Impact of image pre-processing methods on computed tomography radiomics features in chronic obstructive pulmonary disease

AutoCOPD-A novel and practical machine learning model for COPD detection using whole-lung inspiratory quantitative CT measurements: a retrospective, multicenter study

Background

The rate of diagnosis for chronic obstructive pulmonary disease (COPD) is low worldwide. Quantitative computed tomography (QCT) parameters add value to quantify alterations in airway and lung parenchyma for COPD. This study aimed to assess the performance of QCT features in COPD detection using a whole-lung inspiratory CT model.

Methods

This multicenter retrospective study was performed on 4106 participants. The derivation cohort containing 1950 participants who enrolled in Guangzhou communities from August 2017 to December 2019, was separated for training and internal validation cohorts, and three external validation cohorts containing 1703 participants were recruited from the public hospitals (Cohort 1: the First Affiliated Hospital of Guangzhou Medical University; Cohort 2: Xiangyang central hospital; Cohort 3: the Second Affiliated Hospital of Xi'an Jiaotong University) in China between April 2017 and May 2024. Questionnaire information, CT reports, and QCT features derived from inspiratory CT were extracted for model development. A novel multimodal framework using eXtreme gradient boosting and hybrid feature selection was established for COPD detection. National Lung Screening Trial (NLST) cohort (n = 453) was applied to validate the multiracial extrapolation and robustness on low-dose CT scans.

Findings

The QCT model (referred to as AutoCOPD) with ten features achieved the highest AUC of 0·860 (95% CI: 0·823-0·898) in the internal validation cohort, and showed excellent discrimination when externally validated [Cohort 1: AUC = 0·915 (95% CI: 0·898-0·931); Cohort 2: AUC = 0·903 (95% CI: 0·864-0·943); Cohort 3: AUC = 0·914 (95% CI: 0·882-0·947); NLST: AUC = 0·881 (95% CI: 0·846-0·915)]. Decision curve analysis demonstrated that AutoCOPD was valuable across a range of COPD risk thresholds between 0·12 and 0·66 compared with intervention in all patients with COPD or no intervention.

Interpretation

Heterogeneous COPD can be well identified using AutoCOPD (https://lwj-lab.shinyapps.io/autocopd/) constructed by a subset of only ten QCT features. It may be generalizable across clinical settings and serve as a feasible tool for early detecting patients with mild or asymptomatic COPD to reduce delayed diagnosis in routine practice.

Funding

The National Natural Science Foundation of China, Guangzhou Laboratory, Natural Science Foundation of Guangdong Province, Guangzhou Municipal Science and Technology grant, State Key Laboratory of Respiratory Disease.

Optimizing convolutional neural networks for Chronic Obstructive Pulmonary Disease detection in clinical computed tomography imaging

We aim to optimize the binary detection of Chronic Obstructive Pulmonary Disease (COPD) based on emphysema presence in the lung with convolutional neural networks (CNN) by exploring manually adjusted versus automated window-setting optimization (WSO) on computed tomography (CT) images. 7194 contrast-enhanced CT images (3597 with COPD; 3597 healthy controls) from 78 subjects were selected retrospectively (01.2018-12.2021) and preprocessed. For each image, intensity values were manually clipped to the emphysema window setting and a baseline 'full-range' window setting. Class-balanced train, validation, and test sets contained 3392, 1114, and 2688 images. The network backbone was optimized by comparing various CNN architectures. Furthermore, automated WSO was implemented by adding a customized layer to the model. The image-level area under the Receiver Operating Characteristics curve (AUC) [lower, upper limit 95% confidence] was utilized to compare model variations. Repeated inference (n = 7) on the test set showed that the DenseNet was the most efficient backbone and achieved a mean AUC of 0.80 [0.76, 0.85] without WSO. Comparably, with input images manually adjusted to the emphysema window, the DenseNet model predicted COPD with a mean AUC of 0.86 [0.82, 0.89]. By adding a customized WSO layer to the DenseNet, an optimal window in the proximity of the emphysema window setting was learned automatically, and a mean AUC of 0.82 [0.78, 0.86] was achieved. Detection of COPD with DenseNet models was improved by WSO of CT data to the emphysema window setting range.

