Comparing Bayesian Models for Organ Contouring in Headand Neck Radiotherapy

11/01/2021
by   Prerak Mody, et al.
3

Deep learning models for organ contouring in radiotherapy are poised for clinical usage, but currently, there exist few tools for automated quality assessment (QA) of the predicted contours. Using Bayesian models and their associated uncertainty, one can potentially automate the process of detecting inaccurate predictions. We investigate two Bayesian models for auto-contouring, DropOut and FlipOut, using a quantitative measure - expected calibration error (ECE) and a qualitative measure - region-based accuracy-vs-uncertainty (R-AvU) graphs. It is well understood that a model should have low ECE to be considered trustworthy. However, in a QA context, a model should also have high uncertainty in inaccurate regions and low uncertainty in accurate regions. Such behaviour could direct visual attention of expert users to potentially inaccurate regions, leading to a speed up in the QA process. Using R-AvU graphs, we qualitatively compare the behaviour of different models in accurate and inaccurate regions. Experiments are conducted on the MICCAI2015 Head and Neck Segmentation Challenge and on the DeepMindTCIA CT dataset using three models: DropOut-DICE, Dropout-CE (Cross Entropy) and FlipOut-CE. Quantitative results show that DropOut-DICE has the highest ECE, while Dropout-CE and FlipOut-CE have the lowest ECE. To better understand the difference between DropOut-CE and FlipOut-CE, we use the R-AvU graph which shows that FlipOut-CE has better uncertainty coverage in inaccurate regions than DropOut-CE. Such a combination of quantitative and qualitative metrics explores a new approach that helps to select which model can be deployed as a QA tool in clinical settings.

READ FULL TEXT
research
08/31/2021

Uncertainty Quantified Deep Learning for Predicting Dice Coefficient of Digital Histopathology Image Segmentation

Deep learning models (DLMs) can achieve state of the art performance in ...
research
06/06/2015

Dropout as a Bayesian Approximation: Appendix

We show that a neural network with arbitrary depth and non-linearities, ...
research
05/24/2023

Sampling-based Uncertainty Estimation for an Instance Segmentation Network

The examination of uncertainty in the predictions of machine learning (M...
research
06/06/2015

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

Deep learning tools have gained tremendous attention in applied machine ...
research
08/21/2023

Automated Identification of Failure Cases in Organ at Risk Segmentation Using Distance Metrics: A Study on CT Data

Automated organ at risk (OAR) segmentation is crucial for radiation ther...
research
02/12/2020

Learnable Bernoulli Dropout for Bayesian Deep Learning

In this work, we propose learnable Bernoulli dropout (LBD), a new model-...

Please sign up or login with your details

Forgot password? Click here to reset