Search for: All records

Abstract Microglia, the brain’s resident macrophages, participate in development and influence neuroinflammation, which is characteristic of multiple brain pathologies. Diverse insults cause microglia to alter their morphology from “resting” to “activated” shapes, which vary with stimulus type, brain location, and microenvironment. This morphologic diversity commonly restricts microglial analyses to specific regions and manual methods. We introduce StainAI, a deep learning tool that leverages 20x whole-slide immunohistochemistry images for rapid, high-throughput analysis of microglial morphology. StainAI maps microglia to a brain atlas, classifies their morphology, quantifies morphometric features, and computes an activation score for any region of interest. As a proof of principle, StainAI was applied to a rat model of pediatric asphyxial cardiac arrest, accurately classifying millions of microglia across multiple slices, surpassing current methods by orders of magnitude, and identifying both known and novel activation patterns. Extending its application to a non-human primate model of simian immunodeficiency virus infection further demonstrated its generalizability beyond rodent datasets, providing new insights into microglial responses across species. StainAI offers a scalable, high-throughput solution for microglial analysis from routine immunohistochemistry images, accelerating research in microglial biology and neuroinflammation. 

Precision in segmenting cardiac MR images is critical for accurately diagnosing cardiovascular diseases. Several deep learning models have been shown useful in segmenting the structure of the heart, such as atrium, ventricle and myocardium, in cardiac MR images. Given the diverse image quality in cardiac MRI scans from various clinical settings, it is currently uncertain how different levels of noise affect the precision of deep learning image segmentation. This uncertainty could potentially lead to bias in subsequent diagnoses. The goal of this study is to examine the effects of noise in cardiac MRI segmentation using deep learning. We employed the Automated Cardiac Diagnosis Challenge MRI dataset and augmented it with varying degrees of Rician noise during model training to test the model’s capability in segmenting heart structures. Three models, including TransUnet, SwinUnet, and Unet, were compared by calculating the SNR-Dice relations to evaluate the models’ noise resilience. Results show that the TransUnet model, which combines CNN and Transformer architectures, demonstrated superior noise resilience. Noise augmentation during model training improved the models’ noise resilience for segmentation. The findings under-score the critical role of deep learning models in adequately handling diverse noise conditions for the segmentation of heart structures in cardiac images.