Expiration CT Gas Trapping Measures with Texture-Based Radiomics Improves Association with Lung Function and Lung Function Decline in COPD

RATIONALE AND OBJECTIVES

Several methods quantify gas-trapping on expiration computed tomography (CT) images, but they do not consider the spatial relationship of voxels. The objective of this study was to determine if the addition of expiration CT texture-based radiomics features to existing gas-trapping measurements improves model performance for lung function, lung function decline, COPD classification and visual gas-trapping.

MATERIALS AND METHODS

CanCOLD participants performed spirometry, plethysmography and CT chest imaging at full-inspiration/expiration with radiologist-assessed gas-trapping. Quantitative CT measurements were performed: low attenuation areas≤-856HU (LAA856), ratio of expiratory-to-inspiratory mean lung attenuation (E/I MLA), and difference between expiratory-inspiratory lung volumes between -856 and -950 HU (RVC856-950). Texture-based radiomics analysis generated 95 features; LASSO regression coefficients were summed to create a representative variable (RadScore). Multivariable linear regression models determined associations for baseline RV/TLC, FEV1/FVC, FEV1, FEF25-75, and 6-year ΔFEV1, with established CT gas-trapping and RadScore. Binary logistic regression determined associations for COPD classification and visual gas-trapping.

RESULTS

1111 participants were investigated (n=234 never-smokers, n=325 at-risk, n=314 mild COPD, n=238 moderate-severe COPD). In separate models for baseline RV/TLC, FEV1/FVC, FEV1, and FEF25-75, ΔFEV1, COPD classification and visual gas-trapping, all CT gas-trapping and CT RadScore measurements were independently significant (p<0.05). When CT gas-trapping and CT RadScore were included in the same model, all model performance metrics improved significantly (p<0.05).

CONCLUSION

CT measures extracted from full-expiratory images that quantify the distribution, not just extent, of gas-trapping provide important information related to lung function and lung function decline in COPD.

SUMMARY STATEMENT

Full-expiratory CT texture-based radiomics improves model performance when used in combination with conventional gas-trapping measurements for lung function and lung function decline, COPD classification and presence of visual gas-trapping.

The textures of sarcoidosis: quantifying lung disease through variograms

Objective. Sarcoidosis is a granulomatous disease affecting the lungs in over 90% of patients. Qualitative assessment of chest CT by radiologists is standard clinical practice and reliable quantification of disease from CT would support ongoing efforts to identify sarcoidosis phenotypes. Standard imaging feature engineering techniques such as radiomics suffer from extreme sensitivity to image acquisition and processing, potentially impeding generalizability of research to clinical populations. In this work, we instead investigate approaches to engineering variogram-based features with the intent to identify a robust, generalizable pipeline for image quantification in the study of sarcoidosis.Approach. For a cohort of more than 300 individuals with sarcoidosis, we investigated 24 feature engineering pipelines differing by decisions for image registration to a template lung, empirical and model variogram estimation methods, and feature harmonization for CT scanner model, and subsequently 48 sets of phenotypes produced through unsupervised clustering. We then assessed sensitivity of engineered features, phenotypes produced through unsupervised clustering, and sarcoidosis disease signal strength to pipeline.Main results. We found that variogram features had low to mild association with scanner model and associations were reduced by image registration. For each feature type, features were also typically robust to all pipeline decisions except image registration. Strength of disease signal as measured by association with pulmonary function testing and some radiologist visual assessments was strong (optimistic AUC ≈ 0.9,p≪0.0001in models for architectural distortion, conglomerate mass, fibrotic abnormality, and traction bronchiectasis) and fairly consistent across engineering approaches regardless of registration and harmonization for CT scanner.Significance. Variogram-based features appear to be a suitable approach to image quantification in support of generalizable research in pulmonary sarcoidosis.

