Citation

K., Revathi and Chidambaram, Pabitha and R., Krishna Priya (2026) Deep Learning Model for Burn Injury Assessment with Enhanced Diagnosis Rate. Journal of Informatics and Web Engineering, 5 (2). p. 266. ISSN 2821-370X

Text sucheng,+2222-Article+Text-Final.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

The skin is considered as the largest organ of our body specifically satisfies the environment. As a result, the skin is vulnerable to various injuries, especially burns. Burns are linked to high rates of morbidity and mortality and can be fatal. Effective diagnosis supported by precise evaluation of the burn area and the depth of wound is critical for enabling efficacy in clinical settings. The characteristics of a burn wound on the skin include: the wound is abnormal, the skin is infected, there is discomfort, the skin is tight, and there are raised areas of skin. To properly diagnose burn injuries a genomic analysis for skin tissue is necessary. In existing studies, various machine learning algorithms exercised over vast datasets to identify the wound patterns and classify the same accordingly. The multilayered neural network used in the deep learning is renowned as a subset of machine learning and resembles the architecture of human neural circuits. Automatically extracting features from a burn image and classifying the wound based on severity is possible with deep neural networks. Our method involves using deep learning techniques to analyse the genome in skin burn wounds according to the extent of damage. Our goal is to examine various deep learning approaches that can support skin genomic analysis and to improve the diagnostic rate of burn injury with the help of tissue segmentation. Further the scope for repairing the tissue which enables quick advancements in skin care is discussed. The development of deep learning techniques has opened a significant avenue for medical image processing and burn trauma cases.

Item Type:	Article
Uncontrolled Keywords:	Skin Genome, Tissue Segmentation, Deep Learning, Skin Burn, Predictive Diagnosis
Subjects:	Q Science > Q Science (General)
Divisions:	Others
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	09 Jul 2026 03:36
Last Modified:	09 Jul 2026 03:36
URII:	http://shdl.mmu.edu.my/id/eprint/16337

Downloads

Edit (login required)