Enhancing the resilience of wireless capsule endoscopy imaging against adversarial contrast reduction using color quaternion modulus and phase patterns

Abstract

Wireless capsule endoscopy (WCE) offers a minimally invasive approach to inspecting the gastrointestinal (GI) tract, crucial for diagnosing conditions such as malnutrition, dehydration, and potential cancers. However, WCE image diagnostics can be compromised by inadequate illumination and adversarial contrast reduction attacks. Adversarial contrast reduction attacks are intentional efforts to degrade image contrast and mislead automated diagnosis systems. Such challenges can result in misclassifications, negatively impacting patient safety.This study examines the effects of contrast degradation on Deep Learning (DL) models designed for WCE image analysis. The study emphasizes the adverse impact of substantial contrast reductions from adversarial attacks on classification accuracy. We propose a novel texture descriptor to mitigate this vulnerability: the Color Quaternion Modulus and Phase Patterns (CQ-MPP). This descriptor effectively extracts textural features within WCE images, enabling the identification of potentially cancerous regions, even under significantly reduced contrast. The effectiveness of CQ-MPP is evaluated using the Wireless Capsule Endoscopy Curated Colon Disease Dataset. Results show that CQ-MPP maintains good accuracy in detecting cancerous lesions and demonstrates remarkable resilience to contrast adversarial degradation. This method ensures reliable performance amidst severe contrast reduction, offering significant potential to improve safety of GI disease diagnosis via WCE.