Towards Accurate Renal Micro-Structure Segmentation: An Assessment of YOLOv8 and Mask R-CNN Models

In the field of medical imaging, correct instance segmentation is essential. This work attempts to address the problems related to renal micro-structure segmentation by using the power of YOLOv8 and special MASK R-CNN models to facilitate the development of more rapid and accurate nephrology diagnosis, which will benefit physicians and other healthcare providers. Improved medical imaging analysis is made possible by the model's high precision rate of “glomerulus” and “blood vessel” structure detection. The application of the MASKRCNN framework, which successfully integrated pertinent annotations to boost visual understanding, increased the clarity of image interpretation. Additionally, this work uses the HuBMAP dataset to segregate renal microstructures using the YOLOv8 and Mask R-CNN techniques. Strong performance was shown by the YOLOv8 model, which received an IoU score of 84.55%. The Mask R-CNN model received an IoU score of 80.66%, indicating its potential. It is an impressive accomplishment to obtain a high IoU score for YOLOv8 in the context of medical photo segmentation, since this suggests that there is still room for further improvement and optimization of the model. For medical professionals, the IoU scores are crucial since they offer a technique to improve accuracy and reliability when it comes to nephrology diagnosis. In order to improve diagnosis accuracy and enable broader clinical adoption, future research aims to improve these IoU ratings. The observed disparity underscored the inherent complexities associated with differentiating between ambiguous kidney structures and also the pressing need for further advancement. Our preliminary work demonstrates the potential of MASK-RCNN and YOLOv8 in the challenging field of renal micro-structure segmentation.