Quantitative CT Imaging Features Associated with Stable PRISm using Machine Learning

RATIONALE AND OBJECTIVES

The structural lung features that characterize individuals with preserved ratio impaired spirometry (PRISm) that remain stable overtime are unknown. The objective of this study was to use machine learning models with computed tomography (CT) imaging to classify stable PRISm from stable controls and stable COPD and identify discriminative features.

MATERIALS AND METHODS

A total of 596 participants that did not transition between control, PRISm and COPD groups at baseline and 3-year follow-up were evaluated: n = 274 with normal lung function (stable control), n = 22 stable PRISm, and n = 300 stable COPD. Investigated features included: quantitative CT (QCT) features (n = 34), such as total lung volume (%TLCCT) and percentage of ground glass and reticulation (%GG+Reticulationtexture), as well as Radiomic (n = 102) features, including varied intensity zone distribution grainy texture (GLDZMZDV). Logistic regression machine learning models were trained using various feature combinations (Base, Base+QCT, Base+Radiomic, Base+QCT+Radiomic). Model performances were evaluated using area under receiver operator curve (AUC) and comparisons between models were made using DeLong test; feature importance was ranked using Shapley Additive Explanations values.

RESULTS

Machine learning models for all feature combinations achieved AUCs between 0.63-0.84 for stable PRISm vs. stable control, and 0.65-0.92 for stable PRISm vs. stable COPD classification. Models incorporating imaging features outperformed those trained solely on base features (p < 0.05). Compared to stable control and COPD, those with stable PRISm exhibited decreased %TLCCT and increased %GG+Reticulationtexture and GLDZMZDV.

CONCLUSION

These findings suggest that reduced lung volumes, and elevated high-density and ground glass/reticulation patterns on CT imaging are associated with stable PRISm.

Diagnostic performance of MRI-based radiomics models using machine learning approaches for the triple classification of parotid tumors

Rationale and objectives

Preoperative differentiation of malignant tumors (MT), pleomorphic adenomas (PA), and other benign tumors of the parotid gland is critical to clinical strategy, this study aimed to develop and validate a T2-weighted image (T2WI) based radiomics model through machine learning approaches for the triple classification of parotid gland tumors.

Materials and methods

We retrospectively enrolled 147 patients from January 2010 to July 2022. T2WIs were used to extract radiomics features. Max-Relevance and Min-Redundancy (mRMR) and Extreme Gradient Boosting (XGBoost) algorithms were used to select features. Using a 5-fold cross-validation strategy, radiomics models were constructed using a Support Vector Machine (SVM), Logistic Regression (LR), and k-Nearest Neighbor (KNN) for the triple classification of parotid tumors. The three models were evaluated and compared using the receiver operator characteristic (ROC) curve, sensitivity, specificity, and accuracy.

Results

A total of 1057 radiomics features were extracted, and 8 features were selected to developed the radiomics model, including First-order Median, First-order Skewness, First-order Minimum, Original_shape_Flatness, Glcm Inverse Variance, Glcm Inverse Variance, Glszm Low Gray Level Zone Emphasis, and Glszm Small Area Low Gray Level Emphasis. The mean area under the curves (AUCs) for the radiomics models in training and validation sets through LR, SVM and KNN were 0.85 and 0.80, 0.85 and 0.80 and 0.83 and 0.79, respectively.

Conclusion

The T2WI-based radiomics models through LR, SVM and KNN demonstrated good performance in the triple classification of parotid tumors.

Impact of Preprocessing Parameters in Medical Imaging-Based Radiomic Studies: A Systematic Review

BACKGROUND

Lately, radiomic studies featuring the development of a signature to use in prediction models in diagnosis or prognosis outcomes have been increasingly published. While the results are shown to be promising, these studies still have many pitfalls and limitations. One of the main issues of these studies is that radiomic features depend on how the images are preprocessed before their computation. Since, in widely known and used software for radiomic features calculation, it is possible to set these preprocessing parameters before the calculation of the radiomic feature, there are ongoing studies assessing the stability and repeatability of radiomic features to find the most suitable preprocessing parameters for every used imaging modality.

