Automated Volumetric Assessment of Hepatocellular Carcinoma Response to Sorafenib: A Pilot Study

David Thomas Alfonso Fuentes, Kareem Ahmed, Jonathan S. Lin, Reham Abdelwahab Hassan Ali, Ahmed Kaseb, Manal M Hassan, Janio Szklaruk, Ali Morshid, John D Hazle, Aliya Qayyum, Khaled M Elsayes

Research output: Contribution to journalArticle

Abstract

PURPOSE: This pilot study evaluates the feasibility of automated volumetric quantification of hepatocellular carcinoma (HCC) as an imaging biomarker to assess treatment response for sorafenib. METHODS: In this institutional review board-approved, Health Insurance Portability and Accountability Act-compliant retrospective study, a training database of manually labeled background liver, enhancing and nonenhancing tumor tissue was established using pretherapy and first posttherapy multiphasic computed tomography images from a registry of 13 HCC patients. For each patient, Hounsfield density and geometry-based feature images were generated from registered multiphasic computed tomography data sets and used as the input for a random forest-based classifier of enhancing and nonenhancing tumor tissue. Leave-one-out cross-validation of the dice similarity measure was applied to quantify the classifier accuracy. A Cox regression model was used to confirm volume changes as predictors of time to progression (TTP) of target lesions for both manual and automatic methods. RESULTS: When compared with manual labels, an overall classification accuracy of dice similarity coefficient of 0.71 for pretherapy and 0.66 posttherapy enhancing tumor labels and 0.45 for pretherapy and 0.59 for posttherapy nonenhancing tumor labels was observed. Automated methods for quantifying volumetric changes in the enhancing lesion agreed with manual methods and were observed as a significant predictor of TTP. CONCLUSIONS: Automated volumetric analysis was determined to be feasible for monitoring HCC response to treatment. The information extracted using automated volumetrics is likely to reproduce labor-intensive manual data and provide a good predictor for TTP. Further work will extend these studies to additional treatment modalities and larger patient populations.

Original languageEnglish (US)
Pages (from-to)499-506
Number of pages8
JournalJournal of computer assisted tomography
Volume43
Issue number3
DOIs
StatePublished - May 1 2019

Fingerprint

Hepatocellular Carcinoma
Neoplasms
Tomography
Health Insurance Portability and Accountability Act
Research Ethics Committees
Proportional Hazards Models
Registries
Therapeutics
Retrospective Studies
Biomarkers
Databases
sorafenib
Liver
Population

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Automated Volumetric Assessment of Hepatocellular Carcinoma Response to Sorafenib : A Pilot Study. / Fuentes, David Thomas Alfonso; Ahmed, Kareem; Lin, Jonathan S.; Ali, Reham Abdelwahab Hassan; Kaseb, Ahmed; Hassan, Manal M; Szklaruk, Janio; Morshid, Ali; Hazle, John D; Qayyum, Aliya; Elsayes, Khaled M.

In: Journal of computer assisted tomography, Vol. 43, No. 3, 01.05.2019, p. 499-506.

Research output: Contribution to journalArticle

@article{8aaac1000cf54cacb37b43ddfa4b495e,
title = "Automated Volumetric Assessment of Hepatocellular Carcinoma Response to Sorafenib: A Pilot Study",
abstract = "PURPOSE: This pilot study evaluates the feasibility of automated volumetric quantification of hepatocellular carcinoma (HCC) as an imaging biomarker to assess treatment response for sorafenib. METHODS: In this institutional review board-approved, Health Insurance Portability and Accountability Act-compliant retrospective study, a training database of manually labeled background liver, enhancing and nonenhancing tumor tissue was established using pretherapy and first posttherapy multiphasic computed tomography images from a registry of 13 HCC patients. For each patient, Hounsfield density and geometry-based feature images were generated from registered multiphasic computed tomography data sets and used as the input for a random forest-based classifier of enhancing and nonenhancing tumor tissue. Leave-one-out cross-validation of the dice similarity measure was applied to quantify the classifier accuracy. A Cox regression model was used to confirm volume changes as predictors of time to progression (TTP) of target lesions for both manual and automatic methods. RESULTS: When compared with manual labels, an overall classification accuracy of dice similarity coefficient of 0.71 for pretherapy and 0.66 posttherapy enhancing tumor labels and 0.45 for pretherapy and 0.59 for posttherapy nonenhancing tumor labels was observed. Automated methods for quantifying volumetric changes in the enhancing lesion agreed with manual methods and were observed as a significant predictor of TTP. CONCLUSIONS: Automated volumetric analysis was determined to be feasible for monitoring HCC response to treatment. The information extracted using automated volumetrics is likely to reproduce labor-intensive manual data and provide a good predictor for TTP. Further work will extend these studies to additional treatment modalities and larger patient populations.",
author = "Fuentes, {David Thomas Alfonso} and Kareem Ahmed and Lin, {Jonathan S.} and Ali, {Reham Abdelwahab Hassan} and Ahmed Kaseb and Hassan, {Manal M} and Janio Szklaruk and Ali Morshid and Hazle, {John D} and Aliya Qayyum and Elsayes, {Khaled M}",
year = "2019",
month = "5",
day = "1",
doi = "10.1097/RCT.0000000000000866",
language = "English (US)",
volume = "43",
pages = "499--506",
journal = "Journal of Computer Assisted Tomography",
issn = "0363-8715",
publisher = "Lippincott Williams and Wilkins",
number = "3",

