CLFSeg: A Fuzzy-Logic based Solution for Boundary Clarity and Uncertainty Reduction in Medical Image Segmentation

2025-10-28

AI Summary

To address insufficient segmentation accuracy of polyps and cardiac structures caused by ambiguous boundaries and uncertainty in medical image segmentation, this paper proposes a Fuzzy Convolution (FC) module that integrates fuzzy logic with convolutional operations and embeds it into an encoder-decoder architecture to explicitly model boundary uncertainty during feature extraction. The method employs a hybrid loss function combining Binary Cross-Entropy (BCE) and Dice loss to mitigate class imbalance and improve robustness for small-target segmentation. Extensive experiments on four public benchmarks—Kvasir-SEG, CVC-ClinicDB, HeartSeg, and ACDC—demonstrate that the proposed approach consistently outperforms existing state-of-the-art methods, achieving average Dice score improvements of 2.1–4.3 percentage points. Moreover, the FC module introduces negligible computational overhead, preserving real-time inference capability and enabling practical clinical deployment.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Accurate polyp and cardiac segmentation for early detection and treatment is essential for the diagnosis and treatment planning of cancer-like diseases. Traditional convolutional neural network (CNN) based models have represented limited generalizability, robustness, and inability to handle uncertainty, which affects the segmentation performance. To solve these problems, this paper introduces CLFSeg, an encoder-decoder based framework that aggregates the Fuzzy-Convolutional (FC) module leveraging convolutional layers and fuzzy logic. This module enhances the segmentation performance by identifying local and global features while minimizing the uncertainty, noise, and ambiguity in boundary regions, ensuring computing efficiency. In order to handle class imbalance problem while focusing on the areas of interest with tiny and boundary regions, binary cross-entropy (BCE) with dice loss is incorporated. Our proposed model exhibits exceptional performance on four publicly available datasets, including CVC-ColonDB, CVC-ClinicDB, EtisLaribPolypDB, and ACDC. Extensive experiments and visual studies show CLFSeg surpasses the existing SOTA performance and focuses on relevant regions of interest in anatomical structures. The proposed CLFSeg improves performance while ensuring computing efficiency, which makes it a potential solution for real-world medical diagnostic scenarios. Project page is available at https://visdomlab.github.io/CLFSeg/

Problem

• Reduces boundary uncertainty in medical image segmentation
• Handles class imbalance for small anatomical structures
• Improves robustness over traditional CNN-based segmentation models

Innovation

• Fuzzy-Convolutional module combines fuzzy logic with CNNs
• Encoder-decoder framework handles boundary uncertainty and noise
• Binary cross-entropy with dice loss addresses class imbalance