An Intelligent Deep Learning Framework for Dermatological Lesion Detection and Segmentation Using YOLOv8 and SAM

Venkatesh Dande; G. Umamaheswara Reddy

doi:10.36948/ijfmr.2025.v07i06.62656

An Intelligent Deep Learning Framework for Dermatological Lesion Detection and Segmentation Using YOLOv8 and SAM

Author(s)	Venkatesh Dande, G. Umamaheswara Reddy
Country	India
Abstract	This A wide range of skin conditions provide a substantial global healthcare burden, and account for almost 30% of outpatient consultations. Precise and timely diagnosis is key, but the use of manual, subjective expert diagnosis has significant challenges. This research gives an introductory of YOLOSAMIC, which is a design of a mix of deep learning frameworks which incorporates YOLOv8 for quick lesions finding with segment anything model (SAM) for fine dividing of boundaries. The system includes a Tkinter-based graphical user interface (GUI) support for enabling real-time visualization, patient and disease-specific precautionary recommendations. A custom dataset of 20 dermatological classes dataset, ranging from acne, eczema and psoriasis to vitiligo and lupus, as well as various skin cancers to name a few was prepared, pre-pocessed and used for massive training and validation. Experimental results proved YOLOSAMIC in three cases achieved detection accuracy of 94%, mAP@0.5 of 93.8%, and F1 score of 94.2%, with a significant improvement over conventional models of DES-YOLOv8 and CNN-based identification in case evaluation of localizing the lesions and delineating the boundary lines. The framework shows strong generalization tolerance with various skin tones and light conditions which in turn guarantees application in field scenarios. The combination of detection, segmentation and a user-friendly interface makes it stand out for potential use in tele-dermatology, remote diagnostics as well as automated clinical screening, ultimately increasing accessibility and efficiency of diagnostics in the medical field.
Keywords	Keywords: YOLOSAMIC, YOLOv8, SAM, Skin Disease Detection, Segmentation, Deep Learning, Tkinter GUI, Telemedicine.
Field	Medical / Pharmacy
Published In	Volume 7, Issue 6, November-December 2025
Published On	2025-12-11
DOI	https://doi.org/10.36948/ijfmr.2025.v07i06.62656

View / Download PDF File

E-ISSN 2582-2160

doi

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

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

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

About IJFMR 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		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

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

An Intelligent Deep Learning Framework for Dermatological Lesion Detection and Segmentation Using YOLOv8 and SAM

Share this