Prognostic value of deep learning-based fibrosis quantification on chest CT in idiopathic pulmonary fibrosis

Identification of risk factors for acute exacerbation of idiopathic pulmonary fibrosis based on baseline high-resolution computed tomography: a prospective observational study

BACKGROUND

This study aimed to investigate risk factors for acute exacerbation of idiopathic pulmonary fibrosis (AE-IPF) based on baseline high-resolution computed tomography (HRCT).

METHODS

This prospective observational study enrolled patients with IPF treated at the General Hospital of Ningxia Medical University between January 2019 and January 2021. HRCT-derived quantitative parameters at baseline were analyzed.

RESULTS

A total of 102 patients [92 (90.2%) males with a mean age of 67 years] with IPF were included, with a median follow-up of 32 (24-40.5) months. AE occurred in 30 (29.4%) IPF patients. Multivariable logistic regression analysis identified Doppler transthoracic echocardiography suggestive of pulmonary hypertension (PH) (13.43; 95% CI: 4.18-41.09; P < 0.001), honeycombing (OR 1.08; 95% CI: 1.02-1.14; P = 0.013), and whole lung volume (OR 0.99; 95% CI: 0.99-1.00; P = 0.037) as independent risk factors for AE-IPF. The combination of PH, honeycombing, whole lung volume, and the percentage of predicted forced vital capacity (FVC% pred) showed a high area under the curve from receiver operating characteristic curves of 0.888, with a sensitivity of 90% and specificity of 78%.

CONCLUSIONS

This study emphasizes that quantitative CT parameters (honeycombing, whole lung volume) may serve as risk factors for AE-IPF. The combination of honeycombing, whole lung volume, FVC% pred, and PH may aid in predicting AE-IPF.

CT Quantification of Interstitial Lung Abnormality and Interstitial Lung Disease: From Technical Challenges to Future Directions

ABSTRACT

Interstitial lung disease (ILD) encompasses a variety of lung disorders with varying degrees of inflammation or fibrosis, requiring a combination of clinical, imaging, and pathologic data for evaluation. Imaging is essential for the noninvasive diagnosis of the disease, as well as for assessing disease severity, monitoring its progression, and evaluating treatment response. However, traditional visual assessments of ILD with computed tomography (CT) suffer from reader variability. Automated quantitative CT offers a more objective approach by using computer-based analysis to consistently evaluate and measure ILD. Advancements in technology have significantly improved the accuracy and reliability of these measurements. Recently, interstitial lung abnormalities (ILAs), which represent potential preclinical ILD incidentally found on CT scans and are characterized by abnormalities in over 5% of any lung zone, have gained attention and clinical importance. The challenge lies in the accurate and consistent identification of ILA, given that its definition relies on a subjective threshold, making quantitative tools crucial for precise ILA evaluation. This review highlights the state of CT quantification of ILD and ILA, addressing clinical and research disparities while emphasizing how machine learning or deep learning in quantitative imaging can improve diagnosis and management by providing more accurate assessments, and finally, suggests the future directions of quantitative CT in this area.

Deep learning-based prognostication in idiopathic pulmonary fibrosis using chest radiographs

OBJECTIVES

To develop and validate a deep learning-based prognostic model in patients with idiopathic pulmonary fibrosis (IPF) using chest radiographs.

METHODS

To develop a deep learning-based prognostic model using chest radiographs (DLPM), the patients diagnosed with IPF during 2011-2021 were retrospectively collected and were divided into training (n = 1007), validation (n = 117), and internal test (n = 187) datasets. Up to 10 consecutive radiographs were included for each patient. For external testing, three cohorts from independent institutions were collected (n = 152, 141, and 207). The discrimination performance of DLPM was evaluated using areas under the time-dependent receiver operating characteristic curves (TD-AUCs) for 3-year survival and compared with that of forced vital capacity (FVC). Multivariable Cox regression was performed to investigate whether the DLPM was an independent prognostic factor from FVC. We devised a modified gender-age-physiology (GAP) index (GAP-CR), by replacing DLCO with DLPM.

