High-density pulmonary lesions: Review in chest imaging.

High-density pulmonary lesions are frequently seen in chest imaging, and it is important to identify their different causes. Radiologists must be able to distinguish between common and rare conditions in order to provide the best diagnosis and treatment. This article provides an overview of the various causes and imaging features of high-density lesions in the lungs. The lesions are classified into various categories, such as pulmonary nodules, inflammatory conditions, deposition diseases, contrast-related lesions, and thoracic devices. A clear understanding of these categories can help radiologists accurately diagnose and manage high-density pulmonary lesions encountered in practice.

Swyer-James Syndrome: A Rare Radiological Report of Two Cases Presenting in Adulthood.

Swyer-James syndrome (SJS), also termed MacLeod syndrome, is an acquired secondary unilateral hyperlucency of the lung due to childhood lung infections. This disorder can be diagnosed in children; however if there are few or no symptoms, diagnosis can be missed and can then be detected later in adult life as an incidental finding. We present here the case reports of two patients, where one of them had a unique presentation of unilateral hyperlucency on a chest radiograph and a bilateral mosaic pattern on CT lung but with no history of childhood infections and another case with unilateral hyperlucency of the lung with the history of childhood infection were diagnosed as SJS. This article is important as it highlights the significant radiological finding in accurately diagnosing this condition, when the presenting complaint and past history are inconclusive, thereby guiding proper management.

Prior tuberculosis, radiographic lung abnormalities and prevalent diabetes in rural South Africa.

BACKGROUND: Growing evidence suggests that chronic inflammation caused by tuberculosis (TB) may increase the incidence of diabetes. However, the relationship between post-TB pulmonary abnormalities and diabetes has not been well characterized. METHODS: We analyzed data from a cross-sectional study in KwaZulu-Natal, South Africa, of people 15 years and older who underwent chest X-ray and diabetes screening with hemoglobin A1c testing. The analytic sample was restricted to persons with prior TB, defined by either (1) a self-reported history of TB treatment, (2) radiologist-confirmed prior TB on chest radiography, and (3) a negative sputum culture and GeneXpert. Chest X-rays of all participants were evaluated by the study radiologist to determine the presence of TB lung abnormalities. To assess the relationships between our outcome of interest, prevalent diabetes (HBA1c ≥6.5%), and our exposure of interest, chest X-ray abnormalities, we fitted logistic regression models adjusted for potential clinical and demographic confounders. In secondary analyses, we used the computer-aided detection system CAD4TB, which scores X-rays from 10 to 100 for detection of TB disease, as our exposure interest, and repeated analyses with a comparator group that had no history of TB disease. RESULTS: In the analytic cohort of people with prior TB (n = 3,276), approximately two-thirds (64.9%) were women, and the average age was 50.8 years (SD 17.4). The prevalence of diabetes was 10.9%, and 53.0% of people were living with HIV. In univariate analyses, there was no association between diabetes prevalence and radiologist chest X-ray abnormalities (OR 1.23, 95%CI 0.95-1.58). In multivariate analyses, the presence of pulmonary abnormalities was associated with an 29% reduction in the odds of prevalent diabetes (aOR 0.71, 95%CI 0.53-0.97, p = 0.030). A similar inverse relationship was observed for diabetes with each 10-unit increase in the CAD4TB chest X-ray scores among people with prior TB (aOR 0.92, 95%CI 0.87-0.97; p = 0.002), but this relationship was less pronounced in the no TB comparator group (aOR 0.96, 95%CI 0.94-0.99). CONCLUSIONS: Among people with prior TB, pulmonary abnormalities on digital chest X-ray are inversely associated with prevalent diabetes. The severity of radiographic post-TB lung disease does not appear to be a determinant of diabetes in this South African population.

Omicron variant and pulmonary involvements: a chest imaging analysis in asymptomatic and mild COVID-19.

