Thoracic Radiologists Research Articles

Evolving and Novel Applications of Artificial Intelligence in Thoracic Imaging.

The advent of artificial intelligence (AI) is revolutionizing medicine, particularly radiology. With the development of newer models, AI applications are demonstrating improved performance and versatile utility in the clinical setting. Thoracic imaging is an area of profound interest, given the prevalence of chest imaging and the significant health implications of thoracic diseases. This review aims to highlight the promising applications of AI within thoracic imaging. It examines the role of AI, including its contributions to improving diagnostic evaluation and interpretation, enhancing workflow, and aiding in invasive procedures. Next, it further highlights the current challenges and limitations faced by AI, such as the necessity of 'big data', ethical and legal considerations, and bias in representation. Lastly, it explores the potential directions for the application of AI in thoracic radiology.

The diagnostic value of CT-based radiomics nomogram for solitary indeterminate smoothly marginated solid pulmonary nodules.

This study aimed to explore the value of radiomics nomogram based on computed tomography (CT) on the diagnosis of benign and malignant solitary indeterminate smoothly marginated solid pulmonary nodules (SMSPNs). This study retrospectively reviewed 205 cases with solitary indeterminate SMSPNs on CT, including 112 cases of benign nodules and 93 cases of malignant nodules. They were divided into training (n=143) and validation (n=62) cohorts based on different CT scanners. Radiomics features of the nodules were extracted from the lung window CT images. The variance threshold method, SelectKBest, and least absolute shrinkage and selection operator were used to select the key radiomics features to construct the rad-score. Through multivariate logistic regression analysis, a nomogram was built by combining rad-score, clinical factors, and CT features. The nomogram performance was evaluated by the area under the receiver operating characteristic curve (AUC). A total of 19 radiomics features were selected to construct the rad-score, and the nomogram was constructed by the rad-score, one clinical factor (history of malignant tumor), and three CT features (including calcification, pleural retraction, and lobulation). The nomogram performed better than the radiomics model, clinical model, and experienced radiologists who specialized in thoracic radiology for nodule diagnosis. The AUC values of the nomogram were 0.942 in the training cohort and 0.933 in the validation cohort. The calibration curve and decision curve showed that the nomogram demonstrated good consistency and clinical applicability. The CT-based radiomics nomogram achieved high efficiency in the preoperative diagnosis of solitary indeterminate SMSPNs, and it is of great significance in guiding clinical decision-making.

Value of CT quantification in progressive fibrosing interstitial lung disease: a deep learning approach.

To evaluate the relationship of changes in the deep learning-based CT quantification of interstitial lung disease (ILD) with changes in forced vital capacity (FVC) and visual assessments of ILD progression, and to investigate their prognostic implications. This study included ILD patients with CT scans at intervals of over 2 years between January 2015 and June 2021. Deep learning-based texture analysis software was used to segment ILD findings on CT images (fibrosis: reticular opacity + honeycombing cysts; total ILD extent: ground-glass opacity + fibrosis). Patients were grouped according to the absolute decline of predicted FVC (< 5%, 5-10%, and ≥ 10%) and ILD progression assessed by thoracic radiologists, and their quantification results were compared among these groups. The associations between quantification results and survival were evaluated using multivariable Cox regression analysis. In total, 468 patients (239 men; 64 ± 9.5 years) were included. Fibrosis and total ILD extents more increased in patients with larger FVC decline (p < .001 in both). Patients with ILD progression had higher fibrosis and total ILD extent increases than those without ILD progression (p < .001 in both). Increases in fibrosis and total ILD extent were significant prognostic factors when adjusted for absolute FVC declines of ≥ 5% (hazard ratio [HR] 1.844, p = .01 for fibrosis; HR 2.484, p < .001 for total ILD extent) and ≥ 10% (HR 2.918, p < .001 for fibrosis; HR 3.125, p < .001 for total ILD extent). Changes in ILD CT quantification correlated with changes in FVC and visual assessment of ILD progression, and they were independent prognostic factors in ILD patients. Quantifying the CT features of interstitial lung disease using deep learning techniques could play a key role in defining and predicting the prognosis of progressive fibrosing interstitial lung disease. • Radiologic findings on high-resolution CT are important in diagnosing progressive fibrosing interstitial lung disease. • Deep learning-based quantification results for fibrosis and total interstitial lung disease extents correlated with the decline in forced vital capacity and visual assessments of interstitial lung disease progression, and emerged as independent prognostic factors. • Deep learning-based interstitial lung disease CT quantification can play a key role in diagnosing and prognosticating progressive fibrosing interstitial lung disease.

