Bexotegrast in Patients with Idiopathic Pulmonary Fibrosis: The INTEGRIS-IPF Study.

RATIONALE: Idiopathic pulmonary fibrosis (IPF) is a rare and progressive disease, which causes progressive cough, exertional dyspnea, impaired quality of life and death. OBJECTIVES: Bexotegrast (PLN 74809) is an oral, once-daily, investigational drug in development for the treatment of IPF. METHODS: This Phase 2a, multicenter, clinical trial, randomized participants with IPF to receive oral, once daily bexotegrast 40 mg, 80 mg, 160 mg, 320 mg, or placebo, with or without background IPF therapy (pirfenidone or nintedanib), in an approximately 3:1 ratio in each bexotegrast dose cohort, for at least 12 weeks. The primary endpoint was incidence of treatment-emergent adverse events (TEAEs). Exploratory efficacy endpoints included change from baseline in forced vital capacity (FVC); quantitative lung fibrosis (QLF) extent (%) and changes from baseline in fibrosis-related biomarkers. MEASUREMENTS AND MAIN RESULTS: Bexotegrast was well tolerated with similar rates of TEAEs in the pooled bexotegrast and placebo groups (62/89 [69.7%] and 21/31 [67.7%], respectively). Diarrhea was the most common TEAE; most participants with diarrhea also received nintedanib. Bexotegrast treated participants experienced a reduction in FVC decline over 12 weeks vs. placebo, with or without background therapy. A dose-dependent antifibrotic effect of bexotegrast was observed with QLF imaging and a decrease in fibrosis-associated biomarkers was observed with bexotegrast vs. placebo. CONCLUSIONS: Bexotegrast demonstrated a favorable safety and tolerability profile, up to 12 weeks for the doses studied. Exploratory analyses suggest an antifibrotic effect according to FVC, QLF imaging, and circulating levels of fibrosis biomarkers. Clinical trial registration available at www. CLINICALTRIALS: gov, ID: NCT04396756. This article is open access and distributed under the terms of the Creative Commons Attribution Non-Commercial No Derivatives License 4.0 (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Evaluation of ChatGPT-Generated Educational Patient Pamphlets for Common Interventional Radiology Procedures.

RATIONALE AND OBJECTIVES: This study aimed to evaluate the accuracy and reliability of educational patient pamphlets created by ChatGPT, a large language model, for common interventional radiology (IR) procedures. METHODS AND MATERIALS: Twenty frequently performed IR procedures were selected, and five users were tasked to independently request ChatGPT to generate educational patient pamphlets for each procedure using identical commands. Subsequently, two independent radiologists assessed the content, quality, and accuracy of the pamphlets. The review focused on identifying potential errors, inaccuracies, the consistency of pamphlets. RESULTS: In a thorough analysis of the education pamphlets, we identified shortcomings in 30% (30/100) of pamphlets, with a total of 34 specific inaccuracies, including missing information about sedation for the procedure (10/34), inaccuracies related to specific procedural-related complications (8/34). A key-word co-occurrence network showed consistent themes within each group of pamphlets, while a line-by-line comparison at the level of users and across different procedures showed statistically significant inconsistencies (P < 0.001). CONCLUSION: ChatGPT-generated education pamphlets demonstrated potential clinical relevance and fairly consistent terminology; however, the pamphlets were not entirely accurate and exhibited some shortcomings and inter-user structural variabilities. To ensure patient safety, future improvements and refinements in large language models are warranted, while maintaining human supervision and expert validation.

Quantifying lung fissure integrity using a three-dimensional patch-based convolutional neural network on CT images for emphysema treatment planning.

