Interstitial lung abnormalities detected incidentally on CT: a Position Paper from the Fleischner Society

Progressive Pulmonary Fibrosis and Interstitial Lung Abnormalities: AJR Expert Panel Narrative Review

Progressive pulmonary fibrosis (PPF) and interstitial lung abnormalities (ILA) are relatively new concepts in interstitial lung disease (ILD) imaging and clinical management. Recognition of signs of PPF and identification and classification of ILA are important tasks during chest high-resolution CT interpretation to optimize management of patients with ILD and those at risk of developing ILD. However, in professional society guidance, the role of imaging surveillance remains unclear for stable patients with ILD, asymptomatic patients with ILA who are at risk of progression, and asymptomatic patients at risk of developing ILD without imaging abnormalities. In this AJR Expert Panel Narrative Review, we summarize the current knowledge regarding PPF and ILA and describe the range of clinical practice with respect to imaging patients with ILD, those with ILA, and those at risk of developing ILD. In addition, we offer suggestions to help guide surveillance imaging in areas with an absence of published guidelines, where such decisions are currently driven primarily by local pulmonologists' preference.

Antinuclear antibodies and progression of quantitative interstitial lung changes: The Multi-Ethnic Study of Atherosclerosis (MESA)-Lung Study

Antinuclear antibodies (ANA) are often found in ILD; whether ANA is associated with radiographic progression of quantitive interstitial lung changes is unknown. We performed longitudinal analyses of adults in the Multi-Ethnic Study of Atherosclerosis using linear mixed effects models with random intercept and slope to evaluate whether baseline ANA was associated with change in the amount of lung with high attenuation areas on CT (HAAs, percentage of imaged lung with -600 to -250 HU). In 6,638 subjects with 17,293 CT scans over 18 years, 741 (11 %) were ANA positive. ANA was not associated with HAA progression with ANA as a dichotomous variable (0.13 % less progression per year for ANA positive vs negative, 95%CI -0.33 %-0.07 %, p = 0.19) or as a continuous variable (0.004 % less progression per year per 10 % increase in ANA, 95%CI -0.01 %-0.005 %, p = 0.37). ANA was not associated with progression of HAA in community dwelling adults.

Imaging Climate-Related Environmental Exposures: Impact and Opportunity

Climate change is the most important challenge of this century. Global surface temperature is continuously rising to new record highs, adversely affecting the health of the planet and humans. The purpose of this article is to review the impact of climate related environmental exposures on human health, healthcare delivery, and medical imaging and explore the potential to leverage medical imaging as a non-invasive tool to advance our understanding of climate related health effects. Radiology departments and healthcare systems must focus on building resilience to the effects of climate change while ensuring that the delivery of care is environmentally sustainable. Further research is needed to refine our understanding of the effects of climate change on human health and to forecast the expected changes in the demand for healthcare and radiology services.

Validation of a semi-quantitative method to assess interstitial lung disease severity and progression in systemic sclerosis by standard and low-dose HRCT scans

BACKGROUND

While the presence of distinct imaging abnormalities by high-resolution CT (HRCT) defines interstitial lung disease (ILD), there is a relative lack of validated methods to quantify these abnormalities in clinical practice, limiting ILD severity and progression assessments. We aimed to validate a semi-quantitative method for lung fibrosis assessment in patients with systemic sclerosis associated ILD (SSc-ILD) by standard and low-dose HRCT, considering lung structure and function as integral components of ILD evaluation.

METHODS

SSc patients from Oslo and Zurich with HRCT images, pulmonary function tests, including forced vital capacity (FVC), diffusing capacity for carbon monoxide (DLCO) and the 6-minute walk test with oxygen (O2) desaturation were enrolled. We validated the semi-quantitative fibrosis extent method by HRCT using criteria for content and construct validity, discrimination, sensitivity to change and feasibility, as well as inter- and intra-rater variability.

RESULTS

65 SSc patients from Zurich and 90 from Oslo were included. Significant correlations were observed between the extent of fibrosis on HRCT and FVC (r=-0.517, p<0.001), DLCO (r=-0.400, p<0.001) and O2 desaturation (r=-0.500, p<0.001), indicating content, construct and criterion validity. Discrimination and sensitivity to change assessments showed moderate correlation with DLCO (r=-0.377, p=0.003) but not with FVC or O2 desaturation. Inter- and intra-rater variability demonstrated excellent reliability (κ=0.891 and κ=0.996, respectively), with HRCT quantification averaging 9-15 min, indicating high feasibility.

CONCLUSION

This study confirms that semi-quantitative fibrosis assessment of HRCT for SSc-ILD meets most validation criteria, supporting its use in clinical practice and showing additive value of structural to functional ILD assessment.

Lung ultrasound outperforms symptom-based screening to detect interstitial lung disease associated with rheumatoid arthritis

OBJECTIVES

Interstitial lung disease associated with rheumatoid arthritis (RA-ILD) is linked to high mortality. Currently, effective screening tools are lacking. We assessed the role of symptoms and lung ultrasound (LUS) as potential screening tools.

METHODS

116 adult patients with RA presenting to the rheumatology outpatient clinic underwent high-resolution CT (HRCT) scans, pulmonary function tests, LUS (72 zones) and completed a Visual Analogue Scale (VAS) for cough and modified Medical Research Council dyspnoea scale (mMRC). Kruskal-Wallis (KW) tests evaluated the correlation between clinical-radiological HRCT score (no ILD, non-specific abnormalities, subclinical ILD or ILD) and the B-lines on LUS, diffusion capacity (DLCO%pred), forced vital capacity (FVC%pred), VAS Cough and mMRC. Sensitivity and specificity analyses were performed to assess symptom-based questionnaires and the number of B-lines to detect RA-ILD. Area under the receiver operating characteristics (AUROC) for detecting clinical ILD and subclinical ILD were calculated.

RESULTS

In 11.8% of patients, an ILD was detected on HRCT. Additionally, in 5%, a diagnosis of subclinical interstitial lung changes was made. The number of B-lines was most strongly associated with the clinical-radiological score (KW χ²=41.2, p=<0.001). DLCO%pred was also significantly correlated with the clinical-radiological score (KW χ²=27.4, p=<0.001), but FVC%pred, mMRC and VAS cough were not. Cough and dyspnoea only weakly predicted the ILD score in the sensitivity-specificity analyses, while B-lines showed AUROCs>0.9 for predicting subclinical and clinical ILD.

CONCLUSION

LUS is a promising tool for early detection of RA-ILD, outperforming symptom-based questionnaires or the presence of dyspnoea or cough.

Interstitial Lung Abnormalities: Unraveling the Journey from Incidental Discovery to Clinical Significance

Interstitial lung abnormalities (ILAs) are incidental radiologic abnormalities on chest computed tomography (CT) examination performed on people in whom interstitial lung disease (ILD) is not suspected. Despite the fact that most of these individuals are asymptomatic, ILAs are not synonymous with subclinical ILD, as a subset of them have symptoms and lung function impairment. On the other hand, not all ILAs progress to clinically significant ILD. Specific imaging features and patterns have been proven more likely to progress, while some individuals may comprise a higher risk group for progression. Numerous studies have demonstrated that ILAs are not only associated with an increased risk of progression toward pulmonary fibrosis and fibrosis-related mortality but are also linked to a greater incidence of lung cancer and a higher rate of all-cause mortality. Considering that the systematic evaluation of large cohorts has shown a prevalence of ILAs up to 7% and that the natural history of ILAs is unclear, successful screening and appropriate monitoring of ILAs is of particular significance for earlier diagnosis, risk factor modification, and treatment. The present review aims to summarize the current knowledge on ILAs and highlight the need to define those at greatest risk of progression to ILD and worse clinical outcomes.

Association of interstitial lung abnormalities with cytotoxic agent-induced pneumonitis in patients with malignancy

BACKGROUND AND OBJECTIVE

The association between interstitial lung abnormalities (ILA) and various conditions and diseases, including drug-related pneumonitis (DRP), has been reported. However, the association of the presence of ILA with developing DRP in patients undergoing cytotoxic agent-based chemotherapy, one of the standard treatments for malignancies, remains unclear. This warrants urgent investigation.

METHODS

We included consecutive patients diagnosed with malignancy and treated with cytotoxic agents with/without immune checkpoint inhibitors (ICIs). We used Gray's method and multivariate Fine-Gray sub-distribution hazards analysis to evaluate the cumulative incidence of DRP (common terminology criteria for adverse events grade of ≥3) and the association between ILA and DRP development, respectively.

RESULTS

Among 786 patients, 58 (7.3 %) demonstrated ILA. Patients with ILA were older, predominantly male, and reported a higher smoking history compared to those without ILA. The 90-day cumulative incidence of cytotoxic agent-induced DRP with/without ICIs was significantly higher in patients with ILA than in those without ILA (6.0 % vs. 1.2 %, p = 0.006). Multivariate analysis, adjusted for age, sex, and smoking history, revealed that ILA was associated with an increased risk of developing DRP due to cytotoxic agents with/without ICIs (hazard ratio [HR] 3.11, 95 % confidence interval [CI]: 1.06-9.14, p = 0.039) and cytotoxic agents alone (HR: 5.53, 95 % CI: 1.55-19.7, p = 0.008).

CONCLUSIONS

The presence of ILA is associated with an increased risk of developing DRP in patients undergoing cytotoxic agent-based chemotherapy. Therefore, evaluating the presence of ILA before determining chemotherapy regimens that include cytotoxic agents is recommended.

Ultra-high resolution spectral photon-counting CT outperforms dual layer CT for lung imaging: Results of a phantom study

PURPOSE

The purpose of this study was to compare lung image quality obtained with ultra-high resolution (UHR) spectral photon-counting CT (SPCCT) with that of dual-layer CT (DLCT), at standard and low dose levels using an image quality phantom and an anthropomorphic lung phantom.