MATERIALS AND METHODS

We performed a comprehensive literature search using four electronic databases: PubMed, Cochrane Library, Embase, and Scopus. Mesh terms and free text were modeled in search strategies for databases. The inclusion criteria were studies where preprocessing parameters' influence on feature values and model predictions was addressed. Records lacking information on image acquisition parameters were excluded, and any eligible studies with full-text versions were included in the review process, while conference proceedings and monographs were disregarded. We used the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2) tool to investigate the risk of bias. We synthesized our data in a table divided by the imaging modalities subgroups.

RESULTS

After applying the inclusion and exclusion criteria, we selected 43 works. This review examines the impact of preprocessing parameters on the reproducibility and reliability of radiomic features extracted from multimodality imaging (CT, MRI, CBCT, and PET/CT). Standardized preprocessing is crucial for consistent radiomic feature extraction. Key preprocessing steps include voxel resampling, normalization, and discretization, which influence feature robustness and reproducibility. In total, 44% of the included works studied the effects of an isotropic voxel resampling, and most studies opted to employ a discretization strategy. From 2021, several studies started selecting the best set of preprocessing parameters based on models' best performance. As for comparison metrics, ICC was the most used in MRI studies in 58% of the screened works.

CONCLUSIONS

From our work, we highlighted the need to harmonize the use of preprocessing parameters and their values, especially in light of future studies of prospective studies, which are still lacking in the current literature.

Enhancing COPD classification using combined quantitative computed tomography and texture-based radiomics: a CanCOLD cohort study

Background

Recent advances in texture-based computed tomography (CT) radiomics have demonstrated its potential for classifying COPD.

Methods

Participants from the Canadian Cohort Obstructive Lung Disease (CanCOLD) study were evaluated. A total of 108 features were included: eight quantitative CT (qCT), 95 texture-based radiomic and five demographic features. Machine-learning models included demographics along with texture-based radiomics and/or qCT. Combinations of five feature selection and five classification methods were evaluated; a training dataset was used for feature selection and to train the models, and a testing dataset was used for model evaluation. Models for classifying COPD status and severity were evaluated using the area under the receiver operating characteristic curve (AUC) with DeLong's test for comparison. SHapely Additive exPlanations (SHAP) analysis was used to investigate the features selected.

Results

A total of 1204 participants were evaluated (n=602 no COPD; n=602 COPD). There were no differences between the groups for sex (p=0.77) or body mass index (p=0.21). For classifying COPD status, the combination of demographics, texture-based radiomics and qCT performed better (AUC=0.87) than the combination of demographics and texture-based radiomics (AUC=0.81, p<0.05) or qCT alone (AUC=0.84, p<0.05). Similarly, for classifying COPD severity, the combination of demographics, texture-based radiomics and qCT performed better (AUC=0.81) than demographics and texture-based radiomics (AUC=0.72, p<0.05) or qCT alone (AUC=0.79, p<0.05). Texture-based radiomics and qCT features were among the top five features selected (15th percentile of the CT density histogram, CT total airway count, pack-years, CT grey-level distance zone matrix zone distance entropy, CT low-attenuation clusters) for classifying COPD status.

Conclusion

Texture-based radiomics and conventional qCT features in combination improve machine‑learning models for classification of COPD status and severity.

Prediction of solid and micropapillary components in lung invasive adenocarcinoma: radiomics analysis from high-spatial-resolution CT data with 1024 matrix

PURPOSE

To predict solid and micropapillary components in lung invasive adenocarcinoma using radiomic analyses based on high-spatial-resolution CT (HSR-CT).

MATERIALS AND METHODS

For this retrospective study, 64 patients with lung invasive adenocarcinoma were enrolled. All patients were scanned by HSR-CT with 1024 matrix. A pathologist evaluated subtypes (lepidic, acinar, solid, micropapillary, or others). Total 61 radiomic features in the CT images were calculated using our modified texture analysis software, then filtered and minimized by least absolute shrinkage and selection operator (LASSO) regression to select optimal radiomic features for predicting solid and micropapillary components in lung invasive adenocarcinoma. Final data were obtained by repeating tenfold cross-validation 10 times. Two independent radiologists visually predicted solid or micropapillary components on each image of the 64 nodules with and without using the radiomics results. The quantitative values were analyzed with logistic regression models. The receiver operating characteristic curves were generated to predict of solid and micropapillary components. P values < 0.05 were considered significant.