Digital health delivery in respiratory medicine: adjunct, replacement or cause for division?

Digital medicine is already well established in respiratory medicine through remote monitoring digital devices which are used in the day-to-day care of patients with asthma, COPD and sleep disorders. Image recognition software, deployed in thoracic radiology for many applications including lung cancer screening, is another application of digital medicine. Used as clinical decision support, this software will soon become part of day-to-day practice once concerns regarding generalisability have been addressed. Embodied in the electronic health record, digital medicine also plays a substantial role in the day-to-day clinical practice of respiratory medicine. Given the considerable work the electronic health record demands from clinicians, the next tangible impact of digital medicine may be artificial intelligence that aids administration, makes record keeping easier and facilitates better digital communication with patients. Future promises of digital medicine are based on their potential to analyse and characterise the large amounts of digital clinical data that are collected in routine care. Offering the potential to predict outcomes and personalise therapy, there is much to be excited by in this new epoch of innovation. However, these digital tools are by no means a silver bullet. It remains uncertain whether, let alone when, the promises of better models of personalisation and prediction will translate into clinically meaningful and cost-effective products for clinicians.

Risk of Lung Cancer in Peripheral Pulmonary Nodules

PurposeTo determine the risk of lung cancer and inter-observer agreement for small pulmonary nodules either touching or near the pleura. MethodsNodules were derived from two cohorts: patients from the National Lung Screening Trial with a solid nodule measuring 6-9.5 mm; and patients with incidental pulmonary nodules in our healthcare system with a solid nodule measuring 1-8 mm. Only the dominant nodule was evaluated for each patient. All malignant nodules as well as a random sample of 200 benign nodules from each cohort were included. Two fellowship-trained thoracic radiologists independently reviewed each case to record nodule morphology (compatible with lymph node or not) and nodule location (pleural-based, septal connection to the pleura, or neither). One radiologist measured the distance to the pleura. ResultsAfter exclusion criteria were applied, a total of 434 nodules were included, of which 45 were lung cancers. Considering all pleural-based nodules with lymph node morphology as benign, 0-7% of cancers were misclassified as benign, specificity 33%, and κ = 0.69. Considering subpleural nodules and those with septal connection to the pleura, 7-11% of cancers were misclassified (p=0.16-0.25 versus pleural-based), specificity 40-52% (p<.0001), and κ = 0.60. Considering nodules with lymph node morphology ≤ 2 mm from the pleura, 2-7% of cancers were misclassified (p=1 versus pleural-based), specificity 41-36% (p<.0001), and κ = 0.78. ConclusionConsidering nodules with lymph node morphology with septal connection, or those ≤ 2 mm from the pleura, as benign does not lead to significant misclassification of lung cancers as benign.

Immunoglobulin G4-related thoracic disease: clinical and radiological findings of a Turkish cohort.