METHODS

An image quality phantom was scanned using a clinical SPCCT prototype and an 8 cm collimation DLCT from the same manufacturer at 10 mGy. Additional acquisitions at 6 mGy were performed with SPCCT only. Images were reconstructed with dedicated high-frequency reconstruction kernels, slice thickness between 0.58 and 0.67 mm, and matrix between 5122 and 10242 mm, using a hybrid iterative algorithm at level 6. Noise power spectrum (NPS), task-based transfer function (TTF) for iodine and air inserts, and detectability index (d') were assessed for ground-glass and solid nodules of 2 mm to simulate highly detailed lung lesions. Subjective analysis of an anthropomorphic lung phantom was performed by two radiologists using a five-point quality score.

RESULTS

At 10 mGy, noise magnitude was reduced by 29.1 % with SPCCT images compared to DLCT images for all parameters (27.1 ± 11.0 [standard deviation (SD)] HU vs. 38.2 ± 1.0 [SD] HU, respectively). At 6 mGy with SPCCT images, noise magnitude was reduced by 8.9 % compared to DLCT images at 10 mGy (34.8 ± 14.1 [SD] HU vs. 38.2 ± 1.0 [SD] HU, respectively). At 10 mGy and 6 mGy, average NPS spatial frequency (fav) was greater for SPCCT images (0.75 ± 0.17 [SD] mm-1) compared to DLCT images at 10 mGy (0.55 ± 0.04 [SD] mm-1) while remaining constant from 10 to 6 mGy. At 10 mGy, TTF at 50 % (f50) was greater for SPCCT images (0.92 ± 0.08 [SD] mm-1) compared to DLCT images (0.67 ± 0.06 [SD] mm-1) for both inserts. At 6 mGy, f50 decreased by 1.1 % for SPCCT images, while remaining greater compared to DLCT images at 10 mGy (0.91 ± 0.06 [SD] mm-1 vs. 0.67 ± 0.06 [SD] mm-1, respectively). At both dose levels, d' were greater for SPCCT images compared to DLCT for all clinical tasks. Subjective analysis performed by two radiologists revealed a greater median image quality for SPCCT (5; Q1, 4; Q3, 5) compared to DLCT images (3; Q1, 3; Q3, 3).

CONCLUSION

UHR SPCCT outperforms DLCT in terms of image quality for lung imaging. In addition, UHR SPCCT contributes to a 40 % reduction in radiation dose compared to DLCT.

Predictive factors of fibrotic interstitial lung abnormality on high-resolution computed tomography scans: a prospective observational study

BACKGROUND

Fibrotic types of interstitial lung abnormalities seen on high-resolution computed tomography scans, characterised by traction bronchiolectasis/bronchiectasis with or without honeycombing, are predictors of progression and poor prognostic factors of interstitial lung abnormalities. There are no reports on the clinical characteristics of fibrotic interstitial lung abnormalities on high-resolution computed tomography scans. Therefore, we aimed to examine these clinical characteristics and clarify the predictive factors of fibrotic interstitial lung abnormalities on high-resolution computed tomography scans.

METHODS

Clinical and paraclinical data of 164 patients enrolled in the initial year of a multicentre prospective observational study (Kumamoto interstitial lung abnormalities study in Japan) involving over 62,000 examinees during routine health examinations were analysed. Clinical laboratory evaluations are expressed as medians and interquartile ranges for each evaluation time point, and boxplots were created for graphical representation. The percentages of abnormal clinical laboratory results were compared between the groups using chi-square or Fisher's exact tests. Univariate or multivariate logistic regression analyses were performed to analyse the relationship between fibrotic interstitial lung abnormalities and other clinical factors.

RESULTS

Fibrotic interstitial lung abnormalities were observed on high-resolution computed tomography scans in 135 (82%) patients at the time of diagnosis. Multivariate analysis showed that older age (Odds ratio, 1.06; 95% confidence interval, 1.01-1.12; p = 0.021), auscultatory fine crackles (Odds ratio, 3.39; 95% confidence interval, 1.33-8.65; p < 0.01), and elevated serum surfactant protein-D (Odds ratio, 2.68; 95% confidence interval, 1.02-8.64; p = 0.045) were independent predictive factors of fibrotic interstitial lung abnormalities. The predicted area under the curve of the fibrotic interstitial lung abnormalities based on these three factors was 0.77 (95% confidence interval, 0.68-0.86). The proportion of undecided diagnoses in the fibrotic interstitial lung abnormalities group (14%) was significantly lower than that in the non-fibrotic interstitial lung abnormalities group (41%) (p = 0.0027).

CONCLUSIONS

Fine crackles on auscultation and elevated serum surfactant protein-D levels are predictors of fibrotic interstitial lung abnormalities in older patients with interstitial lung abnormalities. These findings may assist non-radiological physicians in referring patients to specialists for early intervention in progressive fibrotic interstitial lung diseases.

TRIAL REGISTRATION NUMBER/DATE

UMIN000045149/2021.12.1.

Prediction of pulmonary function decline in fibrous interstitial lung abnormalities based on quantitative chest CT parameters

BACKGROUND

Interstitial lung abnormalities (ILA) are a proposed imaging concept. Fibrous ILA have a higher risk of progression and death. Clinically, computed tomography (CT) examination is a frequently used and convenient method compared with pulmonary function tests. This study aimed to correlate quantitative CT airway parameters with pulmonary function parameters in patients with fibrous ILA, with the goal of establishing a prediction model for abnormal pulmonary function parameters in patients with fibrous ILA.

METHODS

Ninety-five cases of fibrous ILA including CT images and 64 normal control cases were collected. All patients completed pulmonary function tests within one week. The airway parameters of the CT images of the two groups of cases were measured using a commercial software (Aview). Differences in airway parameters and lung function parameters between the two groups were analyzed by logistic multifactorial regression. The correlation between airway parameters and lung function parameters among 95 patients with fibrous ILA and a prediction model was determined for the decreased percentage forced vital capacity to predicted normal value (FVC%pred) in patients with fibrous ILA.

RESULTS

Logistic multifactorial regression correlated FVC%pred and bronchial wall thickness (WT) were correlated with fibrous ILA. The 95 patients with fibrous ILA were divided into normal FVC%pred (n = 69) and decreased FVC%pred (n = 26) groups at the 80% cut-off. Logistic multifactorial regression revealed that FVC%pred decline in patients with fibrous ILA was effectively predicted by age (odds ratio [OR]: 1.11, 95% confidence interval [CI]: 1.02-1.21, p = 0.014), gender (OR: 4.16,95% CI: 1.27-13.71, p = 0.019), luminal area of the sixth generation brochi (LA6; OR: 0.87, 95%CI: 0.78-0.970,p = 0.015), and airway wall area (WA; OR: 1.12, 95%CI: 1.02-1.24, p = 0.020) were effective predictors of. The area under the curve of the prediction model based on the four parameters was 0.8428.

CONCLUSION

WT is a quantitative CT biomarker and FVC%pred is a valid lung function parameter in fibrous ILA patients. Age, gender, LA6, and WA are effective predictors of FVC%pred decline in fibrous ILA patients. The combined model has good predictive value.

CLINICAL TRIAL NUMBER

2024K249.

Risk factors for interstitial lung disease in early rheumatoid arthritis and external validation of screening strategies: Baseline results of SAIL-RA

Background

Risk factors and screening strategies for rheumatoid arthritis-associated interstitial lung disease (RA-ILD) have received limited evaluation in patients with early RA. We investigated RA-ILD prevalence, risk factors, and the performance of proposed RA-ILD screening methodologies in a multicenter, prospective study of patients with early RA.

Methods

Participants with early RA, defined as being within two years of RA diagnosis, were enrolled at five US sites and assessed with high-resolution computed tomography (HRCT) chest imaging, pulmonary function tests, and autoantibodies. RA-ILD presence was determined through independent HRCT review by thoracic radiologists. We investigated RA-ILD risk factors using multivariable logistic regression and reported the predictive performance of RA-ILD screening strategies (ANCHOR-RA, 2023 ACR/CHEST, Four Factor Score, and ESPOIR).

Results

Among 172 participants (74% female, 82% seropositive, median RA duration 0.79 years, mean age 55.3 years), 19 (11%) had ILD on HRCT. Moderate/high RA disease activity by DAS28ESR (OR 7.00 [1.95, 25.1]) and age ≥60 years (OR 3.87 [1.33, 11.3]) were associated with RA-ILD. Sensitivity and specificity of screening strategies ranged from 0.32-0.95 and 0.32-0.81, respectively. The number of early RA patients needing screening to detect one ILD case ranged from 3.6 to 6.4.

Discussion

In this prospective, multicenter study, ILD prevalence in early RA was 11%. Disease activity and older age were strongly associated with ILD in early RA, and several proposed ILD screening strategies performed showed promise for enabling ILD screening in early RA.

Unmasking Pulmonary Parenchymal Changes in Psoriasis Patients: A Radiological Perspective

Background and Objectives: The relationship between psoriasis and pulmonary comorbidities remains to be explained. Our main objective was to investigate pulmonary parenchymal alterations in psoriasis outpatients with chest CT scans who did not exhibit pulmonary symptoms, regardless of their course of treatment or disease severity. Materials and Methods: We examined pulmonary function tests, laboratory data, and SF-36 questionnaires from 270 consecutive psoriasis patients who underwent high-resolution computed tomography scans. Psoriasis duration, treatment details, and smoking status were analyzed to identify the associations affecting lung involvement. Results: The median age was 48 years, and the median duration of psoriasis was 15 years. A total of 72.6% were on biologics with a median PASI score of 1.5. In total, 43.2% were current smokers. Radiologists reported parenchymal lesions in 118 (43%) of the 270 patients' HRCT images. Reticular changes (41%) were the most common radiological finding, followed by nodules (38%), and emphysematous changes (21%). Only age, mental health, and smoking status were found to influence the possibility of the occurrence of HRCT findings in multivariate analysis (p < 0.001). PASI scores and treatment options did not impact pulmonary parenchymal alterations (p > 0.05). Conclusions: The striking part was that when compared to never smokers, the imaging findings were 1.9 times more common in current smokers (p < 0.05). Using international consensus criteria, two (0.01%) patients were radiologically diagnosed as UIP, and two (0.01%) were identified as NSIP. Psoriasis patients may exert pulmonary disease without clinical manifestation. Pulmonary function tests and radiological evaluation with CT are highly recommended in detecting pulmonary parenchymal changes when indications such as age and current smoking history are present.

