Computer-aided detection of therapy-induced leukoencephalopathy in pediatric acute lymphoblastic leukemia patients treated with intravenous high-dose methotrexate

John O. Glass, Wilburn E. Reddick, Chin-Shang Li, Fred H. Laningham, Kathleen J. Helton, Ching Hon Pui

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The purpose of this study was to use objective quantitative magnetic resonance imaging (MRI) methods to develop a computer-aided detection (CAD) tool to differentiate white matter (WM) hyperintensities into either leukoencephalopathy (LE) induced by chemotherapy or normal maturational processes in children treated for acute lymphoblastic leukemia without irradiation. A combined MRI set consisting of T1-weighted, T2-weighted, proton-density-weighted and fluid-attenuated inversion recovery images and WM, gray matter and cerebrospinal fluid proportional volume maps from a spatially normalized atlas were analyzed with a neural network segmentation based on a Kohonen self-organizing map (SOM). Segmented maps were manually classified to identify the most hyperintense WM region and the normal-appearing genu region. Signal intensity differences normalized to the genu within each examination were generated for four time points in 228 children. A second Kohonen SOM was trained on the first examination data and divided the WM into normal-appearing or LE groups. Reviewing labels from the CAD tool revealed a consistency measure of 89.8% (167 of 186) within patients. The overall agreement between the CAD tool and the consensus reading of two trained observers was 84.1% (535 of 636), with 84.2% (170 of 202) agreement in the training set and 84.1% (365 of 434) agreement in the testing set. These results suggest that subtle therapy-induced LE can be objectively and reproducibly detected in children treated for cancer using this CAD approach based on relative differences in quantitative signal intensity measures normalized within each examination.

Original languageEnglish (US)
Pages (from-to)785-791
Number of pages7
JournalMagnetic Resonance Imaging
Volume24
Issue number6
DOIs
StatePublished - Jul 2006
Externally publishedYes

Fingerprint

Leukoencephalopathies
Pediatrics
leukemias
Precursor Cell Lymphoblastic Leukemia-Lymphoma
Methotrexate
therapy
dosage
Self organizing maps
Magnetic resonance
examination
organizing
Magnetic Resonance Imaging
magnetic resonance
Cerebrospinal fluid
Imaging techniques
Chemotherapy
Atlases
cerebrospinal fluid
Therapeutics
reviewing

Keywords

  • Childhood acute lymphoblastic leukemia
  • Computer-aided detection
  • Neurotoxicity
  • Segmentation
  • White matter

ASJC Scopus subject areas

  • Biophysics
  • Clinical Biochemistry
  • Structural Biology
  • Radiology Nuclear Medicine and imaging
  • Condensed Matter Physics

Cite this

Computer-aided detection of therapy-induced leukoencephalopathy in pediatric acute lymphoblastic leukemia patients treated with intravenous high-dose methotrexate. / Glass, John O.; Reddick, Wilburn E.; Li, Chin-Shang; Laningham, Fred H.; Helton, Kathleen J.; Pui, Ching Hon.

In: Magnetic Resonance Imaging, Vol. 24, No. 6, 07.2006, p. 785-791.

Research output: Contribution to journalArticle

Glass, John O. ; Reddick, Wilburn E. ; Li, Chin-Shang ; Laningham, Fred H. ; Helton, Kathleen J. ; Pui, Ching Hon. / Computer-aided detection of therapy-induced leukoencephalopathy in pediatric acute lymphoblastic leukemia patients treated with intravenous high-dose methotrexate. In: Magnetic Resonance Imaging. 2006 ; Vol. 24, No. 6. pp. 785-791.
@article{512ff8f8e8134f78967c704844ccd7b7,
title = "Computer-aided detection of therapy-induced leukoencephalopathy in pediatric acute lymphoblastic leukemia patients treated with intravenous high-dose methotrexate",
abstract = "The purpose of this study was to use objective quantitative magnetic resonance imaging (MRI) methods to develop a computer-aided detection (CAD) tool to differentiate white matter (WM) hyperintensities into either leukoencephalopathy (LE) induced by chemotherapy or normal maturational processes in children treated for acute lymphoblastic leukemia without irradiation. A combined MRI set consisting of T1-weighted, T2-weighted, proton-density-weighted and fluid-attenuated inversion recovery images and WM, gray matter and cerebrospinal fluid proportional volume maps from a spatially normalized atlas were analyzed with a neural network segmentation based on a Kohonen self-organizing map (SOM). Segmented maps were manually classified to identify the most hyperintense WM region and the normal-appearing genu region. Signal intensity differences normalized to the genu within each examination were generated for four time points in 228 children. A second Kohonen SOM was trained on the first examination data and divided the WM into normal-appearing or LE groups. Reviewing labels from the CAD tool revealed a consistency measure of 89.8{\%} (167 of 186) within patients. The overall agreement between the CAD tool and the consensus reading of two trained observers was 84.1{\%} (535 of 636), with 84.2{\%} (170 of 202) agreement in the training set and 84.1{\%} (365 of 434) agreement in the testing set. These results suggest that subtle therapy-induced LE can be objectively and reproducibly detected in children treated for cancer using this CAD approach based on relative differences in quantitative signal intensity measures normalized within each examination.",
keywords = "Childhood acute lymphoblastic leukemia, Computer-aided detection, Neurotoxicity, Segmentation, White matter",
author = "Glass, {John O.} and Reddick, {Wilburn E.} and Chin-Shang Li and Laningham, {Fred H.} and Helton, {Kathleen J.} and Pui, {Ching Hon}",
year = "2006",
month = "7",
doi = "10.1016/j.mri.2006.02.001",
language = "English (US)",
volume = "24",
pages = "785--791",
journal = "Magnetic Resonance Imaging",
issn = "0730-725X",
publisher = "Elsevier Inc.",
number = "6",