Thoracic involvement of Immunoglobulin G4-related disease (IgG4-RD) is relatively rare and may be disregarded at the time of initial diagnosis due to its asymptomatic nature. This study aimed to ascertain the prevalence and patterns of thoracic involvement in a retrospective cohort of Turkish patients with IgG4-RD. A total of 90 patients (47 males and 43 females, with a mean age of 57.7±15.5 years) diagnosed with IgG4-RD were reviewed retrospectively. All computed tomography (CT) scans were re-evaluated by two thoracic radiologists and IgG4-related thoracic disease was assessed on four compartments: The mediastinum, pulmonary parenchyma, airways, and pleura. IgG4-related thoracic disease was categorized as: definite, highly probable, probable or possible. There were 64 patients who had undergone at least one thorax CT examination, and 18 (28%) were diagnosed with IgG4-related thoracic disease. The rate of IgG4-related thoracic disease increased by 20% and reached a ratio of 48.4% (n=31) after a thorough reevaluation of registry data specifically to thoracic findings. The mediastinum was the most frequently involved compartment, affecting 16 (51.6%) patients, followed by pulmonary parenchyma in 14 (45.2%) patients, and airways and pleura in 10 (32.3%) patients each. Other organ involvements were more prevalent and IgG4 levels were higher in patients with thoracic involvement. Eosinophils were significantly elevated in patients with thoracic involvement (p=0.023). IgG4-related thoracic disease is heterogeneous and likely to be more prevalent than currently recognized. The mediastinum is the most frequently involved compartment. It is important to assess IgG4-related thoracic disease at the time of initial diagnosis. Elevated levels of serum IgG4 and eosinophils, as well as a greater number of organ involvements may serve as indicators of thoracic involvement.

Society of Thoracic Radiology Abstracts from the 2024 Annual Meeting February 24th-28th, 2024.

Society of Thoracic Radiology Abstracts from the 2024 Annual Meeting February 24th-28th, 2024.

Detection of Interstitial Lung Disease in Rheumatoid Arthritis by Thoracic Ultrasound: A Diagnostic Test Accuracy Study.

To determine the diagnostic accuracy of thoracic ultrasound (TUS) for detecting interstitial lung disease (ILD) in rheumatoid arthritis (RA) with respiratory symptoms. Individuals with RA visiting rheumatologic outpatient clinics in the Region of Southern Denmark were systematically screened for dyspnea, cough, recurrent pneumonia, prior severe pneumonia, or a chest x-ray indicating interstitial abnormalities. Eighty participants with a positive screening were consecutively included. Individuals were not eligible if they had a chest high-resolution computed tomography (HRCT) less than 12 months ago or were already diagnosed with ILD. A blinded TUS expert evaluated TUS, and TUS was registered as positive for ILD if at least 10 B-lines or bilateral thickened and fragmented pleura were present. The primary outcomes were TUS's sensitivity, specificity, and positive predictive value and negative predictive value. An ILD-specialized thoracic radiologist assessed HRCT, followed by a multidisciplinary team discussion, which was the reference standard. The accepted window of HRCT was less than 30 days after TUS was performed. A total of 77 participants received HRCT less than 30 days after TUS, and 23 (30%) were diagnosed with ILD. TUS had a sensitivity of 82.6% (95% confidence interval [CI] 61.2%-95.0%) and a specificity of 51.9% (95% CI 37.8%-65.7%), corresponding to a positive predictive value of 42.2% (95% CI 27.7%-57.8%) and a negative predictive value of 87.5% (95% CI 71.0%-96.5%). To our knowledge, this prospective study is the first to use respiratory symptoms in RA as inclusion criteria. Systematic screening for respiratory symptoms combined with TUS can reduce the diagnostic delay of ILD in RA.

Integrated cardio-thoracic imaging curriculum for residents: Design, implementation, and analysis of test and evaluation results

