Automated analysis of low-field brain MRI in cerebral malaria

Authors

Danni Tu, The Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Manu S. Goyal, Mallinckrodt Institute of Radiology, Washington University in St. Louis, St. Louis, Missouri, USA.
Jordan D. Dworkin, Department of Psychiatry, Columbia University Irving Medical Center, New York, New York, USA.
Samuel Kampondeni, Blantyre Malaria Project, Kamuzu University of Health Sciences, Southern Region, Blantyre, Malawi.
Lorenna Vidal, Department of Radiology, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA.
Eric Biondo-Savin, Department of Radiology, Michigan State University, East Lansing, Michigan, USA.
Sandeep Juvvadi, Tenet Diagnostics, Hyderabad, India.
Prashant Raghavan, Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, Maryland, USA.
Jennifer Nicholas, University Hospitals Cleveland Medical Center, Department of Radiology, Case Western Reserve University, Cleveland, Ohio, USA.
Karen Chetcuti, Department of Paediatrics and Child Health, Kamuzu University of Health Sciences, Southern Region, Blantyre, Malawi.
Kelly Clark, The Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Timothy Robert-Fitzgerald, The Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Theodore D. Satterthwaite, Department of Psychiatry, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Paul Yushkevich, Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Christos Davatzikos, Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Guray Erus, Center for Biomedical Image Computing and Analysis (CBICA), Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Nicholas J. Tustison, Department of Radiology and Medical Imaging, University of Virginia, Charlottesville, Virginia, USA.
Douglas G. Postels, Division of Neurology, George Washington University/Children's National Medical Center, Washington, District of Columbia, USA.
Terrie E. Taylor, Blantyre Malaria Project, Kamuzu University of Health Sciences, Southern Region, Blantyre, Malawi.
Dylan S. Small, Department of Statistics, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Russell T. Shinohara, The Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, Pennsylvania, USA.

Document Type

Journal Article

Publication Date

6-22-2022

Journal

Biometrics

DOI

10.1111/biom.13708

Keywords

MRI; Markov random field; brain segmentation; data integration

Abstract

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.

Department

Neurology

Share

COinS