Improving clinical disease subtyping and future events prediction through a chest CT-based deep learning approach

Artificial intelligence in COPD CT images: identification, staging, and quantitation

Chronic obstructive pulmonary disease (COPD) stands as a significant global health challenge, with its intricate pathophysiological manifestations often demanding advanced diagnostic strategies. The recent applications of artificial intelligence (AI) within the realm of medical imaging, especially in computed tomography, present a promising avenue for transformative changes in COPD diagnosis and management. This review delves deep into the capabilities and advancements of AI, particularly focusing on machine learning and deep learning, and their applications in COPD identification, staging, and imaging phenotypes. Emphasis is laid on the AI-powered insights into emphysema, airway dynamics, and vascular structures. The challenges linked with data intricacies and the integration of AI in the clinical landscape are discussed. Lastly, the review casts a forward-looking perspective, highlighting emerging innovations in AI for COPD imaging and the potential of interdisciplinary collaborations, hinting at a future where AI doesn't just support but pioneers breakthroughs in COPD care. Through this review, we aim to provide a comprehensive understanding of the current state and future potential of AI in shaping the landscape of COPD diagnosis and management.

How do deep-learning models generalize across populations? Cross-ethnicity generalization of COPD detection

OBJECTIVES

To evaluate the performance and potential biases of deep-learning models in detecting chronic obstructive pulmonary disease (COPD) on chest CT scans across different ethnic groups, specifically non-Hispanic White (NHW) and African American (AA) populations.

MATERIALS AND METHODS

Inspiratory chest CT and clinical data from 7549 Genetic epidemiology of COPD individuals (mean age 62 years old, 56-69 interquartile range), including 5240 NHW and 2309 AA individuals, were retrospectively analyzed. Several factors influencing COPD binary classification performance on different ethnic populations were examined: (1) effects of training population: NHW-only, AA-only, balanced set (half NHW, half AA) and the entire set (NHW + AA all); (2) learning strategy: three supervised learning (SL) vs. three self-supervised learning (SSL) methods. Distribution shifts across ethnicity were further assessed for the top-performing methods.

RESULTS

The learning strategy significantly influenced model performance, with SSL methods achieving higher performances compared to SL methods (p < 0.001), across all training configurations. Training on balanced datasets containing NHW and AA individuals resulted in improved model performance compared to population-specific datasets. Distribution shifts were found between ethnicities for the same health status, particularly when models were trained on nearest-neighbor contrastive SSL. Training on a balanced dataset resulted in fewer distribution shifts across ethnicity and health status, highlighting its efficacy in reducing biases.

CONCLUSION

Our findings demonstrate that utilizing SSL methods and training on large and balanced datasets can enhance COPD detection model performance and reduce biases across diverse ethnic populations. These findings emphasize the importance of equitable AI-driven healthcare solutions for COPD diagnosis.

CRITICAL RELEVANCE STATEMENT

Self-supervised learning coupled with balanced datasets significantly improves COPD detection model performance, addressing biases across diverse ethnic populations and emphasizing the crucial role of equitable AI-driven healthcare solutions.

KEY POINTS

Self-supervised learning methods outperform supervised learning methods, showing higher AUC values (p < 0.001). Balanced datasets with non-Hispanic White and African American individuals improve model performance. Training on diverse datasets enhances COPD detection accuracy. Ethnically diverse datasets reduce bias in COPD detection models. SimCLR models mitigate biases in COPD detection across ethnicities.

Prediction of disease severity in COPD: a deep learning approach for anomaly-based quantitative assessment of chest CT

OBJECTIVES

To quantify regional manifestations related to COPD as anomalies from a modeled distribution of normal-appearing lung on chest CT using a deep learning (DL) approach, and to assess its potential to predict disease severity.

MATERIALS AND METHODS

Paired inspiratory/expiratory CT and clinical data from COPDGene and COSYCONET cohort studies were included. COPDGene data served as training/validation/test data sets (N = 3144/786/1310) and COSYCONET as external test set (N = 446). To differentiate low-risk (healthy/minimal disease, [GOLD 0]) from COPD patients (GOLD 1-4), the self-supervised DL model learned semantic information from 50 × 50 × 50 voxel samples from segmented intact lungs. An anomaly detection approach was trained to quantify lung abnormalities related to COPD, as regional deviations. Four supervised DL models were run for comparison. The clinical and radiological predictive power of the proposed anomaly score was assessed using linear mixed effects models (LMM).

