Efficient Medical Image Segmentation Based on Knowledge Distillation

Abstract

Recent advances have been made in applying convolutional neural networks to achieve more precise prediction results for medical image segmentation problems. However, the success of existing methods has highly relied on huge computational complexity and massive storage, which is impractical in the real-world scenario. To deal with this problem, we propose an efficient architecture by distilling knowledge from well-trained medical image segmentation networks to train another lightweight network. This architecture empowers the lightweight network to get a significant improvement on segmentation capability while retaining its runtime efficiency. We further devise a novel distillation module tailored for medical image segmentation to transfer semantic region information from teacher to student network. It forces the student network to mimic the extent of difference of representations calculated from different tissue regions. This module avoids the ambiguous boundary problem encountered when dealing with medical imaging but instead encodes the internal information of each semantic region for transferring. Benefited from our module, the lightweight network could receive an improvement of up to 32.6% in our experiment while maintaining its portability in the inference phase. The entire structure has been verified on two widely accepted public CT datasets LiTS17 and KiTS19. We demonstrate that a lightweight network distilled by our method has non-negligible value in the scenario which requires relatively high operating speed and low storage usage.

arXiv commentAccepted by IEEE TMI, Code Avalivable

References in corpus (9)

• Distilling the Knowledge in a Neural Network
• FitNets: Hints for Thin Deep Nets
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields
• RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans
• Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning
• The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomes
• SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth
• Improving Fast Segmentation With Teacher-student Learning

Cited by in corpus (6)

• WORD: A large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image
• Knowledge Distillation approach towards Melanoma Detection
• Computer Vision Model Compression Techniques for Embedded Systems: A Survey
• Multi-AD: Cross-Domain Unsupervised Anomaly Detection for Medical and Industrial Applications
• FedBrain-Distill: Communication-Efficient Federated Brain Tumor Classification Using Ensemble Knowledge Distillation on Non-IID Data
• Rethinking Intermediate Layers design in Knowledge Distillation for Kidney and Liver Tumor Segmentation