Frequency Domain Unlocks New Perspectives for Abdominal Medical Image Segmentation
This work addresses segmentation challenges in abdominal medical imaging for surgical planning and tumor staging, representing an incremental advance with domain-specific impact.
The paper tackles the problem of medical image segmentation where malignant tumors resemble normal organs in low-contrast backgrounds, proposing the FASS framework that amplifies foreground distinction and enhances boundary recognition. Experiments on multiple datasets show superior performance across all metrics, with significant improvements in robustness and fine structure recognition.
Accurate segmentation of tumors and adjacent normal tissues in medical images is essential for surgical planning and tumor staging. Although foundation models generally perform well in segmentation tasks, they often struggle to focus on foreground areas in complex, low-contrast backgrounds, where some malignant tumors closely resemble normal organs, complicating contextual differentiation. To address these challenges, we propose the Foreground-Aware Spectrum Segmentation (FASS) framework. First, we introduce a foreground-aware module to amplify the distinction between background and the entire volume space, allowing the model to concentrate more effectively on target areas. Next, a feature-level frequency enhancement module, based on wavelet transform, extracts discriminative high-frequency features to enhance boundary recognition and detail perception. Eventually, we introduce an edge constraint module to preserve geometric continuity in segmentation boundaries. Extensive experiments on multiple medical datasets demonstrate superior performance across all metrics, validating the effectiveness of our framework, particularly in robustness under complex conditions and fine structure recognition. Our framework significantly enhances segmentation of low-contrast images, paving the way for applications in more diverse and complex medical imaging scenarios.