CRCNet: Global-local context and multi-modality cross attention for polyp segmentation

Zhu, Jian‐Bo; Ge, Ming‐Feng; Chang, Zhimin; Dong, Wen‐Fei

doi:10.1016/j.bspc.2023.104593

Cited by 20 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advantage of the MFPPM is that it can capture rich contextual information at different resolutions and enhance the receptive field which is favorable to segmenting the sharp object boundaries. The analysis illustrates that the global information helps to localize large polyps and the local information facilitates the localization of small polyps 22 . The MFPPM utilizes all of the features from the entire dual‐branch encoder to locate the polyp region more accurately and improve the segmentation performance.…”

Section: Methodsmentioning

confidence: 99%

“…The analysis illustrates that the global information helps to localize large polyps and the local information facilitates the localization of small polyps. 22 The MFPPM utilizes all of the features from the entire dual-branch encoder to locate the polyp region more accurately and improve the segmentation performance. The calculation formula is as follows:…”

Section: Multi-feature Pyramid Pooling Modulementioning

confidence: 99%

“…However, Transformer cannot provide sufficient information acquisition for low-level local details, leading to coarse segmentation results, 20 especially for small-size polyp segmentation. Some research 12,21,22 shows that local context information is essential for identifying tiny polyps, and global context information aids in segmenting large polyps. Therefore, simultaneously utilizing the advantages of CNNs and Transformer to improve the performance of polyp segmentation comes into fashion.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dual‐branch feature extraction network combined with Transformer and CNN for polyp segmentation

Liu,

Lin,

Han

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

To overcome the difficulty of accurate polyp segmentation, a novel encoder–decoder network DFETC‐Net is proposed, in which two encoders based on Swin Transformer and CNN are utilized to extract the global and local features respectively. Further, a new self‐attention and convolution feature fusion module is designed to fuse the two branch features to enhance the feature representative capability and alleviate the influence of the semantic gap. In the bottleneck, a new multi‐feature pyramid pooling module fuses all deep features from two branches to obtain multi‐scale information and promote segmentation accuracy. The coordinate attention is used in the skip connections between two shallow CNN blocks and corresponding decoder blocks to pay more attention to doubtful and complicated regions. Extensive experiments demonstrate the proposed network outperforms several state‐of‐the‐art methods in terms of both qualitative effects and quantitative measurements. All codes are available on https://github.com/LYJieH/DFETC-NET.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Multi-feature Pyramid Pooling Modulementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dual‐branch feature extraction network combined with Transformer and CNN for polyp segmentation

Liu,

Lin,

Han

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…Global Context and Local Position: Because of the feature map's continuous downsampling, which removes feature information, there is a bias in the localization of polyps. Researchers have devised spatial pyramid pooling [25] for feature compensation, and have demonstrated through extensive experiments that this method not only mitigates feature information loss but also improves the robustness of the model to the overall position and layout of the object by extracting spatial information of different sizes. The location information of the markers is disregarded during model training [26] as a result of the invariance of the self-attentive mechanism [27], which leads to hazy local detail segmentation of polyps.…”

Section: Related Workmentioning

confidence: 99%

“…Figure 4 illustrates the structure of the GCM, which uses a multi-branch design for better extraction of information at different feature maps. Specifically, the module consists of a 1 × 1 Conv, three 3 × 3 Atrous Conv [33,34] with different rates and an adaptive level pooling branch [25]. With the feature information collected from the encoder, the GCM uses the above branches to perform extraction and channel concatenate the feature maps at different scales to obtain a global feature map, which is sequentially upsampled and assigned to the CSwin block of the corresponding decoder.…”

Section: Global Context Module (Gcm)mentioning

confidence: 99%

GCCSwin-UNet: Global Context and Cross-Shaped Windows Vision Transformer Network for Polyp Segmentation

Zhu

Chang

et al. 2023

Processes

Self Cite

View full text Add to dashboard Cite

Accurate polyp segmentation is of great importance for the diagnosis and treatment of colon cancer. Convolutional neural networks (CNNs) have made significant strides in the processing of medical images in recent years. The limited structure of convolutional operations prevents CNNs from learning adequately about global and long-range semantic information interactions, despite the remarkable performance they have attained. Therefore, the GCCSwin-UNet framework is suggested in this study. Specifically, the model utilizes an encoder–decoder structure, using the patch-embedding layer for feature downsampling and the CSwin Transformer block as the encoder for contextual feature extraction. To restore the feature map’s spatial resolution during upsampling operations, a symmetric decoder and patch expansion layer are also created. In order to help the backbone module to do better feature learning, we also create a global context module (GCM) and a local position-enhanced module (LPEM). We conducted extensive experiments on the Kvasir-SEG and CVC-ClinicDB datasets, and compared them with existing methods. GCCSwin-UNet reached remarkable results with Dice and MIoU of 86.37% and 83.19% for Kvasir-SEG, respectively, and 91.26% and 84.65% for CVC-ClinicDB, respectively. Finally, quantitative analysis and statistical tests are applied to further demonstrate the validity and plausibility of our method.

show abstract

PolyDSS: computer-aided decision support system for multiclass polyp segmentation and classification using deep learning

Saad,

Maghraby,

Badawy

2023

Neural Comput & Applic

View full text Add to dashboard Cite

Colorectal cancer (CRC) is a malignant condition that affects the colon or rectum, and it is distinguished by abnormal cell growth in these areas. Colon polyps, which are abnormalities, can turn into cancer. To stop the spread of cancer, early polyp detection is essential. The timely removal of polyps without submitting a sample for histology is made possible by computer-assisted polyp classification. In addition to Locally Shared Features (LSF) and ensemble learning majority voting, this paper introduces a computer-aided decision support system named PolyDSS to assist endoscopists in segmenting and classifying various polyp classes using deep learning models like ResUNet and ResUNet++ and transfer learning models like EfficientNet. The PICCOLO dataset is used to train and test the PolyDSS model. To address the issue of class imbalance, data augmentation techniques were used on the dataset. To investigate the impact of each technique on the model, extensive experiments were conducted. While the classification module achieved the highest accuracy of 0.9425 by utilizing the strength of ensemble learning using majority voting, the proposed segmenting module achieved the highest Dice Similarity Coefficient (DSC) of 0.9244 using ResUNet++ and LSF. In conjunction with the Paris classification system, the PolyDSS model, with its significant results, can assist clinicians in identifying polyps early and choosing the best approach to treatment.

show abstract

CRCNet: Global-local context and multi-modality cross attention for polyp segmentation

Cited by 20 publications

References 33 publications

Dual‐branch feature extraction network combined with Transformer and CNN for polyp segmentation

Dual‐branch feature extraction network combined with Transformer and CNN for polyp segmentation

GCCSwin-UNet: Global Context and Cross-Shaped Windows Vision Transformer Network for Polyp Segmentation

PolyDSS: computer-aided decision support system for multiclass polyp segmentation and classification using deep learning

Contact Info

Product

Resources

About