https://www.ncbi.nlm.nih.gov/pubmed/30105375
Real-Time Use of Artificial Intelligence in Identification of Diminutive Polyps During Colonoscopy: A Prospective Study.
Author information
- 1
- Showa University Northern Yokohama Hospital, Yokohama, Japan (Y.M., S.K., M.M., F.U., S.K., Y.O., Y.M., K.T., H.N., K.I., T.K., T.H., K.W., F.I.).
- 2
- National Cancer Center Hospital, Tokyo, Japan (Y.S.).
- 3
- National Cancer Center Hospital East, Kashiwa, Japan (H.I.).
- 4
- Shizuoka Cancer Center, Shizuoka, Japan (K.H.).
- 5
- Tokyo Medical and Dental University, Tokyo, Japan (K.O.).
- 6
- Showa University Koto-Toyosu Hospital, Tokyo, Japan (H.I.).
- 7
- Nagoya University, Nagoya, Japan (H.I., M.O., K.M.).
Abstract
BACKGROUND:
Computer-aided diagnosis (CAD) for colonoscopy may help endoscopists distinguish neoplastic polyps (adenomas) requiring resection from nonneoplastic polyps not requiring resection, potentially reducing cost.
OBJECTIVE:
To evaluate the performance of real-time CAD with endocytoscopes (×520 ultramagnifying colonoscopes providing microvascular and cellular visualization of colorectal polyps after application of the narrow-band imaging [NBI] and methylene blue staining modes, respectively).
DESIGN:
Single-group, open-label, prospective study. (UMIN [University hospital Medical Information Network] Clinical Trial Registry: UMIN000027360).
SETTING:
University hospital.
PARTICIPANTS:
791 consecutive patients undergoing colonoscopy and 23 endoscopists.
INTERVENTION:
Real-time use of CAD during colonoscopy.
MEASUREMENTS:
CAD-predicted pathology (neoplastic or nonneoplastic) of detected diminutive polyps (≤5 mm) on the basis of real-time outputs compared with pathologic diagnosis of the resected specimen (gold standard). The primary end point was whether CAD with the stained mode produced a negative predictive value (NPV) of 90% or greater for identifying diminutive rectosigmoid adenomas, the threshold required to "diagnose-and-leave" nonneoplastic polyps. Best- and worst-case scenarios assumed that polyps lacking either CAD diagnosis or pathology were true- or false-positive or true- or false-negative, respectively.
RESULTS:
Overall, 466 diminutive (including 250 rectosigmoid) polyps from 325 patients were assessed by CAD, with a pathologic prediction rate of 98.1% (457 of 466). The NPVs of CAD for diminutive rectosigmoid adenomas were 96.4% (95% CI, 91.8% to 98.8%) (best-case scenario) and 93.7% (CI, 88.3% to 97.1%) (worst-case scenario) with stained mode and 96.5% (CI, 92.1% to 98.9%) (best-case scenario) and 95.2% (CI, 90.3% to 98.0%) (worst-case scenario) with NBI.
LIMITATION:
Two thirds of the colonoscopies were conducted by experts who had each experienced more than 200 endocytoscopies; 186 polyps not assessed by CAD were excluded.
CONCLUSION:
Real-time CAD can achieve the performance level required for a diagnose-and-leave strategy for diminutive, nonneoplastic rectosigmoid polyps.
PRIMARY FUNDING SOURCE:
Japan Society for the Promotion of Science.
- PMID:
- 30105375
- DOI:
- 10.7326/M18-0249
대장내시경할 때, 보이는 작은 용종들.
Neoplastic polyp 인지, non-neoplastic polyp 인지를
대장내시경 하면서 실시간으로 판별.
폴립을 NBI 및 methylene-blue stain 하여, endocytoscopy 를 통해서 이미지를 읽엇
support vector machine 방법으로 machine learning 한 알고리즘에 넣어서
나중에 병리소견이라 맞춰보니,
overall prediction rate = 98.1% (457 / 466)
일본 단일기관 연구. 전향적 연구.
Real-time 으로 판별했다는 것에 의의가 있음.
올림푸스 장비를 사용함 ( (CF-Y-0058; the same model is commercially available as CF-H290ECI [Olympus]) )
< machine learning training descriptions >
After extraction, a support vector machine classified the imaged polyp as neoplastic or nonneoplastic on the basis of the 312 extracted features. Our support vector machine, a machine-learning method for optimal separation of complex objects (11), was trained by using endocytoscopic images provided by the aforementioned 5 academic centers. During the study period, we updated the CAD system 5 times by periodically adding training images for machine learning—starting with 28 152 images (1 June 2017) and ending with 61 925 (5 December 2017).