ERS: a novel comprehensive endoscopy image dataset for machine learning, compliant with the MST 3.0 specification
This dataset addresses the need for standardized, large-scale endoscopy data for machine learning applications in gastrointestinal analysis, though it is incremental as it builds on existing medical specifications.
The authors introduced ERS, a comprehensive multi-label endoscopy image dataset compliant with MST 3.0, containing labeled frames, segmentation masks, and unlabeled frames from over 1,500 videos. They demonstrated its utility through four classification experiments, showing high usefulness for training and testing machine learning algorithms in endoscopic data analysis.
The article presents a new multi-label comprehensive image dataset from flexible endoscopy, colonoscopy and capsule endoscopy, named ERS. The collection has been labeled according to the full medical specification of 'Minimum Standard Terminology 3.0' (MST 3.0), describing all possible findings in the gastrointestinal tract (104 possible labels), extended with an additional 19 labels useful in common machine learning applications. The dataset contains around 6000 precisely and 115,000 approximately labeled frames from endoscopy videos, 3600 precise and 22,600 approximate segmentation masks, and 1.23 million unlabeled frames from flexible and capsule endoscopy videos. The labeled data cover almost entirely the MST 3.0 standard. The data came from 1520 videos of 1135 patients. Additionally, this paper proposes and describes four exemplary experiments in gastrointestinal image classification task performed using the created dataset. The obtained results indicate the high usefulness and flexibility of the dataset in training and testing machine learning algorithms in the field of endoscopic data analysis.