MLP-based classification of COVID-19 and skin diseases

Zhang, R; Wang, Liejun; Cheng, Shuli; Song, Sejun

doi:10.1016/j.eswa.2023.120389

Cited by 7 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of deep learning methods has become widespread in cancer detection systems, especially for large datasets. This area of research has been studied intensively in recent years [57][58][59]. Some of the leading methods are the MLP-Mixer method or the vision transformer model.…”

Section: Comparative Resultsmentioning

confidence: 99%

A Comparative Analysis of Skin Cancer Detection Applications Using Histogram-Based Local Descriptors

Aydin

2023

Diagnostics

View full text Add to dashboard Cite

Among the most serious types of cancer is skin cancer. Despite the risk of death, when caught early, the rate of survival is greater than 95%. This inspires researchers to explore methods that allow for the early detection of skin cancer that could save millions of lives. The ability to detect the early signs of skin cancer has become more urgent in light of the rising number of illnesses, the high death rate, and costly healthcare treatments. Given the gravity of these issues, experts have created a number of existing approaches for detecting skin cancer. Identifying skin cancer and whether it is benign or malignant involves detecting features of the lesions such as size, form, symmetry, color, etc. The aim of this study is to determine the most successful skin cancer detection methods by comparing the outcomes and effectiveness of the various applications that categorize benign and malignant forms of skin cancer. Descriptors such as the Local Binary Pattern (LBP), the Local Directional Number Pattern (LDN), the Pyramid of Histogram of Oriented Gradients (PHOG), the Local Directional Pattern (LDiP), and Monogenic Binary Coding (MBC) are used to extract the necessary features. Support vector machines (SVM) and XGBoost are used in the classification process. In addition, this study uses colored histogram-based features to classify the various characteristics obtained from the color images. In the experimental results, the applications implemented with the proposed color histogram-based features were observed to be more successful. Under the proposed method (the colored LDN feature obtained using the YCbCr color space with the XGBoost classifier), a 90% accuracy rate was achieved on Dataset 1, which was obtained from the Kaggle website. For the HAM10000 data set, an accuracy rate of 96.50% was achieved under a similar proposed method (the colored MBC feature obtained using the HSV color space with the XGBoost classifier).

show abstract

Section: Comparative Resultsmentioning

confidence: 99%

A Comparative Analysis of Skin Cancer Detection Applications Using Histogram-Based Local Descriptors

Aydin

2023

Diagnostics

View full text Add to dashboard Cite

show abstract

“…In recent years, artificial intelligence (AI) has been referenced in various aspects of the medical field. For example, Zhang et al 6 proposed an MLP-based model for the classification of COVID-19 and skin diseases. Wang et al 7 proposed an arterial and venous de-entanglement network (AVDNet), which is the first work to segment coronary arteries and veins at the same time.…”

Section: Related Workmentioning

confidence: 99%

A graph convolutional network with dynamic weight fusion of multi-scale local features for diabetic retinopathy grading

Wang,

Guo

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is a serious ocular complication that can pose a serious risk to a patient’s vision and overall health. Currently, the automatic grading of DR is mainly using deep learning techniques. However, the lesion information in DR images is complex, variable in shape and size, and randomly distributed in the images, which leads to some shortcomings of the current research methods, i.e., it is difficult to effectively extract the information of these various features, and it is difficult to establish the connection between the lesion information in different regions. To address these shortcomings, we design a multi-scale dynamic fusion (MSDF) module and combine it with graph convolution operations to propose a multi-scale dynamic graph convolutional network (MDGNet) in this paper. MDGNet firstly uses convolution kernels with different sizes to extract features with different shapes and sizes in the lesion regions, and then automatically learns the corresponding weights for feature fusion according to the contribution of different features to model grading. Finally, the graph convolution operation is used to link the lesion features in different regions. As a result, our proposed method can effectively combine local and global features, which is beneficial for the correct DR grading. We evaluate the effectiveness of method on two publicly available datasets, namely APTOS and DDR. Extensive experiments demonstrate that our proposed MDGNet achieves the best grading results on APTOS and DDR, and is more accurate and diverse for the extraction of lesion information.

show abstract

“…Numerous studies have utilized attention mechanisms in their deep learning models for skin cancer classification, although their approaches and implementations varied [105][106][107][108]. Omeroglu, Mohammed, Oral and Aydin [105] and Bao, Han, Huang and Muzahid [108] explicitly used soft attention mechanisms to enhance feature detection in skin lesions, Desale and Patil [107]'employed an attention mechanism in a convolutional capsule network, and Zhang, Wang, Cheng and Song [106]'s approach, while not explicitly stated as an attention mechanism, focused on capturing comprehensive image features, which can be seen as a form of attention to image details. Moreover, To, et al [109] introduced the MetaAttention model for skin lesion diagnosis.…”

Section: Attention To Skin Lesionsmentioning

confidence: 99%

SkinLiTE: Lightweight Supervised Contrastive Learning Model for Enhanced Skin Lesion Detection and Disease Typification in Dermoscopic Images

Alzahrani

2024

Preprint

View full text Add to dashboard Cite

This study introduces SkinLiTE, a lightweight supervised contrastive learning model, tailored to enhance the detection and typification of skin lesions in dermoscopic images. The core of SkinLiTE lies in its unique integration of supervised and contrastive learning approaches, which leverages labeled data to learn generalizable representations. This approach is particularly adept at handling the complexities and imbalances inherent in skin lesions datasets. The methodology encompasses a two-phase learning process. In the first phase, SkinLiTE utilizes an encoder network and a projection head to transform and project dermoscopic images into a feature space where contrastive loss is applied, focusing on minimizing intra-class variations while maximizing inter-class differences. The second phase freezes the encoder's weights, leveraging the learned representations for classification through a series of dense and dropout layers. The model was evaluated using three datasets from Skin Cancer ISIC 2019-2020, covering a wide range of skin conditions. SkinLiTE demonstrated superior performance across various metrics—accuracy, AUC , and F1 score—particularly when compared with traditional supervised learning models. Notably, SkinLiTE achieved an accuracy of 0.9087 using AugMix augmentation for binary classification of skin lesions. It also showed comparable results with the state-of-the-art approaches of ISIC challenge without relying on external data, underscoring its efficacy and efficiency. The results highlight the potential of SkinLiTE as a significant step forward in the field of dermatological AI, offering a robust, efficient, and accurate tool for skin lesion detection and classification. Its lightweight architecture and ability to handle imbalanced datasets make it particularly suited for integration into Internet of Medical Things environments, paving the way for enhanced remote patient monitoring and diagnostic capabilities. This research contributes to the evolving landscape of AI in healthcare, demonstrating the impact of innovative learning methodologies in medical image analysis.

show abstract

MLP-based classification of COVID-19 and skin diseases

Cited by 7 publications

References 32 publications

A Comparative Analysis of Skin Cancer Detection Applications Using Histogram-Based Local Descriptors

A Comparative Analysis of Skin Cancer Detection Applications Using Histogram-Based Local Descriptors

A graph convolutional network with dynamic weight fusion of multi-scale local features for diabetic retinopathy grading

SkinLiTE: Lightweight Supervised Contrastive Learning Model for Enhanced Skin Lesion Detection and Disease Typification in Dermoscopic Images

Contact Info

Product

Resources

About