Universität zu Köln

Tolkach, Yuri, Dohmgoergen, Tilmann, Toma, Marieta and Kristiansen, Glen (2020). High-accuracy prostate cancer pathology using deep learning. Nat. Mach. Intell., 2 (7). S. 411 - 422. LONDON: SPRINGERNATURE. ISSN 2522-5839

Full text not available from this repository.

Abstract

Deep learning methods can be a powerful part of digital pathology workflows, provided well-annotated training datasets are available. Tolkach and colleagues develop a deep learning model to recognize and grade prostate cancer, based on a convolution neural network and a dataset with high-quality labels at gland-level precision. Deep learning (DL) is a powerful methodology for the recognition and classification of tissue structures in digital pathology. Its performance in prostate cancer pathology is still under intensive investigation. Here we develop DL-based models for the detection of prostate cancer tissue in whole-slide images based on a large high-quality annotated training dataset and a modern state-of-the-art convolutional network architecture (NASNetLarge). The overall accuracy of our model for tumour detection in two validation cohorts is comparable to that of pathologists and reaches 97.3% in a native version and more than 98% using the suggested DL-based augmentation strategies. As a second step, we suggest a new biologically meaningful DL-based algorithm for Gleason grading of prostatic adenocarcinomas with high, human-level performance in prognostic stratification of patients when tested in several well-characterized validation cohorts. Furthermore, we determine the optimal minimal tumour size (real size of approximately 560 x 560 mu m) for robust Gleason grading representative of the whole tumour focus. Our approach is realized in the unified digital pathology pipeline, which delivers all the relevant tumour metrics for a pathology report.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Tolkach, Yuri UNSPECIFIED UNSPECIFIED UNSPECIFIED Dohmgoergen, Tilmann UNSPECIFIED UNSPECIFIED UNSPECIFIED Toma, Marieta UNSPECIFIED UNSPECIFIED UNSPECIFIED Kristiansen, Glen UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-327272
DOI:	10.1038/s42256-020-0200-7
Journal or Publication Title:	Nat. Mach. Intell.
Volume:	2
Number:	7
Page Range:	S. 411 - 422
Date:	2020
Publisher:	SPRINGERNATURE
Place of Publication:	LONDON
ISSN:	2522-5839
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language IMAGES; BIOPSIES; SYSTEM Multiple languages Computer Science, Artificial Intelligence; Computer Science, Interdisciplinary Applications Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/32727