Automated detection and delineation of lymph nodes in haematoxylin & eosin stained digitised slides.
Date
2023-01-01ICR Author
Author
Beuque, M
Magee, DR
Chatterjee, A
Woodruff, HC
Langley, RE
Allum, W
Nankivell, MG
Cunningham, D
Lambin, P
Grabsch, HI
Type
Journal Article
Metadata
Show full item recordAbstract
Treatment of patients with oesophageal and gastric cancer (OeGC) is guided by disease stage, patient performance status and preferences. Lymph node (LN) status is one of the strongest prognostic factors for OeGC patients. However, survival varies between patients with the same disease stage and LN status. We recently showed that LN size from patients with OeGC might also have prognostic value, thus making delineations of LNs essential for size estimation and the extraction of other imaging biomarkers. We hypothesized that a machine learning workflow is able to: (1) find digital H&E stained slides containing LNs, (2) create a scoring system providing degrees of certainty for the results, and (3) delineate LNs in those images. To train and validate the pipeline, we used 1695 H&E slides from the OE02 trial. The dataset was divided into training (80%) and validation (20%). The model was tested on an external dataset of 826 H&E slides from the OE05 trial. U-Net architecture was used to generate prediction maps from which predefined features were extracted. These features were subsequently used to train an XGBoost model to determine if a region truly contained a LN. With our innovative method, the balanced accuracies of the LN detection were 0.93 on the validation dataset (0.83 on the test dataset) compared to 0.81 (0.81) on the validation (test) datasets when using the standard method of thresholding U-Net predictions to arrive at a binary mask. Our method allowed for the creation of an "uncertain" category, and partly limited false-positive predictions on the external dataset. The mean Dice score was 0.73 (0.60) per-image and 0.66 (0.48) per-LN for the validation (test) datasets. Our pipeline detects images with LNs more accurately than conventional methods, and high-throughput delineation of LNs can facilitate future LN content analyses of large datasets.
Collections
Subject
AUC, area under the curve
Autodelineation
DL, deep learning
Deep learning
Digital pathology
Explainability
H&E, haematoxylin and eosin
LN, lymph node
Lymph nodes
OeGC, Oeosphageal and gastric cancers
Oesophageal cancer
ROC, receiver operating characteristic
Research team
Medicine (RMH)
Language
eng
Date accepted
2023-01-17
License start date
2023-01-01
Citation
Journal of Pathology Informatics, 2023, 14 pp. 100192 -
Publisher
Elsevier BV