Purpose: Evaluation of lung fissure integrity is required to determine whether emphysema patients have complete fissures and are candidates for endobronchial valve (EBV) therapy. We propose a deep learning (DL) approach to segment fissures using a three-dimensional patch-based convolutional neural network (CNN) and quantitatively assess fissure integrity on CT to evaluate it in subjects with severe emphysema. Approach: From an anonymized image database of patients with severe emphysema, 129 CT scans were used. Lung lobe segmentations were performed to identify lobar regions, and the boundaries among these regions were used to construct approximate interlobar regions of interest (ROIs). The interlobar ROIs were annotated by expert image analysts to identify voxels where the fissure was present and create a reference ROI that excluded non-fissure voxels (where the fissure is incomplete). A CNN configured by nnU-Net was trained using 86 CT scans and their corresponding reference ROIs to segment the ROIs of left oblique fissure (LOF), right oblique fissure (ROF), and right horizontal fissure (RHF). For an independent test set of 43 cases, fissure integrity was quantified by mapping the segmented fissure ROI along the interlobar ROI. A fissure integrity score (FIS) was then calculated as the percentage of labeled fissure voxels divided by total voxels in the interlobar ROI. Predicted FIS (p-FIS) was quantified from the CNN output, and statistical analyses were performed comparing p-FIS and reference FIS (r-FIS). Results: The absolute percent error mean (±SD) between r-FIS and p-FIS for the test set was 4.0% (±4.1%), 6.0% (±9.3%), and 12.2% (±12.5%) for the LOF, ROF, and RHF, respectively. Conclusions: A DL approach was developed to segment lung fissures on CT images and accurately quantify FIS. It has potential to assist in the identification of emphysema patients who would benefit from EBV treatment.

MIDRC-MetricTree: a decision tree-based tool for recommending performance metrics in artificial intelligence-assisted medical image analysis.

Purpose: The Medical Imaging and Data Resource Center (MIDRC) was created to facilitate medical imaging machine learning (ML) research for tasks including early detection, diagnosis, prognosis, and assessment of treatment response related to the coronavirus disease 2019 pandemic and beyond. The purpose of this work was to create a publicly available metrology resource to assist researchers in evaluating the performance of their medical image analysis ML algorithms. Approach: An interactive decision tree, called MIDRC-MetricTree, has been developed, organized by the type of task that the ML algorithm was trained to perform. The criteria for this decision tree were that (1) users can select information such as the type of task, the nature of the reference standard, and the type of the algorithm output and (2) based on the user input, recommendations are provided regarding appropriate performance evaluation approaches and metrics, including literature references and, when possible, links to publicly available software/code as well as short tutorial videos. Results: Five types of tasks were identified for the decision tree: (a) classification, (b) detection/localization, (c) segmentation, (d) time-to-event (TTE) analysis, and (e) estimation. As an example, the classification branch of the decision tree includes two-class (binary) and multiclass classification tasks and provides suggestions for methods, metrics, software/code recommendations, and literature references for situations where the algorithm produces either binary or non-binary (e.g., continuous) output and for reference standards with negligible or non-negligible variability and unreliability. Conclusions: The publicly available decision tree is a resource to assist researchers in conducting task-specific performance evaluations, including classification, detection/localization, segmentation, TTE, and estimation tasks.

Assessing variability in non-contrast CT for the evaluation of stroke: The effect of CT image reconstruction conditions on AI-based CAD measurements of ASPECTS value and hypodense volume.

Purpose: To rule out hemorrhage, non-contrast CT (NCCT) scans are used for early evaluation of patients with suspected stroke. Recently, artificial intelligence tools have been developed to assist with determining eligibility for reperfusion therapies by automating measurement of the Alberta Stroke Program Early CT Score (ASPECTS), a 10-point scale with > 7 or ≤ 7 being a threshold for change in functional outcome prediction and higher chance of symptomatic hemorrhage, and hypodense volume. The purpose of this work was to investigate the effects of CT reconstruction kernel and slice thickness on ASPECTS and hypodense volume. Methods: The NCCT series image data of 87 patients imaged with a CT stroke protocol at our institution were reconstructed with 3 kernels (H10s-smooth, H40s-medium, H70h-sharp) and 2 slice thicknesses (1.5mm and 5mm) to create a reference condition (H40s/5mm) and 5 non-reference conditions. Each reconstruction for each patient was analyzed with the Brainomix e-Stroke software (Brainomix, Oxford, England) which yields an ASPECTS value and measure of total hypodense volume (mL). Results: An ASPECTS value was returned for 74 of 87 cases in the reference condition (13 failures). ASPECTS in non-reference conditions changed from that measured in the reference condition for 59 cases, 7 of which changed above or below the clinical threshold of 7 for 3 non-reference conditions. ANOVA tests were performed to compare the differences in protocols, Dunnett's post-hoc tests were performed after ANOVA, and a significance level of p < 0.05 was defined. There was no significant effect of kernel (p = 0.91), a significant effect of slice thickness (p < 0.01) and no significant interaction between these factors (p = 0.91). Post-hoc tests indicated no significant difference between ASPECTS estimated in the reference and any non-reference conditions. There was a significant effect of kernel (p < 0.01) and slice thickness (p < 0.01) on hypodense volume, however there was no significant interaction between these factors (p = 0.79). Post-hoc tests indicated significantly different hypodense volume measurements for H10s/1.5mm (p = 0.03), H40s/1.5mm (p < 0.01), H70h/5mm (p < 0.01). No significant difference was found in hypodense volume measured in the H10s/5mm condition (p = 0.96). Conclusion: Automated ASPECTS and hypodense volume measurements can be significantly impacted by reconstruction kernel and slice thickness.

