Deep Learning-based Outcome Prediction in Progressive Fibrotic Lung Disease Using High-Resolution Computed Tomography.

Rationale: Reliable outcome prediction in patients with fibrotic lung disease using baseline high-resolution computed tomography (HRCT) data remains challenging. Objectives: To evaluate the prognostic accuracy of a deep learning algorithm (SOFIA [Systematic Objective Fibrotic Imaging Analysis Algorithm]), trained and validated in the identification of usual interstitial pneumonia (UIP)-like features on HRCT (UIP probability), in a large cohort of well-characterized patients with progressive fibrotic lung disease drawn from a national registry. Methods: SOFIA and radiologist UIP probabilities were converted to Prospective Investigation of Pulmonary Embolism Diagnosis (PIOPED)-based UIP probability categories (UIP not included in the differential, 0-4%; low probability of UIP, 5-29%; intermediate probability of UIP, 30-69%; high probability of UIP, 70-94%; and pathognomonic for UIP, 95-100%), and their prognostic utility was assessed using Cox proportional hazards modeling. Measurements and Main Results: In multivariable analysis adjusting for age, sex, guideline-based radiologic diagnosis, anddisease severity (using total interstitial lung disease [ILD] extent on HRCT, percent predicted FVC, DlCO, or the composite physiologic index), only SOFIA UIP probability PIOPED categories predicted survival. SOFIA-PIOPED UIP probability categories remained prognostically significant in patients considered indeterminate (n = 83) by expert radiologist consensus (hazard ratio, 1.73; P < 0.0001; 95% confidence interval, 1.40-2.14). In patients undergoing surgical lung biopsy (n = 86), after adjusting for guideline-based histologic pattern and total ILD extent on HRCT, only SOFIA-PIOPED probabilities were predictive of mortality (hazard ratio, 1.75; P < 0.0001; 95% confidence interval, 1.37-2.25). Conclusions: Deep learning-based UIP probability on HRCT provides enhanced outcome prediction in patients with progressive fibrotic lung disease when compared with expert radiologist evaluation or guideline-based histologic pattern. In principle, this tool may be useful in multidisciplinary characterization of fibrotic lung disease. The utility of this technology as a decision support system when ILD expertise is unavailable requires further investigation.

Quantitative computed tomography predicts outcomes in idiopathic pulmonary fibrosis.

BACKGROUND AND OBJECTIVE: Prediction of disease course in patients with progressive pulmonary fibrosis remains challenging. The purpose of this study was to assess the prognostic value of lung fibrosis extent quantified at computed tomography (CT) using data-driven texture analysis (DTA) in a large cohort of well-characterized patients with idiopathic pulmonary fibrosis (IPF) enrolled in a national registry. METHODS: This retrospective analysis included participants in the Australian IPF Registry with available CT between 2007 and 2016. CT scans were analysed using the DTA method to quantify the extent of lung fibrosis. Demographics, longitudinal pulmonary function and quantitative CT metrics were compared using descriptive statistics. Linear mixed models, and Cox analyses adjusted for age, gender, BMI, smoking history and treatment with anti-fibrotics were performed to assess the relationships between baseline DTA, pulmonary function metrics and outcomes. RESULTS: CT scans of 393 participants were analysed, 221 of which had available pulmonary function testing obtained within 90 days of CT. Linear mixed-effect modelling showed that baseline DTA score was significantly associated with annual rate of decline in forced vital capacity and diffusing capacity of carbon monoxide. In multivariable Cox proportional hazard models, greater extent of lung fibrosis was associated with poorer transplant-free survival (hazard ratio [HR] 1.20, p < 0.0001) and progression-free survival (HR 1.14, p < 0.0001). CONCLUSION: In a multi-centre observational registry of patients with IPF, the extent of fibrotic abnormality on baseline CT quantified using DTA is associated with outcomes independent of pulmonary function.

