Robust Quantification of Percent Emphysema on CT via Domain Attention: the Multi-Ethnic Study of Atherosclerosis (MESA) Lung Study

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xuzhe, Angelini, Elsa D., Hoffman, Eric A., Watson, Karol E., Smith, Benjamin M., Barr, R. Graham, Laine, Andrew F.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911789953843200
author Zhang, Xuzhe
Angelini, Elsa D.
Hoffman, Eric A.
Watson, Karol E.
Smith, Benjamin M.
Barr, R. Graham
Laine, Andrew F.
author_facet Zhang, Xuzhe
Angelini, Elsa D.
Hoffman, Eric A.
Watson, Karol E.
Smith, Benjamin M.
Barr, R. Graham
Laine, Andrew F.
contents Robust quantification of pulmonary emphysema on computed tomography (CT) remains challenging for large-scale research studies that involve scans from different scanner types and for translation to clinical scans. Existing studies have explored several directions to tackle this challenge, including density correction, noise filtering, regression, hidden Markov measure field (HMMF) model-based segmentation, and volume-adjusted lung density. Despite some promising results, previous studies either required a tedious workflow or limited opportunities for downstream emphysema subtyping, limiting efficient adaptation on a large-scale study. To alleviate this dilemma, we developed an end-to-end deep learning framework based on an existing HMMF segmentation framework. We first demonstrate that a regular UNet cannot replicate the existing HMMF results because of the lack of scanner priors. We then design a novel domain attention block to fuse image feature with quantitative scanner priors which significantly improves the results.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18383
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust Quantification of Percent Emphysema on CT via Domain Attention: the Multi-Ethnic Study of Atherosclerosis (MESA) Lung Study
Zhang, Xuzhe
Angelini, Elsa D.
Hoffman, Eric A.
Watson, Karol E.
Smith, Benjamin M.
Barr, R. Graham
Laine, Andrew F.
Computer Vision and Pattern Recognition
Robust quantification of pulmonary emphysema on computed tomography (CT) remains challenging for large-scale research studies that involve scans from different scanner types and for translation to clinical scans. Existing studies have explored several directions to tackle this challenge, including density correction, noise filtering, regression, hidden Markov measure field (HMMF) model-based segmentation, and volume-adjusted lung density. Despite some promising results, previous studies either required a tedious workflow or limited opportunities for downstream emphysema subtyping, limiting efficient adaptation on a large-scale study. To alleviate this dilemma, we developed an end-to-end deep learning framework based on an existing HMMF segmentation framework. We first demonstrate that a regular UNet cannot replicate the existing HMMF results because of the lack of scanner priors. We then design a novel domain attention block to fuse image feature with quantitative scanner priors which significantly improves the results.
title Robust Quantification of Percent Emphysema on CT via Domain Attention: the Multi-Ethnic Study of Atherosclerosis (MESA) Lung Study
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.18383