Skin Lesion Diagnosis Through Deep Learning and Hybrid Texture Feature Augmentation
Skin cancer is a leading cause of cancer-related deaths globally, with melanoma being the most lethal subtype. Early detection remains critical for improving patient outcomes. However, dermoscopic image analysis faces challenges due to inter-class similarity between malignant melanoma and benign ne...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Center for Research and Community Service, Institut Informatika Indonesia Surabaya
2025-07-01
|
| Series: | Teknika |
| Subjects: | |
| Online Access: | https://ejournal.ikado.ac.id/index.php/teknika/article/view/1253 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849429490423300096 |
|---|---|
| author | Irpan Adiputra Pardosi Roni Yunis Arwin Halim |
| author_facet | Irpan Adiputra Pardosi Roni Yunis Arwin Halim |
| author_sort | Irpan Adiputra Pardosi |
| collection | DOAJ |
| description |
Skin cancer is a leading cause of cancer-related deaths globally, with melanoma being the most lethal subtype. Early detection remains critical for improving patient outcomes. However, dermoscopic image analysis faces challenges due to inter-class similarity between malignant melanoma and benign nevi. This study proposes a robust framework for optimizing Gray-Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP) parameters using the ISIC 2023 dataset. The framework integrates handcrafted features with Convolutional Neural Networks (CNNs) to enhance classification accuracy. Key contributions include: Automated parameter tuning for GLCM and LBP using grid search and cross-validation; A hybrid model combining EfficientNet-B3 with full handcrafted features; Comprehensive evaluation on the ISIC 2023 dataset (10,015 images). Results demonstrate that the hybrid model (Scenario 2) achieves 93.7% accuracy and 92.8% F1-score, outperforming the standalone CNN model (Scenario 1) by 3.5%. The proposed framework reduces false positives by 15% compared to dermatologist assessments, highlighting its potential for clinical decision support. Future work will explore advanced architectures like EfficientNet-B4 and integration of external factors such as lesion location.
|
| format | Article |
| id | doaj-art-9fc764fe906e4a94b7a934997beca009 |
| institution | Kabale University |
| issn | 2549-8037 2549-8045 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Center for Research and Community Service, Institut Informatika Indonesia Surabaya |
| record_format | Article |
| series | Teknika |
| spelling | doaj-art-9fc764fe906e4a94b7a934997beca0092025-08-20T03:28:21ZengCenter for Research and Community Service, Institut Informatika Indonesia SurabayaTeknika2549-80372549-80452025-07-0114210.34148/teknika.v14i2.1253Skin Lesion Diagnosis Through Deep Learning and Hybrid Texture Feature AugmentationIrpan Adiputra PardosiRoni YunisArwin Halim Skin cancer is a leading cause of cancer-related deaths globally, with melanoma being the most lethal subtype. Early detection remains critical for improving patient outcomes. However, dermoscopic image analysis faces challenges due to inter-class similarity between malignant melanoma and benign nevi. This study proposes a robust framework for optimizing Gray-Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP) parameters using the ISIC 2023 dataset. The framework integrates handcrafted features with Convolutional Neural Networks (CNNs) to enhance classification accuracy. Key contributions include: Automated parameter tuning for GLCM and LBP using grid search and cross-validation; A hybrid model combining EfficientNet-B3 with full handcrafted features; Comprehensive evaluation on the ISIC 2023 dataset (10,015 images). Results demonstrate that the hybrid model (Scenario 2) achieves 93.7% accuracy and 92.8% F1-score, outperforming the standalone CNN model (Scenario 1) by 3.5%. The proposed framework reduces false positives by 15% compared to dermatologist assessments, highlighting its potential for clinical decision support. Future work will explore advanced architectures like EfficientNet-B4 and integration of external factors such as lesion location. https://ejournal.ikado.ac.id/index.php/teknika/article/view/1253Skin Cancer ClassificationGLCMLBPParameter OptimizationISIC 2023 DatasetHybrid Models |
| spellingShingle | Irpan Adiputra Pardosi Roni Yunis Arwin Halim Skin Lesion Diagnosis Through Deep Learning and Hybrid Texture Feature Augmentation Teknika Skin Cancer Classification GLCM LBP Parameter Optimization ISIC 2023 Dataset Hybrid Models |
| title | Skin Lesion Diagnosis Through Deep Learning and Hybrid Texture Feature Augmentation |
| title_full | Skin Lesion Diagnosis Through Deep Learning and Hybrid Texture Feature Augmentation |
| title_fullStr | Skin Lesion Diagnosis Through Deep Learning and Hybrid Texture Feature Augmentation |
| title_full_unstemmed | Skin Lesion Diagnosis Through Deep Learning and Hybrid Texture Feature Augmentation |
| title_short | Skin Lesion Diagnosis Through Deep Learning and Hybrid Texture Feature Augmentation |
| title_sort | skin lesion diagnosis through deep learning and hybrid texture feature augmentation |
| topic | Skin Cancer Classification GLCM LBP Parameter Optimization ISIC 2023 Dataset Hybrid Models |
| url | https://ejournal.ikado.ac.id/index.php/teknika/article/view/1253 |
| work_keys_str_mv | AT irpanadiputrapardosi skinlesiondiagnosisthroughdeeplearningandhybridtexturefeatureaugmentation AT roniyunis skinlesiondiagnosisthroughdeeplearningandhybridtexturefeatureaugmentation AT arwinhalim skinlesiondiagnosisthroughdeeplearningandhybridtexturefeatureaugmentation |