RESULTS

The proposed approach achieved an area under the curve of 84.3 ± 0.3 (p < 0.001) for COPDGene and 76.3 ± 0.6 (p < 0.001) for COSYCONET, outperforming supervised models even when including only inspiratory CT. Anomaly scores significantly improved fitting of LMM for predicting lung function, health status, and quantitative CT features (emphysema/air trapping; p < 0.001). Higher anomaly scores were significantly associated with exacerbations for both cohorts (p < 0.001) and greater dyspnea scores for COPDGene (p < 0.001).

CONCLUSION

Quantifying heterogeneous COPD manifestations as anomaly offers advantages over supervised methods and was found to be predictive for lung function impairment and morphology deterioration.

CLINICAL RELEVANCE STATEMENT

Using deep learning, lung manifestations of COPD can be identified as deviations from normal-appearing chest CT and attributed an anomaly score which is consistent with decreased pulmonary function, emphysema, and air trapping.

KEY POINTS

• A self-supervised DL anomaly detection method discriminated low-risk individuals and COPD subjects, outperforming classic DL methods on two datasets (COPDGene AUC = 84.3%, COSYCONET AUC = 76.3%). • Our contrastive task exhibits robust performance even without the inclusion of expiratory images, while voxel-based methods demonstrate significant performance enhancement when incorporating expiratory images, in the COPDGene dataset. • Anomaly scores improved the fitting of linear mixed effects models in predicting clinical parameters and imaging alterations (p < 0.001) and were directly associated with clinical outcomes (p < 0.001).

Clinical utilization of airway inflammatory biomarkers in the prediction and monitoring of clinical outcomes in patients with chronic obstructive pulmonary disease

INTRODUCTION

Chronic obstructive pulmonary disease (COPD) accounts for 545 million people living with chronic respiratory disorders and is the third leading cause of morbidity and mortality around the world. COPD is a progressive disease, characterized by episodes of acute worsening of symptoms such as cough, dyspnea, and sputum production.

AREAS COVERED

Airway inflammation is a prominent feature of COPD. Chronic airway inflammation results in airway structural remodeling and emphysema. Persistent airway inflammation is a treatable trait of COPD and plays a significant role in disease development and progression. In this review, the authors summarize the current and emerging biomarkers that reveal the heterogeneity of airway inflammation subtypes, clinical outcomes, and therapeutic response in COPD.

EXPERT OPINION

Airway inflammation can be broadly categorized as eosinophilic (type 2 inflammation) and non-eosinophilic (non-type 2 inflammation) in COPD. Currently, blood eosinophil counts are incorporated in clinical practice guidelines to identify COPD patients who are at a higher risk of exacerbations and lung function decline, and who are likely to respond to inhaled corticosteroids. As new therapeutics are being developed for the chronic management of COPD, it is essential to identify biomarkers that will predict treatment response.

Screening and staging of chronic obstructive pulmonary disease with deep learning based on chest X-ray images and clinical parameters

BACKGROUND

Chronic obstructive pulmonary disease (COPD) is underdiagnosed with the current gold standard measure pulmonary function test (PFT). A more sensitive and simple option for early detection and severity evaluation of COPD could benefit practitioners and patients.

METHODS

In this multicenter retrospective study, frontal chest X-ray (CXR) images and related clinical information of 1055 participants were collected and processed. Different deep learning algorithms and transfer learning models were trained to classify COPD based on clinical data and CXR images from 666 subjects, and validated in internal test set based on 284 participants. External test including 105 participants was also performed to verify the generalization ability of the learning algorithms in diagnosing COPD. Meanwhile, the model was further used to evaluate disease severity of COPD by predicting different grads.

RESULTS

The Ensemble model showed an AUC of 0.969 in distinguishing COPD by simultaneously extracting fusion features of clinical parameters and CXR images in internal test, better than models that used clinical parameters (AUC = 0.963) or images (AUC = 0.946) only. For the external test set, the AUC slightly declined to 0.934 in predicting COPD based on clinical parameters and CXR images. When applying the Ensemble model to determine disease severity of COPD, the AUC reached 0.894 for three-classification and 0.852 for five-classification respectively.

CONCLUSION

The present study used DL algorithms to screen COPD and predict disease severity based on CXR imaging and clinical parameters. The models showed good performance and the approach might be an effective case-finding tool with low radiation dose for COPD diagnosis and staging.