Objectives: To identify clinical characteristics and risk factors for pulmonary involvements in asymptomatic and mildly symptomatic patients infected with SARS-CoV-2 Omicron variant by chest imaging analysis. Methods: Detailed data and chest computed tomography (CT) imaging features were retrospectively analyzed from asymptomatic and mildly symptomatic patients infected with Omicron between 24 April and 10 May 2022. We scored chest CT imaging features and categorized the patients into obvious pulmonary involvements (OPI) (score > 2) and not obvious pulmonary involvements (NOPI) (score ≤ 2) groups based on the median score. The risk factors for OPI were identified with analysis results visualized by nomogram. Results: In total, 339 patients were included (145 were male and 194 were female), and the most frequent clinical symptoms were cough (75.5%); chest CT imaging features were mostly linear opacities (42.8%). Pulmonary involvements were more likely to be found in the left lower lung lobe, with a significant difference in the lung total severity score of the individual lung lobes (p < 0.001). Logistic regression analysis revealed age stratification [odds ratio (OR) = 1.92, 95% confidence interval (CI) (1.548-2.383); p < 0.001], prolonged nucleic acid negative conversion time (NCT) (NCT > 8d) [OR = 1.842, 95% CI (1.104-3.073); p = 0.019], and pulmonary diseases [OR = 4.698, 95% CI (1.159-19.048); p = 0.03] as independent OPI risk factors. Conclusion: Asymptomatic and mildly symptomatic patients infected with Omicron had pulmonary involvements which were not uncommon. Potential risk factors for age stratification, prolonged NCT, and pulmonary diseases can help clinicians to identify OPI in asymptomatic and mildly symptomatic patients infected with Omicron.

Understanding contextual and practical factors to inform WHO recommendations on using chest imaging to monitor COVID-19 pulmonary sequelae: a qualitative study exploring stakeholders' perspective.

BACKGROUND: A recommendation by the World Health Organization (WHO) was issued about the use of chest imaging to monitor pulmonary sequelae following recovery from COVID-19. This qualitative study aimed to explore the perspective of key stakeholders to understand their valuation of the outcome of the proposition, preferences for the modalities of chest imaging, acceptability, feasibility, impact on equity and practical considerations influencing the implementation of using chest imaging. METHODS: A qualitative descriptive design using in-depth interviews approach. Key stakeholders included adult patients who recovered from the acute illness of COVID-19, and providers caring for those patients. The Evidence to Decision (EtD) conceptual framework was used to guide data collection of contextual and practical factors related to monitoring using imaging. Data analysis was based on the framework thematic analysis approach. RESULTS: 33 respondents, including providers and patients, were recruited from 15 different countries. Participants highly valued the ability to monitor progression and resolution of long-term sequelae but recommended the avoidance of overuse of imaging. Their preferences for the imaging modalities were recorded along with pros and cons. Equity concerns were reported across countries (e.g., access to resources) and within countries (e.g., disadvantaged groups lacked access to insurance). Both providers and patients accepted the use of imaging, some patients were concerned about affordability of the test. Facilitators included post- recovery units and protocols. Barriers to feasibility included low number of specialists in some countries, access to imaging tests among elderly living in nursing homes, experience of poor coordination of care, emotional exhaustion, and transportation challenges driving to a monitoring site. CONCLUSION: We were able to demonstrate that there is a high value and acceptability using imaging but there were factors influencing feasibility, equity and some practical considerations associated with implementation. We had a few suggestions to be considered by the expert panel in the formulation of the guideline to facilitate its implementation such as using validated risk score predictive tools for lung complications to recommend the appropriate imaging modality and complementary pulmonary function test.

Impact of nondiameter aortic indices on surgical eligibility: Results from the Treatment in Thoracic Aortic Aneurysm: Surgery Versus Surveillance (TITAN: SvS) randomized controlled trial.

