AI Case Study
Scientists automate detection of polyps during colonoscopy using deep learning
Scientists from Sichuan Academy of Medical Sciences & Sichuan Provincial People’s Hospital, Shanghai Wision AI Co. Ltd and Beth Israel Deaconess Medical Center and Harvard Medical School, have developed a deep-learning algorithm, integrated with a multi-threaded processing system, to automatically detect polyps during colonoscopy.
Healthcare Providers And Services
In the paper, scientists "show that a machine-learning algorithm can detect polyps in clinical colonoscopies, in real time and with high sensitivity and specificity.
We developed the deep-learning algorithm by using data from 1,290 patients, and validated it on newly collected 27,113 colonoscopy images from 1,138 patients with at least one detected polyp (per-image-sensitivity, 94.38%; per-image-specificity, 95.92%; area under the receiver operating characteristic curve, 0.984), on a public database of 612 polyp-containing images (per-image-sensitiv- ity, 88.24%), on 138 colonoscopy videos with histologically confirmed polyps (per-image-sensitivity of 91.64%; per-polyp-sen- sitivity, 100%), and on 54 unaltered full-range colonoscopy videos without polyps (per-image-specificity, 95.40%). By using a multi-threaded processing system, the algorithm can process at least 25 frames per second with a latency of 76.80 ± 5.60 ms in real-time video analysis. The software may aid endoscopists while performing colonoscopies, and help assess differences in polyp and adenoma detection performance among endoscopists."
"If an AI system is trained mostly on overall shape of colon polyps and is thus only aimed to detect polyps of typical polyp-like shape (a protruding shape with definable boundary), then the potential clinical value of using such an AI system for decreasing colorectal cancer incidence is significantly reduced."
R And D
Core Research And Development
"The detection and removal of precancerous polyps via colonoscopy is the gold standard for the prevention of colon cancer. However, the detection rate of adenomatous polyps can vary significantly among endoscopists. Several studies have shown that observation of the video monitor by either nurses or gastroenterology trainees may increase polyp detection by up to 30%. Ideally, a real-time automatic polyp-detection system could serve as a similarly effective second observer that could draw the endoscopist’s eye, in real time, to concerning lesions, effec- tively creating an ‘extra set of eyes’ on all aspects of the video data with fidelity."
"Data from 1,290 patients, and validated it on newly collected 27,113 colonoscopy images from 1,138 patients with at least one detected polyp, on a public database of 612 polyp-containing images, on 138 colonoscopy videos with histologically confirmed polyps, and on 54 unaltered full-range colonoscopy videos without polyps.