This type of automated sorting would allow prioritisation of malignant slides so that pathologists can review them first and reduce the time to diagnosis for patients with cancer.
The final model was able to correctly detect 97% of malignant slides and correctly detect 90% of all slides.
The final model is in two stages. Firstly, the very large images are split into smaller patches and a deep learning model is trained to classify each patch as malignant or not.
Next, a second stage model combines the small patches back together and predicts a classification for the whole slide, this compensates for noise in the predictions of the first stage.
Authors: Christina Fell (lead), Mahnaz Mohammadi, David Morrison,Ognjen Arandjelović, Sheeba Syed, Prakash Konanahalli, Sarah Bell, Gareth Bryson, David J. Harrison, David Harris-Birtill.
Journal
PLoS ONE
Method of Research
Computational simulation/modeling
Subject of Research
Human tissue samples
Article Title
Detection of malignancy in whole slide images of endometrial cancer biopsies using artificial intelligence
Article Publication Date
8-Mar-2023
COI Statement
In this study we use artificial intelligence (AI) to categorise endometrial biopsy whole slide images (WSI) from digital pathology as either “malignant”, “other or benign” or “insufficient”. An endometrial biopsy is a key step in diagnosis of endometrial cancer, biopsies are viewed and diagnosed by pathologists. Pathology is increasingly digitised, with slides viewed as images on screens rather than through the lens of a microscope. The availability of these images is driving automation via the application of AI. A model that classifies slides in the manner proposed would allow prioritisation of these slides for pathologist review and hence reduce time to diagnosis for patients with cancer. Previous studies using AI on endometrial biopsies have examined slightly different tasks, for example using images alongside genomic data to differentiate between cancer subtypes. We took 2909 slides with “malignant” and “other or benign” areas annotated by pathologists. A fully supervised convolutional neural network (CNN) model was trained to calculate the probability of a patch from the slide being “malignant” or “other or benign”. Heatmaps of all the patches on each slide were then produced to show malignant areas. These heatmaps were used to train a slide classification model to give the final slide categorisation as either “malignant”, “other or benign” or “insufficient”. The final model was able to accurately classify 90% of all slides correctly and 97% of slides in the malignant class; this accuracy is good enough to allow prioritisation of pathologists’ workload.