As the field of cardiac imaging has demonstrated exceptional growth over the past several decades, radiology departments and residency programs have struggled to integrate cardiac imaging instruction into training curricula. PurposeTo create an integrated cardio-thoracic teaching and lecture curriculum and resident rotation in accordance with AGGME and Society of Thoracic Radiology (STR) guidelines. Materials and methodsConsecutive PGY-2 to PGY-4 residents (n = 14) rotating through our Cardiothoracic Imaging (CTI) section from 1/1/2021 to 04/18/2022 were give pre- and post- rotation tests of knowledge and feedback evaluations. Attending feedback of the curriculum was obtained at 3-months and 9-months post curriculum implementation. A Wilcxon test was used to evaluate differences in improvement between pre- and post- rotation resident feedback scores, test scores for thoracic and cardiac test questions in addition to attending feedback scores at 3 and 9-months post curriculum implementation. ResultsThe overall post-rotation scores in addition to thoracic only and cardiac only scores improved, with the difference between improved versus stable or decreased scores being statistically significant overall (P = 0.039) and for cardiac scores (P = 0.003), but not for thoracic scores (P = 0.22). The overall (P = 0.002), thoracic (P = 0.027), and cardiac (P = 0.026) resident feedback scores were significantly improved post-rotation. Similarly, the overall attending feedback scores significantly improved over time (P = 0.021). ConclusionAn integrated Cardio-thoracic Imaging teaching curriculum was well received by both residents and attendings with significant improvement in post rotation feedback scores by both groups. Moreover, residents demonstrated improved scores on knowledge tests post rotation.

Forced vital capacity trajectories and risk of lung transplant and ILD-related mortality among patients with rheumatoid arthritis-associated interstitial lung disease.

We aimed to determine the prevalence and outcomes for forced vital capacity percent predicted (FVCpp) decline among patients with rheumatoid arthritis-associated interstitial lung disease (RA-ILD). We identified patients with RA-ILD in the Mass General Brigham Healthcare system. RA-ILD diagnosis was determined by review of high-resolution computed tomography (HRCT) imaging by up to three thoracic radiologists. We abstracted FVCpp measurements, covariates, lung transplant, and ILD-related death from the medical record. We employed a relative FVCpp decline cutoff of > 10% within 24months. We also used a group-based trajectory model to obtain patterns of change from RA-ILD diagnosis. We then assessed for associations of each FVC decline definition with risk of lung transplant or ILD-related death using multivariable logistic regression. We analyzed 172 patients with RA-ILD with a median of 6 FVCpp measurements per patient over 6.5years of follow-up (mean age 62.2years, 36% male). There were seven (4%) lung transplants and 44 (26%) ILD-related deaths. Ninety-eight (57%) patients had relative decline of FVCpp by > 10% in 24months. We identified three trajectory groups of FVCpp change: rapidly declining (n = 24/168 [14%]), slowly declining (n = 90/168 [54%]), and stable/improving (n = 54/168 [32%]). The rapidly declining group and FVCpp > 10% had adjusted odds ratios (aOR) for lung transplant/ILD-related death of 19.2 (95%CI 4.9 to 75.5) and 2.8 (95%CI 1.3 to 6.1) respectively. Over half of patients with RA-ILD had declining FVCpp. The different trajectory patterns demonstrate the importance of FVC monitoring for identifying patients at the highest risk of poor outcomes. Key Points • Over half of patients with RA-ILD had declining FVCpp over a median of6.5years of follow-up. • The rapidly declining FVCpp trajectory group had stronger associations with lung transplant and ILD-related death compared to those with FVCpp decline by > 10%. • Clinicians can employ FVC monitoring to proactively treat patients who are at risk of poor outcomes.

Chest x-ray has low sensitivity to detect silicosis in artificial stone benchtop industry workers.

Chest x-ray (CXR) remains a core component of health monitoring guidelines for workers at risk of exposure to crystalline silica. There has however been a lack of evidence regarding the sensitivity of CXR to detect silicosis in artificial stone benchtop industry workers. Paired CXR and high-resolution computed tomography (HRCT) images were acquired from 110 artificial stone benchtop industry workers. Blinded to the clinical diagnosis, each CXR and HRCT was independently read by two thoracic radiologists from a panel of seven, in accordance with International Labour Office (ILO) methodology for CXR and International Classification of HRCT for Occupational and Environmental Respiratory Diseases. Accuracy of screening positive (ILO major category 1, 2 or 3) and negative (ILO major category 0) CXRs were compared with identification of radiological features of silicosis on HRCT. CXR was positive for silicosis in 27/110 (24.5%) workers and HRCT in 40/110 (36.4%). Of the 83 with a negative CXR (ILO category 0), 15 (18.1%) had silicosis on HRCT. All 11 workers with ILO category 2 or 3 CXRs had silicosis on HRCT. In 99 workers ILO category 0 or 1 CXRs, the sensitivity of screening positive CXR compared to silicosis identified by HRCT was 48% (95%CI 29-68) and specificity 97% (90-100). Compared to HRCT, sensitivity of CXR was low but specificity was high. Reliance on CXR for health monitoring would provide false reassurance for many workers, delay management and underestimate the prevalence of silicosis in the artificial stone benchtop industry.

