Instructive Feature Enhancement for Dichotomous Medical Image Segmentation
This work addresses the challenge of ambiguous boundary identification in medical image segmentation for clinicians and researchers, offering a plug-and-play method that is incremental in nature.
The authors tackled the problem of improving dichotomous medical image segmentation by proposing an instructive feature enhancement (IFE) approach that adaptively selects feature channels based on texture cues, which enhances performance across diverse tasks. They demonstrated this by constructing a large-scale dataset (Cosmos55k with 55,023 images) and showing that IFE improves classic segmentation networks with slight modifications.
Deep neural networks have been widely applied in dichotomous medical image segmentation (DMIS) of many anatomical structures in several modalities, achieving promising performance. However, existing networks tend to struggle with task-specific, heavy and complex designs to improve accuracy. They made little instructions to which feature channels would be more beneficial for segmentation, and that may be why the performance and universality of these segmentation models are hindered. In this study, we propose an instructive feature enhancement approach, namely IFE, to adaptively select feature channels with rich texture cues and strong discriminability to enhance raw features based on local curvature or global information entropy criteria. Being plug-and-play and applicable for diverse DMIS tasks, IFE encourages the model to focus on texture-rich features which are especially important for the ambiguous and challenging boundary identification, simultaneously achieving simplicity, universality, and certain interpretability. To evaluate the proposed IFE, we constructed the first large-scale DMIS dataset Cosmos55k, which contains 55,023 images from 7 modalities and 26 anatomical structures. Extensive experiments show that IFE can improve the performance of classic segmentation networks across different anatomies and modalities with only slight modifications. Code is available at https://github.com/yezi-66/IFE