CHCharles R. Hatt

Charles R. Hatt

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Charles R. Hatt has a total of 274 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Machine Learning Outperforms Traditional Quantitative Methods for CT-based COPD Diagnosis: An Analysis of the National Lung Cancer Screening Trial

    by Charles Hatt, Wassim Labaki, Craig Galban, Ella Kazerooni, Catherine Meldrum, Lantian Xu, Susan Murray, Michael Sjoding, Amanda Cox, Amal Othman, et al.

    Chronic obstructive pulmonary disease (COPD) remains underdiagnosed, even among patients undergoing lung cancer screening. Recent advances in deep learning, including task-specific convolutional neural networks (CNNs) and task-agnostic foundation models (e.g. Pillar-0), offer an opportunity to improve COPD risk prediction from low-dose CT and enable targeted spirometry within screening programs. We included 5,971 National Lung Screening Trial (NLST) participants with low-dose CT, spirometry, and clinical data, excluding scans with interstitial lung disease. COPD was defined as post-bronchodilator FEV₁/FVC <0.70. Three random forest risk models were developed by combining clinical variables with CT-derived imaging features: (1) a COPD-specific CNN probability, (2) Pillar-0 chest CT embeddings trained to predict COPD, or (3) Low attenuation area (LAA). Imaging models were trained on 10,957 COPDGene CTs and applied to NLST. Performance was assessed using area under the receiver operating characteristic curve (AUC). In participants ≥65 years, CNN- and Pillar-0–based risk models performed similarly in men (AUC 0.849 vs 0.827, p=0.21) and women (AUC 0.838 vs 0.823, p=0.48). In participants <65 years, CNN-based models outperformed Pillar-0 models in both men (AUC 0.859 vs 0.805, p<0.001) and women (AUC 0.861 vs 0.821, p<0.001). CNN and Pillar-0-based risk models outperformed all LAA-based risk models. These results show that machine learning improves COPD risk prediction vs LAA in lung cancer screening CT imaging. erj;68/suppl_70/PA2498/F1 F1 F1

  • A Quantitative Imaging Measure of Progressive Pulmonary Fibrosis

    by Jennifer M. Wang, Ayodeji Adegunsoye, Janelle Vu Pugashetti, Cathryn T. Lee, Susan Murray, Nisha Mohan, Nazanin Nazemi, Edward Kang, Lydia Chelala, Ella A. Kazerooni, et al.

    Rationale: Progressive pulmonary fibrosis (PPF) is common in patients with fibrotic interstitial lung disease (ILD) and leads to high mortality. Although PPF guideline criteria include computed tomography (CT)-based progression, these measures are qualitative and prone to interreader variability. Quantitative computed tomography (qCT) measurements have the potential to overcome this limitation. Objectives: The objectives of this study were to determine whether changes in qCT measures of pulmonary fibrosis are associated with transplant-free survival (TFS) in a diverse ILD cohort and establish a quantitative computed tomography measure of progressive pulmonary fibrosis (qctPPF). Methods: A retrospective cohort analysis was performed in individuals with fibrotic ILD, including idiopathic pulmonary fibrosis (n = 350), who underwent serial chest CT for clinical indications. Commercially available software was used to generate qCT measures of pulmonary fibrosis, which were tested for association with 2-year TFS using a multivariable Cox proportional hazards model. Iterative modeling was then performed to develop a composite qctPPF measure. Results were validated in an independent ILD cohort (n = 92). Measurements and Main Results: Increasing ground-glass opacity and decreasing lung volume showed consistent association with decreased TFS across cohorts when modeled continuously and dichotomously. qctPPF classification was associated with a greater than threefold increased hazard of death or transplant in the test (hazard ratio, 4.41; 95% confidence interval, 2.77–7.03) and validation (hazard ratio, 3.54; 95% confidence interval, 1.62–7.71) cohorts. Agreement between qctPPF and radiologist-determined PPF was poor (κ = 0.20), with qctPPF classification maintaining prognostic significance when discordant with radiologist interpretation. Conclusions: Changes in qCT measures are associated with clinically relevant outcomes and could improve PPF classification.