Recent trends in scientific research in chest radiology: What to do or not to do? That is the critical question in research

Hereby inviting young rising stars in chest radiology in Japan for contributing what they are working currently, we would like to show the potentials and directions of the near future research trends in the research field. I will provide a reflection on my own research topics. At the end, we also would like to discuss on how to choose the themes and topics of research: What to do or not to do? We strongly believe it will stimulate and help investigators in the field.

Exploring the Potential Value of [ 68 Ga]Ga-FAPI-46 PET/CT for Molecular Assessment of Fibroblast Activation in Interstitial Lung Disease : A Single-Center Pilot Study

BACKGROUND

The aim of the study was to evaluate the association of high-resolution computed tomography (HRCT) findings with pulmonary fibrotic activity in the corresponding regions using [ 68 Ga]Ga-fibroblast activation fibroblast inhibitor (FAPI) PET/CT in patients with interstitial lung disease (ILD). Additionally, the potential of [ 68 Ga]Ga-FAPI-46 PET/CT for evaluating the active fibrosis process and 99m Tc-MIBI scintigraphy for assessing the inflammatory process in ILD patients was also assessed.

METHODS

In this pilot study, 20 ILD patients underwent [ 68 Ga]Ga-FAPI-46 PET/CT and 99m Tc-MIBI SPECT/CT. Additionally, 10 patients without lung or thoracic involvement who were undergoing [ 68 Ga]Ga-FAPI PET/CT for cancer detection were enrolled in the control group. The images were evaluated both visually and semiquantitatively and also compared with HRCT and pulmonary function tests. Multiple quantitative parameters were derived from the lung segments in the PET scan, including SUV max , SUV mean , maximum target-to-liver ratio, mean target-to-liver ratio (TLR mean ), and total lesion FAPI expression for the entire lung, as well as its lobes and zones. Additionally, the maximum Hounsfield unit (HU) and mean HU in HRCT were calculated for the whole lung as well as its lobes and zones. Furthermore, an HRCT fibrosis score (HFS) was defined according to the HRCT findings.

RESULTS

Twenty ILD patients with a mean age of 58.70 (SD, 11.09) years were enrolled. Additionally, 10 control patients were enrolled with a mean age of 57.70 (SD, 15.19) years. Based on visual assessment, the FAPI scan was positive in 12 (60%) patients. Similarly, the MIBI scan was positive in 12 (60%) patients. In the 20 ILD cases, both scans were positive in 6 cases, and both were negative in 2 cases. Six cases showed FAPI-negative and MIBI-positive results, whereas another 6 cases showed FAPI-positive and MIBI-negative results. Comparing the control and ILD patients, there was a significant difference in SUV max , SUV mean , total lesion FAPI expression, TLR mean , maximum HU, and mean HU ( P < 0.05). When comparing HFS with PET-derived parameters in zones, a significant positive correlation was found between HFS and SUV mean , SUV max , maximum target-to-liver ratio, and TLR mean ( P < 0.05). Additionally, a significant difference was noted between FAPI results and HFS ( P = 0.003). An ancillary finding, 9 of 20 (45%) ILD patients showed intense FAPI uptakes in gallbladder, whereas none of the 10 in the control group showed such uptake.

CONCLUSION

The present study may suggest that combining [ 68 Ga]Ga-FAPI PET/CT and 99m Tc-MIBI SPECT/CT yields an additive effect for evaluating ILD-related fibrosis and inflammatory processes over using either modality alone. Furthermore, it appears that [ 68 Ga]Ga-FAPI PET/CT has the potential to ascertain levels of fibrotic activity from population of resident fibroblasts, active fibroblasts, and scar maturation among ILD patients based on their HRCT patterns.

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.

Prevalence and progression rate of interstitial lung abnormalities detected on thoracic CT: a systematic review and meta-analysis

OBJECTIVES

To estimate the pooled prevalence and progression rate of ILAs and identify the risk factors for radiological progression.

MATERIALS AND METHODS

An EMBASE and PubMed search was undertaken, identifying all studies meeting the inclusion criteria performed before May 10, 2023. Random effect models were used to estimate pooled prevalence, ILA progression rates, and odds ratio for radiological progression based on radiological subtype. Subgroup analyses were performed to compare the general and high-risk populations for lung cancer. The quality of the included studies was evaluated using the risk of bias assessment tool for non-randomized studies.

RESULTS

We analyzed 19 studies (241,541 patients) and 10 studies (1317 patients) for the pooled prevalence and progression rate of ILA, respectively. The pooled ILA prevalence was 9.7% (95% CI, 6.1-13.9%). The pooled prevalence was 6.8% (95% CI, 3.1-11.6%) and 7.1% (95% CI, 2.2-14.4%) in the general (six studies) and high-risk population for lung cancer (six studies), respectively. The pooled progression rate was 47.1% (95% CI, 29.1-65.5%). The pooled progression rate was 64.2% (95% CI, 45.0-81.2%, five studies) and 31.0% (95% CI, 8.2-60.5%, five studies) for longer (≥ 4.5 years) and shorter follow-up periods (< 4.5 years), respectively (p = 0.009). Fibrotic ILAs were significantly associated with a higher progression probability (combined OR, 5.55; 95% CI, 1.95-15.82).

CONCLUSIONS

The prevalence of ILAs was approximately 9.7%. Approximately half of the patients exhibited radiological progression, with the rate increasing over a longer follow-up period. Fibrotic ILA was a significant risk factor for radiological progression.

CLINICAL RELEVANCE STATEMENT

The prevalence of interstitial lung abnormalities (ILAs) is approximately 9.7%, with about half exhibiting progression; a longer follow-up duration and fibrotic ILAs are associated with a higher progression rate.

KEY POINTS

ILAs are increasingly recognized as important, but few population data are available. ILAs exhibited a pooled prevalence of 9.7% with a progression rate of 47.1%. Fibrotic ILAs were associated with increased progression likelihood.

Idiopathic Dendriform Pulmonary Ossification Diagnosed by Transbronchial Lung Cryobiopsy: A Case Report

Dendriform pulmonary ossification (DPO) is a rare condition characterized by ossification in the lungs. Lung ossification can be categorized into idiopathic ossification or secondary ossification associated with underlying pulmonary, cardiac, and systemic disorders. We herein present a case of a 60-year-old man with bilateral reticulonodular shadows detected on chest radiography during a medical checkup. A transbronchial lung biopsy did not provide a definitive diagnosis, and the asymptomatic patient was referred to our hospital due to worsening imaging findings. Further evaluation, including transbronchial lung cryobiopsy (TBLC), revealed dendriform ossification with components of bone marrow within the lung parenchyma. In the absence of underlying disease, the patient was diagnosed with idiopathic DPO (IDPO). This case highlights the importance of considering DPO in the differential diagnosis of unexplained pulmonary ossification and suggests that TBLC is a useful diagnostic tool for IDPO.

Optimizing prone CT use for suspected interstitial lung abnormalities

OBJECTIVES

We investigated whether supine chest CT alone suffices for diagnosing ILAs, thereby reducing the need for prone chest CT.

MATERIALS AND METHODS

Patients who underwent prone chest CT for suspected ILAs from January 2021 to July 2023, with matching supine CT within 1 year, were retrospectively evaluated. Five multinational thoracic radiologists independently rated ILA suspicion and fibrosis scores (1 to 5-point) and ILA extent (1-100%) using supine CT first, then combined supine-prone CT after a 1-month washout. We categorized ILA suspicion and fibrosis scores into four diagnostic groups; normal, non-fibrotic, indeterminate-type, and fibrotic ILAs. The areas under the receiver operating characteristic curve (AUCs) of ILA suspicion scores, inter-reader agreement on diagnostic categories, and intra-reader/inter-reader reliability for ILA extent were evaluated.

RESULTS

This study included 69 patients (mean age 67.2 ± 7.2 years; 36 women), with 23 age- and sex-matched patients in each group: normal, non-fibrotic ILAs, and fibrotic ILAs. The pooled AUC for ILA suspicion and inter-reader agreement on diagnostic categories improved for non-fibrotic ILAs with prone CT (AUC 0.76 to 0.92, p < 0.001; Fleiss kappa 0.25 to 0.51, p = 0.004), but not for fibrotic ILAs (AUC 0.94 to 0.99, p = 0.06; Fleiss kappa 0.63 to 0.72, p = 0.08). ILA extent was 1-2% smaller with prone CT for both ILA types (p < 0.001).

CONCLUSION

For fibrotic ILAs, supine CT alone exhibited substantial diagnostic accuracy and inter-reader agreement, while the diagnosis of non-fibrotic ILAs benefited from adding prone CT. Supine CT alone slightly overestimated extent regardless of ILA type.

KEY POINTS

Question Prone CT is recommended when interstitial lung abnormalities (ILAs) are suspected on supine CT, but its benefits remain underexplored. Findings Supine CT alone sufficed for diagnosing fibrotic ILAs, while prone CT improved non-fibrotic ILA diagnosis and reduced extent overestimation for both types. Clinical relevance Omitting prone CT reduces extra time, space, and radiation exposure without compromising the diagnosis of fibrotic ILAs, which have higher rates of progression and mortality risks, enhancing patient comfort and simplifying patient management.

