Advanced Deep Learning Models for Melanoma Diagnosis in Computer-Aided Skin Cancer Detection

The most deadly type of skin cancer is melanoma. A visual examination does not provide an accurate diagnosis of melanoma during its early to middle stages. Therefore, an automated model could be developed that assists with early skin cancer detection. It is possible to limit the severity of melanoma...

Full description

Saved in:
Bibliographic Details
Main Authors: Ranpreet Kaur, Hamid GholamHosseini, Maria Lindén
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/3/594
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199781768429568
author Ranpreet Kaur
Hamid GholamHosseini
Maria Lindén
author_facet Ranpreet Kaur
Hamid GholamHosseini
Maria Lindén
author_sort Ranpreet Kaur
collection DOAJ
description The most deadly type of skin cancer is melanoma. A visual examination does not provide an accurate diagnosis of melanoma during its early to middle stages. Therefore, an automated model could be developed that assists with early skin cancer detection. It is possible to limit the severity of melanoma by detecting it early and treating it promptly. This study aims to develop efficient approaches for various phases of melanoma computer-aided diagnosis (CAD), such as preprocessing, segmentation, and classification. The first step of the CAD pipeline includes the proposed hybrid method, which uses morphological operations and context aggregation-based deep neural networks to remove hairlines and improve poor contrast in dermoscopic skin cancer images. An image segmentation network based on deep learning is then used to extract lesion regions for detailed analysis and calculate the optimized classification features. Lastly, a deep neural network is used to distinguish melanoma from benign lesions. The proposed approaches use a benchmark dataset named International Skin Imaging Collaboration (ISIC) 2020. In this work, two forms of evaluations are performed with the classification model. The first experiment involves the incorporation of the results from the preprocessing and segmentation stages into the classification model. The second experiment involves the evaluation of the classifier without employing these stages i.e., using raw images. From the study results, it can be concluded that a classification model using segmented and cleaned images contributes more to achieving an accurate classification rate of 93.40% with a 1.3 s test time on a single image.
format Article
id doaj-art-c71f6e66475f480eba78506811f0b958
institution OA Journals
issn 1424-8220
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c71f6e66475f480eba78506811f0b9582025-08-20T02:12:33ZengMDPI AGSensors1424-82202025-01-0125359410.3390/s25030594Advanced Deep Learning Models for Melanoma Diagnosis in Computer-Aided Skin Cancer DetectionRanpreet Kaur0Hamid GholamHosseini1Maria Lindén2Department of Software Engineering & AI, Media Design School, Auckland 1010, New ZealandSchool of Engineering, Computer, and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New ZealandDivision of Intelligent Future Technologies, Mälardalen University, 721 23 Västerås, SwedenThe most deadly type of skin cancer is melanoma. A visual examination does not provide an accurate diagnosis of melanoma during its early to middle stages. Therefore, an automated model could be developed that assists with early skin cancer detection. It is possible to limit the severity of melanoma by detecting it early and treating it promptly. This study aims to develop efficient approaches for various phases of melanoma computer-aided diagnosis (CAD), such as preprocessing, segmentation, and classification. The first step of the CAD pipeline includes the proposed hybrid method, which uses morphological operations and context aggregation-based deep neural networks to remove hairlines and improve poor contrast in dermoscopic skin cancer images. An image segmentation network based on deep learning is then used to extract lesion regions for detailed analysis and calculate the optimized classification features. Lastly, a deep neural network is used to distinguish melanoma from benign lesions. The proposed approaches use a benchmark dataset named International Skin Imaging Collaboration (ISIC) 2020. In this work, two forms of evaluations are performed with the classification model. The first experiment involves the incorporation of the results from the preprocessing and segmentation stages into the classification model. The second experiment involves the evaluation of the classifier without employing these stages i.e., using raw images. From the study results, it can be concluded that a classification model using segmented and cleaned images contributes more to achieving an accurate classification rate of 93.40% with a 1.3 s test time on a single image.https://www.mdpi.com/1424-8220/25/3/594skin cancermelanomaclassificationsegmentationdeep learning
spellingShingle Ranpreet Kaur
Hamid GholamHosseini
Maria Lindén
Advanced Deep Learning Models for Melanoma Diagnosis in Computer-Aided Skin Cancer Detection
Sensors
skin cancer
melanoma
classification
segmentation
deep learning
title Advanced Deep Learning Models for Melanoma Diagnosis in Computer-Aided Skin Cancer Detection
title_full Advanced Deep Learning Models for Melanoma Diagnosis in Computer-Aided Skin Cancer Detection
title_fullStr Advanced Deep Learning Models for Melanoma Diagnosis in Computer-Aided Skin Cancer Detection
title_full_unstemmed Advanced Deep Learning Models for Melanoma Diagnosis in Computer-Aided Skin Cancer Detection
title_short Advanced Deep Learning Models for Melanoma Diagnosis in Computer-Aided Skin Cancer Detection
title_sort advanced deep learning models for melanoma diagnosis in computer aided skin cancer detection
topic skin cancer
melanoma
classification
segmentation
deep learning
url https://www.mdpi.com/1424-8220/25/3/594
work_keys_str_mv AT ranpreetkaur advanceddeeplearningmodelsformelanomadiagnosisincomputeraidedskincancerdetection
AT hamidgholamhosseini advanceddeeplearningmodelsformelanomadiagnosisincomputeraidedskincancerdetection
AT marialinden advanceddeeplearningmodelsformelanomadiagnosisincomputeraidedskincancerdetection