Robust deep labeling of radiological emphysema subtypes using squeeze and excitation convolutional neural networks: The MESA Lung and SPIROMICS Studies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wysoczanski, Artur, Ettehadi, Nabil, Arabshahi, Soroush, Sun, Yifei, Stukovsky, Karen Hinkley, Watson, Karol E., Han, MeiLan K., Michos, Erin D, Comellas, Alejandro P., Hoffman, Eric A., Laine, Andrew F., Barr, R. Graham, Angelini, Elsa D.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916143651880960
author Wysoczanski, Artur
Ettehadi, Nabil
Arabshahi, Soroush
Sun, Yifei
Stukovsky, Karen Hinkley
Watson, Karol E.
Han, MeiLan K.
Michos, Erin D
Comellas, Alejandro P.
Hoffman, Eric A.
Laine, Andrew F.
Barr, R. Graham
Angelini, Elsa D.
author_facet Wysoczanski, Artur
Ettehadi, Nabil
Arabshahi, Soroush
Sun, Yifei
Stukovsky, Karen Hinkley
Watson, Karol E.
Han, MeiLan K.
Michos, Erin D
Comellas, Alejandro P.
Hoffman, Eric A.
Laine, Andrew F.
Barr, R. Graham
Angelini, Elsa D.
contents Pulmonary emphysema, the progressive, irreversible loss of lung tissue, is conventionally categorized into three subtypes identifiable on pathology and on lung computed tomography (CT) images. Recent work has led to the unsupervised learning of ten spatially-informed lung texture patterns (sLTPs) on lung CT, representing distinct patterns of emphysematous lung parenchyma based on both textural appearance and spatial location within the lung, and which aggregate into 6 robust and reproducible CT Emphysema Subtypes (CTES). Existing methods for sLTP segmentation, however, are slow and highly sensitive to changes in CT acquisition protocol. In this work, we present a robust 3-D squeeze-and-excitation CNN for supervised classification of sLTPs and CTES on lung CT. Our results demonstrate that this model achieves accurate and reproducible sLTP segmentation on lung CTscans, across two independent cohorts and independently of scanner manufacturer and model.
format Preprint
id arxiv_https___arxiv_org_abs_2403_00257
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust deep labeling of radiological emphysema subtypes using squeeze and excitation convolutional neural networks: The MESA Lung and SPIROMICS Studies
Wysoczanski, Artur
Ettehadi, Nabil
Arabshahi, Soroush
Sun, Yifei
Stukovsky, Karen Hinkley
Watson, Karol E.
Han, MeiLan K.
Michos, Erin D
Comellas, Alejandro P.
Hoffman, Eric A.
Laine, Andrew F.
Barr, R. Graham
Angelini, Elsa D.
Computer Vision and Pattern Recognition
Machine Learning
Pulmonary emphysema, the progressive, irreversible loss of lung tissue, is conventionally categorized into three subtypes identifiable on pathology and on lung computed tomography (CT) images. Recent work has led to the unsupervised learning of ten spatially-informed lung texture patterns (sLTPs) on lung CT, representing distinct patterns of emphysematous lung parenchyma based on both textural appearance and spatial location within the lung, and which aggregate into 6 robust and reproducible CT Emphysema Subtypes (CTES). Existing methods for sLTP segmentation, however, are slow and highly sensitive to changes in CT acquisition protocol. In this work, we present a robust 3-D squeeze-and-excitation CNN for supervised classification of sLTPs and CTES on lung CT. Our results demonstrate that this model achieves accurate and reproducible sLTP segmentation on lung CTscans, across two independent cohorts and independently of scanner manufacturer and model.
title Robust deep labeling of radiological emphysema subtypes using squeeze and excitation convolutional neural networks: The MESA Lung and SPIROMICS Studies
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2403.00257