ChatGPT in radiology: A systematic review of performance, pitfalls, and future perspectives.

PURPOSE: The purpose of this study was to systematically review the reported performances of ChatGPT, identify potential limitations, and explore future directions for its integration, optimization, and ethical considerations in radiology applications. MATERIALS AND METHODS: After a comprehensive review of PubMed, Web of Science, Embase, and Google Scholar databases, a cohort of published studies was identified up to January 1, 2024, utilizing ChatGPT for clinical radiology applications. RESULTS: Out of 861 studies derived, 44 studies evaluated the performance of ChatGPT; among these, 37 (37/44; 84.1%) demonstrated high performance, and seven (7/44; 15.9%) indicated it had a lower performance in providing information on diagnosis and clinical decision support (6/44; 13.6%) and patient communication and educational content (1/44; 2.3%). Twenty-four (24/44; 54.5%) studies reported the proportion of ChatGPT's performance. Among these, 19 (19/24; 79.2%) studies recorded a median accuracy of 70.5%, and in five (5/24; 20.8%) studies, there was a median agreement of 83.6% between ChatGPT outcomes and reference standards [radiologists' decision or guidelines], generally confirming ChatGPT's high accuracy in these studies. Eleven studies compared two recent ChatGPT versions, and in ten (10/11; 90.9%), ChatGPTv4 outperformed v3.5, showing notable enhancements in addressing higher-order thinking questions, better comprehension of radiology terms, and improved accuracy in describing images. Risks and concerns about using ChatGPT included biased responses, limited originality, and the potential for inaccurate information leading to misinformation, hallucinations, improper citations and fake references, cybersecurity vulnerabilities, and patient privacy risks. CONCLUSION: Although ChatGPT's effectiveness has been shown in 84.1% of radiology studies, there are still multiple pitfalls and limitations to address. It is too soon to confirm its complete proficiency and accuracy, and more extensive multicenter studies utilizing diverse datasets and pre-training techniques are required to verify ChatGPT's role in radiology.

Automated abdominal adipose tissue segmentation and volume quantification on longitudinal MRI using 3D convolutional neural networks with multi-contrast inputs.

OBJECTIVE: Increased subcutaneous and visceral adipose tissue (SAT/VAT) volume is associated with risk for cardiometabolic diseases. This work aimed to develop and evaluate automated abdominal SAT/VAT segmentation on longitudinal MRI in adults with overweight/obesity using attention-based competitive dense (ACD) 3D U-Net and 3D nnU-Net with full field-of-view volumetric multi-contrast inputs. MATERIALS AND METHODS: 920 adults with overweight/obesity were scanned twice at multiple 3 T MRI scanners and institutions. The first scan was divided into training/validation/testing sets (n = 646/92/182). The second scan from the subjects in the testing set was used to evaluate the generalizability for longitudinal analysis. Segmentation performance was assessed by measuring Dice scores (DICE-SAT, DICE-VAT), false negatives (FN), and false positives (FP). Volume agreement was assessed using the intraclass correlation coefficient (ICC). RESULTS: ACD 3D U-Net achieved rapid (< 4.8 s/subject) segmentation with high DICE-SAT (median ≥ 0.994) and DICE-VAT (median ≥ 0.976), small FN (median ≤ 0.7%), and FP (median ≤ 1.1%). 3D nnU-Net yielded rapid (< 2.5 s/subject) segmentation with similar DICE-SAT (median ≥ 0.992), DICE-VAT (median ≥ 0.979), FN (median ≤ 1.1%) and FP (median ≤ 1.2%). Both models yielded excellent agreement in SAT/VAT volume versus reference measurements (ICC > 0.997) in longitudinal analysis. DISCUSSION: ACD 3D U-Net and 3D nnU-Net can be automated tools to quantify abdominal SAT/VAT volume rapidly, accurately, and longitudinally in adults with overweight/obesity.

