MIA-Net: Multi-information aggregation network combining transformers and convolutional feature learning for polyp segmentation

Li, Weisheng; Zhao, Yinghui; Li, Feiyan; Wang, Lınhong

doi:10.1016/j.knosys.2022.108824

Cited by 26 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, Pan et al 24 utilized a Hierarchical Transformer as an encoder to extract more potent multiscale features. Li et al 25 proposed a multiinformation aggregation network model called MIA-Net, which combines Transformer and convolutional feature learning. In 2024, Liu et al 26 proposed a new visual transformer model by introducing an attention mechanism and pyramid structure to improve the segmentation results.…”

Section: Related Workmentioning

confidence: 99%

MAUNet: Polyp segmentation network based on multiscale feature fusion of attention U‐shaped network structure

Long,

Lin,

Liu

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Colorectal cancer is a prevalent malignant tumor affecting the digestive tract. Although colonoscopy remains the most effective method for colon examination, it may occasionally fail to detect polyps. In an effort to enhance the detection rate of intestinal polyps during colonoscopy, we propose MAUNet, a polyp segmentation network based on a multi‐scale feature fusion of an Attention U‐shaped network structure. Our model incorporates advanced components, including the Receptive Field Block, Reverse Attention Block, and Residual Refinement Module, mirroring the analytical process performed by medical imaging professionals. We evaluated the performance of MAUNet on five challenging datasets and conducted a comparative analysis against five state‐of‐the‐art models using six evaluation metrics. The experimental results demonstrate that MAUNet achieves varying levels of performance improvement across the five datasets. Particularly on the Kvasir dataset, the Mean Dice and Mean IOU metrics reached 91.6% and 84.3%, respectively, confirming the model's outstanding performance in polyp segmentation.

show abstract

Section: Related Workmentioning

confidence: 99%

MAUNet: Polyp segmentation network based on multiscale feature fusion of attention U‐shaped network structure

Long,

Lin,

Liu

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…Recently, Transformer-based ideas turn popular [30]. The common way is to combine both Transformer and CNN for robust feature exploration [8,53]. For example, MIA-Net [8] uses both to capture global dependences and low-level spatial details.…”

Section: Polyp Segmentation In Imagesmentioning

confidence: 99%

“…The common way is to combine both Transformer and CNN for robust feature exploration [8,53]. For example, MIA-Net [8] uses both to capture global dependences and low-level spatial details. Some studies [4,6,7,9,54] adopt pure Transformers for feature abstraction.…”

Section: Polyp Segmentation In Imagesmentioning

confidence: 99%

“…This characteristic fits well with the advantages of Transformers which do well in discovering the long-range relations. Actually, the encoders built by Transformer [5], or Transformer encoders, have already been adopted in recent studies [4,[6][7][8][9] for robust feature extraction when doing polyp segmentation, which is also interesting to us for better performance. Some Transformer encoder-based methods [4,9] aggregated different stage encoder features, but are unable to exploit multi-scale contextual information.…”

Section: Introductionmentioning

confidence: 99%

“…Some Transformer encoder-based methods [4,9] aggregated different stage encoder features, but are unable to exploit multi-scale contextual information. Others [6][7][8] often adopted atrous convolution to further learn multi-scale feature from the encoder. These methods have improved the segmentation accuracy; however, they may not be efficient to cope with the vast size and shape of polyps due to the limited receptive field of convolution.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

CafeNet: A Novel Multi‐Scale Context Aggregation and Multi‐Level Foreground Enhancement Network for Polyp Segmentation

Ji,

Li,

Wang

et al. 2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The detection of polyps plays a significant role in colonoscopy examinations, cancer diagnosis, and early patient treatment. However, due to the diversity in the size, color, and shape of polyps, as well as the presence of low image contrast with the surrounding mucosa and fuzzy boundaries, precise polyp segmentation remains a challenging task. Furthermore, this task requires excellent real‐time performance to promptly and efficiently present predictive results to doctors during colonoscopy examinations. To address these challenges, a novel neural network, called CafeNet, is proposed in this paper for rapid and accurate polyp segmentation. CafeNet utilizes newly designed multi‐scale context aggregation (MCA) modules to adapt to the extensive variations in polyp morphology, covering small to large polyps by fusing simplified global contextual information and local information at different scales. Additionally, the proposed network utilizes newly designed multi‐level foreground enhancement (MFE) modules to compute and extract differential features between adjacent layers and uses the prediction output from the adjacent lower‐layer decoder as a guidance map to enhance the polyp information extracted by the upper‐layer encoder, thereby improving the contrast between polyps and the background. The polyp segmentation performance of the proposed CafeNet network is evaluated on five benchmark public datasets using six evaluation metrics. Experimental results indicate that CafeNet outperforms the state‐of‐the‐art networks, while also exhibiting the least parameter count along with excellent real‐time operational speed.

show abstract

MIA-Net: Multi-information aggregation network combining transformers and convolutional feature learning for polyp segmentation

Cited by 26 publications

References 10 publications

MAUNet: Polyp segmentation network based on multiscale feature fusion of attention U‐shaped network structure

MAUNet: Polyp segmentation network based on multiscale feature fusion of attention U‐shaped network structure

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

CafeNet: A Novel Multi‐Scale Context Aggregation and Multi‐Level Foreground Enhancement Network for Polyp Segmentation

Contact Info

Product

Resources

About