TY  - JOUR
AU  - Hilgers, Lars
AU  - Ghaffari Laleh, Narmin
AU  - West, Nicholas P
AU  - Westwood, Alice
AU  - Hewitt, Katherine J
AU  - Quirke, Philip
AU  - Grabsch, Heike I
AU  - Carrero, Zunamys I
AU  - Matthaei, Emylou
AU  - Loeffler, Chiara M L
AU  - Brinker, Titus J
AU  - Yuan, Tanwei
AU  - Brenner, Hermann
AU  - Brobeil, Alexander
AU  - Hoffmeister, Michael
AU  - Kather, Jakob Nikolas
TI  - Automated curation of large-scale cancer histopathology image datasets using deep learning.
JO  - Histopathology
VL  - 84
IS  - 7
SN  - 0309-0167
CY  - Oxford [u.a.]
PB  - Wiley-Blackwell
M1  - DKFZ-2024-00429
SP  - 1139-1153
PY  - 2024
N1  - 2024 Jun;84(7):1139-1153
AB  - Artificial intelligence (AI) has numerous applications in pathology, supporting diagnosis and prognostication in cancer. However, most AI models are trained on highly selected data, typically one tissue slide per patient. In reality, especially for large surgical resection specimens, dozens of slides can be available for each patient. Manually sorting and labelling whole-slide images (WSIs) is a very time-consuming process, hindering the direct application of AI on the collected tissue samples from large cohorts. In this study we addressed this issue by developing a deep-learning (DL)-based method for automatic curation of large pathology datasets with several slides per patient.We collected multiple large multicentric datasets of colorectal cancer histopathological slides from the United Kingdom (FOXTROT, N = 21,384 slides; CR07, N = 7985 slides) and Germany (DACHS, N = 3606 slides). These datasets contained multiple types of tissue slides, including bowel resection specimens, endoscopic biopsies, lymph node resections, immunohistochemistry-stained slides, and tissue microarrays. We developed, trained, and tested a deep convolutional neural network model to predict the type of slide from the slide overview (thumbnail) image. The primary statistical endpoint was the macro-averaged area under the receiver operating curve (AUROCs) for detection of the type of slide.In the primary dataset (FOXTROT), with an AUROC of 0.995 [95
KW  - colorectal cancer (Other)
KW  - deep learning (Other)
KW  - digital pathology (Other)
KW  - quality control (Other)
LB  - PUB:(DE-HGF)16
C6  - pmid:38409878
DO  - DOI:10.1111/his.15159
UR  - https://inrepo02.dkfz.de/record/288710
ER  -