Category guided attention network for brain tumor segmentation in MRI

Li, Jiangyun; Yu, Hong; Chen, Chen; Ding, Meng; Zha, Sen

doi:10.1088/1361-6560/ac628a

Cited by 11 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attention mechanisms can assist models to focus on the specific object of the input, which are widely used in various tasks including machine translation, classification, semantic segmentation, recognition, and image generation (Li et al 2022). Oktay et al (2018) combined attention gate with U-net in CT image segmentation of pancreatic cancer to improve the prediction performance of U-Net while maintaining the computational efficiency.…”

Section: Attention Mechanismmentioning

confidence: 99%

JAAL-Net: a joint attention and adversarial learning network for skin lesion segmentation

Xiong¹,

Pan²,

Lei³

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective. Skin lesion segmentation plays an important role in the diagnosis and treatment of melanoma. Existing skin lesion segmentation methods have trouble distinguishing hairs, air bubbles, and blood vessels around lesions, which affects the segmentation performance. Approach. To clarify the lesion boundary and raise the accuracy of skin lesion segmentation, a joint attention and adversarial learning network (JAAL-Net) is proposed that consists of a generator and a discriminator. In the JAAL-Net, the generator is a Local Fusion Network (LF-Net) utilizing the encoder-decoder structure. The encoder contains a convolutional block attention module to increase the weight of lesion information. The decoder involves a contour attention to obtain edge information and locate the lesion. To aid the LF-Net generate higher confidence predictions, a discriminant Dual Attention Network (DA-Net) is constructed with channel attention and position attention. Main results. The JAAL-Net is evaluated on three datasets ISBI2016, ISBI2017 and ISIC2018. The intersection over union (IoU) of the JAAL-Net on the three datasets are 90.27%, 89.56% and 80.76%, respectively. Experimental results show that the JAAL-Net obtains rich lesion and boundary information, enhances the confidence of the predictions, and improves the accuracy of skin lesion segmentation. Significance. The proposed approach effectively improves the performance of the model for skin lesion segmentation, which can assist physicians in accurate diagnosis well.

show abstract

Section: Attention Mechanismmentioning

confidence: 99%

JAAL-Net: a joint attention and adversarial learning network for skin lesion segmentation

Xiong¹,

Pan²,

Lei³

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…A c→c and A p→p perform the After that, we reverse the enhanced sequence back to class tokens and patch tokens according to the order of concatenation. Moreover, we introduce an auxiliary Euclidean distance loss L EU (Li et al 2022) to maximize the distance between the enhanced class tokens, which can further improve the feature discrepancy. The enhanced patch tokens are reshaped into 2D features and upsampled into the original size of H × W × D. To retain the source information, the input X intra is also combined, which is reformed by a 1×1 convolutional layer, to obtain the final output X inter ∈ R H×W ×D .…”

Section: Class Tokens (G)mentioning

confidence: 99%

ClassFormer: Exploring Class-Aware Dependency with Transformer for Medical Image Segmentation

Huang

Xie

Lin

et al. 2023

AAAI

View full text Add to dashboard Cite

Vision Transformers have recently shown impressive performances on medical image segmentation. Despite their strong capability of modeling long-range dependencies, the current methods still give rise to two main concerns in a class-level perspective: (1) intra-class problem: the existing methods lacked in extracting class-specific correspondences of different pixels, which may lead to poor object coverage and/or boundary prediction; (2) inter-class problem: the existing methods failed to model explicit category-dependencies among various objects, which may result in inaccurate localization. In light of these two issues, we propose a novel transformer, called ClassFormer, powered by two appealing transformers, i.e., intra-class dynamic transformer and inter-class interactive transformer, to address the challenge of fully exploration on compactness and discrepancy. Technically, the intra-class dynamic transformer is first designed to decouple representations of different categories with an adaptive selection mechanism for compact learning, which optimally highlights the informative features to reflect the salient keys/values from multiple scales. We further introduce the inter-class interactive transformer to capture the category dependency among different objects, and model class tokens as the representative class centers to guide a global semantic reasoning. As a consequence, the feature consistency is ensured with the expense of intra-class penalization, while inter-class constraint strengthens the feature discriminability between different categories. Extensive empirical evidence shows that ClassFormer can be easily plugged into any architecture, and yields improvements over the state-of-the-art methods in three public benchmarks.

show abstract

“…Specifically, there are two types of attention methods: channel attention and spatial attention. Recently, integrating channel attention, spatial attention, or both into convolution blocks has attracted much interest, achieving significant performance improvement (Woo et al 2018, Goceri 2020, Wang et al 2020, Hou et al 2021, Qin et al 2021, Zeng et al 2021, Li et al 2022. One of the representative methods of channel attention is the squeeze and excitation (SE) module, which can be effectively improved by selectively capturing highly sophisticated channel correlations.…”

Section: Attention Mechanismmentioning

confidence: 99%

Dermoscopy lesion classification based on GANs and a fuzzy rank-based ensemble of CNN models

Chang

et al. 2022

Phys. Med. Biol.

View full text Add to dashboard Cite

Background and Objective. Skin lesion classification by using deep learning technologies is still a considerable challenge due to high similarity among classes and large intraclass differences, serious class imbalance in data, and poor classification accuracy with low robustness. Approach. To address these issues, a two-stage framework for dermoscopy lesion classification using adversarial training and a fuzzy rank-based ensemble of multilayer feature fusion convolutional neural network (CNN) models is proposed. In the first stage, dermoscopy dataset augmentation based on generative adversarial networks (DDA-GANs) is proposed to obtain realistic dermoscopy lesion images, enabling significant improvement for balancing the number of lesions in each class. In the second stage, a fuzzy rank-based ensemble of multilayer feature fusion CNN models is proposed to classify skin lesions. In addition, an efficient channel integrating spatial attention (ECISA) module, in which a novel dilated pyramid pooling (DPP) structure is designed to extract multiscale features from an enlarged receptive field and filter meaningful information of the initial features. Combining the cross-entropy loss function with the focal loss function, a novel united loss function is designed to reduce the intraclass sample distance and to focus on difficult and error-prone samples to improve the recognition accuracy of the proposed model. Main results. In this paper, the common dataset (HAM10000) is selected to conduct simulation experiments to evaluate and verify the effectiveness of the proposed method. The subjective and objective experimental results demonstrate that the proposed method is superior over the state-of-the-art methods for skin lesion classification due to its higher accuracy, specificity and robustness. Significance. The proposed method effectively improves the classification performance of the model for skin diseases, which will help doctors make accurate and efficient diagnoses, reduce the incidence rate and improve the survival rates of patients.

show abstract

Category guided attention network for brain tumor segmentation in MRI

Cited by 11 publications

References 47 publications

JAAL-Net: a joint attention and adversarial learning network for skin lesion segmentation

JAAL-Net: a joint attention and adversarial learning network for skin lesion segmentation

ClassFormer: Exploring Class-Aware Dependency with Transformer for Medical Image Segmentation

Dermoscopy lesion classification based on GANs and a fuzzy rank-based ensemble of CNN models

Contact Info

Product

Resources

About