Systematic Performance Evaluation of a Novel Optimized Differential Localization Method for Capsule Endoscopes.

Capsule endoscopy is a well-established diagnostic tool for the gastrointestinal tract. However, the reliable tracking of capsule endoscopes needs further investigation. Recently, the static magnetic differential method for the localization of capsule endoscopes has shown promising results. This method was experimentally validated by investigating the difference in the measured values of the geomagnetic flux density of a representative sensor pair. In the measurements, it was revealed that misalignment of the sensors and ferromagnetic material near the sensor pair had the most significant impact on the differential approach. Besides, a systematical simulation-based study was conducted. Herein, the position and alignment of all sensors of the localization system were randomly varied. Furthermore, root-mean-squared noise was added to the sensor measurements, and the influence of nearby ferromagnetic material was evaluated. Subsequently, non-idealities were applied simultaneously on the proposed localization system, and the entire system was rotated. The proposed method was significantly better than state-of-the-art geomagnetic compensation methods for the localization of capsule endoscopes with mean position and orientation errors of approximately 2 mm and 1°, respectively.

EndoL2H: Deep Super-Resolution for Capsule Endoscopy.

Although wireless capsule endoscopy is the preferred modality for diagnosis and assessment of small bowel diseases, the poor camera resolution is a substantial limitation for both subjective and automated diagnostics. Enhanced-resolution endoscopy has shown to improve adenoma detection rate for conventional endoscopy and is likely to do the same for capsule endoscopy. In this work, we propose and quantitatively validate a novel framework to learn a mapping from low-to-high-resolution endoscopic images. We combine conditional adversarial networks with a spatial attention block to improve the resolution by up to factors of 8× , 10× , 12× , respectively. Quantitative and qualitative studies demonstrate the superiority of EndoL2H over state-of-the-art deep super-resolution methods Deep Back-Projection Networks (DBPN), Deep Residual Channel Attention Networks (RCAN) and Super Resolution Generative Adversarial Network (SRGAN). Mean Opinion Score (MOS) tests were performed by 30 gastroenterologists qualitatively assess and confirm the clinical relevance of the approach. EndoL2H is generally applicable to any endoscopic capsule system and has the potential to improve diagnosis and better harness computational approaches for polyp detection and characterization. Our code and trained models are available at https://github.com/CapsuleEndoscope/EndoL2H.