OBJECTIVES: Traditional criterion for intervention on an asymptomatic ascending aortic aneurysm has been a maximal aortic diameter of 5.5 cm or more. The 2022 American College of Cardiology/American Heart Association aortic guidelines adopted cross-sectional aortic area/height ratio, aortic size index, and aortic height index as alternate parameters for surgical intervention. The objective of this study was to evaluate the impact of using these newer indices on patient eligibility for surgical intervention in a prospective, multicenter cohort with moderate-sized ascending aortic aneurysms between 5.0 and 5.4 cm. METHODS: Patients enrolled from 2018 to 2023 in the randomization or registry arms of the multicenter trial, Treatment In Thoracic Aortic aNeurysm: Surgery versus Surveillance, were included in the study. Clinical data were captured prospectively in an online database. Imaging data were derived from a core computed laboratory. RESULTS: Among the 329 included patients, 20% were female. Mean age was 65.0 ± 11.6 years, and mean maximal aortic diameter was 50.8 ± 3.9 mm. In the one-third of all patients (n = 109) who met any 1 of the 3 criteria (ie, aortic size index ≥3.08 cm/m2, aortic height index ≥3.21 cm/m, or cross-sectional aortic area/height ≥ 10 cm2/m), their mean maximal aortic diameter was 52.5 ± 0.52 mm. Alternate criteria were most commonly met in women compared with men: 20% versus 2% for aortic size index (P < .001), 39% versus 5% for aortic height index (P < .001), and 39% versus 21% for cross-sectional aortic area/height (P = .002), respectively. CONCLUSIONS: One-third of patients in Treatment In Thoracic Aortic aNeurysm: Surgery versus Surveillance would meet criteria for surgical intervention based on novel parameters versus the classic definition of diameter 5.5 cm or more. Surgical thresholds for aortic size index, aortic height index, or cross-sectional aortic area/height ratio are more likely to be met in female patients compared with male patients.

Doctor's Orders-Why Radiologists Should Consider Adjusting Commercial Machine Learning Applications in Chest Radiography to Fit Their Specific Needs.

This retrospective study evaluated a commercial deep learning (DL) software for chest radiographs and explored its performance in different scenarios. A total of 477 patients (284 male, 193 female, mean age 61.4 (44.7-78.1) years) were included. For the reference standard, two radiologists performed independent readings on seven diseases, thus reporting 226 findings in 167 patients. An autonomous DL reading was performed separately and evaluated against the gold standard regarding accuracy, sensitivity and specificity using ROC analysis. The overall average AUC was 0.84 (95%-CI 0.76-0.92) with an optimized DL sensitivity of 85% and specificity of 75.4%. The best results were seen in pleural effusion with an AUC of 0.92 (0.885-0.955) and sensitivity and specificity of each 86.4%. The data also showed a significant influence of sex, age, and comorbidity on the level of agreement between gold standard and DL reading. About 40% of cases could be ruled out correctly when screening for only one specific disease with a sensitivity above 95% in the exploratory analysis. For the combined reading of all abnormalities at once, only marginal workload reduction could be achieved due to insufficient specificity. DL applications like this one bear the prospect of autonomous comprehensive reporting on chest radiographs but for now require human supervision. Radiologists need to consider possible bias in certain patient groups, e.g., elderly and women. By adjusting their threshold values, commercial DL applications could already be deployed for a variety of tasks, e.g., ruling out certain conditions in screening scenarios and offering high potential for workload reduction.

A Case report: Synovial sarcoma of the mediastinum in an 18-year-old teenager.

Synovial sarcomas (SSs) are a rare group of malignant tumors originating from pluripotential mesenchymal cells, which commonly occur as the primary tumor in the soft tissues near the articular surface, tendons, and articular synovium. Herein, we report a rare case of mediastinal SS in an 18-year-old teenager who initially presented with cough as the primary symptom. In this case, plain chest CT and contrast-enhanced CT clearly revealed the lesion presenting as a round-like and uneven density mass in the mediastinum with heterogeneous enhancement, which compressed the trachea and invaded the adjacent vessels. Based on the results of immunohistochemistry and fluorescence in situ hybridization (FISH), combined with the differential diagnosis with other types of tumors in the mediastinum on imaging, we were able to diagnose the tumor as an SS located in the mediastinum. Subsequent resection of the lesion coupled with chemotherapy and immunotherapy led to an improvement in the patient's symptoms.

Crossed raised arm position improves the flow of contrast medium in torso contrast-enhanced computed Tomography.

