International Journal on Science and Technology

E-ISSN: 2229-7677   •   Impact Factor: 9.88

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 16 Issue 4 October-December 2025 Submit your research before last 3 days of December to publish your research paper in the issue of October-December.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 16 Issue 4
October-December 2025

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

A Hybrid AI System for Real-Time Dermatological Condition Recognition and Interpretability Using YOLOv8 and EfficientNet-B0

Author(s) Mr. Harshith . S, Mr. Mirza Ayyan Abbas, Mr. Mohammad shahabuddin ., Mr. Syed Zaid .
Country India
Abstract Skin conditions, ranging from harmless spots to serious skin cancers, are a major global health issue, especially in places with few specialists. In busy clinics, traditional clinical assessments often face problems related to differences in opinions among observers and time limits because they rely heavily on visual and subjective evaluation. This paper presents a hybrid artificial intelligence system that integrates seven-class dermatoscopic image classification using EfficientNet-B0 and real-time lesion detection using YOLOv8m within a combined framework to tackle these challenges. To improve transparency and clinical use, the platform features lesion bounding-box visualization, Grad-CAM-based visual explanations, and risk assessment based on metadata. A meta-classifier refines predictions into low-, medium-, or high-risk categories based on patient factors such as age, sex, and lesion location. Additionally, a Flask-based web interface allows for tracking patient lesions over time, provides interactive visualization, and supports the uploading of images and metadata.
This system ranks among the top dermatology AI methods on the HAM10000 dataset, achieving an overall accuracy of 94.4% and maintaining good precision and recall for both common and rare lesion types. This shows that the proposed hybrid, interpretable, and ready-for-use system offers a practical and dependable solution for AI-assisted dermatological diagnosis in both clinic and teledermatology settings.
Keywords Dermatology AI, YOLOv8, EfficientNet-B0, Ensemble Models, Grad-CAM, Risk Stratification, Real-Time Inference, Flask, HAM10000.
Field Engineering
Published In Volume 16, Issue 4, October-December 2025
Published On 2025-11-30
View / Download PDF File

Share this


CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 16 Isu 3Cover Page Vol 16 Isu 2Cover Page Vol 16 Isu 1

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJSAT
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us Message on WhatsApp +91-9687-182-185 editor@ijsat.org