RESULTS

Two features (Coefficient Variation and Entropy) were independent indicators associated with solid and micropapillary components (odds ratio, 30.5 and 11.4; 95% confidence interval, 5.1-180.5 and 1.9-66.6; and P = 0.0002 and 0.0071, respectively). The area under the curve for predicting solid and micropapillary components was 0.902 (95% confidence interval, 0.802 to 0.962). The radiomics results significantly improved the accuracy and specificity of the prediction of the two radiologists.

CONCLUSION

Two texture features (Coefficient Variation and Entropy) were significant indicators to predict solid and micropapillary components in lung invasive adenocarcinoma.

The textures of sarcoidosis: quantifying lung disease through variograms

Objective

Sarcoidosis is a granulomatous disease affecting the lungs in over 90% of patients. Qualitative assessment of chest CT by radiologists is standard clinical practice and reliable quantification of disease from CT would support ongoing efforts to identify sarcoidosis phenotypes. Standard imaging feature engineering techniques such as radiomics suffer from extreme sensitivity to image acquisition and processing, potentially impeding generalizability of research to clinical populations. In this work, we instead investigate approaches to engineering variogram-based features with the intent to identify a robust, generalizable pipeline for image quantification in the study of sarcoidosis.

Approach

For a cohort of more than 300 individuals with sarcoidosis, we investigated 24 feature engineering pipelines differing by decisions for image registration to a template lung, empirical and model variogram estimation methods, and feature harmonization for CT scanner model, and subsequently 48 sets of phenotypes produced through unsupervised clustering. We then assessed sensitivity of engineered features, phenotypes produced through unsupervised clustering, and sarcoidosis disease signal strength to pipeline.

Main results

We found that variogram features had low to mild association with scanner model and associations were reduced by image registration. For each feature type, features were also typically robust to all pipeline decisions except image registration. Strength of disease signal as measured by association with pulmonary function testing and some radiologist visual assessments was strong (optimistic AUC ≈ 0.9, p ≪ 0.0001 in models for architectural distortion, conglomerate mass, fibrotic abnormality, and traction bronchiectasis) and fairly consistent across engineering approaches regardless of registration and harmonization for CT scanner.

Significance

Variogram-based features appear to be a suitable approach to image quantification in support of generalizable research in pulmonary sarcoidosis.

CT whole lung radiomic nomogram: a potential biomarker for lung function evaluation and identification of COPD

BACKGROUND

Computed tomography (CT) plays a great role in characterizing and quantifying changes in lung structure and function of chronic obstructive pulmonary disease (COPD). This study aimed to explore the performance of CT-based whole lung radiomic in discriminating COPD patients and non-COPD patients.

METHODS

This retrospective study was performed on 2785 patients who underwent pulmonary function examination in 5 hospitals and were divided into non-COPD group and COPD group. The radiomic features of the whole lung volume were extracted. Least absolute shrinkage and selection operator (LASSO) logistic regression was applied for feature selection and radiomic signature construction. A radiomic nomogram was established by combining the radiomic score and clinical factors. Receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) were used to evaluate the predictive performance of the radiomic nomogram in the training, internal validation, and independent external validation cohorts.

RESULTS

Eighteen radiomic features were collected from the whole lung volume to construct a radiomic model. The area under the curve (AUC) of the radiomic model in the training, internal, and independent external validation cohorts were 0.888 [95% confidence interval (CI) 0.869-0.906], 0.874 (95%CI 0.844-0.904) and 0.846 (95%CI 0.822-0.870), respectively. All were higher than the clinical model (AUC were 0.732, 0.714, and 0.777, respectively, P < 0.001). DCA demonstrated that the nomogram constructed by combining radiomic score, age, sex, height, and smoking status was superior to the clinical factor model.

