Unraveling the deep learning gearbox in optical coherence tomography image segmentation towards explainable artificial intelligence
Open Access
- 5 February 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in Communications Biology
- Vol. 4 (1), 1-12
- https://doi.org/10.1038/s42003-021-01697-y
Abstract
Machine learning has greatly facilitated the analysis of medical data, while the internal operations usually remain intransparent. To better comprehend these opaque procedures, a convolutional neural network for optical coherence tomography image segmentation was enhanced with a Traceable Relevance Explainability (T-REX) technique. The proposed application was based on three components: ground truth generation by multiple graders, calculation of Hamming distances among graders and the machine learning algorithm, as well as a smart data visualization (‘neural recording’). An overall average variability of 1.75% between the human graders and the algorithm was found, slightly minor to 2.02% among human graders. The ambiguity in ground truth had noteworthy impact on machine learning results, which could be visualized. The convolutional neural network balanced between graders and allowed for modifiable predictions dependent on the compartment. Using the proposed T-REX setup, machine learning processes could be rendered more transparent and understandable, possibly leading to optimized applications.Funding Information
- This research was supported by Roche, Switzerland.
This publication has 83 references indexed in Scilit:
- Deep learning in neural networks: An overviewNeural Networks, 2015
- Multi-country real-life experience of anti-vascular endothelial growth factor therapy for wet age-related macular degenerationBritish Journal of Ophthalmology, 2014
- Proposed Lexicon for Anatomic Landmarks in Normal Posterior Segment Spectral-Domain Optical Coherence TomographyOphthalmology, 2014
- Optical coherence tomography: Imaging of the choroid and beyondSurvey of Ophthalmology, 2013
- Watson: Beyond Jeopardy!Artificial Intelligence, 2013
- Reporting and Methods in Clinical Prediction Research: A Systematic ReviewPLoS Medicine, 2012
- Errors in Retinal Thickness Measurements Obtained by Optical Coherence TomographyOphthalmology, 2006
- Ultrahigh resolution optical coherence tomography of the monkey fovea. Identification of retinal sublayers by correlation with semithin histology sectionsExperimental Eye Research, 2004
- A Measure of OriginalitySocial Studies of Science, 1999
- Some Studies in Machine Learning Using the Game of Checkers. II—Recent ProgressPublished by Springer Science and Business Media LLC ,1988