Parametric response mapping of dynamic CT as an imaging biomarker to distinguish viability of hepatocellular carcinoma treated with transcatheter arterial chemoembolization

Seung Joon Choi, Jonghoon Kim, Jongbum Seo, Hyung Sik Kim, Jong Min Lee, Hyunjin Park

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Purpose: Accurate assessment of viability of hepatocellular carcinoma (HCC) after transcatheter arterial chemoembolization (TACE) is important for therapy planning. The purpose of this study is to determine the diagnostic value of a novel image analysis method called parametric response mapping (PRM) in predicting viability of tumor in HCC treated with TACE for dynamic CT images. Methods: 35 patients who had 35 iodized-oil defect areas (IODAs) in HCCs treated with TACE were included in our study. These patients were divided into two groups, one group with viable tumors (n = 22) and the other group with non-viable tumors (n = 13) in the IODA. All patients were followed up using triple-phase dynamic CT after the treatment. We compared (a) manual analysis, (b) using PRM results, and (c) using PRM results with automatic classifier to distinguish between two tumor groups based on dynamic CT images from two longitudinal exams. Two radiologists performed the manual analysis. The PRM approach was implemented using prototype software. We adopted an off-the-shelf k nearest neighbor (kNN) classifier and leave-one-out cross-validation for the third approach. The area under the curve (AUC) values were compared for three approaches. Results: Manual analysis yielded AUC of 0.74, using PRM results yielded AUC of 0.84, and using PRM results with an automatic classifier yielded AUC of 0.87. Conclusions: We improved upon the standard manual analysis approach by adopting a novel image analysis method of PRM combined with an automatic classifier.

Original languageEnglish
Pages (from-to)518-525
Number of pages8
JournalAbdominal Imaging
Volume39
Issue number3
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Area Under Curve
Hepatocellular Carcinoma
Biomarkers
Ethiodized Oil
Neoplasms
Software
Therapeutics

All Science Journal Classification (ASJC) codes

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Gastroenterology
  • Urology

Cite this

@article{3b27760cc09b4e729059242f8b067281,
title = "Parametric response mapping of dynamic CT as an imaging biomarker to distinguish viability of hepatocellular carcinoma treated with transcatheter arterial chemoembolization",
abstract = "Purpose: Accurate assessment of viability of hepatocellular carcinoma (HCC) after transcatheter arterial chemoembolization (TACE) is important for therapy planning. The purpose of this study is to determine the diagnostic value of a novel image analysis method called parametric response mapping (PRM) in predicting viability of tumor in HCC treated with TACE for dynamic CT images. Methods: 35 patients who had 35 iodized-oil defect areas (IODAs) in HCCs treated with TACE were included in our study. These patients were divided into two groups, one group with viable tumors (n = 22) and the other group with non-viable tumors (n = 13) in the IODA. All patients were followed up using triple-phase dynamic CT after the treatment. We compared (a) manual analysis, (b) using PRM results, and (c) using PRM results with automatic classifier to distinguish between two tumor groups based on dynamic CT images from two longitudinal exams. Two radiologists performed the manual analysis. The PRM approach was implemented using prototype software. We adopted an off-the-shelf k nearest neighbor (kNN) classifier and leave-one-out cross-validation for the third approach. The area under the curve (AUC) values were compared for three approaches. Results: Manual analysis yielded AUC of 0.74, using PRM results yielded AUC of 0.84, and using PRM results with an automatic classifier yielded AUC of 0.87. Conclusions: We improved upon the standard manual analysis approach by adopting a novel image analysis method of PRM combined with an automatic classifier.",
author = "Choi, {Seung Joon} and Jonghoon Kim and Jongbum Seo and Kim, {Hyung Sik} and Lee, {Jong Min} and Hyunjin Park",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/s00261-014-0087-z",
language = "English",
volume = "39",
pages = "518--525",
journal = "Abdominal Radiology",
issn = "2366-004X",
publisher = "Springer New York",
number = "3",

}

Parametric response mapping of dynamic CT as an imaging biomarker to distinguish viability of hepatocellular carcinoma treated with transcatheter arterial chemoembolization. / Choi, Seung Joon; Kim, Jonghoon; Seo, Jongbum; Kim, Hyung Sik; Lee, Jong Min; Park, Hyunjin.

