Rich-U-Net: A medical image segmentation model for fusing spatial depth features and capturing minute structural details

TL;DR

Rich-U-Net is a novel medical image segmentation model that fuses spatial and depth features to improve the detection of fine structures and complex details, outperforming existing models on multiple datasets.

Contribution

The paper introduces Rich-U-Net, a new model that effectively integrates multi-level spatial and depth features for enhanced medical image segmentation.

Findings

Outperforms state-of-the-art models on ISIC2018, BUSI, GLAS, and CVC datasets.

Achieves higher Dice, IoU, and HD95 metrics.

Effectively detects minute structural details in complex images.

Abstract

Medical image segmentation is of great significance in analysis of illness. The use of deep neural networks in medical image segmentation can help doctors extract regions of interest from complex medical images, thereby improving diagnostic accuracy and enabling better assessment of the condition to formulate treatment plans. However, most current medical image segmentation methods underperform in accurately extracting spatial information from medical images and mining potential complex structures and variations. In this article, we introduce the Rich-U-Net model, which effectively integrates both spatial and depth features. This fusion enhances the model's capability to detect fine structures and intricate details within complex medical images. Our multi-level and multi-dimensional feature fusion and optimization strategies enable our model to achieve fine structure localization and accurate segmentation results in medical image segmentation. Experiments on the ISIC2018, BUSI, GLAS, and CVC datasets show that Rich-U-Net surpasses other state-of-the-art models in Dice, IoU, and HD95 metrics.