INTRODUCTION: This retrospective cohort study examined the effects of the crossed raised arm (CRA) position in contrast-enhanced computed tomography (CECT) on contrast medium influx and image quality relative to the conventional position. METHODS: Contrast medium influx into the collateral veins on CECT images was evaluated in 92 participants. The CT values of the pulmonary artery, descending aorta, and spleen were obtained in both positions and compared. Anatomical changes in the diameters and area of the subclavian vein and costoclavicular distance were also analyzed. RESULTS: Contras 27 and 6 patients in the conventional and CRA positions, respectively. The influx risk ratio in the CRA position versus that in the conventional position was 0.22 (95% confidence interval, 0.10-0.51). Elevations in the median CT value of the pulmonary artery, descending aorta, and spleen in the CRA position were 7.0% (p < .001), 7.4% (p < .001), and 9.8% (p < .001), respectively. Enlargements in the major and minor diameters of the subclavian vein, subclavian vein area, and costoclavicular distance in the CRA position versus those in the conventional position were 19.3% (p < .001), 28.1% (p < .001), 53.6%, and 30.0% (p < .001), respectively. CONCLUSION: The CRA position effectively prevented contrast medium influx into the collateral veins due to SVS and increased CT values in the target organs in CECT. The diameters and area of the subclavian vein and costoclavicular distance were enlarged at the thoracic outlet, which improved the flow of the contrast medium into the targeted organs. IMPLICATIONS FOR PRACTICE: The CRA position can contribute to obtaining better CECT images during common clinical assessments at no additional cost.

Cryptococcosis with pulmonary cavitation in an immunocompetent child: a case report and literature review.

BACKGROUND: Pulmonary cryptococcosis (PC) rarely occurs in immunocompetent children. CASE PRESENTATION: A 13-year-old boy was admitted to the First Affiliated Hospital of Ningbo University in February 2023 with complaints of cough and chest pain. Physical examination showed slightly moist rales in the right lung. Chest computed tomography (CT) suggested a lung lesion and cavitation. Blood routine test, lymphocyte subsets, immunoglobulin, and complement tests indicated that the immune system was normal. However, the serum cryptococcal antigen test was positive. Next-generation sequencing revealed Cryptococcus infection. The child was diagnosed with PC and was discharged after treating with fluconazole 400 mg. Four months later, chest CT showed that the lung lesion diminished, and reexamination of serum cryptococcal antigen test turned positive. CONCLUSION: PC should be considered in an immunocompetent child with pulmonary cavities with nonspecific symptoms.

Pilot study of paediatric regional lung function assessment via X-ray velocimetry (XV) imaging in children with normal lungs and in children with cystic fibrosis.

INTRODUCTION: Cystic fibrosis (CF) is a life-limiting autosomal recessive genetic condition. It is caused by mutations in the gene that encodes for a chloride and bicarbonate conducting transmembrane channel. X-ray velocimetry (XV) is a novel form of X-ray imaging that can generate lung ventilation data through the breathing cycle. XV technology has been validated in multiple animal models, including the ß-ENaC mouse model of CF lung disease. It has since been assessed in early-phase clinical trials in adult human subjects; however, there is a paucity of data in the paediatric cohort, including in CF. The aim of this pilot study was to investigate the feasibility of performing a single-centre cohort study in paediatric patients with CF and in those with normal lungs to demonstrate the appropriateness of proceeding with further studies of XV in these cohorts. METHODS AND ANALYSIS: This is a cross-sectional, single-centre, pilot study. It will recruit children aged 3-18 years to have XV lung imaging performed, as well as paired pulmonary function testing. The study will aim to recruit 20 children without CF with normal lungs and 20 children with CF. The primary outcome will be the feasibility of recruiting children and performing XV testing. Secondary outcomes will include comparisons between XV and current assessments of pulmonary function and structure. ETHICS AND DISSEMINATION: This project has ethical approval granted by The Women's and Children's Hospital Human Research Ethics Committee (HREC ID 2021/HRE00396). Findings will be disseminated through peer-reviewed publication and conferences. TRIAL REGISTRATION NUMBER: ACTRN12623000109606.

Noninfectious Granulomatous Lung Disease: Radiological Findings and Differential Diagnosis.