  • Quantitative Computed Tomography Measures of Lung Fibrosis and Outcomes in the National Lung Screening Trial

    by Jennifer M. Wang, Swaraj Bose, Susan Murray, Wassim W. Labaki, Ella A. Kazerooni, Jonathan H. Chung, Kevin R. Flaherty, MeiLan K. Han, Charles R. Hatt, Justin M. Oldham

    Rationale: Incidental features of interstitial lung disease (ILD) are commonly observed on chest computed tomography (CT) scans and are independently associated with poor outcomes. Although most studies to date have relied on qualitative assessments of ILD, quantitative imaging algorithms have the potential to effectively detect ILD and assist in risk stratification for population-based cohorts. Objectives: To determine whether quantitative measures of ILD are associated with clinically relevant outcomes in the NLST (National Lung Screening Trial). Methods: Quantitative measures of ILD were generated using low-dose CT (LDCT) data collected as part of the NLST and processed with Computer-Aided Lung Informatics for Pathology Evaluation and Ratings (CALIPER) and deep learning–based usual interstitial pneumonia (DL-UIP) algorithms (Imbio Inc.). A multivariable Cox proportional hazard regression model was used to test the association between ILD measures (percentage ground-glass opacity, reticular opacity, and honeycombing of total lung volume and binary DL-UIP classification) and all-cause mortality. Secondary outcomes of incident lung cancer and lung cancer mortality were also explored. Results: Quantitative CT data were generated in 11,518 individuals. Mean age was 61.5 years, and 58.7% were male. An increased risk of all-cause mortality was observed for each percentage increase in CALIPER-derived ground-glass opacity (hazard ratio [HR], 1.02; 95% confidence interval [CI], 1.01–1.02), reticular opacity (HR, 1.18; 95% CI, 1.12–1.24), and honeycombing (HR, 6.23; 95% CI, 4.23–9.16). Individuals with a positive DL-UIP classification pattern had a 4.8-fold increased risk of all-cause mortality (HR, 4.75; 95% CI, 2.50–9.04). CALIPER-derived reticular opacity was also associated with increased lung cancer–specific mortality. No quantitative measures of ILD were associated with incident lung cancer. Conclusions: Quantitative measures of ILD on LDCT are associated with clinically relevant endpoints in a large at-risk population of individuals with tobacco use history.


  • Temporal Exploration of Chronic Obstructive Pulmonary Disease Phenotypes: Insights from the COPDGene and SPIROMICS Cohorts

    by Alexander J. Bell, Sundaresh Ram, Wassim W. Labaki, Susan Murray, Ella A. Kazerooni, Stefanie Galban, Fernando J. Martinez, Charles R. Hatt, Jennifer M. Wang, Vladimir Ivanov, et al.

    Rationale: Chronic obstructive pulmonary disease (COPD) exhibits considerable progression heterogeneity. We hypothesized that elastic principal graph analysis (EPGA) would identify distinct clinical phenotypes and their longitudinal relationships. Objectives: Our primary objective was to create a map of COPD phenotypes and their connectivity using EPGA. Secondarily, we used longitudinal and external data sets to test the validity and reproducibility of this map. Methods: Cross-sectional data from 8,972 tobacco-exposed COPDGene participants, with and without COPD, were used to train a model with EPGA, using thirty clinical, physiologic and CT features. 4,585 participants from COPDGene Phase 2 were used to test longitudinal trajectories. 2,652 participants from SPIROMICS tested external reproducibility. Measurements and Main Results: Our analysis used cross-sectional data to create an elastic principal tree, where time is associated with distance on the tree. Six clinically distinct tree segments were identified that differed by lung function, symptoms, and CT features: Subclinical (SC); Parenchymal Abnormality (PA); Chronic Bronchitis (CB); Emphysema Male (EM); Emphysema Female (EF); and Severe Airways (SA) disease. 5-year data from COPDGene mapped longitudinal changes onto the tree, and longitudinal trajectories demonstrated a net flow of patients from SC towards EM and EF, including trajectories through airway disease predominant phenotypes, CB and SA. Cross-sectional SPIROMICS data projected onto the tree showed clinically similar patient groupings. Conclusions: This novel analytic methodology provides an approach to defining longitudinal phenotypic trajectories using cross sectional data. These insights are clinically relevant and could facilitate precision therapy and future trials to modify disease progression.


