A Novel Approach for Nuclei Segmentation Using U-Net

Several automated methods for segmenting micro-scopic images have recently been developed and deployed. Nuclei segmentation is an important yet difficult process for examining histopathology images. This assay allows for the early detection of illnesses such as breast cancer, cardiac issues, and COVID19. Also It provides a thorough understanding of nuclei’s features and functionality. Manual diagnosis is challenging, timeconsuming, and expensive all at the same time. The U-Net deep learning model is the focus of this study since it offers a potential way for efficiently segmenting and detecting cell nuclei. The model was trained using images from the 2018 Data Science Bowl competition. The experimental results show that the proposed techniques perform well, with IoU values of 0.863 and Dice -Coef values of 0.9262.