Progressive Early Interstitial Lung Abnormalities in Persons at Risk for Familial Pulmonary Fibrosis: A Prospective Cohort Study

Rationale: Relatives of patients with familial pulmonary fibrosis (FPF) are at increased risk to develop FPF. Interstitial lung abnormalities (ILAs) are a radiologic biomarker of subclinical disease, but the implications of very mild abnormalities remain unclear. Objectives: To quantify the progression risk among FPF relatives with abnormalities below the threshold for ILAs as described by the Fleischner Society and to describe the characteristics of participants with new or progressive ILAs during observation. Methods: Asymptomatic FPF relatives undergo serial screening high-resolution chest computed tomography. For this analysis, early ILAs (no minimum threshold of lung involvement) were subclassified as mild (all interstitial abnormalities involve <5% of a lung zone) or moderate (any abnormality involves >5%). Identification of new or progressive ILAs on high-resolution chest computed tomography and the development of pulmonologist-diagnosed clinical FPF were defined as progression. Covariate-adjusted logistic regression identified progression-associated characteristics. Measurements and Main Results: From 2008 to 2023, 273 participants in follow-up procedures were 53.2 ± 9.4 years of age at enrollment, 95 (35%) were men, and 73 of 268 (27%) were ever-smokers. During a mean follow-up period of 6.2 ± 3.0 years, progression occurred among 31 of 211 (15%) of those with absence of ILAs at enrollment, 32 of 49 (65%) of those with mild ILAs, and 10 of 13 (77%) of those with moderate ILAs. Subjects with mild ILAs had 9.15 (95% confidence interval, 4.40-19.00; P < 0.0001) times and those with moderate ILAs had 17.14 (95% confidence interval, 4.42-66.49; P < 0.0001) times the odds of progression as subjects without ILAs. Conclusions: In persons at risk for FPF, minor interstitial abnormalities, including reticulation that is unilateral or involves <5% of a lung zone, frequently represent subclinical disease.

Association of Ground-Glass Opacities with Systemic Inflammation and Progression of Emphysema

Rationale: Ground-glass opacities (GGOs) in the absence of interstitial lung disease are understudied. Objectives: To assess the association of GGOs with white blood cells (WBCs) and progression of quantified chest computed tomography emphysema. Methods: We analyzed data of participants in the SPIROMICS study (Subpopulations and Intermediate Outcome Measures in COPD Study). Chest radiologists and pulmonologists labeled regions of the lung as GGOs, and the adaptive multiple feature method (AMFM) trained the computer to assign those labels to image voxels and quantify the volume of the lung with GGOs (%GGOAMFM). We used multivariable linear regression, zero-inflated negative binomial, and proportional hazards regression models to assess the association of %GGOAMFM with WBCs, changes in percentage emphysema, and clinical outcomes. Measurements and Main Results: Among 2,714 participants, 1,680 had chronic obstructive pulmonary disease (COPD) and 1,034 had normal spirometry. Among participants with COPD, on the basis of multivariable analysis, current smoking and chronic productive cough were associated with higher %GGOAMFM. Higher %GGOAMFM was cross-sectionally associated with higher WBC and neutrophil concentrations. Higher %GGOAMFM per interquartile range at visit 1 (baseline) was associated with an increase in emphysema at 1-year follow-up visit by 11.7% (relative increase; 95% confidence interval, 7.5-16.1%; P < 0.001). We found no association between %GGOAMFM and 1-year FEV1 decline, but %GGOAMFM was associated with exacerbations and all-cause mortality during a median follow-up of 1,544 days (interquartile interval, 1,118-2,059). Among normal spirometry participants, we found similar results, except that %GGOAMFM was associated with progression to COPD at 1-year follow-up. Conclusions: Our findings suggest that GGOAMFM is associated with increased systemic inflammation and emphysema progression.

Development, Progression, and Mortality of Suspected Interstitial Lung Disease in COPDGene

Rationale: Some with interstitial lung abnormalities (ILA) are suspected to have interstitial lung disease (ILD), a subgroup with adverse outcomes. Rates of development and progression of suspected ILD and their effect on mortality are unknown. Objectives: To determine rates of development, progression, and mortality in those with suspected ILD and assess effects of individual ILD and progression criteria. Methods: Participants from COPDGene (Genetic Epidemiology of Chronic Obstructive Pulmonary Disease) with ILA characterization and FVC at enrollment and 5-year follow-up were included. ILD was defined as ILA and fibrosis and/or FVC < 80% predicted. Prevalent ILD was assessed at enrollment and incident ILD and progression were assessed at 5-year follow-up. Computed tomography (CT) progression was assessed visually and FVC decline as relative change. Multivariable Cox regression tested associations between mortality and prevalent ILD, incident ILD, and progression groups. Measurements and Main Results: Of 9,588 participants at enrollment, 268 (2.8%; 51% of ILA) had prevalent ILD. Those with prevalent ILD had 51% mortality after median 10.6 years, which was higher than those with ILA without prevalent ILD (henceforth ILA) (33%; hazard ratio [HR], 2.0; P < 0.001). The subgroup of prevalent ILD with only fibrosis criteria (FVC ≥ 80%) had worse mortality (58%) than ILA (HR, 2.2; P < 0.001). A total of 98 participants with prevalent ILD completed 5-year follow-up: 33% had stable CT and relative FVC decline <10%, 6% had FVC decline ≥10% only, 39% had CT progression only, and 22% had both CT progression and FVC decline ≥10%. Mortality rates were 31%, 50%, 45%, and 45%, respectively; those with only CT progression had worse mortality than those with ILA (HR, 2.6; P = 0.005). At 5-year follow-up, incident ILD occurred in 148/4,842 participants without prevalent ILD (5.5/1,000 person-years) and had worse mortality than ILA (HR, 2.4; P < 0.001). Conclusion: Rates of mortality and progression are high among those with suspected ILD in COPDGene; fibrosis and radiologic progression are important predictors of mortality.

Longitudinal microcomputed tomography detects onset and progression of pulmonary fibrosis in conditional Nedd4-2 deficient mice

Idiopathic pulmonary fibrosis (IPF) is a fatal lung disease, which is usually diagnosed late in advanced stages. Little is known about the subclinical development of IPF. We previously generated a mouse model with conditional Nedd4-2 deficiency (Nedd4-2-/-) that develops IPF-like lung disease. The aim of this study was to characterize the onset and progression of IPF-like lung disease in conditional Nedd4-2-/- mice by longitudinal micro-computed tomography (CT). In vivo micro-CT was performed longitudinally in control and conditional Nedd4-2-/- mice at 1, 2, 3, 4, and 5 mo after doxycycline induction. Furthermore, terminal in vivo micro-CT followed by pulmonary function testing and post mortem micro-CT was performed in age-matched mice. Micro-CT images were evaluated for pulmonary fibrosis using an adapted fibrosis scoring system. Histological assessment of lung collagen content was conducted as well. Micro-CT is sensitive to detect the onset and progression of pulmonary fibrosis in vivo and to quantify distinct radiological IPF-like features along disease development in conditional Nedd4-2-/- mice. Nonspecific interstitial alterations were detected from 3 mo, whereas key features such as honeycombing-like lesions were detected from 4 mo onward. Pulmonary function correlated well with in vivo (r = -0.738) and post mortem (r = -0.633) micro-CT fibrosis scores and collagen content. Longitudinal micro-CT enables in vivo monitoring of the onset and progression and detects radiological key features of IPF-like lung disease in conditional Nedd4-2-/- mice. Our data support micro-CT as a sensitive quantitative endpoint for the preclinical evaluation of novel antifibrotic strategies.NEW & NOTEWORTHY IPF diagnosis, particularly in early stages, remains challenging. In this study, micro-CT is used in conditional Nedd4-2-/- mice to closely monitor the onset and progression of progressive pulmonary fibrosis in vivo. Together with high-resolution post mortem micro-CT, this allowed us to track how nonspecific lung lesions develop into key IPF-like features. This approach offers a noninvasive method to monitor pulmonary fibrosis, providing a quantitative endpoint for the preclinical evaluation of novel antifibrotic strategies.

First-line chemoimmunotherapy for patients with small-cell lung cancer and interstitial lung abnormality: CIP risk and prognostic analysis

BACKGROUND

Patients with non-small-cell lung cancer (NSCLC) receiving immunotherapy face a potential risk of developing checkpoint inhibitor-related pneumonitis (CIP). However, there is no clear understanding of the specific link between interstitial lung abnormality (ILA) and CIP in patients with small-cell lung cancer (SCLC). In addition, the prognosis of SCLC patients with ILA who receive chemoimmunotherapy is uncertain. Our study aimed to investigate the effect of ILA on the occurrence of CIP in SCLC patients receiving first-line chemoimmunotherapy and to assess its relationship with prognosis.

METHODS

We conducted a retrospective analysis of SCLC patients who received chemoimmunotherapy as a first-line treatment between January 2018 and April 2024. The diagnosis of ILA was assessed by two experienced pulmonologists based on pretreatment chest computed tomography images. We investigated independent risk factors for CIP using logistic regression analysis and factors affecting PFS and OS using Cox regression analysis.

RESULTS

A total of 128 patients with SCLC were included in the study. ILA was present in 41 patients (32.03%), and CIP occurred in 16 patients (12.50%). In multivariate logistic regression analysis, previous ILA (OR, 5.419; 95% CI, 1.574-18.652; p = 0.007) and thoracic radiation therapy (TRT) (OR, 5.259; 95% CI, 1.506-18.365; p = 0.009) were independent risk factors for CIP. ILA (HR, 2.083; 95% CI, 1.179-3.681; p = 0.012) and LDH (HR, 1.002; 95% CI, 1.001-1.002; p < 0.001) were statistically significant for increased mortality risk in multivariate Cox regression analysis.

