Optimized Grasshopper Optimisation Algorithm enabled DETR (DEtection TRansformer) model for skin disease classification

Shakti Kundu, Yogesh Kumar Sharma, Khan Vajid Nabilal, Gopalsamy Venkatesan Samkumar, Sultan Mesfer Aldossary, Shanu Kuttan Rakesh, Nasratullah Nuristani, Arshad Hashmi

Research output: Contribution to journalArticlepeer-review

Abstract

Skin disease classification is a choir cognate for early diagnosis and therapy. The novelty of this study lies in integrating the Grasshopper Optimisation Algorithm (GOA) with a DETR (DEtection TRansformer) model which is developed for the classification of skin disease. Hyperparameter tuning using GOA optimizes the critical parameters of the proposed model to improve classification accuracy. After extensive testing on a large dataset of skin disease photos, the optimised DETR model returned an accuracy of at least 99.26%. The superiority of the DETR improved using GOA compared to standard ones indicates its potential to be used for automatically diagnosing skin diseases. Findings demonstrate that the proposed method contributes to enhancing diagnostic accuracy and creates a basis for improving transformer-based medical image analysis.

Original languageEnglish
Article numbere0323920
JournalPLoS ONE
Volume20
Issue number5 May
DOIs
StatePublished - May 2025

Fingerprint

Dive into the research topics of 'Optimized Grasshopper Optimisation Algorithm enabled DETR (DEtection TRansformer) model for skin disease classification'. Together they form a unique fingerprint.

Cite this