Motion Artifact Detection in Confocal Laser Endomicroscopy Images
This work addresses motion artifacts in CLE images to improve clinical applicability of automatic carcinoma detection, representing an incremental advancement in medical imaging.
The paper tackled the problem of motion artifact detection in Confocal Laser Endomicroscopy (CLE) images, which are crucial for automatic carcinoma detection, and developed algorithmic approaches with a deep learning-based method achieving an AUC of 0.90.
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.