ResGANet: Residual group attention network for medical image classification and segmentation

Cheng, Junlong; Tian, Shengwei; Yu, Long; Gao, Chengrui; Kang, Xiaojing; Ma, Xiang; Wu, Weidong; Liu, Shijia; Lu, Hongchun

doi:10.1016/j.media.2021.102313

Cited by 116 publications

(33 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 3 shows that ResNet101 backbone achieves slightly better results in classifying the four tissues. Experimental results show that, regardless of whether it is DenseNet or ResNet, a deeper network indicates better analysis results, which has also been verified in other image classification or segmentation tasks Khened et al ( 51 ) Cheng et al ( 52 ).…”

Section: Experiments and Resultsmentioning

confidence: 54%

A semi-supervised learning approach with consistency regularization for tumor histopathological images analysis

Jiang

Sui

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

IntroductionManual inspection of histopathological images is important in clinical cancer diagnosis. Pathologists implement pathological diagnosis and prognostic evaluation through the microscopic examination of histopathological slices. This entire process is time-consuming, laborious, and challenging for pathologists. The modern use of whole-slide imaging, which scans histopathology slides to digital slices, and analysis using computer-aided diagnosis is an essential problem.MethodsTo solve the problem of difficult labeling of histopathological data, and improve the flexibility of histopathological analysis in clinical applications, we herein propose a semi-supervised learning algorithm coupled with consistency regularization strategy, called“Semi- supervised Histopathology Analysis Network”(Semi-His-Net), for automated normal-versus-tumor and subtype classifications. Specifically, when inputted disturbing versions of the same image, the model should predict similar outputs. Based on this, the model itself can assign artificial labels to unlabeled data for subsequent model training, thereby effectively reducing the labeled data required for training.ResultsOur Semi-His-Net is able to classify patches from breast cancer histopathological images into normal tissue and three other different tumor subtypes, achieving an accuracy was 90%. The average AUC of cross-classification between tumors reached 0.893.DiscussionTo overcome the limitations of visual inspection by pathologists for histopathology images, such as long time and low repeatability, we have developed a deep learning-based framework (Semi-His-Net) for automatic classification subdivision of the subtypes contained in the whole pathological images. This learning-based framework has great potential to improve the efficiency and repeatability of histopathological image diagnosis.

show abstract

Section: Experiments and Resultsmentioning

confidence: 54%

A semi-supervised learning approach with consistency regularization for tumor histopathological images analysis

Jiang

Sui

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…Most downstream applications still use ResNet and its variants as the backbone network. Cheng et al [ 30 ] proposed a modular group attention block that captures feature dependencies in medical images in both channel and spatial dimensions and stacked these group attention blocks in the ResNet style to improve model classification performance. Extensive experiments by Rathore et al [ 31 ] on ADNI [ 32 ] dataset showed that the DenseNet model improved classification accuracy by about 9% compared to traditional machine learning, which proved the usefulness of the DenseNet model.…”

Section: Related Workmentioning

confidence: 99%

NSCGCN: A novel deep GCN model to diagnosis COVID-19

Tang

Sun

et al. 2022

Computers in Biology and Medicine

View full text Add to dashboard Cite

“…We compare the proposed F2RNet with eight state-of-theart methods (U-Net [1], U-Net++ [3], ResUNet [5], R2UNet [16], BiONet [15], ResGANet [21], TransUNet [8] and Swi-nUNet [22]) on three datasets. We adopt the two most commonly used evaluation metrics in semantic segmentation (i.e., IoU and Dice) to evaluate above methods.…”

Section: Comparison With State-of-the-artsmentioning

confidence: 99%

F2RNET: A Full-Resolution Representation Network for Biomedical Image Segmentation

Cheng

Gao

et al. 2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

In this paper, we are interested in exploring the problem of full-resolution image segmentation, with the focus placed on learning full-resolution representations for biomedicine images. We divide the original resolution image into patches of different sizes in different stages and then extracte local features from large to small patches using efficient and flexible components in modern convolutional neural networks (CNN). Meanwhile, a multilayer perceptron (MLP) block intended for modeling long-range dependencies between patches is designed to compensate for the inherent inductive bias caused by convolution operations. In addition, we perform multiscale fusion and receive representation information from parallel paths at each stage, resulting in a rich full-resolution representation. We evaluate the proposed method on different biomedical image segmentation tasks and it achieves a competitive performance compared to the latest deep learning segmentation methods. It is hoped that this method will serve as a useful alternative to biomedical image segmentation and provide an improved idea for the research based on full-resolution representation.

show abstract

ResGANet: Residual group attention network for medical image classification and segmentation

Cited by 116 publications

References 17 publications

A semi-supervised learning approach with consistency regularization for tumor histopathological images analysis

A semi-supervised learning approach with consistency regularization for tumor histopathological images analysis

NSCGCN: A novel deep GCN model to diagnosis COVID-19

F2RNET: A Full-Resolution Representation Network for Biomedical Image Segmentation

Contact Info

Product

Resources

About