Interstitial lung abnormality evaluated by an automated quantification system: prevalence and progression rate.

BACKGROUND: Despite the importance of recognizing interstitial lung abnormalities, screening methods using computer-based quantitative analysis are not well developed, and studies on the subject with an Asian population are rare. We aimed to identify the prevalence and progression rate of interstitial lung abnormality evaluated by an automated quantification system in the Korean population. METHODS: A total of 2,890 healthy participants in a health screening program (mean age: 49 years, men: 79.5%) with serial chest computed tomography images obtained at least 5 years apart were included. Quantitative lung fibrosis scores were measured on the chest images by an automated quantification system. Interstitial lung abnormalities were defined as a score ≥ 3, and progression as any score increased above baseline. RESULTS: Interstitial lung abnormalities were identified in 251 participants (8.6%), who were older and had a higher body mass index. The prevalence increased with age. Quantification of the follow-up images (median interval: 6.5 years) showed that 23.5% (59/251) of participants initially diagnosed with interstitial lung abnormality exhibited progression, and 11% had developed abnormalities (290/2639). Older age, higher body mass index, and higher erythrocyte sedimentation rate were independent risk factors for progression or development. The interstitial lung abnormality group had worse survival on follow-up (5-year mortality: 3.4% vs. 1.5%; P = 0.010). CONCLUSIONS: Interstitial lung abnormality could be identified in one-tenth of the participants, and a quarter of them showed progression. Older age, higher body mass index and higher erythrocyte sedimentation rate increased the risk of development or progression of interstitial lung abnormality.

Quantitative Computed Tomography Lung COVID Scores with Laboratory Markers: Utilization to Predict Rapid Progression and Monitor Longitudinal Changes in Patients with Coronavirus 2019 (COVID-19) Pneumonia.

Coronavirus disease 2019 (COVID-19), is an ongoing issue in certain populations, presenting rapidly worsening pneumonia and persistent symptoms. This study aimed to test the predictability of rapid progression using radiographic scores and laboratory markers and present longitudinal changes. This retrospective study included 218 COVID-19 pneumonia patients admitted at the Chungnam National University Hospital. Rapid progression was defined as respiratory failure requiring mechanical ventilation within one week of hospitalization. Quantitative COVID (QCOVID) scores were derived from high-resolution computed tomography (CT) analyses: (1) ground glass opacity (QGGO), (2) mixed diseases (QMD), and (3) consolidation (QCON), and the sum, quantitative total lung diseases (QTLD). Laboratory data, including inflammatory markers, were obtained from electronic medical records. Rapid progression was observed in 9.6% of patients. All QCOVID scores predicted rapid progression, with QMD showing the best predictability (AUC = 0.813). In multivariate analyses, the QMD score and interleukin(IL)-6 level were important predictors for rapid progression (AUC = 0.864). With >2 months follow-up CT, remained lung lesions were observed in 21 subjects, even after several weeks of negative reverse transcription polymerase chain reaction test. AI-driven quantitative CT scores in conjugation with laboratory markers can be useful in predicting the rapid progression and monitoring of COVID-19.

Pulmonary Fibrosis Stakeholder Summit: A Joint NHLBI, Three Lakes Foundation, and Pulmonary Fibrosis Foundation Workshop Report.

Despite progress in elucidation of disease mechanisms, identification of risk factors, biomarker discovery, and the approval of two medications to slow lung function decline in idiopathic pulmonary fibrosis and one medication to slow lung function decline in progressive pulmonary fibrosis, pulmonary fibrosis remains a disease with a high morbidity and mortality. In recognition of the need to catalyze ongoing advances and collaboration in the field of pulmonary fibrosis, the NHLBI, the Three Lakes Foundation, and the Pulmonary Fibrosis Foundation hosted the Pulmonary Fibrosis Stakeholder Summit on November 8-9, 2022. This workshop was held virtually and was organized into three topic areas: 1) novel models and research tools to better study pulmonary fibrosis and uncover new therapies, 2) early disease risk factors and methods to improve diagnosis, and 3) innovative approaches toward clinical trial design for pulmonary fibrosis. In this workshop report, we summarize the content of the presentations and discussions, enumerating research opportunities for advancing our understanding of the pathogenesis, treatment, and outcomes of pulmonary fibrosis.

