St Andrews research shows automated sorting can diagnose cancer faster
Scientists say method helps pathologists prioritize malignant biopsies
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.
END
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.
END