GastroEndoNet: Comprehensive Endoscopy Image Dataset for GERD and Polyp Detection

This dataset contains a total of 27, 624 (primary 4,604 images with 6 augmented techniques) high-quality gastrointestinal endoscopy images categorized into four distinct classes: GERD, GERD Normal, Polyp, and Polyp Normal. The dataset is curated to aid research and advancements in medical image analysis, focusing on the automatic detection and classification of Gastroesophageal Reflux Disease (GERD) and gastrointestinal polyps, both critical conditions in gastroenterology. - GERD: 1,076 * 6 = 6,456 images of patients diagnosed with GERD through endoscopic evaluation, depicting various manifestations of reflux damage in the esophagus. - GERD Normal: 1,168 * 6 = 7,008 images of healthy gastrointestinal tracts without GERD, serving as control cases for the GERD category. - Polyp: 1,188 * 6 = 7,128 images featuring gastrointestinal polyps, including various types and stages, aimed at supporting early detection of potentially precancerous conditions. - Polyp Normal: 1,172 * 6 = 7,032 images representing normal gastrointestinal conditions with no polyps, included to provide a comparison for effective polyp detection. This comprehensive dataset is ideal for developing and testing machine learning algorithms for diagnosis, classification, and detection of GERD and polyps, ultimately contributing to improved AI-driven healthcare solutions in the field of gastroenterology.