Sequestration of imaging studies in MIDRC: stratified sampling to balance demographic characteristics of patients in a multi-institutional data commons.

Purpose: The Medical Imaging and Data Resource Center (MIDRC) is a multi-institutional effort to accelerate medical imaging machine intelligence research and create a publicly available image repository/commons as well as a sequestered commons for performance evaluation and benchmarking of algorithms. After de-identification, approximately 80% of the medical images and associated metadata become part of the open commons and 20% are sequestered from the open commons. To ensure that both commons are representative of the population available, we introduced a stratified sampling method to balance the demographic characteristics across the two datasets. Approach: Our method uses multi-dimensional stratified sampling where several demographic variables of interest are sequentially used to separate the data into individual strata, each representing a unique combination of variables. Within each resulting stratum, patients are assigned to the open or sequestered commons. This algorithm was used on an example dataset containing 5000 patients using the variables of race, age, sex at birth, ethnicity, COVID-19 status, and image modality and compared resulting demographic distributions to naïve random sampling of the dataset over 2000 independent trials. Results: Resulting prevalence of each demographic variable matched the prevalence from the input dataset within one standard deviation. Mann-Whitney U test results supported the hypothesis that sequestration by stratified sampling provided more balanced subsets than naïve randomization, except for demographic subcategories with very low prevalence. Conclusions: The developed multi-dimensional stratified sampling algorithm can partition a large dataset while maintaining balance across several variables, superior to the balance achieved from naïve randomization.

Combining Clinical and Biological Data to Predict Progressive Pulmonary Fibrosis in Patients With Systemic Sclerosis Despite Immunomodulatory Therapy.

OBJECTIVE: Progressive pulmonary fibrosis (PPF) is the leading cause of death in systemic sclerosis (SSc). This study aimed to develop a clinical prediction nomogram using clinical and biological data to assess risk of PPF among patients receiving treatment of SSc-related interstitial lung disease (SSc-ILD). METHODS: Patients with SSc-ILD who participated in the Scleroderma Lung Study II (SLS II) were randomized to treatment with either mycophenolate mofetil (MMF) or cyclophosphamide (CYC). Clinical and biological parameters were analyzed using univariable and multivariable logistic regression, and a nomogram was created to assess the risk of PPF and validated by bootstrap resampling. RESULTS: Among 112 participants with follow-up data, 22 (19.6%) met criteria for PPF between 12 and 24 months. An equal proportion of patients randomized to CYC (n = 11 of 56) and mycophenolate mofetil (n = 11 of 56) developed PPF. The baseline severity of ILD was similar for patients who did, compared to those who did not, experience PPF in terms of their baseline forced vital capacity percent predicted, diffusing capacity for carbon monoxide percent predicted, and quantitative radiological extent of ILD. Predictors in the nomogram included sex, baseline CXCL4 level, and baseline gastrointestinal reflux score. The nomogram demonstrated moderate discrimination in estimating the risk of PPF, with a C-index of 0.72 (95% confidence interval 0.60-0.84). CONCLUSION: The SLS II data set provided a unique opportunity to investigate predictors of PPF and develop a nomogram to help clinicians identify patients with SSc-ILD who require closer monitoring while on therapy and potentially an alternative treatment approach. This nomogram warrants external validation in other SSc-ILD cohorts to confirm its predictive power.

How AI Responds to Common Lung Cancer Questions: ChatGPT vs Google Bard.

