Automatic Segmentation of Psoriasis Skin Images Using Adaptive Chimp Optimization Algorithm-Based CNN.

Area of Science:

• Dermatology
• Computer Vision
• Artificial Intelligence

Background:

• Psoriasis diagnosis relies on visual surveys by dermatologists.
• Computer vision and machine learning techniques are increasingly used for psoriasis segmentation.
• Existing methods face challenges in accuracy and time efficiency.

Purpose of the Study:

• To develop an automated system for psoriasis skin image segmentation.
• To improve the accuracy and efficiency of psoriasis segmentation models.
• To introduce an adaptive chimp optimization algorithm (AChOA)-based convolutional neural network (CNN).

Main Methods:

• Image pre-processing was applied to input images.
• An AChOA-CNN model was utilized for segmentation, optimizing CNN weights and biases with AChOA.
• Chimp optimization algorithm (ChOA) search capabilities were enhanced using a chaotic tent map sequence.
• Artifact removal was performed using a threshold module on segmented images.

Main Results:

• The AChOA-CNN model achieved high accuracy in segmenting psoriasis skin images.
• The adaptive nature of AChOA improved the optimization process.
• The method demonstrated effective artifact removal post-segmentation.
• An overall accuracy of 97% was attained.

Conclusions:

• The proposed AChOA-CNN model offers a promising automated solution for psoriasis skin image segmentation.
• This approach significantly enhances diagnostic accuracy and efficiency in clinical dermatology.
• Further research can explore broader applications of this optimized deep learning model.