Impact of the COVID-19 pandemic on the selection of chest imaging modalities and reporting systems: a survey of Italian radiologists.

PURPOSE: Chest imaging modalities play a key role for the management of patient with coronavirus disease (COVID-19). Unfortunately, there is no consensus on the optimal chest imaging approach in the evaluation of patients with COVID-19 pneumonia, and radiology departments tend to use different approaches. Thus, the main objective of this survey was to assess how chest imaging modalities have been used during the different phases of the first COVID-19 wave in Italy, and which diagnostic technique and reporting system would have been preferred based on the experience gained during the pandemic. MATERIAL AND METHODS: The questionnaire of the survey consisted of 26 questions. The link to participate in the survey was sent to all members of the Italian Society of Medical and Interventional Radiology (SIRM). RESULTS: The survey gathered responses from 716 SIRM members. The most notable result was that the most used and preferred chest imaging modality to assess/exclude/monitor COVID-19 pneumonia during the different phases of the first COVID-19 wave was computed tomography (51.8% to 77.1% of participants). Additionally, while the narrative report was the most used reporting system (55.6% of respondents), one-third of participants would have preferred to utilize structured reporting systems. CONCLUSION: This survey shows that the participants' responses did not properly align with the imaging guidelines for managing COVID-19 that have been made by several scientific, including SIRM. Therefore, there is a need for continuing education to keep radiologists up to date and aware of the advantages and limitations of the chest imaging modalities and reporting systems.

Variable radiological lung nodule evaluation leads to divergent management recommendations.

Radiological evaluation of incidentally detected lung nodules on computed tomography (CT) influences management. We assessed international radiological variation in 1) pulmonary nodule characterisation; 2) hypothetical guideline-derived management; and 3) radiologists' management recommendations.107 radiologists from 25 countries evaluated 69 CT-detected nodules, recording: 1) first-choice composition (solid, part-solid or ground-glass, with percentage confidence); 2) morphological features; 3) dimensions; 4) recommended management; and 5) decision-influencing factors. We modelled hypothetical management decisions on the 2005 and updated 2017 Fleischner Society, and both liberal and parsimonious interpretations of the British Thoracic Society 2015 guidelines.Overall agreement for first-choice nodule composition was good (Fleiss' κ=0.65), but poorest for part-solid nodules (weighted κ 0.62, interquartile range 0.50-0.71). Morphological variables, including spiculation (κ=0.35), showed poor-to-moderate agreement (κ=0.23-0.53). Variation in diameter was greatest at key thresholds (5 mm and 6 mm). Agreement for radiologists' recommendations was poor (κ=0.30); 21% disagreed with the majority. Although agreement within the four guideline-modelled management strategies was good (κ=0.63-0.73), 5-10% of radiologists would disagree with majority decisions if they applied guidelines strictly.Agreement was lowest for part-solid nodules, while significant measurement variation exists at important size thresholds. These variations resulted in generally good agreement for guideline-modelled management, but poor agreement for radiologists' actual recommendations.

Radiological and nuclear medicine imaging of sarcoidosis.

Sarcoidosis is a multisystem chronic inflammatory disease of unknown etiology characterized by widespread growth of non-caseating granulomas. The diagnosis of sarcoidosis is based on clinical and imaging presentation, histologic confirmation and the absence of alternative diseases. Radiology and Nuclear Medicine play an essential role in the diagnostic work-up of patients with sarcoidosis to assess disease extent and activity. In addition, imaging modalities have shown their potential in managing these patients in terms of treatment response and prognostic assessment. Sarcoidosis has a predilection for chest involvement, showing typical and atypical manifestations in the lungs, airways and hilar/mediastinal lymph nodes. Chest radiography (X-ray) still plays an important role in suggesting diagnosis for cases with typical presentation of sarcoidosis, while computed tomography (CT) has higher accuracy in detecting early stage disease and in narrowing differential diagnosis, particularly in atypical manifestations. For extrathoracic involvement, both CT and MR (magnetic resonance) have comparable performance even though MR is the modality of choice for assessing neurosarcoidosis and cardiac sarcoidosis. In the last decades positron emission tomography/CT (PET/CT) has demonstrated an increasing and relevant value in assessing disease extent and activity, treatment planning and therapy response, with a crucial role in the management of cardiac sarcoidosis. In this article, an overview of the possible imaging manifestations of thoracic and extrathoracic sarcoidosis and current concepts on staging, response assessment and prognosis is provided. Finally, the potential applications of non-FDG radiotracers is briefly discussed.