Capturing COPD heterogeneity: anomaly detection and parametric response mapping comparison for phenotyping on chest computed tomography

Background

Chronic obstructive pulmonary disease (COPD) poses a substantial global health burden, demanding advanced diagnostic tools for early detection and accurate phenotyping. In this line, this study seeks to enhance COPD characterization on chest computed tomography (CT) by comparing the spatial and quantitative relationships between traditional parametric response mapping (PRM) and a novel self-supervised anomaly detection approach, and to unveil potential additional insights into the dynamic transitional stages of COPD.

Methods

Non-contrast inspiratory and expiratory CT of 1,310 never-smoker and GOLD 0 individuals and COPD patients (GOLD 1-4) from the COPDGene dataset were retrospectively evaluated. A novel self-supervised anomaly detection approach was applied to quantify lung abnormalities associated with COPD, as regional deviations. These regional anomaly scores were qualitatively and quantitatively compared, per GOLD class, to PRM volumes (emphysema: PRMEmph, functional small-airway disease: PRMfSAD) and to a Principal Component Analysis (PCA) and Clustering, applied on the self-supervised latent space. Its relationships to pulmonary function tests (PFTs) were also evaluated.

Results

Initial t-Distributed Stochastic Neighbor Embedding (t-SNE) visualization of the self-supervised latent space highlighted distinct spatial patterns, revealing clear separations between regions with and without emphysema and air trapping. Four stable clusters were identified among this latent space by the PCA and Cluster Analysis. As the GOLD stage increased, PRMEmph, PRMfSAD, anomaly score, and Cluster 3 volumes exhibited escalating trends, contrasting with a decline in Cluster 2. The patient-wise anomaly scores significantly differed across GOLD stages (p < 0.01), except for never-smokers and GOLD 0 patients. In contrast, PRMEmph, PRMfSAD, and cluster classes showed fewer significant differences. Pearson correlation coefficients revealed moderate anomaly score correlations to PFTs (0.41-0.68), except for the functional residual capacity and smoking duration. The anomaly score was correlated with PRMEmph (r = 0.66, p < 0.01) and PRMfSAD (r = 0.61, p < 0.01). Anomaly scores significantly improved fitting of PRM-adjusted multivariate models for predicting clinical parameters (p < 0.001). Bland-Altman plots revealed that volume agreement between PRM-derived volumes and clusters was not constant across the range of measurements.

Conclusion

Our study highlights the synergistic utility of the anomaly detection approach and traditional PRM in capturing the nuanced heterogeneity of COPD. The observed disparities in spatial patterns, cluster dynamics, and correlations with PFTs underscore the distinct - yet complementary - strengths of these methods. Integrating anomaly detection and PRM offers a promising avenue for understanding of COPD pathophysiology, potentially informing more tailored diagnostic and intervention approaches to improve patient outcomes.

[The contribution of artificial intelligence (AI) subsequent to the processing of thoracic imaging]

The contribution of artificial intelligence (AI) to medical imaging is currently the object of widespread experimentation. The development of deep learning (DL) methods, particularly convolution neural networks (CNNs), has led to performance gains often superior to those achieved by conventional methods such as machine learning. Radiomics is an approach aimed at extracting quantitative data not accessible to the human eye from images expressing a disease. The data subsequently feed machine learning models and produce diagnostic or prognostic probabilities. As for the multiple applications of AI methods in thoracic imaging, they are undergoing evaluation. Chest radiography is a practically ideal field for the development of DL algorithms able to automatically interpret X-rays. Current algorithms can detect up to 14 different abnormalities present either in isolation or in combination. Chest CT is another area offering numerous AI applications. Various algorithms have been specifically formed and validated for the detection and characterization of pulmonary nodules and pulmonary embolism, as well as segmentation and quantitative analysis of the extent of diffuse lung diseases (emphysema, infectious pneumonias, interstitial lung disease). In addition, the analysis of medical images can be associated with clinical, biological, and functional data (multi-omics analysis), the objective being to construct predictive approaches regarding disease prognosis and response to treatment.

Machine learning slice-wise whole-lung CT emphysema score correlates with airway obstruction

OBJECTIVES

Quantitative CT imaging is an important emphysema biomarker, especially in smoking cohorts, but does not always correlate to radiologists' visual CT assessments. The objectives were to develop and validate a neural network-based slice-wise whole-lung emphysema score (SWES) for chest CT, to validate SWES on unseen CT data, and to compare SWES with a conventional quantitative CT method.

