Leveraging Expert Input for Robust and Explainable AI-Assisted Lung Cancer Detection in Chest X-rays

TL;DR

This paper introduces ClinicXAI, an expert-driven, concept bottleneck approach for lung cancer detection in chest X-rays that improves interpretability and robustness over traditional deep learning models, aligning explanations with clinical expertise.

Contribution

The study develops ClinicXAI, a novel explainable AI method incorporating domain knowledge, which enhances clinical relevance and adversarial robustness in lung cancer detection.

Findings

ClinicXAI provides clinically meaningful explanations aligned with radiologists' assessments.

ClinicXAI demonstrates higher resilience to adversarial attacks compared to standard models.

Existing XAI methods often fail to produce clinically relevant explanations.

Abstract

Deep learning models show significant potential for advancing AI-assisted medical diagnostics, particularly in detecting lung cancer through medical image modalities such as chest X-rays. However, the black-box nature of these models poses challenges to their interpretability and trustworthiness, limiting their adoption in clinical practice. This study examines both the interpretability and robustness of a high-performing lung cancer detection model based on InceptionV3, utilizing a public dataset of chest X-rays and radiological reports. We evaluate the clinical utility of multiple explainable AI (XAI) techniques, including both post-hoc and ante-hoc approaches, and find that existing methods often fail to provide clinically relevant explanations, displaying inconsistencies and divergence from expert radiologist assessments. To address these limitations, we collaborated with a radiologist to define diagnosis-specific clinical concepts and developed ClinicXAI, an expert-driven approach leveraging the concept bottleneck methodology. ClinicXAI generated clinically meaningful explanations which closely aligned with the practical requirements of clinicians while maintaining high diagnostic accuracy. We also assess the robustness of ClinicXAI in comparison to the original InceptionV3 model by subjecting both to a series of widely utilized adversarial attacks. Our analysis demonstrates that ClinicXAI exhibits significantly greater resilience to adversarial perturbations. These findings underscore the importance of incorporating domain expertise into the design of interpretable and robust AI systems for medical diagnostics, paving the way for more trustworthy and effective AI solutions in healthcare.