AI Recognition in Skin Pathologies Detection

Gavrilov, Daniil; Lazarenko, Lyubov; Закиров, Э. И.

doi:10.1109/ic-aiai48757.2019.00017

Cited by 15 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the architecture of CNN for the activation function is essential, wherein Swish as a new activation function has been used for developing the traditional activation function [ 26 ]. In this study, a Swish activation function has been proposed for improving the Xception based on Swish image classification model for initial melanoma diagnosis [ 25 ].…”

Section: The Modified Xception Network Architecturementioning

confidence: 99%

“…For generating feature maps, the convolution kernels have been separated into input data areas [ 25 ]. The different convolution kernels generate the absolute results of the feature maps, such that the position ( i , j ) upon feature value in the feature map as the k th layer indicates the l th , i.e.,

where Wv k l describes the weight vector, Bv k l describes for the bias value of the k th filter of the l th layer, and C i , j l describes the input patch center on position ( i , j ) of the l th layer.…”

Section: The Modified Xception Network Architecturementioning

confidence: 99%

“…The presented system classifies the input images into three classes: normal, carcinoma, and melanoma. Furthermore, the results of the proposed Xception architecture are compared with some renowned methods, including VGG16 [ 22 ], InceptionV3 [ 23 ], AlexNet [ 24 ], and the original Xception [ 25 ] to show the superiority of the proposed methodology. The configuration of all methods can be achieved by their papers for reproduction.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning-Based Classification for Melanoma Detection Using XceptionNet

Zadeh

2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Skin cancer is one of the most common types of cancer in the world, accounting for at least 40% of all cancers. Melanoma is considered as the 19th most commonly occurring cancer among the other cancers in the human society, such that about 300,000 new cases were found in 2018. While cancer diagnosis is based on interventional methods such as surgery, radiotherapy, and chemotherapy, studies show that the use of new computer technologies such as image processing mechanisms in processes related to early diagnosis of this cancer can help the physicians heal this cancer. This paper proposes an automatic method for diagnosis of skin cancer from dermoscopy images. The proposed model is based on an improved XceptionNet, which utilized swish activation function and depthwise separable convolutions. This system shows an improvement in the classification accuracy of the network compared to the original Xception and other dome architectures. Simulations of the proposed method are compared with some other related skin cancer diagnosis state-of-the-art solutions, and the results show that the suggested method achieves higher accuracy compared to the other comparative methods.

show abstract

Section: The Modified Xception Network Architecturementioning

confidence: 99%

Section: The Modified Xception Network Architecturementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning-Based Classification for Melanoma Detection Using XceptionNet

Zadeh

2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…PH2 dataset was utilized for training and testing with an accuracy rate achieved of 98.61%. Researchers tested CNN variants in [69], including DenseNet, EfficientNet, MobileNet, and Inception V3. The findings indicated that CNN Xception obtained a superior accuracy rate at 89%.…”

Section: Deep Learning With Transfer Learning and Image Augmentationmentioning

confidence: 99%

“…The generated images are subsequently included in augmented trained data towards enhancing deep CNN's performance in classifying skin lesions. Discriminator and generator as outlined in algorithm one may be attained by using formal expressions [69], expressed in Equation ( 1) and (2), respectively, as follows:…”

Section: Deep Learning and Generative Adversarial Network (Gan)mentioning

confidence: 99%

Skin Lesion Classification Based on Deep Convolutional Neural Networks Architectures

Saeed

Zeebaree

2021

JASTT

View full text Add to dashboard Cite

Skin cancer is among the primary cancer types that manifest due to various dermatological disorders, which may be further classified into several types based on morphological features, color, structure, and texture. The mortality rate of patients who have skin cancer is contingent on preliminary and rapid detection and diagnosis of malignant skin cancer cells. Limitations in current dermoscopic images, including shadow, artifact, and noise, affect image quality, which may hamper detection effort. Attempts to overcome these challenges have been made by analyzing the images using deep learning neural networks to perform skin cancer detection. In this paper, the authors review the state-of-the-art in authoritative deep learning concepts pertinent to skin cancer detection and classification.

show abstract

Optimum parameters extraction of proton exchange membrane fuel cells using Fractional‐Order Whale Optimization Algorithm

Ren

Eslami

2022

Energy Science & Engineering

View full text Add to dashboard Cite

This study proposes a novel metaheuristic-based technique for optimum parameters' estimation of the proton exchange membrane fuel cells (PEMFCs).To provide better results with more reliability and accuracy, a Fractional Order-based design of the Whale Optimizer Algorithm (FO-WOA) is designed.A validation test showed that the proposed method provides a good trade-off between accuracy and convergence speed. Performing the algorithm for multiple independent runs also shows that the proposed method delivers reliable results toward some other comparative metaheuristic algorithms. This algorithm is then used for the minimization of the sum of square deviation between the experimental voltage-current polarization and the optimal achieved results by the model based on FO-WOA. The method is validated by considering two practical case studies, which are the Nexa PEMFC and 250 W PEM system, and its achievements are put in comparison with some approaches to indicate the higher effectiveness of the proposed method toward the others. The experimental results on the Nexa PEMFC indicate that the proposed FO-WOA-based method with 12 sum square errors (SSE) provided the minimum error toward the other. Also, the experiments on the 250 W PEM Stack indicated that for 250 W PEM Stack with 3/5 bar and 80°C, the proposed method with 0.01 SSE provides the fittest profile with the experimental data, and finally, the experiments on the same stack with 3/5 bar and 80°C showed the higher accuracy of the proposed method with the least SSE value (0.16) toward the others.

show abstract

AI Recognition in Skin Pathologies Detection

Cited by 15 publications

References 10 publications

Deep Learning-Based Classification for Melanoma Detection Using XceptionNet

Deep Learning-Based Classification for Melanoma Detection Using XceptionNet

Skin Lesion Classification Based on Deep Convolutional Neural Networks Architectures

Optimum parameters extraction of proton exchange membrane fuel cells using Fractional‐Order Whale Optimization Algorithm

Contact Info

Product

Resources

About