An effective approach for the diagnosis of melanoma using the sparse auto-encoder for features detection and the SVM for classification

Zghal, Nadia Smaoui; Kallel, Imène Khanfir

doi:10.1109/atsip49331.2020.9231611

Cited by 8 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is utilized within the window filter hence these are closely related to order statistical filters. In the skin cancer recognition process, various morphological operations are performed to remove the artifacts such as morphology and threshold [ 20 ], top-hat approach [ 21 ], morphological closing [ 22 , 23 , 24 ], and morphological operator bottom hat transforms [ 25 ], etc.…”

Section: Skin Cancer Recognition and Classification Systemmentioning

confidence: 99%

Skin Lesion Analysis and Cancer Detection Based on Machine/Deep Learning Techniques: A Comprehensive Survey

Zafar

Sharif

et al. 2023

Life

View full text Add to dashboard Cite

The skin is the human body’s largest organ and its cancer is considered among the most dangerous kinds of cancer. Various pathological variations in the human body can cause abnormal cell growth due to genetic disorders. These changes in human skin cells are very dangerous. Skin cancer slowly develops over further parts of the body and because of the high mortality rate of skin cancer, early diagnosis is essential. The visual checkup and the manual examination of the skin lesions are very tricky for the determination of skin cancer. Considering these concerns, numerous early recognition approaches have been proposed for skin cancer. With the fast progression in computer-aided diagnosis systems, a variety of deep learning, machine learning, and computer vision approaches were merged for the determination of medical samples and uncommon skin lesion samples. This research provides an extensive literature review of the methodologies, techniques, and approaches applied for the examination of skin lesions to date. This survey includes preprocessing, segmentation, feature extraction, selection, and classification approaches for skin cancer recognition. The results of these approaches are very impressive but still, some challenges occur in the analysis of skin lesions because of complex and rare features. Hence, the main objective is to examine the existing techniques utilized in the discovery of skin cancer by finding the obstacle that helps researchers contribute to future research.

show abstract

Section: Skin Cancer Recognition and Classification Systemmentioning

confidence: 99%

Skin Lesion Analysis and Cancer Detection Based on Machine/Deep Learning Techniques: A Comprehensive Survey

Zafar

Sharif

et al. 2023

Life

View full text Add to dashboard Cite

show abstract

“…A melanoma classification method using sparse auto-encoder and SVM was presented in Zghal and Kallel. 25 Few recent studies 26,27 developed end-to-end deep CNN models for skin cancer diagnosis and achieved significant results. Chaturvedi et al 28 designed a CNN-based ensemble approach for multi-class skin cancer classification.…”

Section: Deep Features-based Approachesmentioning

confidence: 99%

“…Wu et al 24 deigned a densely connected CNN with attention residual learning for skin lesion classification. A melanoma classification method using sparse auto‐encoder and SVM was presented in Zghal and Kallel 25 . Few recent studies 26,27 developed end‐to‐end deep CNN models for skin cancer diagnosis and achieved significant results.…”

Section: Related Workmentioning

confidence: 99%

Patch‐based local deep feature extraction for automated skin cancer classification

Gajera

Zaveri

Nayak

2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Skin cancer detection through dermoscopy images has remained challenging due to higher inter‐class uniformity and intra‐class diversity. Deep convolutional neural networks (CNNs) have recently obtained remarkable attention for automated skin cancer classification; however, most of these methods extract features from the global image of high resolution. One of the major drawbacks of these methods is the downscaling of input images to a low resolution, which leads to information loss. Moreover, the lack of a vast number of dermoscopy images is a concern. To overcome these issues and improve the classification accuracy, we propose a novel method using patch‐based local deep feature extraction. In the proposed method, the features are extracted from different patches of a dermoscopy image using a pre‐trained CNN model and are fused to preserve fine details. The kernel principal component analysis is then employed to select the prominent features, and a feed‐forward neural network is finally used to detect skin cancer. The approach is validated using two benchmark datasets: ISIC 2016 and ISIC 2017. The experimental results show that the suggested method achieves promising results in comparison with state‐of‐the‐art approaches. Moreover, a comparative analysis is made among contemporary pre‐trained CNN models.

show abstract

“…In the latest study, researchers have proposed several techniques for extracting the features that aid in isolating the affected part of the skin from the unaffected part. Some of these techniques are ABCDE, pattern analysis, texture analysis, etc [3]. In all these methods, many characteristics are identified according to some criterion and a numerical score is allotted to these characteristics.…”

Section: Introductionmentioning

confidence: 99%

A Feature Selection Framework for Granular Parakeratosis Lesion Detection

Sheetal¹

2021

IJRASET

View full text Add to dashboard Cite

The dermatoscopy images play an essential role in the identification of skin diseases such as granular parakeratosis. This disease appears as an intertrigo or as a non intertriginous rash (intertrigo is nothing but rash in the body folds) and sometimes causes itchy. Extracting the features from skin lesion image is very important for the classification of skin disease. Some features such as shape, size, and color can be extracted from the image depending upon the ABCD (asymmetry, border, color and diameter) rule of dermoscopy. These extracted features are mainly used to determine asymmetry and border irregularity. Asymmetry is one of the main attributes in the early detection of skin disease. The dermatologists inspect shape and irregular color distribution to identify the lesion asymmetry. This paper provides a large set of skin lesion feature extraction approaches for the lesion analysis. Several techniques exist for extracting the features from lesion images and the computational methods have been developed for enhancing the features and allow dermatologists in the earlier diagnosis of the disease. The methods or the procedures adopted by several researchers for extraction of features are explained and the effect of these methods on the skin lesion is evaluated using suitable metrics. Though extraction of the features from the skin lesion has been successfully addressed in several articles, still there is a requirement for the modification or development of new techniques for improving the efficiency of the diagnosis system.

show abstract

An effective approach for the diagnosis of melanoma using the sparse auto-encoder for features detection and the SVM for classification

Cited by 8 publications

References 18 publications

Skin Lesion Analysis and Cancer Detection Based on Machine/Deep Learning Techniques: A Comprehensive Survey

Skin Lesion Analysis and Cancer Detection Based on Machine/Deep Learning Techniques: A Comprehensive Survey

Patch‐based local deep feature extraction for automated skin cancer classification

A Feature Selection Framework for Granular Parakeratosis Lesion Detection

Contact Info

Product

Resources

About