Melanoma Detection based on Swin Transformer and SimAM

Xie, Junsong; Wu, Zezhi; Zhu, Renju; Zhu, Hong

doi:10.1109/itnec52019.2021.9587071

Cited by 14 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The demographic detail of the finalized relevant articles is shown in Table 2 . Approximately two-thirds of the studies are journal articles ( n = 19, ≈ 68%) (Wu et al, 2021 ; Aladhadh et al, 2022 ; Alahmadi and Alghamdi, 2022 ; Ayas, 2022 ; Cao et al, 2022 ; Dong and Wang, 2022 ; Du et al, 2022 ; Feng et al, 2022 ; He et al, 2022 ; Malik et al, 2022 ; Nakai et al, 2022 ; Nofallah, 2022 ; Wu H. et al, 2022 ; Wu Y. et al, 2022 ; Xin et al, 2022 ; Zhang N. et al, 2022 ), whereas 09 studies were conference proceedings (~ 32%) (Wang et al, 2021 , 2022 ; Xie et al, 2021 ; Zhou and Luo, 2021 ; de Lima and Krohling, 2022 ; Liu et al, 2022 ; Nakai and Han, 2022 ; Sarker et al, 2022 ; Zhang N. et al, 2022 ; Zhao, 2022 ). Most studies were published in 2022 ( n = 24, ≈ 86%).…”

Section: Resultsmentioning

confidence: 99%

“…The research article (Wang et al, 2021 ) reported a boundary aware transformer for lesion visualization, while several studies (Xie et al, 2021 ; Zhou and Luo, 2021 ; Ayas, 2022 ; Du et al, 2022 ) reported vision transformer-based models for skin lesion visualization. The articles (Alahmadi and Alghamdi, 2022 ; Ayas, 2022 ; de Lima and Krohling, 2022 ; Wang et al, 2022 ) reported a semi-supervised deep learning model and CNN architecture for retrieving semantic-based information from skin dermoscopy images.…”

Section: Resultsmentioning

confidence: 99%

“…Twelve studies (Xie et al, 2021 ; Zhou and Luo, 2021 ; Aladhadh et al, 2022 ; Ayas, 2022 ; de Lima and Krohling, 2022 ; Dong and Wang, 2022 ; Du et al, 2022 ; Feng et al, 2022 ; Wu H. et al, 2022 ; Xin et al, 2022 ; Zhao, 2022 ) reported Swin transformer. Three studies (Cao et al, 2022 ; He et al, 2022 ; Liu et al, 2022 ) reported fully transformer network (FTN) in association with SPT for feature extraction using dermoscopy images.…”

Section: Resultsmentioning

confidence: 99%

“…In an additional 22 countries, it ranks as the third or fourth leading cause of death. The American Cancer Society reported that skin cancer is the most common type of cancer, with high mortalities and growth rates in the US and many other countries (Xie et al, 2021 ). Skin cancer is the second leading cause of mortalities in the United States (Siegel et al, 2019 ) and a major health problem in the world.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Identifying the role of vision transformer for skin cancer—A scoping review

Khan

Ali

Shah

2023

Front. Artif. Intell.

View full text Add to dashboard Cite

IntroductionDetecting and accurately diagnosing early melanocytic lesions is challenging due to extensive intra- and inter-observer variabilities. Dermoscopy images are widely used to identify and study skin cancer, but the blurred boundaries between lesions and besieging tissues can lead to incorrect identification. Artificial Intelligence (AI) models, including vision transformers, have been proposed as a solution, but variations in symptoms and underlying effects hinder their performance.ObjectiveThis scoping review synthesizes and analyzes the literature that uses vision transformers for skin lesion detection.MethodsThe review follows the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Revise) guidelines. The review searched online repositories such as IEEE Xplore, Scopus, Google Scholar, and PubMed to retrieve relevant articles. After screening and pre-processing, 28 studies that fulfilled the inclusion criteria were included.Results and discussionsThe review found that the use of vision transformers for skin cancer detection has rapidly increased from 2020 to 2022 and has shown outstanding performance for skin cancer detection using dermoscopy images. Along with highlighting intrinsic visual ambiguities, irregular skin lesion shapes, and many other unwanted challenges, the review also discusses the key problems that obfuscate the trustworthiness of vision transformers in skin cancer diagnosis. This review provides new insights for practitioners and researchers to understand the current state of knowledge in this specialized research domain and outlines the best segmentation techniques to identify accurate lesion boundaries and perform melanoma diagnosis. These findings will ultimately assist practitioners and researchers in making more authentic decisions promptly.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Identifying the role of vision transformer for skin cancer—A scoping review