}

TY - JOUR

T1 - Automated Volumetric Assessment of Hepatocellular Carcinoma Response to Sorafenib

T2 - A Pilot Study

AU - Fuentes, David Thomas Alfonso

AU - Ahmed, Kareem

AU - Lin, Jonathan S.

AU - Ali, Reham Abdelwahab Hassan

AU - Kaseb, Ahmed

AU - Hassan, Manal M

AU - Szklaruk, Janio

AU - Morshid, Ali

AU - Hazle, John D

AU - Qayyum, Aliya

AU - Elsayes, Khaled M

PY - 2019/5/1

Y1 - 2019/5/1

N2 - PURPOSE: This pilot study evaluates the feasibility of automated volumetric quantification of hepatocellular carcinoma (HCC) as an imaging biomarker to assess treatment response for sorafenib. METHODS: In this institutional review board-approved, Health Insurance Portability and Accountability Act-compliant retrospective study, a training database of manually labeled background liver, enhancing and nonenhancing tumor tissue was established using pretherapy and first posttherapy multiphasic computed tomography images from a registry of 13 HCC patients. For each patient, Hounsfield density and geometry-based feature images were generated from registered multiphasic computed tomography data sets and used as the input for a random forest-based classifier of enhancing and nonenhancing tumor tissue. Leave-one-out cross-validation of the dice similarity measure was applied to quantify the classifier accuracy. A Cox regression model was used to confirm volume changes as predictors of time to progression (TTP) of target lesions for both manual and automatic methods. RESULTS: When compared with manual labels, an overall classification accuracy of dice similarity coefficient of 0.71 for pretherapy and 0.66 posttherapy enhancing tumor labels and 0.45 for pretherapy and 0.59 for posttherapy nonenhancing tumor labels was observed. Automated methods for quantifying volumetric changes in the enhancing lesion agreed with manual methods and were observed as a significant predictor of TTP. CONCLUSIONS: Automated volumetric analysis was determined to be feasible for monitoring HCC response to treatment. The information extracted using automated volumetrics is likely to reproduce labor-intensive manual data and provide a good predictor for TTP. Further work will extend these studies to additional treatment modalities and larger patient populations.

AB - PURPOSE: This pilot study evaluates the feasibility of automated volumetric quantification of hepatocellular carcinoma (HCC) as an imaging biomarker to assess treatment response for sorafenib. METHODS: In this institutional review board-approved, Health Insurance Portability and Accountability Act-compliant retrospective study, a training database of manually labeled background liver, enhancing and nonenhancing tumor tissue was established using pretherapy and first posttherapy multiphasic computed tomography images from a registry of 13 HCC patients. For each patient, Hounsfield density and geometry-based feature images were generated from registered multiphasic computed tomography data sets and used as the input for a random forest-based classifier of enhancing and nonenhancing tumor tissue. Leave-one-out cross-validation of the dice similarity measure was applied to quantify the classifier accuracy. A Cox regression model was used to confirm volume changes as predictors of time to progression (TTP) of target lesions for both manual and automatic methods. RESULTS: When compared with manual labels, an overall classification accuracy of dice similarity coefficient of 0.71 for pretherapy and 0.66 posttherapy enhancing tumor labels and 0.45 for pretherapy and 0.59 for posttherapy nonenhancing tumor labels was observed. Automated methods for quantifying volumetric changes in the enhancing lesion agreed with manual methods and were observed as a significant predictor of TTP. CONCLUSIONS: Automated volumetric analysis was determined to be feasible for monitoring HCC response to treatment. The information extracted using automated volumetrics is likely to reproduce labor-intensive manual data and provide a good predictor for TTP. Further work will extend these studies to additional treatment modalities and larger patient populations.

UR - http://www.scopus.com/inward/record.url?scp=85066060672&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066060672&partnerID=8YFLogxK

U2 - 10.1097/RCT.0000000000000866

DO - 10.1097/RCT.0000000000000866

M3 - Article

C2 - 31082956

AN - SCOPUS:85066060672

VL - 43

SP - 499

EP - 506

JO - Journal of Computer Assisted Tomography

JF - Journal of Computer Assisted Tomography

SN - 0363-8715

IS - 3

ER -