Identifying biomarkers in medical images is vital for a wide range of biotech applications. However, recent Transformer and CNN based methods often struggle with variations in morphology and staining, which limits their feature extraction capabilities. In medical image segmentation, where data samples are often limited, state-of-the-art (SOTA) methods improve accuracy by using pre-trained encoders, while end-to-end approaches typically fall short due to difficulties in transferring multiscale features effectively between encoders and decoders. To handle these challenges, we introduce a nested UNet architecture that captures both local and global context through Multiscale Feature Fusion and Attention Mechanisms. This design improves feature integration from encoders, highlights key channels and regions, and restores spatial details to enhance segmentation performance. Our method surpasses SOTA approaches, as evidenced by experiments across four datasets and detailed ablation studies. Code: https://github.com/saadwazir/ReN-UNet
@article{arxiv.2504.06158,
title = {Rethinking the Nested U-Net Approach: Enhancing Biomarker Segmentation with Attention Mechanisms and Multiscale Feature Fusion},
author = {Saad Wazir and Daeyoung Kim},
journal= {arXiv preprint arXiv:2504.06158},
year = {2025}
}
Comments
Published in the Proceedings of the 2024 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2024), Lecture Notes in Electrical Engineering (LNEE), Volume 1372, Springer Nature, Singapore