SAVE: Spectrum-Aided Visual Enhancement for AI-Based Skin Cancer Detection
Diagnostics · 16.06.2026 · 16 (12) · 1864
DOI: 10.3390/diagnostics16121864 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 16.06.2026. Verfasst von Hung-Yi Huang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Dermatology, Ditmanson Medical Foundation Chiayi Christian Hospital, Chiayi 60002, Taiwan. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council, Chia-Yi Christian Hospital, Kaohsiung Armed Forces General Hospital.
Abstract (Originalsprache)
Background/Objectives: The early identification of skin cancer by standard RGB dermoscopy is a clinical difficulty because of the complex visual differences between impacted lesions and healthy tissue.
Methods
For the biomedical challenge, a novel approach to signal processing and image reconstruction is introduced in this study, called the spectrum-aided visual enhancer (SAVE). The proposed SAVE mechanism aims at reconstructing the diagnostically relevant spectral information from the conventional RGB dermoscopic images using the principles of hyperspectral imaging (HSI) and band selection (BS). After quality control and pre-processing, the images in the ISIC2019 dataset were selected, with 865 images that contain basal cell carcinoma (BCC), seborrheic keratosis (SK), and actinic keratosis (AK) lesions. To reduce data leakage, the dataset was split into training, validation, and testing subsets of 70%, 20%, and 10%, respectively. Five supervised deep learning object detection models were trained and tested on the conventional RGB image dataset and on the SAVE-enhanced dataset. Five supervised deep learning object detection models, namely, YOLOv8, YOLOv10, YOLOv11, SSDLite, and SSD, were trained and tested on the conventional RGB image dataset and the SAVE-enhanced dataset. Additional repeated experimental assessments and statistical comparisons were also carried out to evaluate the improvement in performance.
Results
The experimental results showed that the SAVE-based pre-processing always yielded better performance in terms of lesion detection than conventional RGB image processing. The SAVE framework for SSD was evaluated and compared with all other evaluated models and was found to be the most successful, with an accuracy of 96%, a precision of 97%, a recall of 96%, and an F1 score of 96%.
Conclusions
The results indicate that the proposed SAVE framework could be a promising RGB-compatible spectral enhancement technique for boosting skin cancer detection and computer-aided dermatologic analysis with the aid of AI.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Dermatology, Ditmanson Medical Foundation Chiayi Christian Hospital, Chiayi 60002, Taiwan.
- Department of Mechanical Engineering, National Chung Cheng University, 168, University Rd., Min Hsiung, Chiayi 62102, Taiwan.
- Department of Biomedical Imaging, Chennai Institute of Technology, Sarathy Nagar, Chennai 600069, Tamil Nadu, India.
- Department of Computer Science Engineering, School of Engineering and Technology, Sanjivani University, Kopargaon 423603, Maharashtra, India.
- Department of Integrated Bachelor of Technology, School of Engineering and Technology, Sanjivani University, Kopargaon 423603, Maharashtra, India.
- Department of Computer Science Engineering, Jeppiaar Engineering College, SH 49A, Chennai 600119, Tamil Nadu, India.
ORCID-Profile: Yaswanth Nagisetti, Arvind Mukundan, Riya Karmarkar, Hsiang-Chen Wang
Förderung
- National Science and Technology Council
- Chia-Yi Christian Hospital
- Kaohsiung Armed Forces General Hospital
- National Science and Technology Council, the Republic of China
- Ditmanson Medical Foundation, Chia-Yi Christian Hospital-National Chung Cheng University Joint Research Program
- aohsiung Armed Forces General Hospital Research Program
Zitieren
APA
Huang, H. Y., Nagisetti, Y., Mukundan, A., Karmarkar, R., Libu, S. A., Liu, T. Y., & Wang, H. C. (2026). SAVE: Spectrum-Aided Visual Enhancement for AI-Based Skin Cancer Detection. Diagnostics, 16(12), 1864. https://doi.org/10.3390/diagnostics16121864
Vancouver
Huang HY, Nagisetti Y, Mukundan A, Karmarkar R, Libu SA, Liu TY, et al. SAVE: Spectrum-Aided Visual Enhancement for AI-Based Skin Cancer Detection. Diagnostics. 2026;16(12):1864. doi:10.3390/diagnostics16121864
BibTeX
@article{Huang2026,
author = {Huang, Hung-Yi and Nagisetti, Yaswanth and Mukundan, Arvind and Karmarkar, Riya and Libu, Sahaya Ashik and Liu, Tao-Yuan and Wang, Hsiang-Chen},
title = {SAVE: Spectrum-Aided Visual Enhancement for AI-Based Skin Cancer Detection},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {12},
pages = {1864},
doi = {10.3390/diagnostics16121864}
}
EUVIMED