  • Response

    by Charles Hatt, Jonathan H. Chung, Justin M. Oldham

  • A Deep Learning-Based Radiomic Classifier for Usual Interstitial Pneumonia

    by Jonathan H. Chung, Lydia Chelala, Janelle Vu Pugashetti, Jennifer M. Wang, Ayodeji Adegunsoye, Alexander W. Matyga, Lauren Keith, Kai Ludwig, Sahar Zafari, Sahand Ghodrati, et al.


  • Open Access

    Fully automated pipeline for measurement of the thoracic aorta using joint segmentation and localization neural network

    by Sudeep Katakol, Timothy J. Baker, Zhangxing Bian, Yanglong Lu, Greg Spahlinger, Charles R. Hatt, Nicholas S. Burris

    Thoracic aortic aneurysm (TAA) is a common disease affecting between 1% and 3% of the United States population over the age of 50, which is characterized by enlargement of the largest artery in the body (i.e., the thoracic aorta) as a result of weakening of the aortic wall.1 TAA is a largely silent disease until potentially fatal complications, such as rupture, occur. Patients with TAA undergo regular surveillance imaging using computed tomography angiography (CTA) to monitor the overall size of their aneurysm and to detect growth, assessments that in turn determine the need for surgical repair.2 Aortic diameter measurements are used to assess TAA, with measurements performed on volumetric CTA imaging data by manual analysts (i.e., technologists or the physicians themselves) using dedicated three-dimensional (3D) image rendering software. Diameter measurements are made in standardized anatomic locations along the length of the aorta to minimize measurement variability and ensure comparability of measurements across time.3,4


  • Residual Volume versus FRC Computed Tomography Assessment of Functional Small Airway Disease in Smokers with and without Chronic Obstructive Pulmonary Disease

    by Alejandro P. Comellas, John D. Newell, Miranda Kirby, Jered P. Sieren, Sam Peterson, Charles Hatt, Craig J. Galban, Ella A. Kazerooni, David A. Lynch, MeiLan K. Han, et al.


  • Open Access

    Lung Cancer Lesion Detection in Histopathology Images Using Graph-Based Sparse PCA Network

    by Sundaresh Ram, Wenfei Tang, Alexander J. Bell, Cara Spencer, Alexander Buschhaus, Charles R. Hatt, Marina Pasca Dimagliano, Jeffrey J. Rodriguez, Stefanie Galban, Craig J. Galban

    Early detection of lung cancer is critical for improvement of patient survival. To address the clinical need for efficacious treatments, genetically engineered mouse models (GEMM) have become integral in identifying and evaluating the molecular underpinnings of this complex disease that may be exploited as therapeutic targets. Assessment of GEMM tumor burden on histopathological sections performed by manual inspection is both time consuming and prone to subjective bias. Therefore, an interplay of needs and challenges exists for computer-aided diagnostic tools, for accurate and efficient analysis of these histopathology images. In this paper, we propose a simple machine learning approach called the graph-based sparse principal component analysis (GS-PCA) network, for automated detection of cancerous lesions on histological lung slides stained by hematoxylin and eosin (H&E). Our method comprises four steps: 1) cascaded graph-based sparse PCA, 2) PCA binary hashing, 3) block-wise histograms, and 4) support vector machine (SVM) classification. In our proposed architecture, graph-based sparse PCA is employed to learn the filter banks of the multiple stages of a convolutional network. This is followed by PCA hashing and block histograms for indexing and pooling. The meaningful features extracted from this GS-PCA are then fed to an SVM classifier. We evaluate the performance of the proposed algorithm on H&E slides obtained from an inducible K-rasG12D lung cancer mouse model using precision/recall rates, F-score, Tanimoto coefficient, and area under the curve (AUC) of the receiver operator characteristic (ROC) and show that our algorithm is efficient and provides improved detection accuracy compared to existing algorithms.