In: Abdominal Imaging, Vol. 39, No. 3, 01.01.2014, p. 518-525.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Parametric response mapping of dynamic CT as an imaging biomarker to distinguish viability of hepatocellular carcinoma treated with transcatheter arterial chemoembolization

AU - Choi, Seung Joon

AU - Kim, Jonghoon

AU - Seo, Jongbum

AU - Kim, Hyung Sik

AU - Lee, Jong Min

AU - Park, Hyunjin

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Purpose: Accurate assessment of viability of hepatocellular carcinoma (HCC) after transcatheter arterial chemoembolization (TACE) is important for therapy planning. The purpose of this study is to determine the diagnostic value of a novel image analysis method called parametric response mapping (PRM) in predicting viability of tumor in HCC treated with TACE for dynamic CT images. Methods: 35 patients who had 35 iodized-oil defect areas (IODAs) in HCCs treated with TACE were included in our study. These patients were divided into two groups, one group with viable tumors (n = 22) and the other group with non-viable tumors (n = 13) in the IODA. All patients were followed up using triple-phase dynamic CT after the treatment. We compared (a) manual analysis, (b) using PRM results, and (c) using PRM results with automatic classifier to distinguish between two tumor groups based on dynamic CT images from two longitudinal exams. Two radiologists performed the manual analysis. The PRM approach was implemented using prototype software. We adopted an off-the-shelf k nearest neighbor (kNN) classifier and leave-one-out cross-validation for the third approach. The area under the curve (AUC) values were compared for three approaches. Results: Manual analysis yielded AUC of 0.74, using PRM results yielded AUC of 0.84, and using PRM results with an automatic classifier yielded AUC of 0.87. Conclusions: We improved upon the standard manual analysis approach by adopting a novel image analysis method of PRM combined with an automatic classifier.

AB - Purpose: Accurate assessment of viability of hepatocellular carcinoma (HCC) after transcatheter arterial chemoembolization (TACE) is important for therapy planning. The purpose of this study is to determine the diagnostic value of a novel image analysis method called parametric response mapping (PRM) in predicting viability of tumor in HCC treated with TACE for dynamic CT images. Methods: 35 patients who had 35 iodized-oil defect areas (IODAs) in HCCs treated with TACE were included in our study. These patients were divided into two groups, one group with viable tumors (n = 22) and the other group with non-viable tumors (n = 13) in the IODA. All patients were followed up using triple-phase dynamic CT after the treatment. We compared (a) manual analysis, (b) using PRM results, and (c) using PRM results with automatic classifier to distinguish between two tumor groups based on dynamic CT images from two longitudinal exams. Two radiologists performed the manual analysis. The PRM approach was implemented using prototype software. We adopted an off-the-shelf k nearest neighbor (kNN) classifier and leave-one-out cross-validation for the third approach. The area under the curve (AUC) values were compared for three approaches. Results: Manual analysis yielded AUC of 0.74, using PRM results yielded AUC of 0.84, and using PRM results with an automatic classifier yielded AUC of 0.87. Conclusions: We improved upon the standard manual analysis approach by adopting a novel image analysis method of PRM combined with an automatic classifier.

UR - http://www.scopus.com/inward/record.url?scp=84903472542&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903472542&partnerID=8YFLogxK

U2 - 10.1007/s00261-014-0087-z

DO - 10.1007/s00261-014-0087-z

M3 - Article

C2 - 24519566

AN - SCOPUS:84903472542

VL - 39

SP - 518

EP - 525

JO - Abdominal Radiology

JF - Abdominal Radiology

SN - 2366-004X

IS - 3

ER -