TY - JOUR
T1 - A homological approach to a mathematical definition of pulmonary fibrosis and emphysema on computed tomography
AU - Tanabe, Naoya
AU - Kaji, Shizuo
AU - Sato, Susumu
AU - Yokoyama, Tomoo
AU - Oguma, Tsuyoshi
AU - Tanizawa, Kiminobu
AU - Handa, Tomohiro
AU - Sakajo, Takashi
AU - Hirai, Toyohiro
N1 - Funding Information:
K. Tanizawa worked for the Department of Respiratory Care and Sleep Control Medicine at Kyoto University, which was funded by endowments from Philips Respironics, Teijin Pharma Ltd., Fukuda Denshi Inc., and Fukuda Lifetec Keiji, until January 2017. The other authors have no conflicts of interest to declare.
Funding Information:
This study was partially supported by Fujifilm and JST Mirai 18G3 and MathClinic at the Graduate School of Science, Kyoto University.
Publisher Copyright:
Copyright © 2021 The Authors.
PY - 2021/8
Y1 - 2021/8
N2 - Three-dimensional imaging is essential to evaluate local abnormalities and understand structure-function relationships in an organ. However, quantifiable and interpretable methods to localize abnormalities remain unestablished. Visual assessments are prone to bias, machine learning methods depend on training images, and the underlying decision principle is usually difficult to interpret. Here, we developed a homological approach to mathematically define emphysema and fibrosis in the lungs on computed tomography (CT). With the use of persistent homology, the density of homological features, including connected components, tunnels, and voids, was extracted from the volumetric CT scans of lung diseases. A pair of CT values at which each homological feature appeared (birth) and disappeared (death) was computed by sweeping the threshold levels from higher to lower CT values. Consequently, fibrosis and emphysema were defined as voxels with dense voids having a longer lifetime (birth-death difference) and voxels with dense connected components having a lower birth, respectively. In an independent dataset including subjects with idiopathic pulmonary fibrosis (IPF), chronic obstructive pulmonary disease (COPD), and combined pulmonary fibrosis and emphysema (CPFE), the proposed definition enabled accurate segmentation with comparable quality to deep learning in terms of Dice coefficients. Persistent homology-defined fibrosis was closely associated with physiological abnormalities such as impaired diffusion capacity and long-term mortality in subjects with IPF and CPFE, and persistent homology-defined emphysema was associated with impaired diffusion capacity in subjects with COPD. The present persistent homology-based evaluation of structural abnormalities could help explore the clinical and physiological impacts of structural changes and morphological mechanisms of disease progression. NEW & NOTEWORTHY This study proposes a homological approach to mathematically define a three-dimensional texture feature of emphysema and fibrosis on chest computed tomography using persistent homology. The proposed definition enabled accurate segmentation with comparable quality to deep learning while offering higher interpretability than deep learning-based methods.
AB - Three-dimensional imaging is essential to evaluate local abnormalities and understand structure-function relationships in an organ. However, quantifiable and interpretable methods to localize abnormalities remain unestablished. Visual assessments are prone to bias, machine learning methods depend on training images, and the underlying decision principle is usually difficult to interpret. Here, we developed a homological approach to mathematically define emphysema and fibrosis in the lungs on computed tomography (CT). With the use of persistent homology, the density of homological features, including connected components, tunnels, and voids, was extracted from the volumetric CT scans of lung diseases. A pair of CT values at which each homological feature appeared (birth) and disappeared (death) was computed by sweeping the threshold levels from higher to lower CT values. Consequently, fibrosis and emphysema were defined as voxels with dense voids having a longer lifetime (birth-death difference) and voxels with dense connected components having a lower birth, respectively. In an independent dataset including subjects with idiopathic pulmonary fibrosis (IPF), chronic obstructive pulmonary disease (COPD), and combined pulmonary fibrosis and emphysema (CPFE), the proposed definition enabled accurate segmentation with comparable quality to deep learning in terms of Dice coefficients. Persistent homology-defined fibrosis was closely associated with physiological abnormalities such as impaired diffusion capacity and long-term mortality in subjects with IPF and CPFE, and persistent homology-defined emphysema was associated with impaired diffusion capacity in subjects with COPD. The present persistent homology-based evaluation of structural abnormalities could help explore the clinical and physiological impacts of structural changes and morphological mechanisms of disease progression. NEW & NOTEWORTHY This study proposes a homological approach to mathematically define a three-dimensional texture feature of emphysema and fibrosis on chest computed tomography using persistent homology. The proposed definition enabled accurate segmentation with comparable quality to deep learning while offering higher interpretability than deep learning-based methods.
UR - http://www.scopus.com/inward/record.url?scp=85113696447&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85113696447&partnerID=8YFLogxK
U2 - 10.1152/japplphysiol.00150.2021
DO - 10.1152/japplphysiol.00150.2021
M3 - Article
C2 - 34138650
AN - SCOPUS:85113696447
VL - 131
SP - 601
EP - 612
JO - Journal of Applied Physiology
JF - Journal of Applied Physiology
SN - 8750-7587
IS - 2
ER -