Publications by authors named "Huy Quoc Vo"
Article Synopsis
- The study aimed to replicate the Oxford Classification for IgA nephropathy using a deep learning pipeline called MESCnn, which integrates automatic glomerular segmentation and classification for key glomerular components.
- A dataset of 1056 whole slide images from kidney biopsies was annotated, and models were trained and tested to achieve accurate detection and classification of mesangial hypercellularity, endocapillary hypercellularity, segmental sclerosis, and active crescents.
- Results showed that the segmentation models performed well, demonstrated by high accuracy metrics, with EfficientNetV2-L and MobileNetV2 providing the best results for different classification categories, indicating the potential for effective computer-aided diagnosis in nephropathology.