Predicting Pulmonary Function Abnormalities with a Texture-Based Quantification of Normal Lung Parenchyma in Chest Computed Tomography
Principal Investigator
Name
Alysson Carvalho
Degrees
M.D., Ph.D.
Institution
ID'Or Institute Research and Education
Position Title
Professor
Email
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-1223
Initial CDAS Request Approval
Apr 2, 2024
Title
Predicting Pulmonary Function Abnormalities with a Texture-Based Quantification of Normal Lung Parenchyma in Chest Computed Tomography
Summary
Purposes: To predict pulmonary function abnormalities (restrictive and/or obstructive patterns) with the texture-based convolutional neural networks (CNN) quantification of normal lung index (NLI) on conventional and low-dose chest CT images.
Methods: Two CNNs were trained for automatic lung segmentation and classification of low- (LAAs; emphysema, cysts), normal- (NAAs; normal parenchyma), and high-attenuation areas (HAAs; ground-glass opacities, crazy paving/linear opacity, consolidation). NLI was calculated as NLI(%)=100x[NAA/(LAA + NAA + HAA)]. We assessed 880 conventional CT scans from 176 normal subjects, 343 patients with emphysema, 68 with lymphangioleiomyomatosis (LAM) and 293 patients with interstitial lung disease (ILD). A Receiver Operating Characteristic (ROC) analysis was used to assess the performance of NLI to distinguish controls from emphysema, LAM and ILD patients with abnormal pulmonary function tests (PFTs). The criteria used to define normal spirometry findings were a prebronchodilator percent of FVC exhaled in first second related to the forced vital capacity (FEV1/FVC) greater than or equal to 70% and lower or equal 90% and FVC% and FEV1% values greater than or equal to 80%.
Preliminary Results: Out of 880 subjects, 161 controls, 86 patients with emphysema, 34 LAM and 77 ILD subjects were considered as having normal PFTs. NLI 5, 50 and 95% percentiles in healthy control subjects were 93.1, 99.6 and 99.9%, respectively. A reference equation for NLI was also generated: NLI (mL) = 842*Sex (1 = male, 0 = female) + 4164 * Height (m) - 2451 (R2 = 0.55, adjusted R2 = 0.55, F-statistic = 101 and P < 0.0001).
The NLI threshold of 96.1% (AUC = 0.96, 95%CI 0.94–0.99, sensitivity of 0.91 and specificity of 0.88, accuracy of 0,88 and F1-Score of 0,75) was able to differentiate controls from patients with abnormal PFTs.
Methods: Two CNNs were trained for automatic lung segmentation and classification of low- (LAAs; emphysema, cysts), normal- (NAAs; normal parenchyma), and high-attenuation areas (HAAs; ground-glass opacities, crazy paving/linear opacity, consolidation). NLI was calculated as NLI(%)=100x[NAA/(LAA + NAA + HAA)]. We assessed 880 conventional CT scans from 176 normal subjects, 343 patients with emphysema, 68 with lymphangioleiomyomatosis (LAM) and 293 patients with interstitial lung disease (ILD). A Receiver Operating Characteristic (ROC) analysis was used to assess the performance of NLI to distinguish controls from emphysema, LAM and ILD patients with abnormal pulmonary function tests (PFTs). The criteria used to define normal spirometry findings were a prebronchodilator percent of FVC exhaled in first second related to the forced vital capacity (FEV1/FVC) greater than or equal to 70% and lower or equal 90% and FVC% and FEV1% values greater than or equal to 80%.
Preliminary Results: Out of 880 subjects, 161 controls, 86 patients with emphysema, 34 LAM and 77 ILD subjects were considered as having normal PFTs. NLI 5, 50 and 95% percentiles in healthy control subjects were 93.1, 99.6 and 99.9%, respectively. A reference equation for NLI was also generated: NLI (mL) = 842*Sex (1 = male, 0 = female) + 4164 * Height (m) - 2451 (R2 = 0.55, adjusted R2 = 0.55, F-statistic = 101 and P < 0.0001).
The NLI threshold of 96.1% (AUC = 0.96, 95%CI 0.94–0.99, sensitivity of 0.91 and specificity of 0.88, accuracy of 0,88 and F1-Score of 0,75) was able to differentiate controls from patients with abnormal PFTs.
Aims
1) To compare NLI detection on conventional and low-dose chest CT images.
2) To evaluate the accuracy of the previously assessed NLI threshold on low-dose chest CT images from the NSLT dataset.
3) Evaluate new possibilities of prediction using a RESNET classifier using CT scan-derived lung parenchyma images.
Collaborators
1) Alan Guimarães3, PhD.
2) Errison Alves, MSc.
3) Rodrigo Basilio, PhD.
4) Rosana Souza Rodrigues MD, PhD.
5) Bruno Hochhegger, MD, PhD.