Insights into Dermatological Disorders: Understanding Skin Diseases through Medical Image Analysis

Authors

  • Yajnaseni Dash
  • Devesh Ramawat
  • Abhinav Gupta
  • Shreyanshi Parashar
  • Akshat Jain
  • Sudhir C. Sarangi
  • Ajith Abraham

Abstract

Skin disease, from a common disease to a larger problem similar to skin cancers and leprosy, presents significant diagnostic challenges. Easy, accurate, and timely diagnosis is important to successful therapy. This research explores a unique combination of smart computational algorithms to improve the categorization of skin problems. Traditional methods to catch these diseases are very time-consuming as they depend on pathological study, biopsy, and visual inspection resulting in delayed therapy. This study works on developing novel diagnostic techniques by utilizing insights from analysis, which could find out the differences between healthy and unhealthy skin. Furthermore, employing transfer learning involving leveraging pre-trained models like VGG16 and other deep learning models like CNNs, the study handles the complex and diverse nature of skin disease identified in earlier dermatological research. It aims to construct robust automated diagnostic systems, amalgamating findings from existing studies and prior CNN-based models. This paper aims to close the gap between traditional methods and cutting-edge computational techniques to improve the accuracy and speed of skin issues by combining deep learning methods, which may provide good results for the dermatological diagnostic process.

Downloads

Download data is not yet available.

Downloads

Published

2024-07-10

How to Cite

Yajnaseni Dash, Devesh Ramawat, Abhinav Gupta, Shreyanshi Parashar, Akshat Jain, Sudhir C. Sarangi, & Ajith Abraham. (2024). Insights into Dermatological Disorders: Understanding Skin Diseases through Medical Image Analysis. International Journal of Computer Information Systems and Industrial Management Applications, 16(3), 10. Retrieved from https://cspub-ijcisim.org/index.php/ijcisim/article/view/730

Issue

Section

Original Articles