Search Results for author: John Peter Campbell

Found 3 papers, 3 papers with code

Improving the repeatability of deep learning models with Monte Carlo dropout

1 code implementation15 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

Monte Carlo dropout increases model repeatability

1 code implementation12 Nov 2021 Andreanne Lemay, Katharina Hoebel, Christopher P. Bridge, Didem Egemen, Ana Cecilia Rodriguez, Mark Schiffman, John Peter Campbell, Jayashree Kalpathy-Cramer

Leveraging Monte Carlo predictions significantly increased repeatability for all tasks on the binary, multi-class, and ordinal models leading to an average reduction of the 95% limits of agreement by 17% points.

Classification Density Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.