CONCLUSIONS

The intuitive nomogram constructed by CT-based whole-lung radiomic has shown good performance and high accuracy in identifying COPD in this multicenter study.

Multi-Layer Perceptron Classifier with the Proposed Combined Feature Vector of 3D CNN Features and Lung Radiomics Features for COPD Stage Classification

Computed tomography (CT) has been regarded as the most effective modality for characterizing and quantifying chronic obstructive pulmonary disease (COPD). Therefore, chest CT images should provide more information for COPD diagnosis, such as COPD stage classification. This paper proposes a features combination strategy by concatenating three-dimension (3D) CNN features and lung radiomics features for COPD stage classification based on the multi-layer perceptron (MLP) classifier. First, 465 sets of chest HRCT images are automatically segmented by a trained ResU-Net, obtaining the lung images with the Hounsfield unit. Second, the 3D CNN features are extracted from the lung region images based on a truncated transfer learning strategy. Then, the lung radiomics features are extracted from the lung region images by PyRadiomics. Third, the MLP classifier with the best classification performance is determined by the 3D CNN features and the lung radiomics features. Finally, the proposed combined feature vector is used to improve the MLP classifier's performance. The results show that compared with CNN models and other ML classifiers, the MLP classifier with the best classification performance is determined. The MLP classifier with the proposed combined feature vector has achieved accuracy, mean precision, mean recall, mean F1-score, and AUC of 0.879, 0.879, 0.879, 0.875, and 0.971, respectively. Compared to the MLP classifier with the 3D CNN features selected by Lasso, our method based on the MLP classifier has improved the classification performance by 5.8% (accuracy), 5.3% (mean precision), 5.8% (mean recall), 5.4% (mean F1-score), and 2.5% (AUC). Compared to the MLP classifier with lung radiomics features selected by Lasso, our method based on the MLP classifier has improved the classification performance by 5.0% (accuracy), 5.1% (mean precision), 5.0% (mean recall), 5.1% (mean F1-score), and 2.1% (AUC). Therefore, it is concluded that our method is effective in improving the classification performance for COPD stage classification.

CT Imaging With Machine Learning for Predicting Progression to COPD in Individuals at Risk

BACKGROUND

Identifying individuals at risk of progressing to COPD may allow for initiation of treatment to potentially slow the progression of the disease or the selection of subgroups for discovery of novel interventions.

RESEARCH QUESTION

Does the addition of CT imaging features, texture-based radiomic features, and established quantitative CT scan to conventional risk factors improve the performance for predicting progression to COPD in individuals who smoke with machine learning?

STUDY DESIGN AND METHODS

Participants at risk (individuals who currently or formerly smoked, without COPD) from the Canadian Cohort Obstructive Lung Disease (CanCOLD) population-based study underwent CT imaging at baseline and spirometry at baseline and follow-up. Various combinations of CT scan features, texture-based CT scan radiomics (n = 95), and established quantitative CT scan (n = 8), as well as demographic (n = 5) and spirometry (n = 3) measurements, with machine learning algorithms were evaluated to predict progression to COPD. Performance metrics included the area under the receiver operating characteristic curve (AUC) to evaluate the models. DeLong test was used to compare the performance of the models.

RESULTS

Among the 294 at-risk participants who were evaluated (mean age, 65.6 ± 9.2 years; 42% female; mean pack-years, 17.9 ± 18.7), 52 participants (23.7%) in the training data set and 17 participants (23.0%) in the testing data set progressed to spirometric COPD at follow-up (2.5 ± 0.9 years from baseline). Compared with machine learning models with demographics alone (AUC, 0.649), the addition of CT imaging features to demographics (AUC, 0.730; P < .05) or CT imaging features and spirometry to demographics (AUC, 0.877; P < .05) significantly improved the performance for predicting progression to COPD.

INTERPRETATION

Heterogeneous structural changes occur in the lungs of individuals at risk that can be quantified using CT imaging features, and evaluation of these features together with conventional risk factors improves performance for predicting progression to COPD.

