Improving the repeatability of deep learning models with Monte Carlo dropout

1 code implementation • 15 Feb 2022 • Andreanne Lemay, Katharina Hoebel, Christopher P. Bridge, Brian Befano, Silvia de Sanjosé, Diden Egemen, Ana Cecilia Rodriguez, Mark Schiffman, John Peter Campbell, Jayashree Kalpathy-Cramer

During model development and evaluation, much attention is given to classification performance while model repeatability is rarely assessed, leading to the development of models that are unusable in clinical practice.

Attribute Binary Classification +6

Searching beyond the usual papillomavirus suspects in squamous carcinomas of the vulva, penis and head and neck

no code implementations • 6 Nov 2020 • Marta Félez-Sánchez, Marleny Vergara, Silvia de Sanjosé, Xavier Castellsagué, Laia Alemany, Ignacio Bravo

In head and neck carcinoma samples (n = 1141), we recovered DNA from two BetaHPVs, namely HPV20 and HPV21, and from three cutaneous AlphaPVs, namely HPV2, HPV57 and HPV61.