HELPNet: Hierarchical Perturbations Consistency and Entropy-guided Ensemble for Scribble Supervised Medical Image Segmentation

2024-12-25

AI Summary

In medical image segmentation, high annotation costs for fully supervised learning and sparse scribble annotations lead to insufficient accuracy and poor boundary modeling. To address these challenges, this paper proposes HELPNet, a weakly supervised framework. Methodologically, it introduces a novel Hierarchical Perturbation Consistency (HPC) mechanism that integrates density-controlled multi-view Jigsaw perturbations with multi-scale consistency constraints; an Entropy-Guided Pseudo-Label evaluation (EGPL) strategy to enhance confidence calibration; and a Structure Prior Refinement (SPR) module leveraging graph connectivity and boundary regularization for structural refinement. Evaluated on ACDC, MSCMRseg, and CHAOS datasets, HELPNet significantly outperforms existing scribble-supervised methods and approaches the performance of state-of-the-art fully supervised models. The source code is publicly available.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Reasoning under Uncertainty: Graphical Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Creating fully annotated labels for medical image segmentation is prohibitively time-intensive and costly, emphasizing the necessity for innovative approaches that minimize reliance on detailed annotations. Scribble annotations offer a more cost-effective alternative, significantly reducing the expenses associated with full annotations. However, scribble annotations offer limited and imprecise information, failing to capture the detailed structural and boundary characteristics necessary for accurate organ delineation. To address these challenges, we propose HELPNet, a novel scribble-based weakly supervised segmentation framework, designed to bridge the gap between annotation efficiency and segmentation performance. HELPNet integrates three modules. The Hierarchical perturbations consistency (HPC) module enhances feature learning by employing density-controlled jigsaw perturbations across global, local, and focal views, enabling robust modeling of multi-scale structural representations. Building on this, the Entropy-guided pseudo-label (EGPL) module evaluates the confidence of segmentation predictions using entropy, generating high-quality pseudo-labels. Finally, the structural prior refinement (SPR) module incorporates connectivity and bounded priors to enhance the precision and reliability and pseudo-labels. Experimental results on three public datasets ACDC, MSCMRseg, and CHAOS show that HELPNet significantly outperforms state-of-the-art methods for scribble-based weakly supervised segmentation and achieves performance comparable to fully supervised methods. The code is available at https://github.com/IPMI-NWU/HELPNet.

Problem

• Medical Image Segmentation
• Scribble-guided Annotation
• Organ Recognition

Innovation

• HELPNet
• Weakly-Supervised Learning
• Medical Image Segmentation