MATERIALS AND METHODS

Separate cohorts were used for algorithm development and validation. For validation, thin-slice CT stacks from 474 participants in the prospective cross-sectional Swedish CArdioPulmonary bioImage Study (SCAPIS) were included, 395 randomly selected and 79 from an emphysema cohort. Spirometry (FEV1/FVC) and radiologists' visual emphysema scores (sum-visual) obtained at inclusion in SCAPIS were used as reference tests. SWES was compared with a commercially available quantitative emphysema scoring method (LAV950) using Pearson's correlation coefficients and receiver operating characteristics (ROC) analysis.

RESULTS

SWES correlated more strongly with the visual scores than LAV950 (r = 0.78 vs. r = 0.41, p < 0.001). The area under the ROC curve for the prediction of airway obstruction was larger for SWES than for LAV950 (0.76 vs. 0.61, p = 0.007). SWES correlated more strongly with FEV1/FVC than either LAV950 or sum-visual in the full cohort (r =  - 0.69 vs. r =  - 0.49/r =  - 0.64, p < 0.001/p = 0.007), in the emphysema cohort (r =  - 0.77 vs. r =  - 0.69/r =  - 0.65, p = 0.03/p = 0.002), and in the random sample (r =  - 0.39 vs. r =  - 0.26/r =  - 0.25, p = 0.001/p = 0.007).

CONCLUSION

The slice-wise whole-lung emphysema score (SWES) correlates better than LAV950 with radiologists' visual emphysema scores and correlates better with airway obstruction than do LAV950 and radiologists' visual scores.

CLINICAL RELEVANCE STATEMENT

The slice-wise whole-lung emphysema score provides quantitative emphysema information for CT imaging that avoids the disadvantages of threshold-based scores and is correlated more strongly with reference tests than LAV950 and reader visual scores.

KEY POINTS

• A slice-wise whole-lung emphysema score (SWES) was developed to quantify emphysema in chest CT images. • SWES identified visual emphysema and spirometric airflow limitation significantly better than threshold-based score (LAV950). • SWES improved emphysema quantification in CT images, which is especially useful in large-scale research.

Machine learning and deep learning predictive models for long-term prognosis in patients with chronic obstructive pulmonary disease: a systematic review and meta-analysis

BACKGROUND

Machine learning and deep learning models have been increasingly used to predict long-term disease progression in patients with chronic obstructive pulmonary disease (COPD). We aimed to summarise the performance of such prognostic models for COPD, compare their relative performances, and identify key research gaps.

METHODS

We conducted a systematic review and meta-analysis to compare the performance of machine learning and deep learning prognostic models and identify pathways for future research. We searched PubMed, Embase, the Cochrane Library, ProQuest, Scopus, and Web of Science from database inception to April 6, 2023, for studies in English using machine learning or deep learning to predict patient outcomes at least 6 months after initial clinical presentation in those with COPD. We included studies comprising human adults aged 18-90 years and allowed for any input modalities. We reported area under the receiver operator characteristic curve (AUC) with 95% CI for predictions of mortality, exacerbation, and decline in forced expiratory volume in 1 s (FEV1). We reported the degree of interstudy heterogeneity using Cochran's Q test (significant heterogeneity was defined as p≤0·10 or I2>50%). Reporting quality was assessed using the TRIPOD checklist and a risk-of-bias assessment was done using the PROBAST checklist. This study was registered with PROSPERO (CRD42022323052).

FINDINGS

We identified 3620 studies in the initial search. 18 studies were eligible, and, of these, 12 used conventional machine learning and six used deep learning models. Seven models analysed exacerbation risk, with only six reporting AUC and 95% CI on internal validation datasets (pooled AUC 0·77 [95% CI 0·69-0·85]) and there was significant heterogeneity (I2 97%, p<0·0001). 11 models analysed mortality risk, with only six reporting AUC and 95% CI on internal validation datasets (pooled AUC 0·77 [95% CI 0·74-0·80]) with significant degrees of heterogeneity (I2 60%, p=0·027). Two studies assessed decline in lung function and were unable to be pooled. Machine learning and deep learning models did not show significant improvement over pre-existing disease severity scores in predicting exacerbations (p=0·24). Three studies directly compared machine learning models against pre-existing severity scores for predicting mortality and pooled performance did not differ (p=0·57). Of the five studies that performed external validation, performance was worse than or equal to regression models. Incorrect handling of missing data, not reporting model uncertainty, and use of datasets that were too small relative to the number of predictive features included provided the largest risks of bias.

