SWDL: Stratum-Wise Difference Learning with Deep Laplacian Pyramid for Semi-Supervised 3D Intracranial Hemorrhage Segmentation

2025/06/12 by Cheng Wang, Siqi Chen, Wang, Cheng +9
Medicine · Neuroscience · #68T45 #92C55 #Brain Tumor Detection and Classification #Cerebrospinal fluid and hydrocephalus #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #I.2.6 #I.4.6 #I.4.9 #Image and Video Processing (eess.IV) #Intracerebral and Subarachnoid Hemorrhage Research #J.3 #Machine Learning (cs.LG) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2506.10325

openalex publication_date 2025/06/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recent advances in medical imaging have established deep learning-based segmentation as the predominant approach, though it typically requires large amounts of manually annotated data. However, obtaining annotations for intracranial hemorrhage (ICH) remains particularly challenging due to the tedious and costly labeling process. Semi-supervised learning (SSL) has emerged as a promising solution to address the scarcity of labeled data, especially in volumetric medical image segmentation. Unlike conventional SSL methods that primarily focus on high-confidence pseudo-labels or consistency regularization, we propose SWDL-Net, a novel SSL framework that exploits the complementary advantages of Laplacian pyramid and deep convolutional upsampling. The Laplacian pyramid excels at edge sharpening, while deep convolutions enhance detail precision through flexible feature mapping. Our framework achieves superior segmentation of lesion details and boundaries through a difference learning mechanism that effectively integrates these complementary approaches. Extensive experiments on a 271-case ICH dataset and public benchmarks demonstrate that SWDL-Net outperforms current state-of-the-art methods in scenarios with only 2% labeled data. Additional evaluations on the publicly available Brain Hemorrhage Segmentation Dataset (BHSD) with 5% labeled data further confirm the superiority of our approach. Code and data have been released at https://github.com/SIAT-CT-LAB/SWDL.

Citations

• Weakly Supervised Intracranial Hemorrhage Segmentation with YOLO and an Uncertainty Rectified Segment Anything Model
• Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentation
• BHSD: A 3D Multi-Class Brain Hemorrhage Segmentation Dataset
• Diverse Cotraining Makes Strong Semi-Supervised Segmentor
• Cut-Paste Consistency Learning for Semi-Supervised Lesion Segmentation
• Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
• Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation
• Optimized U-Net for Brain Tumor Segmentation
• Mutual Consistency Learning for Semi-supervised Medical Image Segmentation
• Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
• Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
• Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model
• V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• THE DISTRIBUTION OF THE FLORA IN THE ALPINE ZONE. 1

Related

• BHSD: A 3D Multi-Class Brain Hemorrhage Segmentation Dataset
• Class Activation Map-based Weakly supervised Hemorrhage Segmentation using Resnet-LSTM in Non-Contrast Computed Tomography images
• Weakly Supervised Intracranial Hemorrhage Segmentation with YOLO and an Uncertainty Rectified Segment Anything Model
• Automated segmentation of intracranial hemorrhages from 3D CT
• Hemorica: A Comprehensive CT Scan Dataset for Automated Brain Hemorrhage Classification, Segmentation, and Detection