Deep Learning Mixture-of-Experts for Cytotoxic Edema Assessment in Infants and Children
- Resource Type
- Conference
- Authors
- Ghebrechristos, Henok; Nicholas, Stence; Mirsky, David; Huynh, Manh; Kromer, Zackary; Batista, Ligia; Alaghband, Gita; O'Neill, Brent; Moulton, Steven; Lindberg, Daniel M.
- Source
- 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI) Biomedical Imaging (ISBI), 2023 IEEE 20th International Symposium on. :1-5 Apr, 2023
- Subject
- Bioengineering
Computing and Processing
Photonics and Electrooptics
Signal Processing and Analysis
Neuroimaging
Deep learning
Training
Pediatrics
Three-dimensional displays
Head
Magnetic resonance imaging
Cytotoxic Edema Classification
Abusive Head Trauma
Deep Learning
Diffusion Weighted Image
Apparent Diffusion Coefficient
- Language
- ISSN
- 1945-8452
Abusive Head Trauma (AHT) is the most important source of morbidity and mortality for abused children. Cytotoxic Edema (CE) has been suggested to be a sign of poor outcome for children with AHT, but this has not been tested. We propose a Mixture-of-Experts (MoE) deep learning system that includes two 3D network architectures optimized to learn patterns of CE from two types of clinical MRI data – a trace Diffusion Weighted Image (DWI) and the calculated Apparent Diffusion Coefficient map (ADC). We devise a novel approach based on volumetric analysis of 3D images (using pixels from time slices) and 3D convolutional neural network (CNN). Experiments on a dataset curated from a Children's Hospital Colorado (CHCO) [1] patient registry show a predictive performance F1 score of 0.93 at distinguishing CE patients from children with severe neurologic injury without CE. In addition, we perform ablation studies to determine the association between CE and AHT, and overall functional outcome and in-hospital mortality of infants and young children.