emission Tomography Computed Tomography
Research

Keywords

  • FDG PET/CT
  • liver cancer
  • machine vision
  • pretherapy
  • therapy response prediction
  • Y90 radioembolization

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Cite this

A Lesion-Based Response Prediction Model Using Pretherapy PET/CT Image Features for Y90 Radioembolization to Hepatic Malignancies. / Mehta, Rahul; Cai, Kejia; Kumar, Nishant; Knuttinen, Grace; Anderson, Thomas M.; Lu, Hui; Lu, Yang.

In: Technology in Cancer Research and Treatment, Vol. 16, No. 5, 01.10.2017, p. 620-629.

Research output: Contribution to journalArticle

Mehta, Rahul ; Cai, Kejia ; Kumar, Nishant ; Knuttinen, Grace ; Anderson, Thomas M. ; Lu, Hui ; Lu, Yang. / A Lesion-Based Response Prediction Model Using Pretherapy PET/CT Image Features for Y90 Radioembolization to Hepatic Malignancies. In: Technology in Cancer Research and Treatment. 2017 ; Vol. 16, No. 5. pp. 620-629.
@article{e5c9b252543e4873970e6c04daa2df73,
title = "A Lesion-Based Response Prediction Model Using Pretherapy PET/CT Image Features for Y90 Radioembolization to Hepatic Malignancies",
abstract = "We present a probabilistic approach to identify patients with primary and secondary hepatic malignancies as responders or nonresponders to yttrium-90 radioembolization therapy. Recent advances in computer-aided detection have decreased false-negative and false-positive rates of perceived abnormalities; however, there is limited research in using similar concepts to predict treatment response. Our approach is driven by the goal of precision medicine to determine pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography imaging parameters to facilitate the identification of patients who would benefit most from yttrium-90 radioembolization therapy, while avoiding complex and costly procedures for those who would not. Our algorithm seeks to predict a patient’s response by discovering common co-occurring image patterns in the lesions of baseline fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography scans by extracting invariant shape and texture features. The extracted imaging features were represented as a distribution of each subject based on the bag-of-feature paradigm. The distribution was applied in a multinomial naive Bayes classifier to predict whether a patient would be a responder or nonresponder to yttrium-90 radioembolization therapy based on the imaging features of a pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography scan. Comprehensive published criteria were used to determine lesion-based clinical treatment response based on fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography imaging findings. Our results show that the model is able to predict a patient with liver cancer as a responder or nonresponder to yttrium-90 radioembolization therapy with a sensitivity of 0.791 using extracted invariant imaging features from the pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography test. The sensitivity increased to 0.821 when combining extracted invariant image features with variable features of tumor volume.",
keywords = "FDG PET/CT, liver cancer, machine vision, pretherapy, therapy response prediction, Y90 radioembolization",
author = "Rahul Mehta and Kejia Cai and Nishant Kumar and Grace Knuttinen and Anderson, {Thomas M.} and Hui Lu and Yang Lu",
year = "2017",
month = "10",
day = "1",
doi = "10.1177/1533034616666721",
language = "English (US)",
volume = "16",
pages = "620--629",
journal = "Technology in Cancer Research and Treatment",
issn = "1533-0346",
publisher = "Adenine Press",
number = "5",

}

TY - JOUR

T1 - A Lesion-Based Response Prediction Model Using Pretherapy PET/CT Image Features for Y90 Radioembolization to Hepatic Malignancies

AU - Mehta, Rahul

AU - Cai, Kejia

AU - Kumar, Nishant

AU - Knuttinen, Grace

AU - Anderson, Thomas M.

AU - Lu, Hui

AU - Lu, Yang

PY - 2017/10/1

Y1 - 2017/10/1

N2 - We present a probabilistic approach to identify patients with primary and secondary hepatic malignancies as responders or nonresponders to yttrium-90 radioembolization therapy. Recent advances in computer-aided detection have decreased false-negative and false-positive rates of perceived abnormalities; however, there is limited research in using similar concepts to predict treatment response. Our approach is driven by the goal of precision medicine to determine pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography imaging parameters to facilitate the identification of patients who would benefit most from yttrium-90 radioembolization therapy, while avoiding complex and costly procedures for those who would not. Our algorithm seeks to predict a patient’s response by discovering common co-occurring image patterns in the lesions of baseline fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography scans by extracting invariant shape and texture features. The extracted imaging features were represented as a distribution of each subject based on the bag-of-feature paradigm. The distribution was applied in a multinomial naive Bayes classifier to predict whether a patient would be a responder or nonresponder to yttrium-90 radioembolization therapy based on the imaging features of a pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography scan. Comprehensive published criteria were used to determine lesion-based clinical treatment response based on fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography imaging findings. Our results show that the model is able to predict a patient with liver cancer as a responder or nonresponder to yttrium-90 radioembolization therapy with a sensitivity of 0.791 using extracted invariant imaging features from the pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography test. The sensitivity increased to 0.821 when combining extracted invariant image features with variable features of tumor volume.

AB - We present a probabilistic approach to identify patients with primary and secondary hepatic malignancies as responders or nonresponders to yttrium-90 radioembolization therapy. Recent advances in computer-aided detection have decreased false-negative and false-positive rates of perceived abnormalities; however, there is limited research in using similar concepts to predict treatment response. Our approach is driven by the goal of precision medicine to determine pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography imaging parameters to facilitate the identification of patients who would benefit most from yttrium-90 radioembolization therapy, while avoiding complex and costly procedures for those who would not. Our algorithm seeks to predict a patient’s response by discovering common co-occurring image patterns in the lesions of baseline fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography scans by extracting invariant shape and texture features. The extracted imaging features were represented as a distribution of each subject based on the bag-of-feature paradigm. The distribution was applied in a multinomial naive Bayes classifier to predict whether a patient would be a responder or nonresponder to yttrium-90 radioembolization therapy based on the imaging features of a pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography scan. Comprehensive published criteria were used to determine lesion-based clinical treatment response based on fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography imaging findings. Our results show that the model is able to predict a patient with liver cancer as a responder or nonresponder to yttrium-90 radioembolization therapy with a sensitivity of 0.791 using extracted invariant imaging features from the pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography test. The sensitivity increased to 0.821 when combining extracted invariant image features with variable features of tumor volume.

KW - FDG PET/CT

KW - liver cancer

KW - machine vision

KW - pretherapy

KW - therapy response prediction

KW - Y90 radioembolization

UR - http://www.scopus.com/inward/record.url?scp=85028045504&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028045504&partnerID=8YFLogxK

U2 - 10.1177/1533034616666721

DO - 10.1177/1533034616666721

M3 - Article

C2 - 27601017

AN - SCOPUS:85028045504

VL - 16

SP - 620

EP - 629

JO - Technology in Cancer Research and Treatment

JF - Technology in Cancer Research and Treatment

SN - 1533-0346

IS - 5

ER -