Motion Artifact Detection in Confocal Laser Endomicroscopy Images

TL;DR

This paper develops and evaluates machine learning and deep learning algorithms to automatically detect motion artifacts in confocal laser endomicroscopy images, improving the reliability of automated carcinoma detection in clinical settings.

Contribution

It introduces novel deep learning methods for motion artifact detection in CLE images, outperforming traditional machine learning techniques.

Findings

Deep learning approach achieves an AUC of 0.90.

Motion artifact detection enhances the clinical applicability of automated carcinoma diagnosis.

Deep learning outperforms conventional machine learning methods.

Abstract

Confocal Laser Endomicroscopy (CLE), an optical imaging technique allowing non-invasive examination of the mucosa on a (sub)cellular level, has proven to be a valuable diagnostic tool in gastroenterology and shows promising results in various anatomical regions including the oral cavity. Recently, the feasibility of automatic carcinoma detection for CLE images of sufficient quality was shown. However, in real world data sets a high amount of CLE images is corrupted by artifacts. Amongst the most prevalent artifact types are motion-induced image deteriorations. In the scope of this work, algorithmic approaches for the automatic detection of motion artifact-tainted image regions were developed. Hence, this work provides an important step towards clinical applicability of automatic carcinoma detection. Both, conventional machine learning and novel, deep learning-based approaches were assessed. The deep learning-based approach outperforms the conventional approaches, attaining an AUC of 0.90.