CONCLUSIONS

In SCLC patients receiving first-line chemoimmunotherapy, baseline ILA is a risk factor for CIP and is associated with poorer prognosis.

A predictive model for post-COVID-19 pulmonary parenchymal abnormalities based on dual-center data

Documented radiological and physiological anomalies among coronavirus disease 2019 survivors necessitate prompt recognition of residual pulmonary parenchymal abnormalities for effective management of chronic pulmonary consequences. This study aimed to devise a predictive model to identify patients at risk of such abnormalities post-COVID-19. Our prognostic model was derived from a dual-center retrospective cohort comprising 501 hospitalized COVID-19 cases from July 2022 to March 2023. Of these, 240 patients underwent Chest CT scans three months post-infection. A predictive model was developed using stepwise regression based on the Akaike Information Criterion, incorporating clinical and laboratory parameters. The model was trained and validated on a split dataset, revealing a 33.3% incidence of pulmonary abnormalities. It achieved strong discriminatory power in the training set (area under the curve: 0.885, 95% confidence interval 0.832-0.938), with excellent calibration and decision curve analysis suggesting substantial net benefits across various threshold settings. We have successfully developed a reliable prognostic tool, complemented by a user-friendly nomogram, to estimate the probability of residual pulmonary parenchymal abnormalities three months post-COVID-19 infection. This model, demonstrating high performance, holds promise for guiding clinical interventions and improving the management of COVID-19-related pulmonary sequela.

Development of Imaging Complexity Biomarkers for Prediction of Symptomatic Radiation Pneumonitis in Patients with Non-Small Cell Lung Cancer, Focusing on Underlying Lung Disease

Objectives: We aimed to develop imaging biomarkers to predict radiation pneumonitis (RP) in non-small cell lung cancer (NSCLC) patients undergoing thoracic radiotherapy. We hypothesized that measuring morphometric complexity in the lung using simulation computed tomography may provide objective imaging biomarkers for lung parenchyma integrity, potentially forecasting the risk of RP. Materials and Methods: A retrospective study was performed on medical records of 175 patients diagnosed with NSCLC who had received thoracic radiotherapy. Three indices were utilized to measure the morphometric complexity of the lung parenchyma: box-counting fractal dimension, lacunarity, and minimum spanning tree (MST) fractal dimension. Patients were dichotomized into two groups at median values. Cox proportional hazard models were constructed to estimate the hazard ratios for grade ≥ 2 or grade ≥ 3 RP. Results and Conclusions: We found significant associations between lung parenchymal morphometric complexity and RP incidence. In univariate Cox-proportional hazard analysis, patients with a lower MST fractal dimension had a significantly higher hazard ratio of 2.296 (95% CI: 1.348-3.910) for grade ≥ 2 RP. When adjusted for age, sex, smoking status, category of the underlying lung disease, category of radiotherapy technique, clinical stage, histology, and DLCO, patients with a lower MST fractal dimension showed a significantly higher hazard ratio of 3.292 (95% CI: 1.722-6.294) for grade ≥ 2 RP and 7.952 (95% CI: 1.722 36.733) for grade ≥ 3 RP than those with a higher MST fractal dimension. Patients with lower lacunarity exhibited a significantly lower hazard ratio of 0.091 (95% CI: 0.015-0.573) for grade ≥ 3 RP in the adjusted model. We speculated that the lung tissue integrity is captured by morphometric complexity measures, particularly by the MST fractal dimension. We suggest the MST fractal dimension as an imaging biomarker for predicting the occurrence of symptomatic RP after thoracic radiotherapy.

Pulmonary fibrosis may begin in infancy: from childhood to adult interstitial lung disease

BACKGROUND

Childhood interstitial lung disease (chILD) encompasses a group of rare heterogeneous respiratory conditions associated with significant morbidity and mortality. Reports suggest that many patients diagnosed with chILD continue to have potentially progressive or fibrosing disease into adulthood. Over the last decade, the spectrum of conditions within chILD has widened substantially, with the discovery of novel entities through advanced genetic testing. However, most evidence is often limited to small case series, with reports disseminated across an array of subspecialty, clinical and molecular journals. In particular, the frequency, management and outcome of paediatric pulmonary fibrosis is not well characterised, unlike in adults, where clear diagnosis and treatment guidelines are available.

METHODS AND RESULTS

This review assesses the current understanding of pulmonary fibrosis in chILD. Based on registry data, we have provisionally estimated the occurrence of fibrosis in various manifestations of chILD, with 47 different potentially fibrotic chILD entities identified. Published evidence for fibrosis in the spectrum of chILD entities is assessed, and current and future issues in management of pulmonary fibrosis in childhood, continuing into adulthood, are considered.

CONCLUSIONS

There is a need for improved knowledge of chILD among pulmonologists to optimise the transition of care from paediatric to adult facilities. Updated evidence-based guidelines are needed that incorporate recommendations for the diagnosis and management of immune-mediated disorders, as well as chILD in older children approaching adulthood.

Computed tomography morphological assessments of central airways in interstitial lung abnormalities and idiopathic pulmonary fibrosis

BACKGROUND

Little is known about whether central airway morphological changes beyond traction bronchiectasis develop and affect clinical outcomes in patients with idiopathic pulmonary fibrosis (IPF). This study aimed to compare central airway structure comprehensively between patients with IPF, subjects with interstitial lung abnormality (ILA), and those without ILA (control) using computed tomography (CT). We further examined the prognostic impact of IPF-specific CT airway parameters in patients with IPF.

METHODS

This retrospective study included male patients with IPF, and male health checkup subjects divided into those with ILA and control based on lung cancer screening CT. Using an artificial intelligence-based segmentation technique, the extent of fibrotic regions in the lung was quantified. After airway tree segmentation, CT parameters for central airway morphology, including the lumen area of the extrapulmonary airways (LAextra), wall and lumen area of the segmental/subsegmental intrapulmonary airways (WAintra and LAintra), tracheal distortion (tortuosity and curvature) and bifurcation angle of the main carina, were calculated.

RESULTS

There were 106 patients with IPF, 53 subjects with ILA, and 1295 controls. Multivariable models adjusted for age, height and smoking history revealed that LAintra and WAintra were larger in both ILA and IPF, and that tracheal tortuosity and curvature were higher in IPF, but not in ILA, than in the control, whereas the bifurcation angle did not differ between the 3 groups. According to multivariable Cox proportional hazards models including only patients with IPF, increased WAintra was significantly associated with greater mortality (standardized hazard ratio [95% confidence interval] = 1.58 [1.17, 2.14]), independent of the volume of fibrotic regions, normal-appearing regions, or the whole airway tree in the lung.

CONCLUSION

Increased lumen area and wall thickening of the central airways may be involved in the pathogenesis of ILA and IPF, and wall thickening may affect the prognosis of patients with IPF.

Long-Term Clinical, Radiological, and Mortality Outcomes Following Pneumonitis in Nonsmall Cell Lung Cancer Patients Receiving Immune Checkpoint Inhibitors: A Retrospective Analysis

AIMS

Despite known short-term mortality risk of immune checkpoint inhibitor (ICI) pneumonitis, its impact on 1-year mortality, long-term pulmonary function, symptom persistence, and radiological resolution remains unclear.

METHODS

We retrospectively analyzed 71 nonsmall cell lung cancer (NSCLC) patients treated with anti-PD(L)1 monoclonal antibodies between 2018-2021, who developed pneumonitis. Clinical and demographic covariates were collected from electronic medical record. Cox regression assessed associations with mortality, while logistic regression evaluated associations with persistent symptoms, hypoxemia, and radiological resolution.

RESULTS

Steroid-refractory pneumonitis (hazard ratio [HR] = 15.1, 95% confidence interval [95% CI]:3.9-57.8, P < .0001) was associated with higher 1-year mortality compared to steroid-responsive cases. However, steroid-resistant (odds ratio [OR] = 1.4, 95% CI: 0.4-5.1, P = .58) and steroid-dependent (OR = 0.4, 95% CI: 0.1-1.2, P = .08) pneumonitis were not. Nonadenocarcinoma histology (OR = 6.7, 95% CI: 1.6-46.6, P = .01), grade 3+ pneumonitis (OR = 4.6, 95% CI: 1.3-22.7, P = .03), and partial radiological resolution (OR = 6.3, 95% CI: 1.8-23.8, P = .004) were linked to increased pulmonary symptoms after pneumonitis resolution. Grade 3+ pneumonitis (OR = 8.1, 95% CI: 2.3-31.5, P = .001) and partial radiological resolution (OR = 5.45, 95% CI: 1.29-37.7, P = .03) associated with residual hypoxemia. Nonadenocarcinoma histology (OR = 3.6, 95% CI: 1.01-17.6, P = .06) and pretreatment ILAs (OR = 4.8, 95% CI: 1.14-33.09, P = .05) were associated with partial radiological resolution.

CONCLUSIONS

Steroid refractory pneumonitis increases 1-year mortality in NSCLC patients. Pretreatment ILAs may signal predisposition to fibrosis-related outcomes, seen as partial resolution, which in turn is associated with postresolution symptoms and residual hypoxemia. These findings offer insights for identifying patients at risk of adverse outcomes post-pneumonitis resolution.