Optimizing Diagnostic Performance of ChatGPT: The Impact of Prompt Engineering on Thoracic Radiology Cases

Optimizing Diagnostic Performance of ChatGPT: The Impact of Prompt Engineering on Thoracic Radiology Cases

Assistive AI in Lung Cancer Screening: A Retrospective Multinational Study in the United States and Japan.

Purpose To evaluate the impact of an artificial intelligence (AI) assistant for lung cancer screening on multinational clinical workflows. Materials and Methods An AI assistant for lung cancer screening was evaluated on two retrospective randomized multireader multicase studies where 627 (141 cancer-positive cases) low-dose chest CT cases were each read twice (with and without AI assistance) by experienced thoracic radiologists (six U.S.-based or six Japan-based radiologists), resulting in a total of 7524 interpretations. Positive cases were defined as those within 2 years before a pathology-confirmed lung cancer diagnosis. Negative cases were defined as those without any subsequent cancer diagnosis for at least 2 years and were enriched for a spectrum of diverse nodules. The studies measured the readers' level of suspicion (on a 0-100 scale), country-specific screening system scoring categories, and management recommendations. Evaluation metrics included the area under the receiver operating characteristic curve (AUC) for level of suspicion and sensitivity and specificity of recall recommendations. Results With AI assistance, the radiologists' AUC increased by 0.023 (0.70 to 0.72; P = .02) for the U.S. study and by 0.023 (0.93 to 0.96; P = .18) for the Japan study. Scoring system specificity for actionable findings increased 5.5% (57% to 63%; P < .001) for the U.S. study and 6.7% (23% to 30%; P < .001) for the Japan study. There was no evidence of a difference in corresponding sensitivity between unassisted and AI-assisted reads for the U.S. (67.3% to 67.5%; P = .88) and Japan (98% to 100%; P > .99) studies. Corresponding stand-alone AI AUC system performance was 0.75 (95% CI: 0.70, 0.81) and 0.88 (95% CI: 0.78, 0.97) for the U.S.- and Japan-based datasets, respectively. Conclusion The concurrent AI interface improved lung cancer screening specificity in both U.S.- and Japan-based reader studies, meriting further study in additional international screening environments. Keywords: Assistive Artificial Intelligence, Lung Cancer Screening, CT Supplemental material is available for this article. Published under a CC BY 4.0 license.

Patrones radiológicos en enfermedades pulmonares intersticiales

This article explores the role of high-resolution computed tomography (HRCT) in the diagnosis of diffuse interstitial lung diseases (ILD), discussing key tomographic findings, parenchymal changes, and the importance of identifying various radiological patterns, with a special focus on the usual interstitial pneumonia (UIP) pattern. Given the complexity and diversity of manifestations of diffuse ILD, the collaborative evaluation of a multidisciplinary team, in which the radiologist plays a fundamental role in the diagnostic chain using HRCT, is essential. This exam enables the detection of parenchymal alterations in DILD, such as ground-glass opacities, consolidation, reticular patterns, traction bronchiectasis/bronchiectasis, and honeycombing. The interpretation and association of these findings, along with their distribution, facilitate the establishment of specific radiological patterns that, in addition to indicating possible etiologies, guide the most appropriate therapeutic options. The adoption of specific imaging protocols and the use of standardized language are essential to increase diagnostic accuracy. Moreover, the incorporation of technological innovations, such as advanced photon counting technology and automated analysis through artificial intelligence, promise to significantly improve the identification and quantification of interstitial alterations, shaping the future of thoracic radiology.

