DCSNet: Multiscale Feature Aggregation for Small Medical Object Segmentation with Detection-guided Hierarchical Cropping

2026-06-24

AI Summary

This work addresses the challenges of small-object segmentation in medical imaging, where severe class imbalance and ambiguous boundaries often lead conventional global approaches to miss sparse targets and produce degraded edges. To overcome these limitations, the authors propose DCSNet, an end-to-end framework that integrates a Detection-guided Hierarchical Cropping (DGHC) module to accurately localize target-centric regions and a Multiscale Feature Aggregation (MSFA) module to fuse multiscale features within clean local contexts. By combining a Transformer encoder with a pixel-adaptive fusion strategy, DCSNet enables synergistic modeling of semantic context and fine-grained details. Extensive experiments on three medical imaging datasets demonstrate that the proposed method significantly outperforms current state-of-the-art approaches, achieving markedly improved boundary accuracy and robustness for tiny lesion segmentation.

Abstract

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.

Problem

• small object segmentation
• class imbalance
• boundary complexity
• medical imaging
• micro-lesion segmentation

Innovation

• Detection-guided Hierarchical Cropping
• Multiscale Feature Aggregation
• Small Object Segmentation
• Transformer Encoder
• Medical Image Segmentation