PraNet: Parallel Reverse Attention Network for Polyp Segmentation

  title={PraNet: Parallel Reverse Attention Network for Polyp Segmentation},
  author={Deng-Ping Fan and Ge-Peng Ji and Tao Zhou and Geng Chen and H. Fu and Jianbing Shen and Ling Shao},
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… 

Boundary-aware Feature and Prediction Refinement for Polyp Segmentation

This work designs a segmentation decoder for representation learning with boundary prior and proposes a novel consistency loss to learn clues from the polar coordinate and shows that the proposal consistently improves the segmentation performance of polyps.

DilatedSegNet: A Deep Dilated Segmentation Network for Polyp Segmentation

The results on the publicly available Kvasir-SEG and BKAI-IGH datasets suggest that DilatedSegNet can give real-time feedback while retaining a high DSC, indicating high potential for using such models in real clinical settings in the near future.

Pixel-Level Anomaly Detection via Uncertainty-aware Prototypical Transformer

This work designs a memory-guided prototype learning transformer encoder to learn and memorize the prototypical representations of anomalies for enabling the model to capture the diversity of anomalies and proposes an uncertainty-aware prototypical transformer decoder, which takes into account both the diversity and uncertainty of anomaly.

ColonFormer: An Efficient Transformer Based Method for Colon Polyp Segmentation

ColonFormer is an encoder-decoder architecture capable of modeling long-range semantic information at both encoder and decoder branches and outperforms other state-of-the-art methods on all benchmark datasets.

An Efficient Polyp Segmentation Network

This work proposes a new model that requires fewer parameters as well as outperforms the state-of-the-art models for polyps management and uses EfficientNetB0 for the encoder part and partial decoder, which is used to reduce the number of parameters while achieving high accuracy in segmentation.

CRF-EfficientUNet: an improved UNet framework for polyp segmentation in colonoscopy images with combined asymmetric loss function and CRF-RNN layer

Experimental results on popular benchmark datasets show that CRF-EfficientUNet achieves state-of-the-art accuracy compared to existing methods, and it can be a compelling choice for practical applications with considerable data variations.

UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation

Uncertainty Augmented Context Attention network (UACANet) for polyp segmentation which considers an uncertain area of the saliency map is proposed which achieves state-of-the-art performance.

Concealed Object Detection

The first systematic study on concealed object detection (COD), which aims to identify objects that are visually embedded in their background, is presented, and rich annotations including object categories, object boundaries, challenging attributes, object-level labels, and instance-level annotations are provided.

Towards Automated Polyp Segmentation Using Weakly- and Semi-Supervised Learning and Deformable Transformers

This work proposes a novel framework that can be trained using only weakly annotated images along with exploiting unlabeled images, and proposes three ideas to address the problem of pixel-wise annotated datasets.

EINet: camouflaged object detection with pyramid vision transformer

An enhanced identification network (EINet) is proposed to strengthen the COD task’s identification capabilities and is a powerful COD model that outperforms current state-of-the-art models.



ResUNet++: An Advanced Architecture for Medical Image Segmentation

ResUNet++ is proposed, which is an improved ResUNet architecture for colonoscopic image segmentation, which significantly outperforms U-Net and Res UNet, two key state-of-the-art deep learning architectures, by achieving high evaluation scores.

Selective Feature Aggregation Network with Area-Boundary Constraints for Polyp Segmentation

This work proposes a novel selective feature aggregation network with the area and boundary constraints and introduces three up-concatenations between encoder and decoders and embedding Selective Kernel Modules into convolutional layers which can adaptively extract features from different size of kernels.

Road Extraction by Deep Residual U-Net

A semantic segmentation neural network, which combines the strengths of residual learning and U-Net, is proposed for road area extraction, which outperforms all the comparing methods and demonstrates its superiority over recently developed state of the arts methods.

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

This paper presents UNet++, a new, more powerful architecture for medical image segmentation where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways, and argues that the optimizer would deal with an easier learning task when the feature maps from the decoder and encoder networks are semantically similar.

A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images

A comparative study is performed to show that FCNs significantly outperform, without any further postprocessing, prior results in endoluminal scene segmentation, especially with respect to polyp segmentation and localization.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Camouflaged Object Detection

A simple but effective framework for COD, termed Search Identification Network (SINet), which outperforms various state-of-the-art object detection baselines on all datasets tested, making it a robust, general framework that can help facilitate future research in COD.

Bilateral Attention Network for RGB-D Salient Object Detection

This paper introduces a Bilateral Attention Module (BAM) with a complementary attention mechanism: foreground-first (FF) attention and background- first (BF) attention, which can capture more meaningful foreground and background cues, and shift more attention to refining the uncertain details between foreground and Background regions.

Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images

A novel COVID-19 Lung Infection Segmentation Deep Network (Inf-Net) is proposed to automatically identify infected regions from chest CT slices and outperforms most cutting-edge segmentation models and advances the state-of-the-art performance.