Early esophageal cancer detection using RF classiers

One of the fastest rising forms of cancer in the Western world is esophageal cancer. Using High-Denition (HD) endoscopy, gastroenterology experts can identify esophageal cancer at an early stage. Recent research shows that early cancer can be found using a state-of-the-art computer-aided detection (CADe) system based on analyzing static HD endoscopic images. Our research aims at extending this system by applying Random Forest (RF) classication which introduces a condence measure for detected cancer regions. To visualize this data, we propose a novel annotation system, employing the unique characteristics of the previous condence measure. This allows reliable modeling of multi-expert knowledge and provides essential data for real-time video processing, to enable future use of the system in a clinical setting. The performance of the CADe system is evaluated on a 39-patient ataset, containing 100 images annotated by ve expert gastroenterologists. The proposed system reaches a precision of 75% and recall of 90%, thereby improving the state-of-the-art results by 11 and 6 percentage points, espectively.