RESULTS

DLPM showed similar-to-higher performance at predicting 3-year survival than FVC in three external test cohorts (TD-AUC: 0.83 [95% CI: 0.76-0.90] vs. 0.68 [0.59-0.77], p < 0.001; 0.76 [0.68-0.85] vs. 0.70 [0.60-0.80], p = 0.21; 0.79 [0.72-0.86] vs. 0.76 [0.69-0.83], p = 0.41). DLPM worked as an independent prognostic factor from FVC in all three cohorts (ps < 0.001). The GAP-CR index showed a higher 3-year TD-AUC than the original GAP index in two of the three external test cohorts (TD-AUC: 0.85 [0.80-0.91] vs. 0.79 [0.72-0.86], p = 0.02; 0.72 [0.64-0.80] vs. 0.69 [0.61-0.78], p = 0.56; 0.76 [0.69-0.83] vs. 0.68 [0.60-0.76], p = 0.01).

CONCLUSIONS

A deep learning model successfully predicted survival in patients with IPF from chest radiographs, comparable to and independent of FVC.

CLINICAL RELEVANCE STATEMENT

Deep learning-based prognostication from chest radiographs offers comparable-to-higher prognostic performance than forced vital capacity.

KEY POINTS

• A deep learning-based prognostic model for idiopathic pulmonary fibrosis was developed using 6063 radiographs. • The prognostic performance of the model was comparable-to-higher than forced vital capacity, and was independent from FVC in all three external test cohorts. • A modified gender-age-physiology index replacing diffusing capacity for carbon monoxide with the deep learning model showed higher performance than the original index in two external test cohorts.

Hunting imaging biomarkers in pulmonary fibrosis: Benchmarks of the AIIB23 challenge

Airway-related quantitative imaging biomarkers are crucial for examination, diagnosis, and prognosis in pulmonary diseases. However, the manual delineation of airway structures remains prohibitively time-consuming. While significant efforts have been made towards enhancing automatic airway modelling, current public-available datasets predominantly concentrate on lung diseases with moderate morphological variations. The intricate honeycombing patterns present in the lung tissues of fibrotic lung disease patients exacerbate the challenges, often leading to various prediction errors. To address this issue, the 'Airway-Informed Quantitative CT Imaging Biomarker for Fibrotic Lung Disease 2023' (AIIB23) competition was organized in conjunction with the official 2023 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). The airway structures were meticulously annotated by three experienced radiologists. Competitors were encouraged to develop automatic airway segmentation models with high robustness and generalization abilities, followed by exploring the most correlated QIB of mortality prediction. A training set of 120 high-resolution computerised tomography (HRCT) scans were publicly released with expert annotations and mortality status. The online validation set incorporated 52 HRCT scans from patients with fibrotic lung disease and the offline test set included 140 cases from fibrosis and COVID-19 patients. The results have shown that the capacity of extracting airway trees from patients with fibrotic lung disease could be enhanced by introducing voxel-wise weighted general union loss and continuity loss. In addition to the competitive image biomarkers for mortality prediction, a strong airway-derived biomarker (Hazard ratio>1.5, p < 0.0001) was revealed for survival prognostication compared with existing clinical measurements, clinician assessment and AI-based biomarkers.

Usefulness of CT Quantification-Based Assessment in Defining Progressive Pulmonary Fibrosis

RATIONALE AND OBJECTIVES

To establish a quantitative CT threshold for radiological disease progression of progressive pulmonary fibrosis (PPF) and evaluate its feasibility in patients with connective tissue disease-related interstitial lung disease (CTD-ILD).

MATERIALS AND METHODS

Between April 2007 and October 2022, patients diagnosed with CTD-ILD retrospectively evaluated. CT quantification was conducted using a commercial software by summing the percentages of ground-glass opacity, consolidation, reticular opacity, and honeycombing. The quantitative threshold for radiological progression was determined based on the highest discrimination on overall survival (OS). Two thoracic radiologists independently evaluated visual radiological progression, and the senior radiologist's assessment was used as the final result. Cox regression was used to assess prognosis of PPF based on the visual assessment and quantitative threshold.

