A Hybrid Model for Early Melanoma Detection: Integrating YOLOv9 and Faster R-CNN for Enhanced Diagnostic Accuracy

Melanoma accounts for only 1% of skin cancer diagnoses yet causes the majority of skin cancer-related deaths due to its rapid progression and high metastatic potential. Early and accurate detection is crucial for improving patient outcomes; however, existing deep learning models often struggle to ba...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohamed I. Marie, Mohamed S. Elredeny, Ahmad Essayed Yakoub
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11077147/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849318161831165952
author Mohamed I. Marie
Mohamed S. Elredeny
Ahmad Essayed Yakoub
author_facet Mohamed I. Marie
Mohamed S. Elredeny
Ahmad Essayed Yakoub
author_sort Mohamed I. Marie
collection DOAJ
description Melanoma accounts for only 1% of skin cancer diagnoses yet causes the majority of skin cancer-related deaths due to its rapid progression and high metastatic potential. Early and accurate detection is crucial for improving patient outcomes; however, existing deep learning models often struggle to balance diagnostic precision with real-time efficiency. This study presents the Melano Hybrid Model, a novel architecture that integrates the rapid detection capabilities of YOLOv9 with the boundary localization accuracy of Faster R-CNN through an adaptive feature fusion mechanism. The model was rigorously evaluated on three benchmark datasets&#x2014;ISIC 2019, HAM10000, and ISIC 2020&#x2014;using 5-fold cross-validation. On ISIC 2020, the hybrid model achieved a 96.2% classification accuracy (95% CI: 95.8&#x2013;96.6%) and a 95.1% F1-score (95% CI: 94.7&#x2013;95.5%), significantly outperforming standalone models (<inline-formula> <tex-math notation="LaTeX">$p\lt 0.001$ </tex-math></inline-formula>). The architecture delivers an average inference speed of 31.3 frames per second (FPS), surpassing clinical real-time thresholds. Additionally, computational profiling confirms its practical feasibility with 78.3 million parameters, 134.8 GFLOPs, and a 324 MB memory footprint. These results support the hybrid framework as a robust AI-assisted tool for real-world melanoma screening, offering an optimal trade-off between speed and diagnostic performance.
format Article
id doaj-art-0fa43655c0c9436681d649adfdbb5ec0
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-0fa43655c0c9436681d649adfdbb5ec02025-08-20T03:50:59ZengIEEEIEEE Access2169-35362025-01-011312032712034410.1109/ACCESS.2025.358762511077147A Hybrid Model for Early Melanoma Detection: Integrating YOLOv9 and Faster R-CNN for Enhanced Diagnostic AccuracyMohamed I. Marie0https://orcid.org/0000-0003-4784-2953Mohamed S. Elredeny1https://orcid.org/0009-0000-6043-0270Ahmad Essayed Yakoub2Department of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo, EgyptDepartment of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo, EgyptDepartment of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo, EgyptMelanoma accounts for only 1% of skin cancer diagnoses yet causes the majority of skin cancer-related deaths due to its rapid progression and high metastatic potential. Early and accurate detection is crucial for improving patient outcomes; however, existing deep learning models often struggle to balance diagnostic precision with real-time efficiency. This study presents the Melano Hybrid Model, a novel architecture that integrates the rapid detection capabilities of YOLOv9 with the boundary localization accuracy of Faster R-CNN through an adaptive feature fusion mechanism. The model was rigorously evaluated on three benchmark datasets&#x2014;ISIC 2019, HAM10000, and ISIC 2020&#x2014;using 5-fold cross-validation. On ISIC 2020, the hybrid model achieved a 96.2% classification accuracy (95% CI: 95.8&#x2013;96.6%) and a 95.1% F1-score (95% CI: 94.7&#x2013;95.5%), significantly outperforming standalone models (<inline-formula> <tex-math notation="LaTeX">$p\lt 0.001$ </tex-math></inline-formula>). The architecture delivers an average inference speed of 31.3 frames per second (FPS), surpassing clinical real-time thresholds. Additionally, computational profiling confirms its practical feasibility with 78.3 million parameters, 134.8 GFLOPs, and a 324 MB memory footprint. These results support the hybrid framework as a robust AI-assisted tool for real-world melanoma screening, offering an optimal trade-off between speed and diagnostic performance.https://ieeexplore.ieee.org/document/11077147/Melanoma detectionhybrid architectureYOLOv9faster R-CNNdeep learningcomputer vision
spellingShingle Mohamed I. Marie
Mohamed S. Elredeny
Ahmad Essayed Yakoub
A Hybrid Model for Early Melanoma Detection: Integrating YOLOv9 and Faster R-CNN for Enhanced Diagnostic Accuracy
IEEE Access
Melanoma detection
hybrid architecture
YOLOv9
faster R-CNN
deep learning
computer vision
title A Hybrid Model for Early Melanoma Detection: Integrating YOLOv9 and Faster R-CNN for Enhanced Diagnostic Accuracy
title_full A Hybrid Model for Early Melanoma Detection: Integrating YOLOv9 and Faster R-CNN for Enhanced Diagnostic Accuracy
title_fullStr A Hybrid Model for Early Melanoma Detection: Integrating YOLOv9 and Faster R-CNN for Enhanced Diagnostic Accuracy
title_full_unstemmed A Hybrid Model for Early Melanoma Detection: Integrating YOLOv9 and Faster R-CNN for Enhanced Diagnostic Accuracy
title_short A Hybrid Model for Early Melanoma Detection: Integrating YOLOv9 and Faster R-CNN for Enhanced Diagnostic Accuracy
title_sort hybrid model for early melanoma detection integrating yolov9 and faster r cnn for enhanced diagnostic accuracy
topic Melanoma detection
hybrid architecture
YOLOv9
faster R-CNN
deep learning
computer vision
url https://ieeexplore.ieee.org/document/11077147/
work_keys_str_mv AT mohamedimarie ahybridmodelforearlymelanomadetectionintegratingyolov9andfasterrcnnforenhanceddiagnosticaccuracy
AT mohamedselredeny ahybridmodelforearlymelanomadetectionintegratingyolov9andfasterrcnnforenhanceddiagnosticaccuracy
AT ahmadessayedyakoub ahybridmodelforearlymelanomadetectionintegratingyolov9andfasterrcnnforenhanceddiagnosticaccuracy
AT mohamedimarie hybridmodelforearlymelanomadetectionintegratingyolov9andfasterrcnnforenhanceddiagnosticaccuracy
AT mohamedselredeny hybridmodelforearlymelanomadetectionintegratingyolov9andfasterrcnnforenhanceddiagnosticaccuracy
AT ahmadessayedyakoub hybridmodelforearlymelanomadetectionintegratingyolov9andfasterrcnnforenhanceddiagnosticaccuracy