Diagnostic accuracy of a clinical diagnosis of idiopathic pulmonary fibrosis: an international case-cohort study.

We conducted an international study of idiopathic pulmonary fibrosis (IPF) diagnosis among a large group of physicians and compared their diagnostic performance to a panel of IPF experts.A total of 1141 respiratory physicians and 34 IPF experts participated. Participants evaluated 60 cases of interstitial lung disease (ILD) without interdisciplinary consultation. Diagnostic agreement was measured using the weighted kappa coefficient (κw). Prognostic discrimination between IPF and other ILDs was used to validate diagnostic accuracy for first-choice diagnoses of IPF and were compared using the C-index.A total of 404 physicians completed the study. Agreement for IPF diagnosis was higher among expert physicians (κw=0.65, IQR 0.53-0.72, p<0.0001) than academic physicians (κw=0.56, IQR 0.45-0.65, p<0.0001) or physicians with access to multidisciplinary team (MDT) meetings (κw=0.54, IQR 0.45-0.64, p<0.0001). The prognostic accuracy of academic physicians with >20 years of experience (C-index=0.72, IQR 0.0-0.73, p=0.229) and non-university hospital physicians with more than 20 years of experience, attending weekly MDT meetings (C-index=0.72, IQR 0.70-0.72, p=0.052), did not differ significantly (p=0.229 and p=0.052 respectively) from the expert panel (C-index=0.74 IQR 0.72-0.75).Experienced respiratory physicians at university-based institutions diagnose IPF with similar prognostic accuracy to IPF experts. Regular MDT meeting attendance improves the prognostic accuracy of experienced non-university practitioners to levels achieved by IPF experts.

Interobserver agreement for the ATS/ERS/JRS/ALAT criteria for a UIP pattern on CT.

OBJECTIVES: To establish the level of observer variation for the current ATS/ERS/JRS/ALAT criteria for a diagnosis of usual interstitial pneumonia (UIP) on CT among a large group of thoracic radiologists of varying levels of experience. MATERIALS AND METHODS: 112 observers (96 of whom were thoracic radiologists) categorised CTs of 150 consecutive patients with fibrotic lung disease using the ATS/ERS/JRS/ALAT CT criteria for a UIP pattern (3 categories--UIP, possibly UIP and inconsistent with UIP). The presence of honeycombing, traction bronchiectasis and emphysema was also scored using a 3-point scale (definitely present, possibly present, absent). Observer agreement for the UIP categorisation and for the 3 CT patterns in the entire observer group and in subgroups stratified by observer experience, were evaluated. RESULTS: Interobserver agreement across the diagnosis category scores among the 112 observers was moderate, ranging from 0.48 (IQR 0.18) for general radiologists to 0.52 (IQR 0.20) for thoracic radiologists of 10-20 years' experience. A binary score for UIP versus possible or inconsistent with UIP was examined. Observer agreement for this binary score was only moderate. No significant differences in agreement levels were identified when the CTs were stratified according to multidisciplinary team (MDT) diagnosis or patient age or when observers were categorised according to experience. Observer agreement for each of honeycombing, traction bronchiectasis and emphysema were 0.59±0.12, 0.42±0.15 and 0.43±0.18, respectively. CONCLUSIONS: Interobserver agreement for the current ATS/ERS/JRS/ALAT CT criteria for UIP is only moderate among thoracic radiologists, irrespective of their experience, and did not vary with patient age or the MDT diagnosis.

