Beyond binary: multi-class skin lesion classification with AlexNet transfer learning-towards enhanced dermatological diagnosis

Abstract Problem Skin lesions are the major indicator for diagnosing different skin diseases, which are caused by the abnormal growth of skin cells. Skin cancer, one of the most fatal types of cancer in the world, relies on the proper diagnosis of skin lesions and other relevant disease indicators f...

Full description

Saved in:
Bibliographic Details
Main Authors: Abida Noaman, Reyaz Ahmad, Muhammad Farhan Khan, Abdul Salam Mohammed, Muhammad Farooq, Khan Muhammad Adnan
Format: Article
Language:English
Published: Springer 2024-12-01
Series:Discover Applied Sciences
Subjects:
Online Access:https://doi.org/10.1007/s42452-024-06448-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850134786224422912
author Abida Noaman
Reyaz Ahmad
Muhammad Farhan Khan
Abdul Salam Mohammed
Muhammad Farooq
Khan Muhammad Adnan
author_facet Abida Noaman
Reyaz Ahmad
Muhammad Farhan Khan
Abdul Salam Mohammed
Muhammad Farooq
Khan Muhammad Adnan
author_sort Abida Noaman
collection DOAJ
description Abstract Problem Skin lesions are the major indicator for diagnosing different skin diseases, which are caused by the abnormal growth of skin cells. Skin cancer, one of the most fatal types of cancer in the world, relies on the proper diagnosis of skin lesions and other relevant disease indicators for early detection, which can enhance treatment and increase life expectancy by up to 92%. Diagnosing skin lesions accurately is challenging, even for experienced practitioners. Challenge Artificial Intelligence (AI) techniques based on deep learning have proved promising in the field of medical image processing and diagnosis. However, there is a lack of comprehensive medical image datasets. This paper will present a skin lesion classification model that employs a transfer learning approach based on Alex Net and classifies eight different skin diseases. This proposed model was trained, validated, and tested using ISIC 2019 challenge data with a very abnormal class distribution. This variation in class size has been overcome using data augmentation and resizing in the preprocessing phase. Preprocessing is performed in such a way that no colour detail or rich identification features will be lost from the images. Results The proposed model achieved a testing accuracy of 90.9%, with a precision of 90.8%, a sensitivity of 90.9%, and an F1-Score of 90.8%. The values for precision and sensitivity are among the highest reported, specifically for models using the ISIC 2019 dataset.
format Article
id doaj-art-c30d8d9c9882431fb628b9bb3b396079
institution OA Journals
issn 3004-9261
language English
publishDate 2024-12-01
publisher Springer
record_format Article
series Discover Applied Sciences
spelling doaj-art-c30d8d9c9882431fb628b9bb3b3960792025-08-20T02:31:38ZengSpringerDiscover Applied Sciences3004-92612024-12-017111810.1007/s42452-024-06448-2Beyond binary: multi-class skin lesion classification with AlexNet transfer learning-towards enhanced dermatological diagnosisAbida Noaman0Reyaz Ahmad1Muhammad Farhan Khan2Abdul Salam Mohammed3Muhammad Farooq4Khan Muhammad Adnan5Riphah School of Computing and Innovation, Riphah International University, Lahore CampusDepartment of General Education, Skyline University College, University City SharjahDepartment of Forensic Sciences, University of Health SciencesDepartment of General Education, Skyline University College, University City SharjahDepartment of Mathematics and Statistics, College of Arts and Sciences, Abu Dhabi UniversityDepartment of Software, Faculty of Artificial Intelligence and Software, Gachon UniversityAbstract Problem Skin lesions are the major indicator for diagnosing different skin diseases, which are caused by the abnormal growth of skin cells. Skin cancer, one of the most fatal types of cancer in the world, relies on the proper diagnosis of skin lesions and other relevant disease indicators for early detection, which can enhance treatment and increase life expectancy by up to 92%. Diagnosing skin lesions accurately is challenging, even for experienced practitioners. Challenge Artificial Intelligence (AI) techniques based on deep learning have proved promising in the field of medical image processing and diagnosis. However, there is a lack of comprehensive medical image datasets. This paper will present a skin lesion classification model that employs a transfer learning approach based on Alex Net and classifies eight different skin diseases. This proposed model was trained, validated, and tested using ISIC 2019 challenge data with a very abnormal class distribution. This variation in class size has been overcome using data augmentation and resizing in the preprocessing phase. Preprocessing is performed in such a way that no colour detail or rich identification features will be lost from the images. Results The proposed model achieved a testing accuracy of 90.9%, with a precision of 90.8%, a sensitivity of 90.9%, and an F1-Score of 90.8%. The values for precision and sensitivity are among the highest reported, specifically for models using the ISIC 2019 dataset.https://doi.org/10.1007/s42452-024-06448-2Artificial intelligenceMachine learningTransfer learningSkin disease classification
spellingShingle Abida Noaman
Reyaz Ahmad
Muhammad Farhan Khan
Abdul Salam Mohammed
Muhammad Farooq
Khan Muhammad Adnan
Beyond binary: multi-class skin lesion classification with AlexNet transfer learning-towards enhanced dermatological diagnosis
Discover Applied Sciences
Artificial intelligence
Machine learning
Transfer learning
Skin disease classification
title Beyond binary: multi-class skin lesion classification with AlexNet transfer learning-towards enhanced dermatological diagnosis
title_full Beyond binary: multi-class skin lesion classification with AlexNet transfer learning-towards enhanced dermatological diagnosis
title_fullStr Beyond binary: multi-class skin lesion classification with AlexNet transfer learning-towards enhanced dermatological diagnosis
title_full_unstemmed Beyond binary: multi-class skin lesion classification with AlexNet transfer learning-towards enhanced dermatological diagnosis
title_short Beyond binary: multi-class skin lesion classification with AlexNet transfer learning-towards enhanced dermatological diagnosis
title_sort beyond binary multi class skin lesion classification with alexnet transfer learning towards enhanced dermatological diagnosis
topic Artificial intelligence
Machine learning
Transfer learning
Skin disease classification
url https://doi.org/10.1007/s42452-024-06448-2
work_keys_str_mv AT abidanoaman beyondbinarymulticlassskinlesionclassificationwithalexnettransferlearningtowardsenhanceddermatologicaldiagnosis
AT reyazahmad beyondbinarymulticlassskinlesionclassificationwithalexnettransferlearningtowardsenhanceddermatologicaldiagnosis
AT muhammadfarhankhan beyondbinarymulticlassskinlesionclassificationwithalexnettransferlearningtowardsenhanceddermatologicaldiagnosis
AT abdulsalammohammed beyondbinarymulticlassskinlesionclassificationwithalexnettransferlearningtowardsenhanceddermatologicaldiagnosis
AT muhammadfarooq beyondbinarymulticlassskinlesionclassificationwithalexnettransferlearningtowardsenhanceddermatologicaldiagnosis
AT khanmuhammadadnan beyondbinarymulticlassskinlesionclassificationwithalexnettransferlearningtowardsenhanceddermatologicaldiagnosis