Background The recent release of large language models (LLMs) for public use, such as ChatGPT and Google Bard, has opened up a multitude of potential benefits as well as challenges. Purpose To evaluate and compare the accuracy and consistency of responses generated by publicly available ChatGPT-3.5 and Google Bard to non-expert questions related to lung cancer prevention, screening, and terminology commonly used in radiology reports based on the recommendation of Lung Imaging Reporting and Data System (Lung-RADS) v2022 from American College of Radiology and Fleischner society. Materials and Methods Forty of the exact same questions were created and presented to ChatGPT-3.5 and Google Bard experimental version as well as Bing and Google search engines by three different authors of this paper. Each answer was reviewed by two radiologists for accuracy. Responses were scored as correct, partially correct, incorrect, or unanswered. Consistency was also evaluated among the answers. Here, consistency was defined as the agreement between the three answers provided by ChatGPT-3.5, Google Bard experimental version, Bing, and Google search engines regardless of whether the concept conveyed was correct or incorrect. The accuracy among different tools were evaluated using Stata. Results ChatGPT-3.5 answered 120 questions with 85 (70.8%) correct, 14 (11.7%) partially correct, and 21 (17.5%) incorrect. Google Bard did not answer 23 (19.1%) questions. Among the 97 questions answered by Google Bard, 62 (51.7%) were correct, 11 (9.2%) were partially correct, and 24 (20%) were incorrect. Bing answered 120 questions with 74 (61.7%) correct, 13 (10.8%) partially correct, and 33 (27.5%) incorrect. Google search engine answered 120 questions with 66 (55%) correct, 27 (22.5%) partially correct, and 27 (22.5%) incorrect. The ChatGPT-3.5 is more likely to provide correct or partially answer than Google Bard, approximately by 1.5 folds (OR = 1.55, P = 0.004). ChatGPT-3.5 and Google search engine were more likely to be consistent than Google Bard by approximately 7 and 29 folds (OR = 6.65, P = 0.002 for ChatGPT and OR = 28.83, P = 0.002 for Google search engine, respectively). Conclusion Although ChatGPT-3.5 had a higher accuracy in comparison with the other tools, neither ChatGPT nor Google Bard, Bing and Google search engines answered all questions correctly and with 100% consistency.

Translating AI to Clinical Practice: Overcoming Data Shift with Explainability.

To translate artificial intelligence (AI) algorithms into clinical practice requires generalizability of models to real-world data. One of the main obstacles to generalizability is data shift, a data distribution mismatch between model training and real environments. Explainable AI techniques offer tools to detect and mitigate the data shift problem and develop reliable AI for clinical practice. Most medical AI is trained with datasets gathered from limited environments, such as restricted disease populations and center-dependent acquisition conditions. The data shift that commonly exists in the limited training set often causes a significant performance decrease in the deployment environment. To develop a medical application, it is important to detect potential data shift and its impact on clinical translation. During AI training stages, from premodel analysis to in-model and post hoc explanations, explainability can play a key role in detecting model susceptibility to data shift, which is otherwise hidden because the test data have the same biased distribution as the training data. Performance-based model assessments cannot effectively distinguish the model overfitting to training data bias without enriched test sets from external environments. In the absence of such external data, explainability techniques can aid in translating AI to clinical practice as a tool to detect and mitigate potential failures due to data shift. ©RSNA, 2023 Quiz questions for this article are available in the supplemental material.

Quantitative interstitial lung disease scores in idiopathic inflammatory myopathies: longitudinal changes and clinical implications.

OBJECTIVES: To investigate computer-aided quantitative scores from high-resolution CT (HRCT) images and determine their longitudinal changes and clinical significance in patients with idiopathic inflammatory myopathies (IIMs)-related interstitial lung disease (IIMs-ILD). METHODS: The clinical data and HRCT images of 80 patients with IIMs who underwent serial HRCT scans at least twice were retrospectively analysed. Quantitative ILD (QILD) scores (%) were calculated as the sum of the extent of lung fibrosis, ground-glass opacity, and honeycombing. The individual time-estimated ΔQILD between two consecutive scans was derived using a linear approximation of yearly changes. RESULTS: The baseline median QILD (interquartile range) scores in the whole lung were 28.1% (19.1-43.8). The QILD was significantly correlated with forced vital capacity (r = -0.349, P = 0.002) and diffusing capacity for carbon monoxide (r = -0.381, P = 0.001). For ΔQILD between the first two scans, according to the visual ILD subtype, QILD aggravation was more frequent in patients with usual interstitial pneumonia (UIP) than non-UIP (80.0% vs 44.4%, P = 0.013). Multivariable logistic regression analyses identified UIP was significantly related to radiographic ILD progression (ΔQILD >2%, P = 0.015). Patients with higher baseline QILD scores (>28.1%) had a higher risk of lung transplantation or death (P = 0.015). In the analysis of three serial HRCT scans (n = 41), dynamic ΔQILD with four distinct patterns (improving, worsening, convex and concave) was observed. CONCLUSION: QILD changes in IIMs-ILD were dynamic, and baseline UIP patterns seemed to be related to a longitudinal progression in QILD. These may be potential imaging biomarkers for lung function, changes in ILD severity and prognosis in IIMs-ILD.

