MedCAGD: Context-Aware Gated Decoder for Efficient Medical Image Segmentation
2026-07-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors focus on improving the part of medical image segmentation models called the decoder, which turns processed image features into precise pixel-level labels. They design a new decoder that carefully controls how different detail levels and contexts are combined, using techniques like gated feature fusion and global context sharing. Their method helps make segmentation predictions that are more accurate and consistent across multiple medical imaging tests. They show their approach works well through experiments on 11 datasets and provide the code for others to use.
medical image segmentationencoder-decoder architecturefeature fusioncontext aggregationmulti-scale channel recalibrationgated skip connectionsglobal contexttransformer encoderpixel-level predictionboundary preservation
Authors
Saad Wazir, Patrick Dominique Vibild, Dinh Phu Tran, Seongah Kim, Daeyoung Kim
Abstract
Medical image segmentation relies on the ability of encoder-decoder architectures to translate rich feature representations into accurate pixel-level predictions under challenging conditions such as low contrast, structural ambiguity, and scale variability. While recent advances in large-scale pretraining and transformer-based encoders have substantially improved feature extraction, segmentation accuracy remains constrained by decoder design, particularly in terms of cross-scale alignment, contextual integration, and boundary preservation. In this work, we revisit medical image segmentation from a decoder-centric perspective and propose a context-aware gated decoder that systematically regulates feature fusion and contextual aggregation throughout the decoding process. The proposed decoder integrates lightweight multi-scale channel recalibration, gated skip fusion with spatial competition and a global context aggregation mechanism that injects encoder-wide information into intermediate decoding stages. This design enables effective translation of strong pretrained encoder representations into spatially consistent predictions. Extensive experiments across 11 medical image segmentation benchmarks validate the effectiveness and demonstrate that the proposed approach consistently outperforms strong baselines while remaining computationally practical. Code: https://github.com/saadwazir/MedCAGD