Interstitial Lung Abnormalities on Unselected Abdominal and Thoracoabdominal CT Scans in 21 118 Patients

Background Interstitial lung abnormalities (ILAs) are incidental CT findings suggesting early interstitial lung disease. However ILA prevalence data are scarce in an unselected routine clinical setting. Purpose To evaluate the prevalence, underreporting rate, and potential clinical impact of ILAs recognizable on either abdominal CT scans or thoracoabdominal CT scans in a routine clinical setting of unselected patients. Materials and Methods Consecutive abdominal or thoracoabdominal CT scans from unselected inpatients and outpatients (age, ≥50 years; without any available prior chest CT and no clinical history of disease against the diagnosis of ILA) from a single-center tertiary hospital between January 2008 and December 2015 were retrospectively reviewed for the presence of ILAs and compared with the original clinical reports from the CT scans. Radiologic progression of ILA was evaluated by comparing consecutive CT points. Multivariable models adjusted for age, sex, race/ethnicity, oncologic disease, and cardiovascular disease were used to assess factors associated with odds of ILAs progression and all-cause and cause-specific mortality. Results Among 21 118 patients (median age, 72 years [IQR, 64-80 years]; 11 028 [52.2%] female patients), ILAs were observed in 362 (1.7%) patients, notably in 222 (1.0%) patients who had fibrotic features at CT. ILAs were recognized in 122 of 9415 (1.3%) and 240 of 11 703 (2.1%) of abdominal and thoracoabdominal CT scans, respectively. Of available original reports for 360 patients, 158 (43.9%) of all ILAs were not originally reported. Traction bronchiectasis index was the CT factor associated with higher odds of ILA progression (odds ratio, 3.47; 95% CI: 1.83, 6.58; P < .001). Fibrotic ILAs had a fourfold higher risk of respiratory-cause mortality (hazard ratio, 4.01; 95% CI: 2.02, 7.92; P < .001) compared with patients without ILAs. Conclusion The prevalence of ILAs was 1.7% in a large, unselected sample of patients who underwent either abdominal or thoracoabdominal CT for various clinical indications. Despite their prognostic significance, 43.9% of ILAs were unreported. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Hata in this issue.

Impact of preexisting interstitial lung disease on outcomes of lung cancer surgery: A monocentric retrospective study

INTRODUCTION

Interstitial lung disease (ILD) is a known risk factor for lung cancer (LC). However, the surgical risk of LC in patients with ILD remains unclear. Therefore, we conducted a single-center retrospective study to assess clinical features and outcomes of LC population who underwent surgery with or without ILD.

METHODS

Patients who underwent surgery for LC between January 2006 and June 2023 in our center were assessed using data extracted from the nationwide EPITHOR thoracic surgery database. Suspicion of ILD was based on patients' records. Confirmation of ILD was then made on the patient's medical and radiological history. Patients were classified according to the pattern of ILD. The study aimed to describe the outcomes after lung cancer resection in patients with confirmed LC-ILD group compared to those without ILD (LC-non-ILD): post-operative complications, disease-free survival (DFS) and overall survival (OS). A subgroup analysis was also performed on patients with idiopathic pulmonary fibrosis and lung cancer (LC-IPF).

RESULTS

4073 patients underwent surgery for LC at Assistance Publique des Hôpitaux de Marseille between January 2006 and June 2023. Of these, 4030 were in the LC-non-ILD group and 30 were LC-ILD patients. In the LC-ILD group, the predominant CT scan pattern was probable UIP (50 %). OS was not significantly lower in the LC-ILD group (45 months versus 84 months, p = 0.068). Dyspnea and tumor size were identified as potential univariate predictors of OS. No significant differences were observed on post-operative complications or their severity. The most common post-operative complications in the LC-ILD group were prolonged air leak, respiratory failure, or pneumonia. 13 patients had cancer recurrence in the LC-ILD group.

CONCLUSION

Our study provides a comprehensive analysis of a LC-ILD population features and outcome when undergoing surgery for LC. Patients with LC-ILD appeared to have a reduced OS compared with LC-non-ILD. Further investigations with larger prospective studies could be useful to confirm and develop these preliminary findings.

Long-Term Follow-Up of Interstitial Lung Abnormalities in Low-Dose Chest CT in Health Screening: Exploring the Predictors of Clinically Significant Interstitial Lung Diseases Using Artificial Intelligence-Based Quantitative CT Analysis

Purpose

This study examined longitudinal changes in interstitial lung abnormalities (ILAs) and predictors of clinically significant interstitial lung diseases (ILDs) in a screening population with ILAs.

Materials and Methods

We retrieved 36891 low-dose chest CT records from screenings between January 2003 and May 2021. After identifying 101 patients with ILAs, the clinical findings, spirometry results, and initial and follow-up CT findings, including visual and artificial intelligence-based quantitative analyses, were compared between patients diagnosed with ILD (n = 23, 23%) and those who were not (n = 78, 77%). Logistic regression analysis was used to identify significant parameters for the clinical diagnosis of ILD.

Results

Twenty-three patients (n = 23, 23%) were subsequently diagnosed with clinically significant ILDs at follow-up (mean, 8.7 years). Subpleural fibrotic ILAs on initial CT and signs of progression on follow-up CT were common in the ILD group (both p < 0.05). Logistic regression analysis revealed that emerging respiratory symptoms (odds ratio [OR], 5.56; 95% confidence interval [CI], 1.28-24.21; p = 0.022) and progression of ILAs at follow-up chest CT (OR, 4.07; 95% CI, 1.00-16.54; p = 0.050) were significant parameters for clinical diagnosis of ILD.

Conclusion

Clinically significant ILD was subsequently diagnosed in approximately one-quarter of the screened population with ILAs. Emerging respiratory symptoms and progression of ILAs at follow-up chest CT can be predictors of clinically significant ILDs.

Prognostic Impact of Pulmonary Diseases in 952 Patients with Thoracic and/or Abdominal Aortic Aneurysm

Background/Objectives: Pulmonary diseases are common in patients with thoracic aortic aneurysm (TAA) and abdominal aortic aneurysm (AAA). Although high prevalences of chronic obstructive pulmonary disease and lung cancer (LC) are known, the prevalence of these and other pulmonary diseases regarding their relation to the outcome of TAA and/or AAA are not determined. Methods: Pulmonary diseases present at aortic aneurysm (AA) diagnosis and follow-up periods and cause of death of 952 patients with TAA, AAA, or TAA + AAA (including thoracoabdominal AA) treated at our institution in Japan were retrospectively analyzed. Cox regression analysis was used to investigate potential risk factors of mortality. Results: The mean patient age was 72.4 years, and the median follow-up was 4.92 years. At diagnosis, 528 (55.5%) patients had pulmonary diseases, including emphysema without interstitial lung disease (ILD) or LC, LC, idiopathic pulmonary fibrosis (IPF) without LC, non-IPF ILD without LC, and interstitial lung abnormalities (ILAs) without LC in 250, 85, 65, 15, and 58 patients, respectively. During follow-up, LC and acute exacerbation (AE) of IPF developed in 50 and 12 patients, respectively. In 213 patients who died, there were 45 (21.1%) aortic disease-related deaths. Other causes of death included LC (27.7%), cardiovascular events (9.4%), pneumonia (5.6%), and interstitial lung disease (4.7%). In a multivariate Cox regression hazard model, age; larger maximum aneurysm diameter; and coexisting LC, IPF, or concomitant cancer were associated with poor prognosis. Conclusions: In patients with AA, not only age and aneurysm diameter but also coexisting LC and IPF were prognostic factors for mortality.

Genomic and Serological Rheumatoid Arthritis Biomarkers, MUC5B Promoter Variant, and Interstitial Lung Abnormalities

RATIONALE

Rheumatoid arthritis (RA) has been implicated in interstitial lung disease (ILD) as majority of studies have been comprised of patients with known RA. However, it remains unclear whether an underlying risk for RA in combination with genetic risk for pulmonary fibrosis is associated with radiological markers of early lung injury and fibrosis in broader population samples.

OBJECTIVE

Determine whether genetic and serological biomarkers of RA risk in combination with the MUC5B (rs35705950) risk allele (T) are associated with interstitial lung abnormalities (ILA) on computed tomography (CT) scans.

METHODS

Associations of RA-risk HLA-DRB1 alleles (*04:01, *04:08, *04:05, *04:04, *10:01) and serum RA autoantibodies with ILA in the Multi-Ethnic Study of Atherosclerosis (MESA, n=4,018) and COPDGene (n=5,963) cohorts were modeled using logistic regression and adjusted for age, sex, self-reported race and ethnicity, smoking history, body mass index, and principal components of genetic ancestry.

RESULTS

The prevalence of an RA risk HLA-DRB1 allele was 16.5% and 21.9% in MESA and COPDGene, respectively. ILA was present in 3.9% and 11% in MESA and COPDGene, respectively. An RA risk HLA-DRB1 allele was not significantly associated with ILA in MESA and COPDGene. In MESA, higher serum levels of IgA rheumatoid factor (RF) and anti-cyclic citrullinated peptide were associated with an odds ratio (OR) for ILA of 1.20 (95% CI 1.07-1.35) and 1.19 (95% CI 1.04-1.37), respectively. Among smokers without baseline ILA, per doubling of IgM RF was associated with an OR for ILA 10 years later of 1.25 (95% CI 1.08-1.43). Associations were not significantly different by MUC5B risk allele status.

CONCLUSIONS

RA-related HLA-DRB1 alleles were not associated with ILA, whereas higher serum levels of IgM RF among smokers without baseline ILA were associated with subsequent ILA.

Interstitial Lung Abnormality: Narrative Review of the Approach to Diagnosis and Management

TOPIC IMPORTANCE

As interstitial lung abnormalities (ILAs) are increasingly recognized on imaging and in clinical practice, identification and appropriate management are critical. We propose an algorithmic approach to the identification and management of patients with ILAs.