RESULTS

97 patients were included and followed up for a median of 30.3 months (range, 4.7-198.1 months). For defining radiological disease progression, the optimal quantitative CT threshold was 4%. Using this threshold, 12 patients were diagnosed with PPF, while 14 patients were diagnosed with PPF based on the visual assessment, with an agreement rate of 97.9% (95/97). Worsening respiratory symptoms (hazard ratio [HR], 12.73; P < .001), PPF based on the visual assessment (HR, 8.86; P = .002) and based on the quantitative threshold (HR, 6.72; P = .009) were independent risk factors for poor OS.

CONCLUSION

The quantitative CT threshold for radiological disease progression (4%) was feasible in defining PPF in terms of its agreement with PPF grouping and prognostic performance when compared to visual assessment.

Meaningful Endpoints for Idiopathic Pulmonary Fibrosis (IPF) Clinical Trials: Emphasis on 'Feels, Functions, Survives'. Report of a Collaborative Discussion in a Symposium with Direct Engagement from Representatives of Patients, Investigators, the National Institutes of Health, a Patient Advocacy Organization, and a Regulatory Agency

Background: Idiopathic pulmonary fibrosis (IPF) carries significant mortality and unpredictable progression, with limited therapeutic options. Designing trials with patient-meaningful endpoints, enhancing the reliability and interpretability of results, and streamlining the regulatory approval process are of critical importance to advancing clinical care in IPF. Methods: A landmark in-person symposium in June 2023 assembled 43 participants from the US and internationally, including patients with IPF, investigators, and regulatory representatives, to discuss the immediate future of IPF clinical trial endpoints. Patient advocates were central to discussions, which evaluated endpoints according to regulatory standards and the FDA's 'feels, functions, survives' criteria. Results: Three themes emerged: 1) consensus on endpoints mirroring the lived experiences of patients with IPF; 2) consideration of replacing forced vital capacity (FVC) as the primary endpoint, potentially by composite endpoints that include 'feels, functions, survives' measures or FVC as components; 3) support for simplified, user-friendly patient-reported outcomes (PROs) as either components of primary composite endpoints or key secondary endpoints, supplemented by functional tests as secondary endpoints and novel biomarkers as supportive measures (FDA Guidance for Industry (Multiple Endpoints in Clinical Trials) available at: https://www.fda.gov/media/162416/download). Conclusions: This report, detailing the proceedings of this pivotal symposium, suggests a potential turning point in designing future IPF clinical trials more attuned to outcomes meaningful to patients, and documents the collective agreement across multidisciplinary stakeholders on the importance of anchoring IPF trial endpoints on real patient experiences-namely, how they feel, function, and survive. There is considerable optimism that clinical care in IPF will progress through trials focused on patient-centric insights, ultimately guiding transformative treatment strategies to enhance patients' quality of life and survival.

Identifying a survival-associated cell type based on multi-level transcriptome analysis in idiopathic pulmonary fibrosis

BACKGROUND

Idiopathic pulmonary fibrosis (IPF) is a progressive disease with a five-year survival rate of less than 40%. There is significant variability in survival time among IPF patients, but the underlying mechanisms for this are not clear yet.

METHODS AND RESULTS

We collected single-cell RNA sequence data of 13,223 epithelial cells taken from 32 IPF patients and bulk RNA sequence data from 456 IPF patients in GEO. Based on unsupervised clustering analysis at the single-cell level and deconvolution algorithm at bulk RNA sequence data, we discovered a special alveolar type 2 cell subtype characterized by high expression of CCL20 (referred to as ATII-CCL20), and found that IPF patients with a higher proportion of ATII-CCL20 had worse prognoses. Furthermore, we uncovered the upregulation of immune cell infiltration and metabolic functions in IPF patients with a higher proportion of ATII-CCL20. Finally, the comprehensive decision tree and nomogram were constructed to optimize the risk stratification of IPF patients and provide a reference for accurate prognosis evaluation.

CONCLUSIONS

Our study by integrating single-cell and bulk RNA sequence data from IPF patients identified a special subtype of ATII cells, ATII-CCL20, which was found to be a risk cell subtype associated with poor prognosis in IPF patients. More importantly, the ATII-CCL20 cell subtype was linked with metabolic functions and immune infiltration.