Zoom in Lesions for Better Diagnosis: Attention Guided Deformation Network for WCE Image Classification

Xing, Xiaohan; Yuan, Yixuan; Meng, Max Q.-H.

doi:10.1109/tmi.2020.3010102

Cited by 34 publications

(15 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared our method with some existing methods, including two state‐of‐the‐art methods, that is, AGDN 8 and DenseNet201 on the same data set used in the ablation study. VGG16, DenseNet121, and DenseNet201 in this set of experiments are pretrained on the ImageNet data set.…”

Section: Methodsmentioning

confidence: 99%

“…To the best of our knowledge, we are the first to use the capsule‐based network in endoscopic image classification and experimental results on the Kvasir v2 data sets demonstrate the superior performance of our method to the state‐of‐the‐art methods 8 …”

Section: Introductionmentioning

confidence: 90%

“…Then they introduced UD loss to deal with the strong data imbalance and CS loss to make sure that the features have large interclass variations and small intraclass variations. Xing et al 8 proposed a two‐branch Attention Guided Deformation Network (AGDN) for the wireless capsule endoscopy image classification task to guide the deformation of input images to enlarge lesion areas, based on which they can force the network to focus more on the lesion areas. CNNs have strong ability to learn local features, but lack the ability of learning long‐distance dependence and rotation invariance.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Convolutional‐capsule network for gastrointestinal endoscopy image classification

Wang

Yang

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Automated diagnosis of digestive tract diseases from gastrointestinal endoscopy images is of high importance for improving the diagnosis accuracy and efficiency. The current mainstream methods for image classification of digestive tract endoscopy images are based on Convolutional Neural Networks (CNNs). However, due to their inherent defects, CNNs are not strong enough in learning deformation‐invariant global features which is essential in gastrointestinal endoscopic image classification. To solve this problem, in this paper we present a two‐stage endoscopic image classification method which can effectively combine complementary advantages of midlevel CNN features and a capsule network. Specifically, the core of our method is a lesion‐aware CNN feature extraction module which can encode sufficiently detailed information of lesions in midlevel CNN features and in turn enable the subsequent capsule classification network to effectively learn deformation‐invariant relationships between image entities. Extensive experiments demonstrate the superiority of our method to the state‐of‐the‐art methods with the classification accuracy of 94.83% on the Kvasir v2 data set and the classification accuracy of 85.99% on the HyperKvasir data set.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 90%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional‐capsule network for gastrointestinal endoscopy image classification

Wang

Yang

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…Guo et al proposed a semisupervised learning method with adaptive aggregated attention (AAA) module for automatic WCE images classification [31], aiming at the limited endoscopic dataset. Xing et al proposed a two-branch attention-guided deformation network (AGDN) for WCE image classification, which constructed significant inputs to highlight lesion areas and provided prior knowledge for the classification network [32]. Although the AGD module could better magnify the lesion area, they did not consider the effective fusion of the output feature maps from each branch.…”

Section: Computer Aided Diagnosis System For Endoscopic Image Classif...mentioning

confidence: 99%

Adaptive aggregation with self‐attention network for gastrointestinal image classification

Yao

Zhu

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Automatic classification of diseases in endoscopic images is essential to the improvement of diagnostic performance and the reduction of colorectal cancer mortality. However, due to the ambiguous boundary between background and foreground, abnormal classification in endoscopic images is still challenging. To tackle such a situation, an adaptive aggregation with self‐attention network (AASAN), including a global branch, a local branch, and a fusion branch, is proposed imitating the diagnosis process of endoscopists. On this basis, the self‐attention with relative position encoding (SA‐RPE) module is designed to capture long‐range dependencies and gather lesion neighborhood information. Furthermore, an adaptive aggregation feature (AAF) module is proposed and embedded into the fusion branch for final image label prediction, which is helpful to capture more discriminant features. Extensive experiments show that the classification accuracy of the authors' method on Kvasir public dataset reaches 96.37% in a fivefold cross‐validation, higher than the state‐of‐the‐art deep learning algorithms.

show abstract

“…The attention mechanism has been widely used in tasks such as natural language description [33], machine translation [34], image feature extraction [35,36], and image classification [37,38]. In essence, the attention mechanism is a weight probability distribution mechanism that assigns larger weights to important content and smaller weights to other content.…”

Section: Ph(i) = Ph Imentioning

confidence: 99%

AAU-Net: Attention-Based Asymmetric U-Net for Subject-Sensitive Hashing of Remote Sensing Images

Ding

Chen

Wang³

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

The prerequisite for the use of remote sensing images is that their security must be guaranteed. As a special subset of perceptual hashing, subject-sensitive hashing overcomes the shortcomings of the existing perceptual hashing that cannot distinguish between “subject-related tampering” and “subject-unrelated tampering” of remote sensing images. However, the existing subject-sensitive hashing still has a large deficiency in robustness. In this paper, we propose a novel attention-based asymmetric U-Net (AAU-Net) for the subject-sensitive hashing of remote sensing (RS) images. Our AAU-Net demonstrates obvious asymmetric structure characteristics, which is important to improve the robustness of features by combining the attention mechanism and the characteristics of subject-sensitive hashing. On the basis of AAU-Net, a subject-sensitive hashing algorithm is developed to integrate the features of various bands of RS images. Our experimental results show that our AAU-Net-based subject-sensitive hashing algorithm is more robust than the existing deep learning models such as Attention U-Net and MUM-Net, and its tampering sensitivity remains at the same level as that of Attention U-Net and MUM-Net.

show abstract

Zoom in Lesions for Better Diagnosis: Attention Guided Deformation Network for WCE Image Classification

Cited by 34 publications

References 33 publications

Convolutional‐capsule network for gastrointestinal endoscopy image classification

Convolutional‐capsule network for gastrointestinal endoscopy image classification

Adaptive aggregation with self‐attention network for gastrointestinal image classification

AAU-Net: Attention-Based Asymmetric U-Net for Subject-Sensitive Hashing of Remote Sensing Images

Contact Info

Product

Resources

About