REVIEW FINDINGS

The radiologist initially identifies chest CT scan findings suggestive of an ILA pattern and excludes findings that are not consistent with ILAs. The next step is to confirm that these findings occupy > 5% of a nondependent lung zone. At this point, the radiologic pattern of ILA is identified. These findings are classified as non-subpleural, subpleural nonfibrotic, and subpleural fibrotic. It is then incumbent on the clinician to ascertain if the patient has symptoms and/or abnormal pulmonary physiology that may be attributable to these radiologic changes. Based on the patient's symptoms, physiologic assessment, and risk factors for interstitial lung disease (ILD), we recommend classifying patients as having ILA, at high risk for developing ILD, probable ILD, or ILD. In patients identified as having ILA, a multidisciplinary discussion should evaluate features that indicate an increased risk of progression. If these features are present, serial monitoring is recommended to be proactive. If the patient does not have imaging or clinical features that indicate an increased risk of progression, then monitoring is recommended to be reactive. If ILD is subsequently diagnosed, the management is disease specific.

SUMMARY

We anticipate this algorithmic approach will aid clinicians in interpreting the radiologic pattern described as ILA within the clinical context of their patients.

Interstitial lung abnormality in COPD is inversely associated with the comorbidity of lung cancer

BACKGROUND

Interstitial lung abnormality (ILA) has been recognized as a pertinent factor in the development and prognosis of various pulmonary conditions. However, its correlation with co-morbidities remains understudied. The current study endeavors to elucidate the association between ILA and both clinical features and co-morbidities in patients with chronic obstructive pulmonary disease (COPD).

METHODS

A retrospective cohort comprising 1131 hospitalized patients diagnosed with COPD was examined in this observational study. Patients were dichotomously classified based on the presence or absence of ILA, and subsequent analyses scrutinized disparities in demographic, clinical, and laboratory profiles, alongside co-morbid conditions, between the two subgroups.

RESULTS

Of the 1131 COPD patients, 165 (14.6%) exhibited ILA. No statistically significant differences were discerned between COPD patients with and without ILA concerning demographic, clinical, or laboratory parameters, except for levels of circulating fibrinogen and procalcitonin. Nevertheless, a notable discrepancy emerged in the prevalence of multiple co-morbidities. Relative to COPD patients devoid of ILA, those presenting with ILA manifested a diminished prevalence of lung cancer (OR = 0.50, 95% CI: 0.30-0.83, p = 0.006), particularly of the lung adenocarcinoma (OR = 0.32, 95% CI: 0.15-0.71, p = 0.005). Additionally, the presence of ILA in COPD was positively associated with heart failure (OR = 1.75, 95% CI: 1.04-3.00, p = 0.040) and cancers other than lung cancer (OR = 2.27, 95% CI: 1.16-4.39, p = 0.012).

CONCLUSION

These findings demonstrate that the presence of ILA is associated with co-morbidities of COPD, particularly lung cancer.

Clinical utility of lung ultrasound for the detection of interstitial lung disease in patients with rheumatoid arthritis

OBJECTIVE

To establish the diagnostic value of lung ultrasound (LUS) in patients with rheumatoid arthritis (RA) for the detection of interstitial lung disease (ILD).

METHODS

A cross-sectional study was performed. Consecutive patients with RA (American College of Rheumatology/European League Against Rheumatism 2010 criteria) who had a chest high-resolution computed tomography (HRCT) performed within 12 months before inclusion, regardless of symptomatology, were included. Demographic, clinical, laboratory, and pharmacological data were recorded. Each patient underwent a LUS with assessment of B-lines (BL) and pleural irregularities (PI). HRCT was considered the gold standard for the confirmatory diagnosis of ILD. Receiver operating characteristic (ROC) curves were calculated to test the ability of LUS findings (BL and PI) in discriminating patients with ILD.

RESULTS

A total of 104 RA patients were included, of which 21.8% had ILD. Patients with ILD had more BL (median 26 versus 1, p<0.001) and PI (median 16 versus 5, p<0.001) than patients without ILD. The diagnostic accuracy in ROC curves was as follows: area under the curve (AUC) 0.88 and 95% confidence interval (CI) 0.78-0.93 for BL and AUC 0.82 and 95% CI 0.74-0.89 for PI. The best cut-off points for (ILD detection) discriminating the presence of significant interstitial lung abnormalities were 8 BL and 7 PI.

CONCLUSIONS

The presence of 8 BL and/or 7 PI in the LUS showed an adequate cut-off value for discriminating the presence of significant interstitial lung abnormalities, evocative of ILD.

Neoadjuvant and Adjuvant Treatments for Early Stage Resectable NSCLC: Consensus Recommendations From the International Association for the Study of Lung Cancer

Advances in the multidisciplinary care of early stage resectable NSCLC (rNSCLC) are emerging at an unprecedented pace. Numerous phase 3 trials produced results that have transformed patient outcomes for the better, yet these findings also require important modifications to the patient treatment journey trajectory and reorganization of care pathways. Perhaps, most notably, the need for multispecialty collaboration for this patient population has never been greater. These rapid advances have inevitably left us with important gaps in knowledge for which definitive answers will only become available in several years. To this end, the International Association for the Study of Lung Cancer commissioned a diverse multidisciplinary international expert panel to evaluate the current landscape and provide diagnostic, staging, and therapeutic recommendations for patients with rNSCLC, with particular emphasis on patients with American Joint Committee on Cancer-Union for International Cancer Control TNM eighth edition stages II and III disease. Using a team-based approach, we generated 19 recommendations, of which all but one achieved greater than 85% consensus among panel members. A public voting process was initiated, which successfully validated and provided qualitative nuance to our recommendations. Highlights include the following: (1) the critical importance of a multidisciplinary approach to the evaluation of patients with rNSCLC driven by shared clinical decision-making of a multispecialty team of expert providers; (2) biomarker testing for rNSCLC; (3) a preference for neoadjuvant chemoimmunotherapy for stage III rNSCLC; (4) equipoise regarding the optimal management of patients with stage II between upfront surgery followed by adjuvant therapy and neoadjuvant or perioperative strategies; and (5) the robust preference for adjuvant targeted therapy for patients with rNSCLC and sensitizing EGFR and ALK tumor alterations. Our primary goals were to provide practical recommendations sensitive to the global differences in biology and resources for patients with rNSCLC and to provide expert consensus guidance tailored to the individualized patient needs, goals, and preferences in their cancer care journey as these are areas where physicians must make daily clinical decisions in the absence of definitive data. These recommendations will continue to evolve as the treatment landscape for rNSCLC expands and more knowledge is acquired on the best therapeutic approach in specific patient and disease subgroups.

Clinical and radiological pattern of olaparib-induced interstitial lung disease

BACKGROUND

PARP inhibitors (PARPi) are used in the treatment of ovarian, breast, pancreatic, and prostate cancers. Pneumonitis has been identified as a potential side effect, with a higher meta-analysis-assessed risk for olaparib versus other PARPi. Olaparib-induced interstitial lung disease (O-ILD) was first described within the Japanese population, with few information available for Caucasian patients.

METHODS

We performed a retrospective study by pooling data from the French and Belgian pharmacovigilance databases from 2018 to 2022. Patients with O-ILD were included following a central review by: 1) pharmacologists using the French drug causality assessment method; 2) senior pneumologists or radiologists, using the Fleischner Society's recommendations.

RESULTS

Five patients were identified and analysed. All were females, with ovarian or breast cancer. Median age at O-ILD diagnosis was 71 (38-72) years old, with no smoking history. Median delay between treatment initiation and symptom occurrence was 12 (6-33) weeks. Pneumonitis severity assessed using the Common Terminology Criteria for Adverse Events V5 was Grade 3 (n = 4) or 2 (n = 1). CT-scan review (n = 3) described hypersensitivity pneumonitis reaction as a common pattern. Bronchioalveolar lavage (n = 4) revealed lymphocytic alveolitis. Treatments relied on olaparib discontinuation (n = 5) and glucocorticoid intake (n = 4), with no fatal issue. Safe re-challenge with PARPi occurred in two patients. Forty additional O-ILD cases were identified in the WHO VigiBase database, including one fatal case.

CONCLUSIONS

PARPi-ILD is a rare but potentially life-threatening disease, presenting as a hypersensitivity pneumonitis pattern within 3 months of PARPi initiation. Treatment primarily relies on medication discontinuation. Re-challenging with another PARPi could be considered.

CLINICAL TRIAL NUMBER

CEPRO #2023-010.

ESR Essentials: imaging in fibrotic lung diseases-practice recommendations by the European Society of Thoracic Imaging

Fibrotic lung diseases (FLDs) represent a subgroup of interstitial lung diseases (ILDs), which can progress over time and carry a poor prognosis. Imaging has increased diagnostic discrimination in the evaluation of FLDs. International guidelines have stated the role of radiologists in the diagnosis and management of FLDs, in the context of the interdisciplinary discussion. Chest computed tomography (CT) with high-resolution technique is recommended to correctly recognise signs, patterns, and distribution of individual FLDs. Radiologists may be the first to recognise the presence of previously unknown interstitial lung abnormalities (ILAs) in various settings. A systematic approach to CT images may lead to a non-invasive diagnosis of FLDs. Careful comparison of serial CT exams is crucial in determining either disease progression or supervening complications. This 'Essentials' aims to provide radiologists a concise and practical approach to FLDs, focusing on CT technical requirements, pattern recognition, and assessment of disease progression and complications. Hot topics such as ILAs and progressive pulmonary fibrosis (PPF) are also discussed. KEY POINTS: Chest CT with high-resolution technique is the recommended imaging modality to diagnose pulmonary fibrosis. CT pattern recognition is central for an accurate diagnosis of fibrotic lung diseases (FLDs) by interdisciplinary discussion. Radiologists are to evaluate disease behaviour by accurately comparing serial CT scans.