Radiomics for Improved Detection of Chronic Obstructive Pulmonary Disease in Low-Dose and Standard-Dose Chest CT Scans

Background Approximately half of adults with chronic obstructive pulmonary disease (COPD) remain undiagnosed. Chest CT scans are frequently acquired in clinical practice and present an opportunity to detect COPD. Purpose To assess the performance of radiomics features in COPD diagnosis using standard-dose and low-dose CT models. Materials and Methods This secondary analysis included participants enrolled in the Genetic Epidemiology of COPD, or COPDGene, study at baseline (visit 1) and 10 years after baseline (visit 3). COPD was defined by a forced expiratory volume in the 1st second of expiration to forced vital capacity ratio less than 0.70 at spirometry. The performance of demographics, CT emphysema percentage, radiomics features, and a combined feature set derived from inspiratory CT alone was evaluated. CatBoost (Yandex), a gradient boosting algorithm, was used to perform two classification experiments to detect COPD; the two models were trained and tested on standard-dose CT data from visit 1 (model I) and low-dose CT data from visit 3 (model II). Classification performance of the models was evaluated using area under the receiver operating characteristic curve (AUC) and precision-recall curve analysis. Results A total of 8878 participants (mean age, 57 years ± 9 [SD]; 4180 female, 4698 male) were evaluated. Radiomics features in model I achieved an AUC of 0.90 (95% CI: 0.88, 0.91) in the standard-dose CT test cohort versus demographics (AUC, 0.73; 95% CI: 0.71, 0.76; P < .001), emphysema percentage (AUC, 0.82; 95% CI 0.80, 0.84; P < .001), and combined features (AUC, 0.90; 95% CI: 0.89, 0.92; P = .16). Model II, trained on low-dose CT scans, achieved an AUC of 0.87 (95% CI: 0.83, 0.91) on the 20% held-out test set for radiomics features compared with demographics (AUC, 0.70; 95% CI: 0.64, 0.75; P = .001), emphysema percentage (AUC, 0.74; 95% CI: 0.69, 0.79; P = .002), and combined features (AUC, 0.88; 95% CI: 0.85, 0.92; P = .32). Density and texture features were the majority of the top 10 features in the standard-dose model, whereas shape features of lungs and airways were significant contributors in the low-dose CT model. Conclusion A combination of features representing parenchymal texture and lung and airway shape on inspiratory CT scans can be used to accurately detect COPD. ClinicalTrials.gov registration no. NCT00608764 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Vliegenthart in this issue.

Multi-modal data combination strategy based on chest HRCT images and PFT parameters for intelligent dyspnea identification in COPD

Introduction

Because of persistent airflow limitation in chronic obstructive pulmonary disease (COPD), patients with COPD often have complications of dyspnea. However, as a leading symptom of COPD, dyspnea in COPD deserves special consideration regarding treatment in this fragile population for pre-clinical health management in COPD. Methods: Based on the above, this paper proposes a multi-modal data combination strategy by combining the local and global features for dyspnea identification in COPD based on the multi-layer perceptron (MLP) classifier.

Methods

First, lung region images are automatically segmented from chest HRCT images for extracting the original 1,316 lung radiomics (OLR, 1,316) and 13,824 3D CNN features (O3C, 13,824). Second, the local features, including five selected pulmonary function test (PFT) parameters (SLF, 5), 28 selected lung radiomics (SLR, 28), and 22 selected 3D CNN features (S3C, 22), are respectively selected from the original 11 PFT parameters (OLF, 11), 1,316 OLR, and 13,824 O3C by the least absolute shrinkage and selection operator (Lasso) algorithm. Meantime, the global features, including two fused PFT parameters (FLF, 2), six fused lung radiomics (FLR, 6), and 34 fused 3D CNN features (F3C, 34), are respectively fused by 11 OLF, 1,316 OLR, and 13,824 O3C using the principal component analysis (PCA) algorithm. Finally, we combine all the local and global features (SLF + FLF + SLR + FLR + S3C + F3C, 5+ 2 + 28 + 6 + 22 + 34) for dyspnea identification in COPD based on the MLP classifier.

