TY - JOUR
T1 - Automated analysis of low-field brain MRI in cerebral malaria
AU - Tu, Danni
AU - Goyal, Manu S.
AU - Dworkin, Jordan D.
AU - Kampondeni, Samuel
AU - Vidal, Lorenna
AU - Biondo-Savin, Eric
AU - Juvvadi, Sandeep
AU - Raghavan, Prashant
AU - Nicholas, Jennifer
AU - Chetcuti, Karen
AU - Clark, Kelly
AU - Robert-Fitzgerald, Timothy
AU - Satterthwaite, Theodore D.
AU - Yushkevich, Paul
AU - Davatzikos, Christos
AU - Erus, Guray
AU - Tustison, Nicholas J.
AU - Postels, Douglas G.
AU - Taylor, Terrie E.
AU - Small, Dylan S.
AU - Shinohara, Russell T.
N1 - Publisher Copyright:
© 2022 The International Biometric Society.
PY - 2023/9
Y1 - 2023/9
N2 - A central challenge of medical imaging studies is to extract biomarkers that characterize disease pathology or outcomes. Modern automated approaches have found tremendous success in high-resolution, high-quality magnetic resonance images. These methods, however, may not translate to low-resolution images acquired on magnetic resonance imaging (MRI) scanners with lower magnetic field strength. In low-resource settings where low-field scanners are more common and there is a shortage of radiologists to manually interpret MRI scans, it is critical to develop automated methods that can augment or replace manual interpretation, while accommodating reduced image quality. We present a fully automated framework for translating radiological diagnostic criteria into image-based biomarkers, inspired by a project in which children with cerebral malaria (CM) were imaged using low-field 0.35 Tesla MRI. We integrate multiatlas label fusion, which leverages high-resolution images from another sample as prior spatial information, with parametric Gaussian hidden Markov models based on image intensities, to create a robust method for determining ventricular cerebrospinal fluid volume. We also propose normalized image intensity and texture measurements to determine the loss of gray-to-white matter tissue differentiation and sulcal effacement. These integrated biomarkers have excellent classification performance for determining severe brain swelling due to CM.
AB - A central challenge of medical imaging studies is to extract biomarkers that characterize disease pathology or outcomes. Modern automated approaches have found tremendous success in high-resolution, high-quality magnetic resonance images. These methods, however, may not translate to low-resolution images acquired on magnetic resonance imaging (MRI) scanners with lower magnetic field strength. In low-resource settings where low-field scanners are more common and there is a shortage of radiologists to manually interpret MRI scans, it is critical to develop automated methods that can augment or replace manual interpretation, while accommodating reduced image quality. We present a fully automated framework for translating radiological diagnostic criteria into image-based biomarkers, inspired by a project in which children with cerebral malaria (CM) were imaged using low-field 0.35 Tesla MRI. We integrate multiatlas label fusion, which leverages high-resolution images from another sample as prior spatial information, with parametric Gaussian hidden Markov models based on image intensities, to create a robust method for determining ventricular cerebrospinal fluid volume. We also propose normalized image intensity and texture measurements to determine the loss of gray-to-white matter tissue differentiation and sulcal effacement. These integrated biomarkers have excellent classification performance for determining severe brain swelling due to CM.
KW - MRI
KW - Markov random field
KW - brain segmentation
KW - data integration
UR - http://www.scopus.com/inward/record.url?scp=85133350895&partnerID=8YFLogxK
U2 - 10.1111/biom.13708
DO - 10.1111/biom.13708
M3 - Article
C2 - 35731973
AN - SCOPUS:85133350895
SN - 0006-341X
VL - 79
SP - 2417
EP - 2429
JO - Biometrics
JF - Biometrics
IS - 3
ER -