Kidney-SegNet
Contributors
Anirudh Aatresh, Rohit Yatgiri, Amit Chanchal, Aman Kumar, Akansh Ravi, Devikalyan Das, Dr. Raghavendra BS, Dr. Shyam Lal, Dr. Jyoti KiniSummary
Image segmentation remains to be one of the most vital tasks in the area of computer vision and more so in the case of medical image processing. Image segmentation quality is the primary metric that is often considered, with memory and computation efficiency overlooked, limiting the use of power-hungry models for practical use. In this project, we proposed a novel framework (Kidney-SegNet) that combines the effectiveness of an attention-based encoder-decoder architecture, atrous spatial pyramid pooling (ASPP), and highly efficient dimension-wise convolutions. The segmentation results of the proposed Kidney-SegNet architecture have outperformed existing deep learning methods by evaluating them on two publicly available kidney and TNBC breast H&E stained histopathology image datasets. Further, our simulation experiments also reveal that our proposed architecture's computational complexity and memory requirement is very efficient compared to existing deep learning state-of-the-art methods for nuclei segmentation of H&E stained histopathology images.
This work was published in the Computerized Medical Imaging and Graphics journal in 2021.