PraNet: Parallel Reverse Attention Network for Polyp Segmentation

2020/06/13 by Deng-Ping Fan, Ge-Peng Ji, Fan, Deng-Ping +11 · 63 citations
Computer Science · Engineering · Medicine · #Advanced Image and Video Retrieval Techniques #Colorectal Cancer Screening and Detection #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image Retrieval and Classification Techniques #Image and Video Processing (eess.IV) #cs.CV #eess.IV #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2006.11392

Accepted to MICCAI 2020

openalex publication_date 2020/06/13 · arxiv created 2020/07/03 · arxiv updated 2020/07/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Colonoscopy is an effective technique for detecting colorectal polyps, which are highly related to colorectal cancer. In clinical practice, segmenting polyps from colonoscopy images is of great importance since it provides valuable information for diagnosis and surgery. However, accurate polyp segmentation is a challenging task, for two major reasons: (i) the same type of polyps has a diversity of size, color and texture; and (ii) the boundary between a polyp and its surrounding mucosa is not sharp. To address these challenges, we propose a parallel reverse attention network (PraNet) for accurate polyp segmentation in colonoscopy images. Specifically, we first aggregate the features in high-level layers using a parallel partial decoder (PPD). Based on the combined feature, we then generate a global map as the initial guidance area for the following components. In addition, we mine the boundary cues using a reverse attention (RA) module, which is able to establish the relationship between areas and boundary cues. Thanks to the recurrent cooperation mechanism between areas and boundaries, our PraNet is capable of calibrating any misaligned predictions, improving the segmentation accuracy. Quantitative and qualitative evaluations on five challenging datasets across six metrics show that our PraNet improves the segmentation accuracy significantly, and presents a number of advantages in terms of generalizability, and real-time segmentation efficiency.

Citations

• Automated Polyp Detection in Colonoscopy Videos Using Shape and Context Information

