Enhanced Skin Lesion Diagnosis Through Real-Time Deep Learning and Transfer Learning

Syed Yaseen M; Roshan L; Dwarakanathan K; Thejashri S; Dr. Shekhar R

Enhanced Skin Lesion Diagnosis Through Real-Time Deep Learning and Transfer Learning

Author(s)	Mr. Syed Yaseen M, Mr. Roshan L, Mr. Dwarakanathan K, Ms. Thejashri S, Dr. Shekhar R
Country	India
Abstract	The diagnosis of skin lesions is an important step for the early detection of skin cancer and skin diseases. 2D dermoscopic images, which most existing works are based on, can only show limited information of depth, shape and volume of the skin lesions. Due to this constraint, an erroneous evaluation of disease progression could happen.In this paper, we introduce a real-time skin lesion classification framework with transfer learning and deep learning which is computationally efficient. Here, image acquisition, preprocessing, 3D reconstruction and CNN based feature extraction and fusion are all embedded in a unified framework, so as to develop a complete system. To improve the spatial knowledge, SfM and SfS are applied to extract 3D surfaces from a series of 2D plots. The system has additional features for observing changes in lesions with time and generating a quantitative risk score to assist decision making in the clinic. Besides, the framework enables interactive visualization, AI-powered automated report generation, and hospital IT systems integration. In summary, the proposed method contributes in enhancing the diagnostic accuracy, reducing subjectivity, and facilitating a powerful clinical assessment for real-time applications.
Keywords	Dermoscopy, U-Net, MobileNetV3, 3D Reconstruction, SfM, SfS, Risk Scoring, Progression Tracking, Skin Lesion, Deep Learning, Transfer Learning
Field	Engineering
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-04-14

View / Download PDF File

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

Enhanced Skin Lesion Diagnosis Through Real-Time Deep Learning and Transfer Learning

Share this