作者
A Echle, N Ghaffari Laleh, P Quirke, HI Grabsch, HS Muti, OL Saldanha, SF Brockmoeller, PA van den Brandt, GGA Hutchins, SD Richman, K Horisberger, C Galata, MP Ebert, M Eckardt, M Boutros, D Horst, C Reissfelder, E Alwers, TJ Brinker, Rupert Langer, JCA Jenniskens, K Offermans, W Mueller, R Gray, SB Gruber, JK Greenson, G Rennert, JD Bonner, D Schmolze, J Chang-Claude, H Brenner, C Trautwein, P Boor, D Jaeger, NT Gaisa, M Hoffmeister, NP West, JN Kather
发表日期
2022/4/1
期刊
ESMO open
卷号
7
期号
2
页码范围
100400
出版商
Elsevier
简介
Background
Microsatellite instability (MSI)/mismatch repair deficiency (dMMR) is a key genetic feature which should be tested in every patient with colorectal cancer (CRC) according to medical guidelines. Artificial intelligence (AI) methods can detect MSI/dMMR directly in routine pathology slides, but the test performance has not been systematically investigated with predefined test thresholds.
Method
We trained and validated AI-based MSI/dMMR detectors and evaluated predefined performance metrics using nine patient cohorts of 8343 patients across different countries and ethnicities.
Results
Classifiers achieved clinical-grade performance, yielding an area under the receiver operating curve (AUROC) of up to 0.96 without using any manual annotations. Subsequently, we show that the AI system can be applied as a rule-out test: by using cohort-specific thresholds, on average 52.73% of tumors in each surgical …
学术搜索中的文章
A Echle, NG Laleh, P Quirke, HI Grabsch, HS Muti… - ESMO open, 2022