Thesis Details
Deep Learning Model Uncertainty in Medical Image Analysis
This thesis deals with quantifying uncertainty in the predictions of deep learning models. While they achieve state of the art results in many areas of computer vision, their outputs are usually deterministic and provide by themselves little information about how certain the model is about its prediction. This is important especially in the domain of medical image analysis where mistakes are costly and the ability to filter uncertain predictions would allow a supervising physician to review the relevant cases. This work applies several different uncertainty measures developed in recent research to deep learning models trained on a cephalometric landmark localization task. They are then evaluated and compared in a set of experiments which aim to determine whether each of the uncertainty measures provides us with useful information about the model's confidence in its predictions.
deep learning, uncertainty, medical image analysis, landmark detection, cephalometry
Burget Radim, Doc. Ing., Ph.D. (UTKO FEEC BUT), člen
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Hradiš Michal, Ing., Ph.D. (DCGM FIT BUT), člen
Szőke Igor, Ing., Ph.D. (DCGM FIT BUT), člen
@mastersthesis{FITMT22094,
author = "Du\v{s}an Drevick\'{y}",
type = "Master's thesis",
title = "Deep Learning Model Uncertainty in Medical Image Analysis",
school = "Brno University of Technology, Faculty of Information Technology",
year = 2019,
location = "Brno, CZ",
language = "english",
url = "https://www.fit.vut.cz/study/thesis/22094/"
}