AUTHOR=Li Hailong , Parikh Nehal A. , Wang Jinghua , Merhar Stephanie , Chen Ming , Parikh Milan , Holland Scott , He Lili 

TITLE=Objective and Automated Detection of Diffuse White Matter Abnormality in Preterm Infants Using Deep Convolutional Neural Networks

JOURNAL=Frontiers in Neuroscience

VOLUME=13

YEAR=2019

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2019.00610

DOI=10.3389/fnins.2019.00610

ISSN=1662-453X

ABSTRACT=<p>Diffuse white matter abnormality (DWMA), or diffuse excessive high signal intensity is observed in 50–80% of very preterm infants at term-equivalent age. It is subjectively defined as higher than normal signal intensity in periventricular and subcortical white matter in comparison to normal unmyelinated white matter on T<sub>2</sub>-weighted MRI images. Despite the well-documented presence of DWMA, it remains debatable whether DWMA represents pathological tissue injury or a transient developmental phenomenon. Manual tracing of DWMA exhibits poor reliability and reproducibility and unduly increases image processing time. Thus, objective and ideally automatic assessment is critical to accurately elucidate the biologic nature of DWMA. We propose a deep learning approach to automatically identify DWMA regions on T<sub>2</sub>-weighted MRI images. Specifically, we formulated DWMA detection as an image voxel classification task; that is, the voxels on T<sub>2</sub>-weighted images are treated as samples and exclusively assigned as DWMA or normal white matter voxel classes. To utilize the spatial information of individual voxels, small image patches centered on the given voxels are retrieved. A deep convolutional neural networks (CNN) model was developed to differentiate DWMA and normal voxels. We tested our deep CNN in multiple validation experiments. First, we examined DWMA detection accuracy of our CNN model using computer simulations. This was followed by <italic>in vivo</italic> assessments in a cohort of very preterm infants (<italic>N</italic> = 95) using cross-validation and holdout validation. Finally, we tested our approach on an <italic>independent</italic> preterm cohort (<italic>N</italic> = 28) to externally validate our model. Our deep CNN model achieved Dice similarity index values ranging from 0.85 to 0.99 for DWMA detection in the aforementioned validation experiments. Our proposed deep CNN model exhibited significantly better performance than other popular machine learning models. We present an objective and automated approach for accurately identifying DWMA that may facilitate the clinical diagnosis of DWMA in very preterm infants.</p>