PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The high incidence of BCC skin cancer caused that the amount of work for pathologists has risen to unprecedented levels. Acquiring outlined annotations for training deep learning models classifying BCC is often tedious and time consuming. End-to-end learning provides relief in labelling data by using a single label to predict an clinical outcome. We compared multiple-instance-learning (MIL) and a streaming performance for detecting BCC in 420 slides collected from 72 BCC positive patients. This resulted in an ROC with AUC of 0.96 and 0.98 for respectively streaming and MIL. Saliency and probability maps showed that both methods were capable of classifying classifying BCC in an end-to-end way with single labels.
D. J. Geijs,H. Pinckaers,A. L. Amir, andG. J. S. Litjens
"End-to-end classification on basal-cell carcinoma histopathology whole-slides images", Proc. SPIE 11603, Medical Imaging 2021: Digital Pathology, 1160307 (15 February 2021); https://doi.org/10.1117/12.2581042
ACCESS THE FULL ARTICLE
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
D. J. Geijs, H. Pinckaers, A. L. Amir, G. J. S. Litjens, "End-to-end classification on basal-cell carcinoma histopathology whole-slides images," Proc. SPIE 11603, Medical Imaging 2021: Digital Pathology, 1160307 (15 February 2021); https://doi.org/10.1117/12.2581042