Deep neural networks trained for segmentation are sensitive to brightness changes: preliminary results

Zhe Zhu; Mustafa R. Bashir; Maciej A. Mazurowski

doi:10.1117/12.2582190

15 February 2021 Deep neural networks trained for segmentation are sensitive to brightness changes: preliminary results

Zhe Zhu, Mustafa R. Bashir, Maciej A. Mazurowski

Proceedings Volume 11597, Medical Imaging 2021: Computer-Aided Diagnosis; 1159729 (2021) https://doi.org/10.1117/12.2582190
Event: SPIE Medical Imaging, 2021, Online Only

Conference Poster

Abstract

Medical images of a patient may have a significantly different appearance depending on imaging modality (e.g. MRI vs. CT), sequence type (e.g., T1-weighted MRI vs. T2-weighted MRI), and even manufacturer/model of equipment used for the same modality and sequence type (e.g. SIEMENS vs GE). Since in the context of deep learning training and test data often come from different institutions, it is important to determine how well neural networks generalize when image appearance varies. There is currently no systematic answer to this question. In this study, we investigate how deep neural networks trained for segmentation generalize. Our analysis is based on synthesizing a series of datasets of images with the target object of the same shape but with varying pixel intensity of the foreground object and the background. This simulates basic effects of changing equipment models and sequence types. We also consider scenarios when datasets with different image properties are combined to determine whether generalizability of the network to other scenarios is improved. We found that the generalizability of segmentation networks to changing intensities is poor. We also found that the generalizability is somewhat improved when different datasets are combined but that generalizability is typically limited to data similar to the two types of datasets included in training and not to datasets with different image intensities.

Conference Presentation

Citation Download Citation

Zhe Zhu, Mustafa R. Bashir, and Maciej A. Mazurowski "Deep neural networks trained for segmentation are sensitive to brightness changes: preliminary results", Proc. SPIE 11597, Medical Imaging 2021: Computer-Aided Diagnosis, 1159729 (15 February 2021); https://doi.org/10.1117/12.2582190

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

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.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available