Granulomatous lung diseases (GLDs) are a heterogeneous group of pathological entities that can have different clinical presentations and outcomes. Granulomas are histologically defined as focal aggregations of activated macrophages, Langerhans cells, and lymphocytes, and may form in the lungs when the immune system cannot eliminate a foreign antigen and attempts to barricade it. The diagnosis includes clinical evaluation, laboratory testing, and radiological imaging, which especially consists of high-resolution computed tomography. bronchoalveolar lavage, transbronchial needle aspiration or cryobiopsy, positron emission tomography, while genetic evaluation can improve the diagnostic accuracy. Differential diagnosis is challenging due to the numerous different imaging appearances with which GLDs may manifest. Indeed, GLDs include both infectious and noninfectious, and necrotizing and non-necrotizing granulomatous diseases and the imaging appearance of some GLDs may mimic malignancy, leading to confirmatory biopsy. The purposes of our review are to report the different noninfectious granulomatous entities and to show their various imaging features to help radiologists recognize them properly and make an accurate differential diagnosis.

Reversibility of the Enlargement of the Pulmonary Artery in COVID-19 Pneumonia as a Marker of Remission of the Disease.

Coronavirus disease 2019 (COVID-19) pneumonia is associated with extensive pulmonary microangiopathy and the enlargement of the pulmonary artery (PA), while its progression after the remission of the disease has not been investigated yet. The aim was to assess the diametral increase in the PA in COVID-19 pneumonia, as revealed on chest computed tomography (CT), and further investigate its progression. This was a retrospective cohort study of patients with COVID-19 pneumonia, without prior history of pulmonary hypertension, who underwent CT pulmonary angiography before, during, and after the infection. Pulmonary embolism was excluded in all cases. The main PA diameter (MPAD) was assessed in consecutive chest imaging. Statistical analysis was performed with the non-parametric Wilcoxon and Kruskal-Wallis tests, while correlations were performed with the non-parametric Spearman test. A mean ± SD MPAD of 3.1 ± 0.3 cm in COVID-19 pneumonia was significantly decreased to 2.8 ± 0.3 cm in the post-infectious state after 2-18 months in 31 patients (p-value: <0.0001). In a subgroup of six patients with more than one post-COVID-19 CT, a significant further decline in the diameter was observed (p-value: 0.0313). On the other hand, in accordance with the literature, a significant increase in the MPAD during COVID-19 pneumonia was noted in a group of 10 patients with a pre-COVID-19 CT (p-value: 0.0371). The enlargement of the PA is a common finding in COVID-19 pneumonia that regresses after the remission of the disease, indicating that this reversible cardiovascular event is a potential marker of disease activity, while its course in long COVID is yet to be determined.

Determining the impact of an artificial intelligence tool on the management of pulmonary nodules detected incidentally on CT (DOLCE) study protocol: a prospective, non-interventional multicentre UK study.

INTRODUCTION: In a small percentage of patients, pulmonary nodules found on CT scans are early lung cancers. Lung cancer detected at an early stage has a much better prognosis. The British Thoracic Society guideline on managing pulmonary nodules recommends using multivariable malignancy risk prediction models to assist in management. While these guidelines seem to be effective in clinical practice, recent data suggest that artificial intelligence (AI)-based malignant-nodule prediction solutions might outperform existing models. METHODS AND ANALYSIS: This study is a prospective, observational multicentre study to assess the clinical utility of an AI-assisted CT-based lung cancer prediction tool (LCP) for managing incidental solid and part solid pulmonary nodule patients vs standard care. Two thousand patients will be recruited from 12 different UK hospitals. The primary outcome is the difference between standard care and LCP-guided care in terms of the rate of benign nodules and patients with cancer discharged straight after the assessment of the baseline CT scan. Secondary outcomes investigate adherence to clinical guidelines, other measures of changes to clinical management, patient outcomes and cost-effectiveness. ETHICS AND DISSEMINATION: This study has been reviewed and given a favourable opinion by the South Central-Oxford C Research Ethics Committee in UK (REC reference number: 22/SC/0142).Study results will be available publicly following peer-reviewed publication in open-access journals. A patient and public involvement group workshop is planned before the study results are available to discuss best methods to disseminate the results. Study results will also be fed back to participating organisations to inform training and procurement activities. TRIAL REGISTRATION NUMBER: NCT05389774.

