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...
Saved in:
| Main Authors: | , , |
|---|---|
| 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—ISIC 2019, HAM10000, and ISIC 2020—using 5-fold cross-validation. On ISIC 2020, the hybrid model achieved a 96.2% classification accuracy (95% CI: 95.8–96.6%) and a 95.1% F1-score (95% CI: 94.7–95.5%), 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—ISIC 2019, HAM10000, and ISIC 2020—using 5-fold cross-validation. On ISIC 2020, the hybrid model achieved a 96.2% classification accuracy (95% CI: 95.8–96.6%) and a 95.1% F1-score (95% CI: 94.7–95.5%), 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 |