Association of Symptoms of Gastroesophageal Reflux, Esophageal Dilation, and Progression of Systemic Sclerosis-Related Interstitial Lung Disease.

OBJECTIVE: To investigate whether symptoms of gastroesophageal reflux disease and radiographic measures of esophageal dilation are associated with radiographic progression of systemic sclerosis-related interstitial lung disease (SSc-ILD). METHODS: Participants of the Scleroderma Lung Study II, which compared mycophenolate versus cyclophosphamide for SSc-ILD, completed the reflux domain of the University of California Los Angeles Scleroderma Clinical Trials Consortium Gastrointestinal Tract 2.0 at baseline. The diameter and area of the esophagus in the region of maximum dilation was measured by quantitative image analysis. Univariate and multivariable linear regression analyses were created to evaluate the relationship between these measures of esophageal involvement and progression of SSc-ILD over 2 years, based on the radiologic quantitative interstitial lung disease (QILD) and quantitative lung fibrosis (QLF) in the lobe of maximum involvement (LM). All multivariable models controlled for the treatment arm, baseline ILD severity, and proton-pump inhibitor use. RESULTS: The baseline mean patient-reported reflux score was 0.57, indicating moderate reflux (n = 141). Baseline mean maximal esophageal diameter and area were 22 mm and 242 mm2 , respectively. Baseline reflux scores were significantly associated with the change in QLF-LM and QILD-LM in the univariate and multivariable models. Neither radiographic measure of esophageal dilation was associated with the change in radiographic measures of lung involvement. CONCLUSION: Severity of reflux symptoms as measured by an SSc-specific questionnaire was independently associated with the change in the radiographic extent of ILD and fibrosis over 2 years in patients with SSc-ILD. Two objective measures of esophageal dilation were not associated with radiographic progression of ILD, highlighting the need for improved objective measures of esophageal dysfunction in SSc.

Multi-scale, domain knowledge-guided attention + random forest: a two-stage deep learning-based multi-scale guided attention models to diagnose idiopathic pulmonary fibrosis from computed tomography images.

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a progressive, irreversible, and usually fatal lung disease of unknown reasons, generally affecting the elderly population. Early diagnosis of IPF is crucial for triaging patients' treatment planning into anti-fibrotic treatment or treatments for other causes of pulmonary fibrosis. However, current IPF diagnosis workflow is complicated and time-consuming, which involves collaborative efforts from radiologists, pathologists, and clinicians and it is largely subject to inter-observer variability. PURPOSE: The purpose of this work is to develop a deep learning-based automated system that can diagnose subjects with IPF among subjects with interstitial lung disease (ILD) using an axial chest computed tomography (CT) scan. This work can potentially enable timely diagnosis decisions and reduce inter-observer variability. METHODS: Our dataset contains CT scans from 349 IPF patients and 529 non-IPF ILD patients. We used 80% of the dataset for training and validation purposes and 20% as the holdout test set. We proposed a two-stage model: at stage one, we built a multi-scale, domain knowledge-guided attention model (MSGA) that encouraged the model to focus on specific areas of interest to enhance model explainability, including both high- and medium-resolution attentions; at stage two, we collected the output from MSGA and constructed a random forest (RF) classifier for patient-level diagnosis, to further boost model accuracy. RF classifier is utilized as a final decision stage since it is interpretable, computationally fast, and can handle correlated variables. Model utility was examined by (1) accuracy, represented by the area under the receiver operating characteristic curve (AUC) with standard deviation (SD), and (2) explainability, illustrated by the visual examination of the estimated attention maps which showed the important areas for model diagnostics. RESULTS: During the training and validation stage, we observe that when we provide no guidance from domain knowledge, the IPF diagnosis model reaches acceptable performance (AUC±SD = 0.93±0.07), but lacks explainability; when including only guided high- or medium-resolution attention, the learned attention maps are not satisfactory; when including both high- and medium-resolution attention, under certain hyperparameter settings, the model reaches the highest AUC among all experiments (AUC±SD = 0.99±0.01) and the estimated attention maps concentrate on the regions of interests for this task. Three best-performing hyperparameter selections according to MSGA were applied to the holdout test set and reached comparable model performance to that of the validation set. CONCLUSIONS: Our results suggest that, for a task with only scan-level labels available, MSGA+RF can utilize the population-level domain knowledge to guide the training of the network, which increases both model accuracy and explainability.