Detection of fibrosing interstitial lung disease-suspected chest radiographs using a deep learning-based computer-aided detection system: a retrospective, observational study.

OBJECTIVES: To investigate the effectiveness of BMAX, a deep learning-based computer-aided detection system for detecting fibrosing interstitial lung disease (ILD) on chest radiographs among non-expert and expert physicians in the real-world clinical setting. DESIGN: Retrospective, observational study. SETTING: This study used chest radiograph images consecutively taken in three medical facilities with various degrees of referral. Three expert ILD physicians interpreted each image and determined whether it was a fibrosing ILD-suspected image (fibrosing ILD positive) or not (fibrosing ILD negative). Interpreters, including non-experts and experts, classified each of 120 images extracted from the pooled data for the reading test into positive or negative for fibrosing ILD without and with the assistance of BMAX. PARTICIPANTS: Chest radiographs of patients aged 20 years or older with two or more visits that were taken during consecutive periods were accumulated. 1251 chest radiograph images were collected, from which 120 images (24 positive and 96 negative images) were randomly extracted for the reading test. The interpreters for the reading test were 20 non-expert physicians and 5 expert physicians (3 pulmonologists and 2 radiologists). PRIMARY AND SECONDARY OUTCOME MEASURES: The primary outcome was the comparison of area under the receiver-operating characteristic curve (ROC-AUC) for identifying fibrosing ILD-positive images by non-experts without versus with BMAX. The secondary outcome was the comparison of sensitivity, specificity and accuracy by non-experts and experts without versus with BMAX. RESULTS: The mean ROC-AUC of non-expert interpreters was 0.795 (95% CI; 0.765 to 0.825) without BMAX and 0.825 (95% CI; 0.799 to 0.850) with BMAX (p=0.005). After using BMAX, sensitivity was improved from 0.744 (95% CI; 0.697 to 0.791) to 0.802 (95% CI; 0.754 to 0.850) among non-experts (p=0.003), but not among experts (p=0.285). Specificity and accuracy were not changed after using BMAX among either non-expert or expert interpreters. CONCLUSION: BMAX was useful for detecting fibrosing ILD-suspected chest radiographs for non-expert physicians. TRIAL REGISTRATION NUMBER: jRCT1032220090.

Value of Chest X-Ray and Chest Computed Tomography for Systemic Sarcoidosis Diagnosis in Undifferentiated Uveitis.

BACKGROUND: To evaluate the contribution of chest X-ray and chest CT for the diagnosis of sarcoid uveitis. METHODS: Retrospective study on consecutive patients with uveitis of unknown etiology, who underwent both chest X-ray and CT during uveitis diagnosis workup in a tertiary French university hospital. RESULTS: A total of 914 patients were included. Systemic sarcoidosis was identified in 23.1%. The probability of discordance between chest X-ray and CT increased with age at diagnosis (p < 0.001). In patients 30 years of age and younger, the probability of discordance was 5% or less, and 0.8% if the ACE level was normal. After 78.3 years of age, the probability of discordance was 20% or more. CONCLUSION: We recommend not to perform CT in patients under 30 years of age with a normal chest X ray and ACE level, and suggest performing chest CT first in the elderly.

Chest imaging classification in Mycoplasma pneumoniae pneumonia is associated with its clinical features and outcomes.