Cited by

• QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation
• Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing for Weakly-Supervised Camouflaged Object Detection with Scribble Annotations
• Unlocking Generalization in Polyp Segmentation with DINO Self-Attention "keys"
• Assisted Refinement Network Based on Channel Information Interaction for Camouflaged and Salient Object Detection
• From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation
• Colon-X: Advancing Intelligent Colonoscopy toward Clinical Reasoning
• RefOnce: Distilling References into a Prototype Memory for Referring Camouflaged Object Detection
• SCALER: SAM-Enhanced Collaborative Learning for Label-Deficient Concealed Object Segmentation
• MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection
• C3Net: Context-Contrast Network for Camouflaged Object Detection
• MPCGNet: A Multiscale Feature Extraction and Progressive Feature Aggregation Network Using Coupling Gates for Polyp Segmentation
• MACMD: Multi-dilated Contextual Attention and Channel Mixer Decoding for Medical Image Segmentation
• MicroAUNet: Boundary-Enhanced Multi-scale Fusion with Knowledge Distillation for Colonoscopy Polyp Image Segmentation
• CLFSeg: A Fuzzy-Logic based Solution for Boundary Clarity and Uncertainty Reduction in Medical Image Segmentation
• LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation
• Controllable-LPMoE: Adapting to Challenging Object Segmentation via Dynamic Local Priors from Mixture-of-Experts
• EMA-SAM: Exponential Moving-average for SAM-based PTMC Segmentation
• Conformal Risk Training: End-to-End Optimization of Conformal Risk Control
• SPEGNet: Synergistic Perception-Guided Network for Camouflaged Object Detection
• BALR-SAM: Boundary-Aware Low-Rank Adaptation of SAM for Resource-Efficient Medical Image Segmentation
• PVTAdpNet: Polyp Segmentation using Pyramid vision transformer with a novel Adapter block
• Enhancing Polyp Segmentation via Encoder Attention and Dynamic Kernel Update
• Dual-supervised Asymmetric Co-training for Semi-supervised Medical Domain Generalization
• Shallow Attention Network for Polyp Segmentation
• Diffusion-Based Data Augmentation for Medical Image Segmentation
• CMFDNet: Cross-Mamba and Feature Discovery Network for Polyp Segmentation
• MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation
• Rethinking Evaluation of Infrared Small Target Detection
• Improved Segmentation of Polyps and Visual Explainability Analysis
• Multi Anatomy X-Ray Foundation Model
• Phantom-Insight: Adaptive Multi-cue Fusion for Video Camouflaged Object Detection with Multimodal LLM
• Dual Interaction Network with Cross-Image Attention for Medical Image Segmentation
• Advanced Brain Tumor Segmentation Using EMCAD: Efficient Multi-scale Convolutional Attention Decoding
• FreeVPS: Repurposing Training-Free SAM2 for Generalizable Video Polyp Segmentation
• Reversible Unfolding Network for Concealed Visual Perception with Generative Refinement
• SRMA-Mamba: Spatial Reverse Mamba Attention Network for Pathological Liver Segmentation in MRI Volumes
• Synthetic Data-Driven Multi-Architecture Framework for Automated Polyp Segmentation Through Integrated Detection and Mask Generation
• Hybrid(Transformer+CNN)-based Polyp Segmentation
• Mamba-based Efficient Spatio-Frequency Motion Perception for Video Camouflaged Object Detection
• HRVVS: A High-resolution Video Vasculature Segmentation Network via Hierarchical Autoregressive Residual Priors
• Frequency Prior Guided Matching: A Data Augmentation Approach for Generalizable Semi-Supervised Polyp Segmentation
• UniSegDiff: Boosting Unified Lesion Segmentation via a Staged Diffusion Model
• Segment Concealed Objects with Incomplete Supervision
• A Lightweight and Robust Framework for Real-Time Colorectal Polyp Detection Using LOF-Based Preprocessing and YOLO-v11n
• The Power of Certainty: How Confident Models Lead to Better Segmentation
• Crucial-Diff: A Unified Diffusion Model for Crucial Image and Annotation Synthesis in Data-scarce Scenarios
• Dual Semantic-Aware Network for Noise Suppressed Ultrasound Video Segmentation
• CL-Polyp: A Contrastive Learning-Enhanced Network for Accurate Polyp Segmentation
• MEGANet-W: A Wavelet-Driven Edge-Guided Attention Framework for Weak Boundary Polyp Detection
• Mamba Guided Boundary Prior Matters: A New Perspective for Generalized Polyp Segmentation
• LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment
• Pixel-wise Modulated Dice Loss for Medical Image Segmentation
• UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learning
• Uncertainty-Masked Bernoulli Diffusion for Camouflaged Object Detection Refinement
• Lightweight RGB-D Salient Object Detection from a Speed-Accuracy Tradeoff Perspective
• Hierarchical Self-Prompting SAM: A Prompt-Free Medical Image Segmentation Framework
• InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective
• Topo-VM-UNetV2: Encoding Topology into Vision Mamba UNet for Polyp Segmentation
• DFEN: Dual Feature Equalization Network for Medical Image Segmentation
• Multi-Scale Target-Aware Representation Learning for Fundus Image Enhancement
• FractalCovNet architecture for COVID-19 Chest X-ray image Classification and CT-scan image Segmentation
• FocusNet: Transformer-enhanced Polyp Segmentation with Local and Pooling Attention
• PraNet-V2: Dual-Supervised Reverse Attention for Medical Image Segmentation
• ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation

Related

• DDANet: Dual Decoder Attention Network for Automatic Polyp Segmentation
• MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation
• FocusNet: Transformer-enhanced Polyp Segmentation with Local and Pooling Attention
• AG-CUResNeSt: A Novel Method for Colon Polyp Segmentation
• BetterNet: An Efficient CNN Architecture with Residual Learning and Attention for Precision Polyp Segmentation