First-pass perfusion of non-small-cell lung cancer (NSCLC) with 64-detector-row CT: a study of technique repeatability and intra- and interobserver variability.

PURPOSE: This study was done to prospectively assess the repeatability and intra- and interobserver variability of first-pass perfusion with 64-detector-row computed tomography (CT) in non-small-cell lung cancer (NSCLC) with a maximum diameter of up to 8 cm. MATERIALS AND METHODS: Twelve patients with NSCLC underwent 64-detector-row first-pass CT perfusion (CTP) of the whole tumour. Two different techniques were used according to lesion size (cine mode; sequential mode). After 24 h, each study was repeated to assess repeatability. Lesion blood volume (BV), blood flow (BF), mean transit time (MTT) and peak enhancement intensity (PEI) were automatically calculated by two chest radiologists in two different reading sessions. Intra- and interobserver variability was also assessed. RESULTS: The first-pass CTP technique was repeatable and precise with within-subject coefficient of variation (WCV) of 9.3, 16.4, 11.2 and 14.9 %, respectively, for BV, BF, MTT and PEI. High intra- and interobserver agreement was demonstrated for each perfusion parameter, with Cronbach's α coefficients and intraclass correlation coefficients ranging from 0.99 to 1. Precision of measurements was slightly better for intraobserver analysis with WCV ranging between 1.05 and 3.03 %. CONCLUSIONS: Non-small-cell lung cancer first-pass perfusion performed with 64-detector-row CT showed good repeatability and high intra- and interobserver agreement for all perfusion parameters and may be considered a reliable and robust tool for assessing tumour vascularisation.

Towards the adoption of quantitative computed tomography in the management of interstitial lung disease.

The shortcomings of qualitative visual assessment have led to the development of computer-based tools to characterise and quantify disease on high-resolution computed tomography (HRCT) in patients with interstitial lung diseases (ILDs). Quantitative CT (QCT) software enables quantification of patterns on HRCT with results that are objective, reproducible, sensitive to change and predictive of disease progression. Applications developed to provide a diagnosis or pattern classification are mainly based on artificial intelligence. Deep learning, which identifies patterns in high-dimensional data and maps them to segmentations or outcomes, can be used to identify the imaging patterns that most accurately predict disease progression. Optimisation of QCT software will require the implementation of protocol standards to generate data of sufficient quality for use in computerised applications and the identification of diagnostic, imaging and physiological features that are robustly associated with mortality for use as anchors in the development of algorithms. Consortia such as the Open Source Imaging Consortium have a key role to play in the collation of imaging and clinical data that can be used to identify digital imaging biomarkers that inform diagnosis, prognosis and response to therapy.

Comparison between whole-body MRI and Fluorine-18-Fluorodeoxyglucose PET or PET/CT in oncology: a systematic review.

BACKGROUND: The aim of the article is to systematically review published data about the comparison between positron emission tomography (PET) or PET/computed tomography (PET/CT) using Fluorine-18-Fluorodeoxyglucose (FDG) and whole-body magnetic resonance imaging (WB-MRI) in patients with different tumours. METHODS: A comprehensive literature search of studies published in PubMed/MEDLINE, Scopus and Embase databases through April 2012 and regarding the comparison between FDG-PET or PET/CT and WB-MRI in patients with various tumours was carried out. RESULTS: Forty-four articles comprising 2287 patients were retrieved in full-text version, included and discussed in this systematic review. Several articles evaluated mixed tumours with both diagnostic methods. Concerning the specific tumour types, more evidence exists for lymphomas, bone tumours, head and neck tumours and lung tumours, whereas there is less evidence for other tumour types. CONCLUSIONS: Overall, based on the literature findings, WB-MRI seems to be a valid alternative method compared to PET/CT in oncology. Further larger prospective studies and in particular cost-effectiveness analysis comparing these two whole-body imaging techniques are needed to better assess the role of WB-MRI compared to FDG-PET or PET/CT in specific tumour types.

