PSO-Net: Development of an automated psoriasis assessment system using attention-based interpretable deep neural networks

2025-01-30

AI Summary

Psoriasis assessment using the Psoriasis Area and Severity Index (PASI) relies on manual clinical evaluation, which is time-consuming, subjective, and exhibits poor inter-rater reliability. To address these limitations, we propose the first end-to-end interpretable deep learning framework that accepts multi-region skin lesion images as input and directly regresses absolute PASI scores. Our method introduces a novel ranking-based attention mechanism to generate localized severity heatmaps and designs Ranking-based Attention-guided Regression Activation Mapping (RAM) to visualize decision rationale and enhance clinical interpretability. In clinical validation involving two board-certified dermatologists, our system achieved intraclass correlation coefficients (ICCs) of 82.2% (95% CI: 77–87%) and 87.8% (95% CI: 84–91%), respectively—demonstrating strong agreement with expert assessments. This approach significantly alleviates clinical assessment burden while improving objectivity, reproducibility, and scoring consistency.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Psoriasis is a chronic skin condition that requires long-term treatment and monitoring. Although, the Psoriasis Area and Severity Index (PASI) is utilized as a standard measurement to assess psoriasis severity in clinical trials, it has many drawbacks such as (1) patient burden for in-person clinic visits for assessment of psoriasis, (2) time required for investigator scoring and (3) variability of inter- and intra-rater scoring. To address these drawbacks, we propose a novel and interpretable deep learning architecture called PSO-Net, which maps digital images from different anatomical regions to derive attention-based scores. Regional scores are further combined to estimate an absolute PASI score. Moreover, we devise a novel regression activation map for interpretability through ranking attention scores. Using this approach, we achieved inter-class correlation scores of 82.2% [95% CI: 77- 87%] and 87.8% [95% CI: 84-91%] with two different clinician raters, respectively.

Problem

• Psoriasis Severity Assessment
• PASI Scoring
• Consistency Issues

Innovation

• PSO-Net
• Automated Dermatological Assessment
• Explainable AI