Language model-based labeling of German thoracic radiology reports.

The aim of this study was to explore the potential of weak supervision in a deep learning-based label prediction model. The goal was to use this model to extract labels from German free-text thoracic radiology reports on chest X-ray images and for training chest X-ray classification models.The proposed label extraction model for German thoracic radiology reports uses a German BERT encoder as a backbone and classifies a report based on the CheXpert labels. For investigating the efficient use of manually annotated data, the model was trained using manual annotations, weak rule-based labels, and both. Rule-based labels were extracted from 66071 retrospectively collected radiology reports from 2017-2021 (DS 0), and 1091 reports from 2020-2021 (DS 1) were manually labeled according to the CheXpert classes. Label extraction performance was evaluated with respect to mention extraction, negation detection, and uncertainty detection by measuring F1 scores. The influence of the label extraction method on chest X-ray classification was evaluated on a pneumothorax data set (DS 2) containing 6434 chest radiographs with associated reports and expert diagnoses of pneumothorax. For this, DenseNet-121 models trained on manual annotations, rule-based and deep learning-based label predictions, and publicly available data were compared.The proposed deep learning-based labeler (DL) performed on average considerably stronger than the rule-based labeler (RB) for all three tasks on DS 1 with F1 scores of 0.938 vs. 0.844 for mention extraction, 0.891 vs. 0.821 for negation detection, and 0.624 vs. 0.518 for uncertainty detection. Pre-training on DS 0 and fine-tuning on DS 1 performed better than only training on either DS 0 or DS 1. Chest X-ray pneumothorax classification results (DS 2) were highest when trained with DL labels with an area under the receiver operating curve (AUC) of 0.939 compared to RB labels with an AUC of 0.858. Training with manual labels performed slightly worse than training with DL labels with an AUC of 0.934. In contrast, training with a public data set resulted in an AUC of 0.720.Our results show that leveraging a rule-based report labeler for weak supervision leads to improved labeling performance. The pneumothorax classification results demonstrate that our proposed deep learning-based labeler can serve as a substitute for manual labeling requiring only 1000 manually annotated reports for training. · The proposed deep learning-based label extraction model for German thoracic radiology reports performs better than the rule-based model.. · Training with limited supervision outperformed training with a small manually labeled data set.. · Using predicted labels for pneumothorax classification from chest radiographs performed equally to using manual annotations.. Wollek A, Haitzer P, Sedlmeyr T et al. Language modelbased labeling of German thoracic radiology reports. Fortschr Röntgenstr 2024; DOI 10.1055/a-2287-5054.

Clinical and experimental parallels in the assessment of microcirculatory dysfunctions of the lungs in thoracic radiology

Introduction. Chronic obstructive disease (COPD) and thromboembolism of the branches of the pulmonary artery or pulmonary embolism (PE) remain the most common and socially significant lung diseases. Circulatory disorders in these pathologies play a critical role in the development of the disease. Radiation techniques, such as computed tomography/angiography and single-photon emission computed tomography (SPECT), are the leading ones in recognizing changes in the lung parenchyma and vessels. Many questions can be successfully solved experimentally. The main radiation techniques used to study the vascular bed when modeling lung diseases in experimental animals are microangiography and perfusion scintigraphy. Purpose. To show the capabilities of radiation diagnostic methods for identifying vascular disorders in COPD and PE in experiments and clinical manifestations. Material and methods. A clinical and experimental comparison of pulmonary circulation changes during COPD and PE was carried out based on the results of perfusion scintigraphy/SPECT in 55 rats with simulated COPD- like condition and 622 patients with COPD of varying severity, as well as 58 rats with simulated PE and 180 patients with PE. Results. When modelling lung diseases (PE and COPD), the results similar to blood circulation and structural changes in the lung parenchyma in patients with these nosologies were obtained. In COPD, changes in the lung parenchyma correlated with disturbances in functional indicators (microcirculation, PaO2, PaCO2, DSLzd, DLco/VA, SDPA) and increased levels of endothelin-1 (r=0.72) and endothelial growth factor (VEGF-A) (r=0.79). Analysis of experimental and clinical data on PE showed the importance of identifying minor forms of thromboembolism. Conclusion. 1. Persistent microcirculatory dysfunctions in the pulmonary circulation play an important role in the pathogenesis of chronic broncho-obstructive pathology. After just 7 days, initial signs of emphysema can be detected in the ischemic area of the lung tissue, and by the 60th day typical bullous cavities can be detected. 2. In the chronic course of minor forms of thromboembolism of small branches of the pulmonary artery, local emphysema is formed. 3. At the early stages of COPD formation, regional zones of emphysematous restructuring of the lung tissue with a predominance of ventilation dysfunctions and zones of «compressive ischemia» with prevailing vascular disorders are formed. As the pathological process progresses, the ischemia factor acquires independent significance in the pathogenesis of the disease.