Khan

Ali

Shah

2023

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Zhang et al [ 29 ] present a deep learning-based framework for the diagnosis of COVID-19 using chest CTs with a Unet and Swin Transformer backbone and achieved good results. Xie et al [ 30 ] proposed the Swin-SimAM network. They incorporated the SimAM attention module, which is parameter free, to emphasize crucial parts of skin lesions for improved melanoma detection.…”

Section: Introductionmentioning

confidence: 99%

Classification of Mobile-Based Oral Cancer Images Using the Vision Transformer and the Swin Transformer

Song,

KC,

Yang

et al. 2024

Cancers

View full text Add to dashboard Cite

Oral cancer, a pervasive and rapidly growing malignant disease, poses a significant global health concern. Early and accurate diagnosis is pivotal for improving patient outcomes. Automatic diagnosis methods based on artificial intelligence have shown promising results in the oral cancer field, but the accuracy still needs to be improved for realistic diagnostic scenarios. Vision Transformers (ViT) have outperformed learning CNN models recently in many computer vision benchmark tasks. This study explores the effectiveness of the Vision Transformer and the Swin Transformer, two cutting-edge variants of the transformer architecture, for the mobile-based oral cancer image classification application. The pre-trained Swin transformer model achieved 88.7% accuracy in the binary classification task, outperforming the ViT model by 2.3%, while the conventional convolutional network model VGG19 and ResNet50 achieved 85.2% and 84.5% accuracy. Our experiments demonstrate that these transformer-based architectures outperform traditional convolutional neural networks in terms of oral cancer image classification, and underscore the potential of the ViT and the Swin Transformer in advancing the state of the art in oral cancer image analysis.

show abstract

A medical image classification method based on self‐regularized adversarial learning

Fan,

Zhang,

Ruan

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundDeep learning (DL) techniques have been extensively applied in medical image classification. The unique characteristics of medical imaging data present challenges, including small labeled datasets, severely imbalanced class distribution, and significant variations in imaging quality. Recently, generative adversarial network (GAN)‐based classification methods have gained attention for their ability to enhance classification accuracy by incorporating realistic GAN‐generated images as data augmentation. However, the performance of these GAN‐based methods often relies on high‐quality generated images, while large amounts of training data are required to train GAN models to achieve optimal performance.PurposeIn this study, we propose an adversarial learning‐based classification framework to achieve better classification performance. Innovatively, GAN models are employed as supplementary regularization terms to support classification, aiming to address the challenges described above.MethodsThe proposed classification framework, GAN‐DL, consists of a feature extraction network (F‐Net), a classifier, and two adversarial networks, specifically a reconstruction network (R‐Net) and a discriminator network (D‐Net). The F‐Net extracts features from input images, and the classifier uses these features for classification tasks. R‐Net and D‐Net have been designed following the GAN architecture. R‐Net employs the extracted feature to reconstruct the original images, while D‐Net is tasked with the discrimination between the reconstructed image and the original images. An iterative adversarial learning strategy is designed to guide model training by incorporating multiple network‐specific loss functions. These loss functions, serving as supplementary regularization, are automatically derived during the reconstruction process and require no additional data annotation.ResultsTo verify the model's effectiveness, we performed experiments on two datasets, including a COVID‐19 dataset with 13 958 chest x‐ray images and an oropharyngeal squamous cell carcinoma (OPSCC) dataset with 3255 positron emission tomography images. Thirteen classic DL‐based classification methods were implemented on the same datasets for comparison. Performance metrics included precision, sensitivity, specificity, and ‐score. In addition, we conducted ablation studies to assess the effects of various factors on model performance, including the network depth of F‐Net, training image size, training dataset size, and loss function design. Our method achieved superior performance than all comparative methods. On the COVID‐19 dataset, our method achieved , , , and in terms of precision, sensitivity, specificity, and ‐score, respectively. It achieved across all these metrics on the OPSCC dataset. The study to investigate the effects of two adversarial networks highlights the crucial role of D‐Net in improving model performance. Ablation studies further provide an in‐depth understanding of our methodology.ConclusionOur adversarial‐based classification framework leverages GAN‐based adversarial networks and an iterative adversarial learning strategy to harness supplementary regularization during training. This design significantly enhances classification accuracy and mitigates overfitting issues in medical image datasets. Moreover, its modular design not only demonstrates flexibility but also indicates its potential applicability to various clinical contexts and medical imaging applications.

show abstract

Melanoma Detection based on Swin Transformer and SimAM

Cited by 14 publications

References 16 publications

Identifying the role of vision transformer for skin cancer—A scoping review

Identifying the role of vision transformer for skin cancer—A scoping review

Classification of Mobile-Based Oral Cancer Images Using the Vision Transformer and the Swin Transformer

A medical image classification method based on self‐regularized adversarial learning

Contact Info

Product

Resources

About