Classification of Psoriasis Using Vision Transformer: A Deep Learning-Based Approach

Psoriasis is a chronic autoimmune skin condition causing complex symptoms, often complicating accurate diagnosis. While convolutional neural networks (CNN) have potential in dermatological image classification, they struggle to adapt to the subtle variations in skin tones, lesion textures and lighting condition compromising the accuracy in psoriasis classification. In addition, traditional methods have difficulty modelling the various factors associated with psoriasis symptoms. This research provides an enhanced method based on the Vision Transformer (ViT) architecture, which includes data augmentation and transfer learning, to overcome the difficulties of limited data access and class imbalance in medical image classification. The dataset used comprises 1307 images categorized into two classes representing psoriatic and non-psoriatic images. The self-attention mechanism in the ViT effectively captures both local and global picture information, enabling precise identification of patterns unique to psoriatic lesions. The proposed model achieved 97.53% accuracy, a 0.98 F1-score, and a strong Pearson correlation of 0.962 (p<0.001), with high sensitivity (98.37%) and specificity (97.84%), outperforming traditional CNN-based methods. The model’s improved accuracy and reliability has the potential of early diagnosis of psoriasis and assisting dermatologists for making informed decisions. Furthermore, ViT’s ability to effectively capture lesion variation in different skin tones, textures and lighting conditions, highlighting its advantage over CNN-based approaches. These findings indicate that ViT can efficiently manage the complicated nature of dermatological image analysis for timely and improved personalized treatment plans.