Duplex Contextual Relation Network For Polyp Segmentation

Yin, Zijin; Liang, Kongming; Ma, Zhanyu; Guo, Jun

doi:10.1109/isbi52829.2022.9761402

Cited by 72 publications

(31 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, for most severely degraded contents, the methods fail to give significant appearance improvements. Advancements on the network architectures and objective functions of the models, to consider the semantic relations of image pixels [29] as well as the representation consistency of images with the same semantic classes [30], can lead to better content fidelity. Creating a more appropriate data set, generated from absolute HDR data with proper inspection on HDR display devices, can also be considered as a next research direction.…”

Section: Discussionmentioning

confidence: 99%

Content Fidelity of Deep Learning Methods for Clipping and Over-exposure Correction

Abebe¹

2021

lim

View full text Add to dashboard Cite

Exposure problems, due to standard camera sensor limitations, often lead to image quality degradations such as loss of details and change in color appearance. The quality degradations further hiders the performances of imaging and computer vision applications. Therefore, the reconstruction and enhancement of uderand over-exposed images is essential for various applications. Accordingly, an increasing number of conventional and deep learning reconstruction approaches have been introduced in recent years. Most conventional methods follow color imaging pipeline, which strongly emphasize on the reconstructed color and content accuracy. The deep learning (DL) approaches have conversely shown stronger capability on recovering lost details. However, the design of most DL architectures and objective functions don’t take color fidelity into consideration and, hence, the analysis of existing DL methods with respect to color and content fidelity will be pertinent. Accordingly, this work presents performance evaluation and results of recent DL based overexposure reconstruction solutions. For the evaluation, various datasets from related research domains were merged and two generative adversarial networks (GAN) based models were additionally adopted for tone mapping application scenario. Overall results show various limitations, mainly for severely over-exposed contents, and a promising potential for DL approaches, GAN, to reconstruct details and appearance.

show abstract

Section: Discussionmentioning

confidence: 99%

Content Fidelity of Deep Learning Methods for Clipping and Over-exposure Correction

Abebe¹

2021

lim

View full text Add to dashboard Cite

show abstract

“…These methods either adopt U-Net directly or introduce U-Net enhanced architectures for improved performances. Some researchers even considered multiple parallel branches for robust features, such as those from the decoder [44] or intermediate stages [45,46]. Boundaries are often adopted as constraints explicitly [47][48][49] or implicitly [30,[50][51][52].…”

Section: Polyp Segmentation In Imagesmentioning

confidence: 99%

Parallel matters: Efficient polyp segmentation with parallel structured feature augmentation modules

Guo

Fang

Wang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

The large variations of polyp sizes and shapes and the close resemblances of polyps to their surroundings call for features with long-range information in rich scales and strong discrimination. This article proposes two parallel structured modules for building those features. One is the Transformer Inception module (TI) which applies Transformers with different reception fields in parallel to input features and thus enriches them with more long-range information in more scales. The other is the Local-Detail Augmentation module (LDA) which applies the spatial and channel attentions in parallel to each block and thus locally augments the features from two complementary dimensions for more object details. Integrating TI and LDA, a new Transformer encoder based framework, Parallel-Enhanced Network (PENet), is proposed, where LDA is specifically adopted twice in a coarse-tofine way for accurate prediction. PENet is efficient in segmenting polyps with different sizes and shapes without the interference from the background tissues. Experimental comparisons with state-of-the-arts methods show its merits.

show abstract

“…ResUNet++ 8 added residual block, 15 Atrous Spatial Pyramid Pooling, 16 and Squeeze and Excitation mechanism 17 to extract more useful information. DCRNet 18 explored the contextual connections between images to capture global contextual information. All of the above methods have made favorable progress.…”

Section: Related Workmentioning

confidence: 99%

“…The PSPNet 24 proposed a pyramid pooling module, that combines pooling operations of different sizes to extract features for global contextual information fusion. DCRNet 18 paid extra attention to the location relationship between images to extract more potential information on the basis of focusing on contextual connections within images. MSFANet 25 used a PGAM module including global average pool, local average pool, and identity mapping in the encoding phase to obtain global features from the feature map.…”

Section: Related Workmentioning

confidence: 99%

UACENet: Uncertain area attention and cross‐image context extraction network for polyp segmentation

Wang

Gao

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Accurately segmenting polyp from colonoscopy images is essential for early screening and diagnosis of colorectal cancer. In recent years, with the proposed encoder‐decoder architecture, many advanced methods have been applied to this task and have achieved significant improvements. However, accurate segmentation of polyps has always been a challenging task due to the irregular shape and size of polyps, the low contrast between the polyp and the background in some images, and the influence of the environment such as illumination and mucus. In order to tackle these challenges, we propose a novel uncertain area attention and cross‐image context extraction network for accurate polyp segmentation, which consists of the uncertain area attention module (UAAM), the cross‐image context extraction module (CCEM), and the adaptive fusion module (AFM). UAAM is guided by the output prediction of the adjacent decoding layer, and focuses on the difficult region of the boundary without neglecting the attention to the background and foreground so that more edge details and uncertain information can be captured. CCEM innovatively captures multi‐scale global context within an image and implicit contextual information between multiple images, fusing them to enhance the extraction of global location information. AFM fuses the local detail information extracted by UAAM and the global location information extracted by CCEM with the decoding layer feature for multiple fusion and adaptive attention to enhance feature representation. Our method is extensively experimented on four public datasets and generally achieves state‐of‐the‐art performance compared to other advanced methods.

show abstract

Duplex Contextual Relation Network For Polyp Segmentation

Cited by 72 publications

References 15 publications

Content Fidelity of Deep Learning Methods for Clipping and Over-exposure Correction

Content Fidelity of Deep Learning Methods for Clipping and Over-exposure Correction

Parallel matters: Efficient polyp segmentation with parallel structured feature augmentation modules

UACENet: Uncertain area attention and cross‐image context extraction network for polyp segmentation

Contact Info

Product

Resources

About