Pulmonary Hypertension in Chronic Lung Diseases: What Role Do Radiologists Play?

Pulmonary hypertension (PH) is a pathophysiological disorder, defined by a mean pulmonary arterial pressure (mPAP) > 20 mmHg at rest, as assessed by right heart catheterization (RHC). PH is not a specific disease, as it may be observed in multiple clinical conditions and may complicate a variety of thoracic diseases. Conditions associated with the risk of developing PH are categorized into five different groups, according to similar clinical presentations, pathological findings, hemodynamic characteristics, and treatment strategy. Most chronic lung diseases that may be complicated by PH belong to group 3 (interstitial lung diseases, chronic obstructive pulmonary disease, combined pulmonary fibrosis, and emphysema) and are associated with the lowest overall survival among all groups. However, some of the chronic pulmonary diseases may develop PH with unclear/multifactorial mechanisms and are included in group 5 PH (sarcoidosis, pulmonary Langerhans' cell histiocytosis, and neurofibromatosis type 1). This paper focuses on PH associated with chronic lung diseases, in which radiological imaging-particularly computed tomography (CT)-plays a crucial role in diagnosis and classification. Radiologists should become familiar with the hemodynamical, physiological, and radiological aspects of PH and chronic lung diseases in patients at risk of developing PH, whose prognosis and treatment depend on the underlying disease.

Machine learning in radiology: the new frontier in interstitial lung diseases.

Challenges for the effective management of interstitial lung diseases (ILDs) include difficulties with the early detection of disease, accurate prognostication with baseline data, and accurate and precise response to therapy. The purpose of this Review is to describe the clinical and research gaps in the diagnosis and prognosis of ILD, and how machine learning can be applied to image biomarker research to close these gaps. Machine-learning algorithms can identify ILD in at-risk populations, predict the extent of lung fibrosis, correlate radiological abnormalities with lung function decline, and be used as endpoints in treatment trials, exemplifying how this technology can be used in care for people with ILD. Advances in image processing and analysis provide further opportunities to use machine learning that incorporates deep-learning-based image analysis and radiomics. Collaboration and consistency are required to develop optimal algorithms, and candidate radiological biomarkers should be validated against appropriate predictors of disease outcomes.

Extension of Lung Damage at Chest Computed Tomography in Severely Ill COVID-19 Patients Treated with Interleukin-6 Receptor Blockers Correlates with Inflammatory Cytokines Production and Prognosis.

Elevated inflammatory markers are associated with severe coronavirus disease 2019 (COVID-19), and some patients benefit from Interleukin (IL)-6 pathway inhibitors. Different chest computed tomography (CT) scoring systems have shown a prognostic value in COVID-19, but not specifically in anti-IL-6-treated patients at high risk of respiratory failure. We aimed to explore the relationship between baseline CT findings and inflammatory conditions and to evaluate the prognostic value of chest CT scores and laboratory findings in COVID-19 patients specifically treated with anti-IL-6. Baseline CT lung involvement was assessed in 51 hospitalized COVID-19 patients naive to glucocorticoids and other immunosuppressants using four CT scoring systems. CT data were correlated with systemic inflammation and 30-day prognosis after anti-IL-6 treatment. All the considered CT scores showed a negative correlation with pulmonary function and a positive one with C-reactive protein (CRP), IL-6, IL-8, and Tumor Necrosis Factor α (TNF-α) serum levels. All the performed scores were prognostic factors, but the disease extension assessed by the six-lung-zone CT score (S24) was the only independently associated with intensive care unit (ICU) admission (p = 0.04). In conclusion, CT involvement correlates with laboratory inflammation markers and is an independent prognostic factor in COVID-19 patients representing a further tool to implement prognostic stratification in hospitalized patients.