Usar una herramienta comercial de inteligencia artificial no entrenada para COVID-19 mejora ligeramente la interpretación de las radiografías con neumonía COVID-19, especialmente entre lectores inexpertos

IntroductionOur objective is to evaluate how useful an artificial intelligence (AI) tool is to chest radiograph readers with various levels of expertise for the diagnosis of COVID-19 pneumonia when the tool has been trained on a non-COVID-19 pneumonia pathology. MethodsData was collected for patients who had previously undergone a chest radiograph and digital tomosynthesis due to suspected COVID-19 pneumonia. The gold standard consisted of the readings of two expert radiologists who assessed the presence and distribution of COVID-19 pneumonia on the images. Six medical students, two radiology trainees, and two other expert thoracic radiologists participated as additional readers. Two radiograph readings and a third supported by the AI Thoracic Care Suite tool were performed. COVID-19 pneumonia distribution and probability were assessed along with the contribution made by AI. Agreement and diagnostic performance were analysed. ResultsThe sample consisted of 113 cases, of which 56 displayed lung opacities, 52.2% were female, and the mean age was 50.70±14.9. Agreement with the gold standard differed between students, trainees, and radiologists. There was a non-significant improvement for four of the six students when AI was used. The use of AI by students did not improve the COVID-19 pneumonia diagnostic performance but it did reduce the difference in diagnostic performance with the more expert radiologists. Furthermore, it had more influence on the interpretation of mild pneumonia than severe pneumonia and normal radiograph findings. AI resolved more doubts than it generated, especially among students (31.30 vs 8.32%), followed by trainees (14.45 vs 5.7%) and radiologists (10.05% vs 6.15%). ConclusionFor expert and lesser experienced radiologists, this commercial AI tool has shown no impact on chest radiograph readings of patients with suspected COVID-19 pneumonia. However, it aided the assessment of inexperienced readers and in cases of mild pneumonia.

Deep learning segmentation and registration-driven lung parenchymal volume and movement CT analysis in prone positioning.

To conduct a volumetric and movement analysis of lung parenchyma in prone positioning using deep neural networks (DNNs). We included patients with suspected interstitial lung abnormalities or disease who underwent full-inspiratory supine and prone chest CT at a single institution between June 2021 and March 2022. A thoracic radiologist visually assessed the fibrosis extent in the total lung (using units of 10%) on supine CT. After preprocessing the images into 192×192×192 resolution, a DNN automatically segmented the whole lung and pulmonary lobes in prone and supine CT images. Affine registration matched the patient's center and location, and the DNN deformably registered prone and supine CT images to calculate the x-, y-, z-axis, and 3D pixel movements. In total, 108 CT pairs had successful registration. Prone positioning significantly increased the left lower (90.2±69.5 mL, P = 0.000) and right lower lobar volumes (52.5±74.2 mL, P = 0.000). During deformable registration, the average maximum whole-lung pixel movements between the two positions were 1.5, 1.9, 1.6, and 2.8 cm in each axis and 3D plane. Compared to patients with <30% fibrosis, those with ≥30% fibrosis had smaller volume changes (P<0.001) and smaller pixel movements in all axes between the positions (P = 0.000-0.007). Forced vital capacity (FVC) correlated with the left lower lobar volume increase (Spearman correlation coefficient, 0.238) and the maximum whole-lung pixel movements in all axes (coefficients, 0.311 to 0.357). Prone positioning led to the preferential expansion of the lower lobes, correlated with FVC, and lung fibrosis limited lung expansion during prone positioning.