Results

Our proposed method comprehensively improves classification performance. The MLP classifier with all the local and global features achieves the best classification performance at 87.7% of accuracy, 87.7% of precision, 87.7% of recall, 87.7% of F1-scorel, and 89.3% of AUC, respectively.

Discussion

Compared with single-modal data, the proposed strategy effectively improves the classification performance for dyspnea identification in COPD, providing an objective and effective tool for COPD management.

Comparison of Feature Selection Methods and Machine Learning Classifiers for Predicting Chronic Obstructive Pulmonary Disease Using Texture-Based CT Lung Radiomic Features

RATIONALE

Texture-based radiomics analysis of lung computed tomography (CT) images has been shown to predict chronic obstructive pulmonary disease (COPD) status using machine learning models. However, various approaches are used and it is unclear which provides the best performance.

OBJECTIVES

To compare the most commonly used feature selection and classification methods and determine the optimal models for classifying COPD status in a mild, population-based COPD cohort.

MATERIALS AND METHODS

CT images from the multi-center Canadian Cohort Obstructive Lung Disease (CanCOLD) study were pre-processed by resampling the image to a 1mm isotropic voxel volume, segmenting the lung and removing the airways (VIDA Diagnostics Inc.), and applying a threshold of -1000HU-to-0HU. A total of 95 texture features were then extracted from each CT image. Combinations of 17 feature selection methods and 9 classifiers were tested and evaluated. In addition, the role of data cleaning (outlier removal and highly correlated feature removal) was evaluated. The area under the curve (AUC) from the receiver operating characteristic curve was used to evaluate model performance.

RESULTS

A total of 1204 participants were evaluated (n = 602 no COPD, n = 602 COPD). There were no significant differences between the groups for female sex (no COPD = 46.3%; COPD = 38.5%; p = 0.77), or body mass index (no COPD = 27.7 kg/m²; COPD = 27.4 kg/m²; p = 0.21). The highest AUC value for predicting COPD status (AUC = 0.78 [0.73, 0.84]) was obtained following data cleaning and feature selection using Elastic Net with the Linear-SVM classifier.

CONCLUSION

In a population-based cohort, the optimal combination for radiomics-based prediction of COPD status was Elastic Net as the feature selection method and Linear-SVM as the classifier.

Early COPD Risk Decision for Adults Aged From 40 to 79 Years Based on Lung Radiomics Features

Background

Chronic obstructive pulmonary disease (COPD), a preventable lung disease, has the highest prevalence in the elderly and deserves special consideration regarding earlier warnings in this fragile population. The impact of age on COPD is well known, but the COPD risk of the aging process in the lungs remains unclear. Therefore, it is necessary to understand the COPD risk of the aging process in the lungs, providing an early COPD risk decision for adults.

Methods

COPD risk is evaluated for adults to make an early COPD risk decision from the perspective of lung radiomics features. First, the subjects are divided into four groups according to the COPD stages. Their ages are divided into eight equal age intervals in each group. Second, four survival Cox models are established based on the lung radiomics features to evaluate the risk probability from COPD stage 0 to suffering COPD and COPD stages. Finally, four risk ranks are defined by equally dividing the COPD risk probability from 0 to 1. Subsequently, the COPD risk at different stages is evaluated with varying age intervals to provide an early COPD risk decision.

Results

The evaluation metrics area under the curve (AUC)/C index of four survival Cox models are 0.87/0.94, 0.84/0.83, 0.94/0.89, and 0.97/0.86, respectively, showing the effectiveness of the models. The risk rank levels up every 5 years for the subjects who had suffered COPD after 60. For the subjects with COPD stage 0, the risk rank of suffering COPD stage I levels up every 5 years after the age of 65 years, and the risk rank of suffering COPD stages II and III &amp; IV levels up every 5 years after the age of 70 years.

Conclusion

Once the age is above 60 years, the patients with COPD need to take action to prevent the progress and deterioration of COPD. Once the age is above 65 years, the patients with COPD stage 0 need to take precautions against COPD.