}

TY - JOUR

T1 - Computer-aided detection of therapy-induced leukoencephalopathy in pediatric acute lymphoblastic leukemia patients treated with intravenous high-dose methotrexate

AU - Glass, John O.

AU - Reddick, Wilburn E.

AU - Li, Chin-Shang

AU - Laningham, Fred H.

AU - Helton, Kathleen J.

AU - Pui, Ching Hon

PY - 2006/7

Y1 - 2006/7

N2 - The purpose of this study was to use objective quantitative magnetic resonance imaging (MRI) methods to develop a computer-aided detection (CAD) tool to differentiate white matter (WM) hyperintensities into either leukoencephalopathy (LE) induced by chemotherapy or normal maturational processes in children treated for acute lymphoblastic leukemia without irradiation. A combined MRI set consisting of T1-weighted, T2-weighted, proton-density-weighted and fluid-attenuated inversion recovery images and WM, gray matter and cerebrospinal fluid proportional volume maps from a spatially normalized atlas were analyzed with a neural network segmentation based on a Kohonen self-organizing map (SOM). Segmented maps were manually classified to identify the most hyperintense WM region and the normal-appearing genu region. Signal intensity differences normalized to the genu within each examination were generated for four time points in 228 children. A second Kohonen SOM was trained on the first examination data and divided the WM into normal-appearing or LE groups. Reviewing labels from the CAD tool revealed a consistency measure of 89.8% (167 of 186) within patients. The overall agreement between the CAD tool and the consensus reading of two trained observers was 84.1% (535 of 636), with 84.2% (170 of 202) agreement in the training set and 84.1% (365 of 434) agreement in the testing set. These results suggest that subtle therapy-induced LE can be objectively and reproducibly detected in children treated for cancer using this CAD approach based on relative differences in quantitative signal intensity measures normalized within each examination.

AB - The purpose of this study was to use objective quantitative magnetic resonance imaging (MRI) methods to develop a computer-aided detection (CAD) tool to differentiate white matter (WM) hyperintensities into either leukoencephalopathy (LE) induced by chemotherapy or normal maturational processes in children treated for acute lymphoblastic leukemia without irradiation. A combined MRI set consisting of T1-weighted, T2-weighted, proton-density-weighted and fluid-attenuated inversion recovery images and WM, gray matter and cerebrospinal fluid proportional volume maps from a spatially normalized atlas were analyzed with a neural network segmentation based on a Kohonen self-organizing map (SOM). Segmented maps were manually classified to identify the most hyperintense WM region and the normal-appearing genu region. Signal intensity differences normalized to the genu within each examination were generated for four time points in 228 children. A second Kohonen SOM was trained on the first examination data and divided the WM into normal-appearing or LE groups. Reviewing labels from the CAD tool revealed a consistency measure of 89.8% (167 of 186) within patients. The overall agreement between the CAD tool and the consensus reading of two trained observers was 84.1% (535 of 636), with 84.2% (170 of 202) agreement in the training set and 84.1% (365 of 434) agreement in the testing set. These results suggest that subtle therapy-induced LE can be objectively and reproducibly detected in children treated for cancer using this CAD approach based on relative differences in quantitative signal intensity measures normalized within each examination.

KW - Childhood acute lymphoblastic leukemia

KW - Computer-aided detection

KW - Neurotoxicity

KW - Segmentation

KW - White matter

UR - http://www.scopus.com/inward/record.url?scp=33745660560&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745660560&partnerID=8YFLogxK

U2 - 10.1016/j.mri.2006.02.001

DO - 10.1016/j.mri.2006.02.001

M3 - Article

VL - 24

SP - 785

EP - 791

JO - Magnetic Resonance Imaging

JF - Magnetic Resonance Imaging

SN - 0730-725X

IS - 6

ER -