Evaluation of retrieval accuracy and visual similarity in content-based image retrieval of chest CT for obstructive lung disease

The aim of our study was to assess the performance of content-based image retrieval (CBIR) for similar chest computed tomography (CT) in obstructive lung disease. This retrospective study included patients with obstructive lung disease who underwent volumetric chest CT scans. The CBIR database included 600 chest CT scans from 541 patients. To assess the system performance, follow-up chest CT scans of 50 patients were evaluated as query cases, which showed the stability of the CT findings between baseline and follow-up chest CT, as confirmed by thoracic radiologists. The CBIR system retrieved the top five similar CT scans for each query case from the database by quantifying and comparing emphysema extent and size, airway wall thickness, and peripheral pulmonary vasculatures in descending order from the database. The rates of retrieval of the same pairs of query CT scans in the top 1–5 retrievals were assessed. Two expert chest radiologists evaluated the visual similarities between the query and retrieved CT scans using a five-point scale grading system. The rates of retrieving the same pairs of query CTs were 60.0% (30/50) and 68.0% (34/50) for top-three and top-five retrievals. Radiologists rated 64.8% (95% confidence interval 58.8–70.4) of the retrieved CT scans with a visual similarity score of four or five and at least one case scored five points in 74% (74/100) of all query cases. The proposed CBIR system for obstructive lung disease integrating quantitative CT measures demonstrated potential for retrieving chest CT scans with similar imaging phenotypes. Further refinement and validation in this field would be valuable.

Radiological usual interstitial pneumonia pattern is associated with two-year mortality in patients with idiopathic pulmonary fibrosis

IntroductionThe new diagnostic guidelines for idiopathic pulmonary fibrosis (IPF) did not rule out the possibility of combining the radiological patterns of usual interstitial pneumonia (UIP) and probable UIP, given the similar management and diagnostic capacity. However, the prognostic implications of these patterns have not been fully elucidated, with different studies showing heterogeneous results. We applied the new criteria to a retrospective series of patients with IPF, assessing survival based on radiological patterns, findings, and their extension. MethodsTwo thoracic radiologists reviewed high-resolution computed tomography images taken at diagnosis in 146 patients with IPF, describing the radiological findings and patterns. The association of each radiological finding and radiological patterns with two-year mortality was analysed. ResultsThe two-year mortality rate was 40.2% in IPF patients with an UIP radiological pattern versus 7.1% in those with probable UIP. Compared to the UIP pattern, probable UIP was protective against mortality, even after adjusting for age, sex, pulmonary function, and extent of fibrosis (hazard ratio (HR) 0.23, 95% confidence interval (CI) 0.06–0.99). Receiving antifibrotic treatment was also a protective factor (HR 0.51, 95%CI 0.27–0.98). Honeycombing (HR 3.62, 95%CI 1.27–10.32), an acute exacerbation pattern (HR 4.07, 95%CI 1.84–8.96), and the overall extent of fibrosis (HR 1.04, 95%CI 1.02–1.06) were predictors of mortality. ConclusionsIn our series, two-year mortality was higher in patients with IPF who presented a radiological pattern of UIP versus probable UIP on the initial scan. Honeycombing, an acute exacerbation pattern, and a greater overall extent of fibrosis were also predictors of increased mortality. The prognostic differences between the radiological pattern of UIP and probable UIP in our series would support maintaining them as two differentiated patterns.