Automated quantification system predicts survival in rheumatoid arthritis-associated interstitial lung disease.

OBJECTIVE: The prognosis of RA-associated interstitial lung disease (RA-ILD) is difficult to predict because of the variable clinical course. This study aimed to determine the prognostic value of an automated quantification system (AQS) in RA-ILD. METHODS: We retrospectively analysed the clinical data and high-resolution CT (HRCT) images of 144 patients with RA-ILD. Quantitative lung fibrosis (QLF, sum of reticulation and traction bronchiectasis) and ILD [QILD; sum of QLF, honeycombing (QHC), and ground-glass opacity (QGG)] scores were measured using the AQS. RESULTS: The mean age was 61.2 years, 43.8% of the patients were male, and the 5-year mortality rate was 30.5% (median follow-up, 52.2 months). Non-survivors showed older age, higher ESR and greater AQS scores than survivors. In multivariable Cox analysis, higher QLF, QHC and QILD scores were independent prognostic factors along with older age and higher ESR. In receiver-operating characteristic curve analysis, the QLF score showed better performance in predicting 5-year mortality than the QHC and QGG scores but was similar to the QILD score. Patients with high QLF scores (≥12% of total lung volume) showed higher 5-year mortality (50% vs 17.4%, P < 0.001) than those with low QLF scores and similar survival outcome to patients with idiopathic pulmonary fibrosis (IPF). Combining with clinical variables (age, ESR) further improved the performance of QLF score in predicting 5-year mortality. CONCLUSION: QLF scores might be useful for predicting prognosis in patients with RA-ILD. High QLF scores differentiate a poor prognostic phenotype similar to IPF.

Procedural outcomes associated with use of the AngioVac System for right heart thrombi: A safety report from RAPID registry data.

Background: Right heart thrombi can be a source of considerable morbidity and mortality, especially when associated with pulmonary embolism. Methods: To understand the safety and procedural efficacy associated with vacuum-assisted thrombectomy using the AngioVac System (AngioDynamics, Latham, NY, USA) to remove right heart thrombi, we conducted a subanalysis of the Registry of AngioVac Procedures in Detail (RAPID) multicenter registry representing 47 (20.1%) of 234 participants in the registry. Forty-two (89.4%) patients had thrombi located in the right atrium alone, three (6.4%) in the right ventricle alone, and two (4.3%) in both the right atrium and ventricle. Four (8.5%) patients had concomitant caval thrombi, three (6.4%) also had catheter-related thrombi, and one (2.1%) patient had both caval and catheter-related thrombi with their right heart thrombi. Results: Extracorporeal bypass time was less than 1 hour for 39 (83.0%) procedures. Seventy to 100% removal of thrombus was achieved in 59.6% of patients. Estimated blood loss was less than 250 cc for 43 procedures (91.6%). Mean hemoglobin decreased from 10.7 ± 2.2 g/dL preoperatively to 9.6 ± 1.6 g/dL postoperatively. Transfusions were administered for eight procedures (17.0%), with only one (2.1%) patient receiving more than 2 units of blood. Six patients (12.8%) experienced procedure-related adverse events, including three (6.4%) patients who experienced distal emboli and three (6.4%) patients who developed bleeding-related complications. All adverse events resolved prior to discharge. There was one death (2.1%) reported that was not procedure related. Conclusion: Vacuum-assisted thrombectomy can be performed safely in patients with right heart thrombi. ClinicalTrials.gov Identifier: NCT04414332.