INTERPRETATION

There is limited evidence that conventional machine learning and deep learning prognostic models demonstrate superior performance to pre-existing disease severity scores. More rigorous adherence to reporting guidelines would reduce the risk of bias in future studies and aid study reproducibility.

FUNDING

None.

Diagnostic efficacy of visual subtypes and low attenuation area based on HRCT in the diagnosis of COPD

Background

Chronic obstructive pulmonary disease (COPD) is a heterogeneous disease. Current gold standard criteria, pulmonary function tests (PFTs) may result in underdiagnosis of potential COPD patients. Therefore, we hypothesize that the combination of high-resolution computed tomography (HRCT) and clinical basic characteristics will enable the identification of more COPD patients.

Methods

A total of 284 patients with respiratory symptoms who were current or former smokers were included in the study, and were further divided into 5 groups of GOLD grade I–IV and non-COPD according to PFTs. All patients underwent inspiratory HRCT scanning and low attenuation area (LAA) was measured. Then they were divided into seven visual subtypes according to the Fleischner Society classification system. Non-parametric tests were used for exploring differences in basic characteristics and PFTs between different groups of enrolled patients and visual subtypes. Binary logistic regression was to find the influencing factors that affected the patients’ outcome (non-COPD vs GOLD I-IV). The area under the receiver operating characteristic curve (AUC-ROC) was to explore the diagnostic efficacy of LAA, visual subtypes, and combined basic characteristics related to COPD for COPD diagnosis. Finally, based on the cut-off values of ROC analysis, exploring HRCT features in patients who do not meet the diagnostic criteria but clinically suspected COPD.

Results

With the worsening severity of COPD, the visual subtypes gradually progressed (p < 0.01). There was a significant difference in LAA between GOLD II–IV and non-COPD (p < 0.0001). The diagnostic efficacy of LAA, visual subtypes, and LAA combined with visual subtypes for COPD were 0.742, 0.682 and 0.730 respectively. The diagnostic efficacy increased to 0.923–0.943 when basic characteristics were added (all p < 0.001). Based on the cut-off value of ROC analysis, LAA greater than 5.6, worsening of visual subtypes, combined with positive basic characteristics can help identify some potential COPD patients.

Conclusion

The heterogeneous phenotype of COPD requires a combination of multiple evaluation methods. The diagnostic efficacy of combining LAA, visual subtypes, and basic characteristics achieves good consistency with current diagnostic criteria.

Deep-Learning-Based Survival Prediction of Patients in Coronary Care Units

Background

A survival prediction model based on deep learning has higher accuracy than the CPH model in predicting the survival of CCU patients, and it also has a better discrimination ability. We collected information on patients with various diseases in coronary care units (CCUs) from the Medical Information Mart for Intensive Care III (MIMIC-III) database. The purpose of this study was to use this information to construct a neural-network model based on deep learning to predict the survival probabilities of patients with conditions that are common in CCUs.

Method

We collected information on patients in the United States with five common diseases in CCUs from 2001 to 2012. We randomly divided the patients into a training cohort and a testing cohort at a ratio of 7 : 3 and applied a survival prediction method based on deep learning to predict their survival probability. We compared our model with the Cox proportional-hazards regression (CPH) model and used the concordance indexes (C-indexes), receiver operating characteristic (ROC) curve, and calibration plots to evaluate the predictive performance of the model.

Results

The 3,388 CCU patients included in the study were randomly divided into 2,371 in the training cohort and 1,017 in the testing cohort. The stepwise regression results showed that the important factors affecting patient survival were the type of disease, age, race, anion gap, glucose, neutrophils, white blood cells, potassium, creatine kinase, and blood urea nitrogen (P < 0.05). We used the training cohort to construct a deep-learning model, for which the C-index was 0.833, or about 5% higher than that for the CPH model (0.786). The C-index of the deep-learning model for the test cohort was 0.822, which was also higher than that for the CPH model (0.782). The areas under the ROC curve for the 28-day, 90-day, and 1-year survival probabilities were 0.875, 0.865, and 0.874, respectively, in the deep-learning model, respectively, and 0.830, 0.843, and 0.806 in the CPH model. These values indicate that the survival analysis model based on deep learning is better than the traditional CPH model in predicting the survival of CCU patients.

Conclusion

A survival prediction model based on deep learning has higher accuracy than the CPH model in predicting the survival of CCU patients, and it also has a better discrimination ability.