Outcome of immune checkpoint inhibitor treatment in non-small cell lung cancer patients with interstitial lung abnormalities: clinical utility of subcategorizing interstitial lung abnormalities

Interstitial lung abnormalities (ILAs) are immune checkpoint inhibitor (ICI)-related pneumonitis (ICI-P) risk factors. However, the relationship between imaging patterns and immunotherapy outcomes, and treatment strategies remain unclear in patients with non-small cell lung cancer (NSCLC) and ILAs. We retrospectively evaluated patients with ILAs-complicated NSCLC who received ICI therapy. ILAs were subcategorized as non-subpleural, subpleural non-fibrotic, and subpleural fibrotic (SF) based on the 2020 position paper by the Fleischner Society. We investigated ICI-P incidence, ICI-P risk factors, lung cancer prognosis, and ILAs radiological progression. Of the 481 ICI-treated patients, 79 (16.4%) had ILAs (45 non-SF and 34 SF). The ICI-P cumulative incidence (hazard ratio, 4.57; 95% confidence interval [CI], 1.90-10.98; p = 0.001) and any grade and grade ≥ 3 ICI-P incidences were higher in patients with SF-ILAs than in those with non-SF-ILAs (all grades: 7/45 [15.6%)] vs. 18/34 [52.9%]; p < 0.001; grade ≥ 3: 1/45 [2.2%] vs. 10/34 [29.4%]; p = 0.001). According to multivariate analysis, SF-ILAs independently predicted ICI-P (odds ratio, 5.35; 95% CI 1.62-17.61; p = 0.006). Patients with SF-ILAs had shorter progression-free and overall survival and higher ICI-P-related respiratory failure death rates than those with non-SF-ILAs. Approximately 2.5 times more patients with SF-ILAs showed progression by the 2-year follow-up than those with non-SF-ILAs. SF-ILAs is an independent strong predictor of ICI-P development in patients with NSCLC, may increase ICI-P severity, worsen prognosis, and accelerate ILAs progression. ILAs subcategorization is an important treatment strategy for patients with lung cancer treated with ICIs.

Air Pollution Exposure and Interstitial Lung Features in SPIROMICS Participants with Chronic Obstructive Pulmonary Disease

Rationale: It is unknown whether air pollution is associated with radiographic features of interstitial lung disease in individuals with chronic obstructive pulmonary disease (COPD). Objectives: To determine whether air pollution increases the prevalence of interstitial lung abnormalities (ILA) or percent high-attenuation areas (HAA) on computed tomography (CT) in individuals with a heavy smoking history and COPD. Methods: We performed a cross-sectional study of SPIROMICS (Subpopulations and Intermediate Outcome Measures in COPD Study), focused on current or former smokers with COPD. Ten-year exposure to particulate matter ⩽2.5 μm in aerodynamic diameter (PM2.5), nitrogen oxides (NOx), nitrogen dioxide (NO2), and ozone before enrollment CT (completed between 2010 and 2015) were estimated with validated spatiotemporal models at residential addresses. We applied adjusted multivariable modified Poisson regression and linear regression to investigate associations between pollution exposure and relative risk (RR) of ILA or increased percent HAA (between -600 and -250 Hounsfield units), respectively. We assessed for effect modification by MUC5B-promoter polymorphism (variant allele carriers GT or TT vs. GG at rs3705950), smoking status, sex, and percent emphysema. Results: Among 1,272 participants with COPD assessed for HAA, 424 were current smokers, and 249 were carriers of the variant MUC5B allele. A total of 519 participants were assessed for ILA. We found no association between pollution exposure and ILA or HAA. Associations between pollutant exposures and risk of ILA were modified by the presence of MUC5B polymorphism (P value interaction term for NOx = 0.04 and PM2.5 = 0.05) and smoking status (P value interaction term for NOx = 0.05; NO2 = 0.01; and ozone = 0.05). With higher exposure to NOx and PM2.5, MUC5B variant carriers had an increased risk of ILA (RR per 26 ppb NOx, 2.41; 95% confidence interval [CI], 0.97-6.0; and RR per 4 μg ⋅ m-3 PM2.5, 1.43; 95% CI, 0.93-2.2, respectively). With higher exposure to NO2, former smokers had an increased risk of ILA (RR per 10 ppb, 1.64; 95% CI, 1.0-2.7). Conclusions: Exposure to ambient air pollution was not associated with interstitial features on CT in this population of heavy smokers with COPD. MUC5B modified the association between pollution and ILA, suggesting that gene-environment interactions may influence prevalence of interstitial lung features in COPD.

Idiopathic dendriform pulmonary ossification as the phenotype of interstitial lung abnormalities: CT-pathologic correlation and prevalence

BACKGROUND AND PURPOSE

Idiopathic dendriform pulmonary ossification (DPO) is mostly asymptomatic, and detected incidentally in lung CT. There have been no reports on the precise CT-pathologic correlation and the prevalence of idiopathic DPO. This study aimed to clarify the histological background and prevalence of idiopathic DPO.

MATERIALS AND METHODS

Sixteen patients with histologically confirmed idiopathic DPO (12 men and 4 women; mean age, 38.8 years; range 22-56 years) were identified in a nationwide epidemiological survey. Local HRCT findings of pre-biopsy examinations, such as branching, round, linear structures with or without high attenuation were compared side by side with histological findings. The attenuation of branching, round, and linear structures was classified into three-point levels on bone window images (width, 2500 HU; level, 500 HU). Furthermore, we collected continuous pulmonary CT images of 8111 cases for checking up metastasis from extrathoracic malignancy at a single institution, and evaluated the prevalence of interstitial lung abnormalities (ILAs) and DPO.

RESULTS

In all 16 cases, branching (n = 15, 93%), round (n = 5, 31%), or linear (n = 5, 31%) structures were identified, histologically corresponding to dendriform ossification and cicatricial organizing pneumonia (OP)/fibrosis. Histologically, ossification was confirmed in all the 16 patients. However, in two cases, a highly attenuated structure could not be detected on the pre-biopsy CT of the same area. Regarding the prevalence of idiopathic DPO, 283 (3.5%) of 8111 patients had ILAs, of which a total of 26 (0.3% of all cases, 9.2% of ILAs cases) had DPO.

CONCLUSION

Idiopathic DPO showed linear or branching structures with or without high attenuation on CT, corresponded to ossification, cicatricial OP/fibrosis. DPO was seen in 9.2% of ILAs cases. Idiopathic DPO is one of pathologic phenotypes of ILAs.

Automated Interstitial Lung Abnormality Probability Prediction at CT: A Stepwise Machine Learning Approach in the Boston Lung Cancer Study

Background It is increasingly recognized that interstitial lung abnormalities (ILAs) detected at CT have potential clinical implications, but automated identification of ILAs has not yet been fully established. Purpose To develop and test automated ILA probability prediction models using machine learning techniques on CT images. Materials and Methods This secondary analysis of a retrospective study included CT scans from patients in the Boston Lung Cancer Study collected between February 2004 and June 2017. Visual assessment of ILAs by two radiologists and a pulmonologist served as the ground truth. Automated ILA probability prediction models were developed that used a stepwise approach involving section inference and case inference models. The section inference model produced an ILA probability for each CT section, and the case inference model integrated these probabilities to generate the case-level ILA probability. For indeterminate sections and cases, both two- and three-label methods were evaluated. For the case inference model, we tested three machine learning classifiers (support vector machine [SVM], random forest [RF], and convolutional neural network [CNN]). Receiver operating characteristic analysis was performed to calculate the area under the receiver operating characteristic curve (AUC). Results A total of 1382 CT scans (mean patient age, 67 years ± 11 [SD]; 759 women) were included. Of the 1382 CT scans, 104 (8%) were assessed as having ILA, 492 (36%) as indeterminate for ILA, and 786 (57%) as without ILA according to ground-truth labeling. The cohort was divided into a training set (n = 96; ILA, n = 48), a validation set (n = 24; ILA, n = 12), and a test set (n = 1262; ILA, n = 44). Among the models evaluated (two- and three-label section inference models; two- and three-label SVM, RF, and CNN case inference models), the model using the three-label method in the section inference model and the two-label method and RF in the case inference model achieved the highest AUC, at 0.87. Conclusion The model demonstrated substantial performance in estimating ILA probability, indicating its potential utility in clinical settings. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Zagurovskaya in this issue.

Quantitative analysis of interstitial lung abnormalities on computed tomography to predict symptomatic radiation pneumonitis after lung stereotactic body radiotherapy

BACKGROUND AND PURPOSE

Symptomatic radiation pneumonitis (SRP) is a complication of thoracic stereotactic body radiotherapy (SBRT). As visual assessments pose limitations, artificial intelligence-based quantitative computed tomography image analysis software (AIQCT) may help predict SRP risk. We aimed to evaluate high-resolution computed tomography (HRCT) images with AIQCT to develop a predictive model for SRP.

MATERIALS AND METHODS

AIQCT automatically labelled HRCT images of patients treated with SBRT for stage I lung cancer according to lung parenchymal pattern. Quantitative data including the volume and mean dose (Dmean) were obtained for reticulation + honeycombing (Ret + HC), consolidation + ground-glass opacities, bronchi (Br), and normal lungs (NL). After associations between AIQCT's quantified metrics and SRP were investigated, we developed a predictive model using recursive partitioning analysis (RPA) for the training cohort and assessed its reproducibility with the testing cohort.

RESULTS

Overall, 26 of 207 patients developed SRP. There were significant between-group differences in the Ret + HC, Br-volume, and NL-Dmean in patients with and without SRP. RPA identified the following risk groups: NL-Dmean ≥ 6.6 Gy (high-risk, n = 8), NL-Dmean < 6.6 Gy and Br-volume ≥ 2.5 % (intermediate-risk, n = 13), and NL-Dmean < 6.6 Gy and Br-volume < 2.5 % (low-risk, n = 133). The incidences of SRP in these groups within the training cohort were 62.5, 38.4, and 7.5 %; and in the testing cohort 50.0, 27.3, and 5.0 %, respectively.

CONCLUSION

AIQCT identified CT features associated with SRP. A predictive model for SRP was proposed based on AI-detected Br-volume and the NL-Dmean.