Impact of train- and test-time Hounsfield unit window variation on CT segmentation of liver lesions

Z. Abboud; S. Kadoury

doi:10.1117/12.2653974

3 April 2023 Impact of train- and test-time Hounsfield unit window variation on CT segmentation of liver lesions

Z. Abboud, S. Kadoury

Proceedings Volume 12464, Medical Imaging 2023: Image Processing; 124642E (2023) https://doi.org/10.1117/12.2653974
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Conference Poster

Abstract

Data preprocessing is an important step in a deep learning pipeline. Within the context of computed tomography image segmentation, preprocessing includes a Hounsfield unit (HU) windowing step. HU windowing ensures that the contrast of the region of interest is maximized to highlight the important features for the given task. HU windowing is defined by the window level and width. There are general guidelines for optimal window level and width for a given tissue, however, there’s a certain degree of subjectivity involved within the setting. Moreover, the CT imaging protocol and the type of scan (contrast-enhanced vs. none) has an impact on the HU window. In this paper, we evaluate the impact of varying the HU window level and window width at both training and test time to assess whether liver lesion segmentation models can generalize to different contrasts in input data, as well as a method for estimating uncertainty within the task. The experiments show that HU windowing can have a significant impact on model performance at train and test times. Moreover, we show that HU variation at test time is a computationally cheap alternative to test-time augmentation through spatial transformation for estimating uncertainty.

Citation Download Citation

Z. Abboud and S. Kadoury "Impact of train- and test-time Hounsfield unit window variation on CT segmentation of liver lesions", Proc. SPIE 12464, Medical Imaging 2023: Image Processing, 124642E (3 April 2023); https://doi.org/10.1117/12.2653974

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