Generalisation of automatic tumour segmentation in histopathological whole-slide images across multiple cancer types
By: Ole-Johan Skrede , Manohar Pradhan , Maria Xepapadakis Isaksen and more
Potential Business Impact:
Finds cancer in tissue slides automatically.
Deep learning is expected to aid pathologists by automating tasks such as tumour segmentation. We aimed to develop one universal tumour segmentation model for histopathological images and examine its performance in different cancer types. The model was developed using over 20 000 whole-slide images from over 4 000 patients with colorectal, endometrial, lung, or prostate carcinoma. Performance was validated in pre-planned analyses on external cohorts with over 3 000 patients across six cancer types. Exploratory analyses included over 1 500 additional patients from The Cancer Genome Atlas. Average Dice coefficient was over 80% in all validation cohorts with en bloc resection specimens and in The Cancer Genome Atlas cohorts. No loss of performance was observed when comparing the universal model with models specialised on single cancer types. In conclusion, extensive and rigorous evaluations demonstrate that generic tumour segmentation by a single model is possible across cancer types, patient populations, sample preparations, and slide scanners.
Similar Papers
An ensemble deep learning approach to detect tumors on Mohs micrographic surgery slides
CV and Pattern Recognition
Helps doctors find skin cancer faster.
TUMLS: Trustful Fully Unsupervised Multi-Level Segmentation for Whole Slide Images of Histology
Image and Video Processing
Helps doctors see tiny cell details faster.
A Multi-Modal Deep Learning Framework for Colorectal Pathology Diagnosis: Integrating Histological and Colonoscopy Data in a Pilot Study
CV and Pattern Recognition
Helps doctors find gut diseases faster.