DCSNet: Multiscale Feature Aggregation for Small Medical Object Segmentation with Detection-guided Hierarchical Cropping
This work provides a robust solution for clinical micro-lesion segmentation, a challenging task due to class imbalance and boundary complexity.
DCSNet addresses small object segmentation in medical imaging by transforming global dense prediction into localized refinement via detection-guided cropping and multiscale feature aggregation, achieving significant improvements in boundary precision over state-of-the-art methods across three medical datasets.
Small object segmentation in medical imaging is primarily hindered by class imbalance and inherent boundary complexity. Consequently, conventional global networks frequently fail to detect sparse targets or suffer from severe edge degradation. To overcome these limitations, we propose the Detection-guided Cropping Segmentation Network (DCSNet), an end-to-end framework that transforms global dense prediction into a localized refinement process. This framework integrates two core components, namely Detection-guided Hierarchical Cropping (DGHC) and Multiscale Feature Aggregation (MSFA). The DGHC module leverages region proposals to dynamically extract object-centric features, effdataectively filtering out massive background interference to mitigate class imbalance. Subsequently, the MSFA module operates strictly within these purified regions, synergizing a Transformer encoder with a pixel-adaptive fusion strategy. This mechanism dynamically aggregates multiscale features to capture both semantic context and fine-grained details for sharp boundary delineation. Extensive experiments across three diverse medical datasets demonstrate that DCSNet significantly outperforms existing state-of-the-art methods, yielding substantial improvements in boundary precision and offering a highly robust solution for clinical micro-lesion segmentation.