BACKGROUND: The imaging findings of Mycoplasma pneumoniae pneumonia (MPP) vary; however, few studies have focused on the relationship of imaging classification with clinical manifestations and outcomes. OBJECTIVE: To prospectively investigate whether chest imaging classification in Mycoplasma pneumoniae pneumonia (MPP) is associated with its clinical features and outcomes. METHODS: A total of 1,401 hospitalized children with MPP were enrolled from January 2019 to December 2021. Imaging findings were categorized as bronchopneumonia and consolidation/atelectasis according to X-ray, and bronchopneumonia, consolidation/atelectasis, bronchiolitis, and mosaic pattern according to computed tomography (CT). Clinical characteristics and outcomes of patients with different imaging classifications were prospectively analyzed based on electronic medical records. RESULTS: Bronchopneumonia was the most common finding (59.6%), while consolidation/atelectasis was the most severe group. Clinical manifestations and laboratory indicators for the consolidation/atelectasis group included serious abnormalities. Further, outcomes of the patients were worse, including having longer total durations of fever and hospitalization, greater hospitalization expenses, and a higher likelihood of developing refractory MPP, necrotizing pneumonia, and bronchiolitis obliterans (BO) in this group. The incidence of bronchiolitis, a disease characterized by a high prevalence of fever, moist rales, and an atopic constitution, tended to increase after the coronavirus disease pandemic and predisposed patients to BO. A mosaic pattern occurred in allergic and young individuals, with wheezing as the main manifestation, with patients having relatively mild symptoms and good outcomes. CONCLUSION: Different imaging classifications have different clinical features and clinical outcomes; thus, formulating an imaging-based classification system is of great clinical value.

Scrutinizing the use of contrasted chest CTs in extremity sarcoma staging and surveillance.

BACKGROUND: Since 2015, the American College of Radiology (ACR) has recommended staging for lung metastasis via chest computed tomography (CT) without contrast for extremity sarcoma staging and surveillance. The purpose of this study was to determine our institutional compliance with this recommendation. METHODS: This was a retrospective chart review of patients diagnosed with sarcoma in the extremities who received CT imaging of the chest for pulmonary staging and surveillance at our institution from 2005 to 2023. A total of 1916 CT studies were included for analysis. We scrutinized ordering patterns before and after 2015 based on the ACR-published metastasis staging and screening guidelines. An institutional and patient cost analysis was performed between CT modalities. RESULTS: The prevalence of CT scans ordered and performed with contrast was greater than those without contrast both prior and post-ACR 2015 guidelines. Furthermore, 79.2% of patient's final surveillance CTs after 2015 were performed with contrast. A cost analysis was performed and demonstrated an additional $297 704 in patient and institutional costs. CONCLUSIONS: At our institution, upon review of CT chest imaging for pulmonary staging and surveillance in patients with extremity sarcoma the use of contrast has been routinely utilized despite a lack of evidence for its necessity and contrary to ACR guidelines.

Evaluating the performance of artificial intelligence software for lung nodule detection on chest radiographs in a retrospective real-world UK population.

OBJECTIVES: Early identification of lung cancer on chest radiographs improves patient outcomes. Artificial intelligence (AI) tools may increase diagnostic accuracy and streamline this pathway. This study evaluated the performance of commercially available AI-based software trained to identify cancerous lung nodules on chest radiographs. DESIGN: This retrospective study included primary care chest radiographs acquired in a UK centre. The software evaluated each radiograph independently and outputs were compared with two reference standards: (1) the radiologist report and (2) the diagnosis of cancer by multidisciplinary team decision. Failure analysis was performed by interrogating the software marker locations on radiographs. PARTICIPANTS: 5722 consecutive chest radiographs were included from 5592 patients (median age 59 years, 53.8% women, 1.6% prevalence of cancer). RESULTS: Compared with radiologist reports for nodule detection, the software demonstrated sensitivity 54.5% (95% CI 44.2% to 64.4%), specificity 83.2% (82.2% to 84.1%), positive predictive value (PPV) 5.5% (4.6% to 6.6%) and negative predictive value (NPV) 99.0% (98.8% to 99.2%). Compared with cancer diagnosis, the software demonstrated sensitivity 60.9% (50.1% to 70.9%), specificity 83.3% (82.3% to 84.2%), PPV 5.6% (4.8% to 6.6%) and NPV 99.2% (99.0% to 99.4%). Normal or variant anatomy was misidentified as an abnormality in 69.9% of the 943 false positive cases. CONCLUSIONS: The software demonstrated considerable underperformance in this real-world patient cohort. Failure analysis suggested a lack of generalisability in the training and testing datasets as a potential factor. The low PPV carries the risk of over-investigation and limits the translation of the software to clinical practice. Our findings highlight the importance of training and testing software in representative datasets, with broader implications for the implementation of AI tools in imaging.