Inter- and intra-uncertainty based feature aggregation model for semi-supervised histopathology image segmentation

Abstract

Acquiring pixel-level annotations is often limited in applications such as histology studies that require domain expertise. Various semi-supervised learning approaches have been developed to work with limited ground truth annotations, such as the popular teacher-student models. However, hierarchical prediction uncertainty within the student model (intra-uncertainty) and image prediction uncertainty (inter-uncertainty) have not been fully utilized by existing methods. To address these issues, we first propose a novel inter- and intra-uncertainty regularization method to measure and constrain both inter- and intra-inconsistencies in the teacher-student architecture. We also propose a new two-stage network with pseudo-mask guided feature aggregation (PG-FANet) as the segmentation model. The two-stage structure complements with the uncertainty regularization strategy to avoid introducing extra modules in solving uncertainties and the aggregation mechanisms enable multi-scale and multi-stage feature integration. Comprehensive experimental results over the MoNuSeg and CRAG datasets show that our PG-FANet outperforms other state-of-the-art methods and our semi-supervised learning framework yields competitive performance with a limited amount of labeled data.

References in corpus (10)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• U${}^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection
• MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• MILD-Net: Minimal Information Loss Dilated Network for Gland Instance Segmentation in Colon Histology Images
• Micro-Net: A unified model for segmentation of various objects in microscopy images
• RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation
• A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark
• Hybrid Dual Mean-Teacher Network With Double-Uncertainty Guidance for Semi-Supervised Segmentation of MRI Scans
• Enhancing Nucleus Segmentation with HARU-Net: A Hybrid Attention Based Residual U-Blocks Network

Cited by in corpus (3)

• Iterative pseudo-labeling based adaptive copy-paste supervision for semi-supervised tumor segmentation
• DuetMatch: Harmonizing Semi-Supervised Brain MRI Segmentation via Decoupled Branch Optimization
• Full-scale Representation Guided Network for Retinal Vessel Segmentation