RESUMEN
OBJECTIVES: Coronary artery calcium (CAC) scores derived from computed tomography (CT) scans are used for cardiovascular risk stratification. Artificial intelligence (AI) can assist in CAC quantification and potentially reduce the time required for human analysis. This study aimed to develop and evaluate a fully automated model that identifies and quantifies CAC. METHODS: Fully convolutional neural networks for automated CAC scoring were developed and trained on 2439 cardiac CT scans and validated using 771 scans. The model was tested on an independent set of 1849 cardiac CT scans. Agatston CAC scores were further categorised into five risk categories (0, 1-10, 11-100, 101-400, and > 400). Automated scores were compared to the manual reference standard (level 3 expert readers). RESULTS: Of 1849 scans used for model testing (mean age 55.7 ± 10.5 years, 49% males), the automated model detected the presence of CAC in 867 (47%) scans compared with 815 (44%) by human readers (p = 0.09). CAC scores from the model correlated very strongly with the manual score (Spearman's r = 0.90, 95% confidence interval [CI] 0.89-0.91, p < 0.001 and intraclass correlation coefficient = 0.98, 95% CI 0.98-0.99, p < 0.001). The model classified 1646 (89%) into the same risk category as human observers. The Bland-Altman analysis demonstrated little difference (1.69, 95% limits of agreement: -41.22, 44.60) and there was almost excellent agreement (Cohen's κ = 0.90, 95% CI 0.88-0.91, p < 0.001). Model analysis time was 13.1 ± 3.2 s/scan. CONCLUSIONS: This artificial intelligence-based fully automated CAC scoring model shows high accuracy and low analysis times. Its potential to optimise clinical workflow efficiency and patient outcomes requires evaluation. KEY POINTS: ⢠Coronary artery calcium (CAC) scores are traditionally assessed using cardiac computed tomography and require manual input by human operators to identify calcified lesions. ⢠A novel artificial intelligence (AI)-based model for fully automated CAC scoring was developed and tested on an independent dataset of computed tomography scans, showing very high levels of correlation and agreement with manual measurements as a reference standard. ⢠AI has the potential to assist in the identification and quantification of CAC, thereby reducing the time required for human analysis.
Asunto(s)
Enfermedad de la Arteria Coronaria , Vasos Coronarios , Masculino , Humanos , Persona de Mediana Edad , Anciano , Femenino , Vasos Coronarios/diagnóstico por imagen , Inteligencia Artificial , Calcio , Enfermedad de la Arteria Coronaria/diagnóstico por imagen , Tomografía Computarizada por Rayos X/métodos , Angiografía Coronaria/métodosRESUMEN
BACKGROUND AND OBJECTIVE: Asbestos is a major risk factor for lung cancer, with or without tobacco smoke exposure. Low dose computed tomography (LDCT) screening for early lung cancer is effective but only when targeting high risk populations. This study aimed to analyse the effectiveness of LDCT screening in an asbestos exposed population and to compare lung cancer screening program (LCSP) eligibility criteria. METHODS: Participants in an asbestos health surveillance program, the Western Australia Asbestos Review Program, underwent at least one LDCT scan and lung function assessment as part of annual review between 2012 and 2017. Lung cancer cases were confirmed through linkage to the WA cancer registry. Theoretical eligibility for different screening programs was calculated. RESULTS: Five thousand seven hundred and two LDCT scans were performed on 1743 individuals. The median age was 69.8 years, 1481 (85.0%) were male and 1147 (65.8%) were ever-smokers (median pack-year exposure of 20.0). Overall, 26 lung cancers were detected (1.5% of the population; 3.5 cases per 1000 person-years of observation). Lung cancer was early stage in 86.4% and four (15.4%) cases were never smokers. Based on current lung screening program criteria, 1299 (74.5%) of this population, including the majority (17, 65.4%) of lung cancer cases, would not have been eligible for any LCSP. CONCLUSION: This population is at raised risk despite modest tobacco exposure. LDCT screening is effective at identifying early-stage lung cancer in this population and existing lung cancer risk criteria do not capture this population adequately.
Asunto(s)
Amianto , Neoplasias Pulmonares , Humanos , Masculino , Anciano , Femenino , Neoplasias Pulmonares/diagnóstico por imagen , Neoplasias Pulmonares/epidemiología , Detección Precoz del Cáncer/métodos , Amianto/efectos adversos , Factores de Riesgo , Pulmón/diagnóstico por imagen , Tamizaje Masivo/efectos adversosRESUMEN
BACKGROUND: Bronchiectasis has been observed in association with systemic sclerosis (SSc). Theorised aetiology includes aspiration related to oesophageal dysmotility, immunosuppressant medication use and the direct effect of collagen deposition on airway calibre. AIMS: To detail bronchiectasis prevalence in an SSc population who have had a high-resolution computed tomography (HRCT) of the thorax. We assessed whether oesophageal dysmotility, demographic variables, SSc duration or subclass were associated with bronchiectasis. METHODS: Participants in the Australian Scleroderma Cohort Study (ASCS) with a HRCT were included. The ASCS provided demographic and clinical data. HRCT studies were reviewed for bronchiectasis, oesophageal dilatation and interstitial lung disease (ILD). Traction bronchiectasis associated with ILD was recorded as a separate entity to bronchiectasis. Oesophageal dysmotility was defined by symptoms and/or oesophageal dilatation. RESULTS: Of the 256 participants, 16.4% (n = 42) had bronchiectasis. Logistic regression analysis revealed no significant association between bronchiectasis and oesophageal dysmotility (observed in 95.7%), any demographic variable, SSc duration or subclass. A negative association between bronchiectasis and ILD was observed (P = 0.009; odds ratio 0.322; 95% confidence intervals 0.137-0.756). CONCLUSION: Those with SSc appear to have an increased risk for bronchiectasis. Since bronchiectasis was not more frequent in participants with a longer duration of SSc, we hypothesise that its development is not related to immunosuppression alone. Oesophageal dysmotility was almost universal in our population such that its effect on bronchiectasis development could not be concluded. A negative association between bronchiectasis and ILD reflects that bronchiectasis occurring alongside ILD was recorded as a separate entity.
Asunto(s)
Bronquiectasia , Trastornos de la Motilidad Esofágica , Enfermedades Pulmonares Intersticiales , Esclerodermia Sistémica , Humanos , Estudios de Cohortes , Prevalencia , Australia/epidemiología , Esclerodermia Sistémica/complicaciones , Esclerodermia Sistémica/epidemiología , Enfermedades Pulmonares Intersticiales/diagnóstico por imagen , Enfermedades Pulmonares Intersticiales/epidemiología , Bronquiectasia/diagnóstico por imagen , Bronquiectasia/epidemiología , Trastornos de la Motilidad Esofágica/complicacionesRESUMEN
BACKGROUND: The use of low dose CT (LDCT) chest is becoming more widespread in occupationally exposed populations. There is a knowledge gap as to heterogeneity in severity and the natural course of asbestosis after low levels of exposure. This study reports the characteristics of LDCT-detected interstitial lung abnormalities (ILA). METHODS: The Asbestos Review Program offers annual LDCT, health assessments, and pulmonary function tests to an asbestos-exposed cohort. Asbestosis was defined using the Helsinki Consensus statement and the presence of ILA defined using a protocol for occupational CT reports. At least two of three pulmonary function tests: forced expiratory volume in 1 s (FEV1 );â forced vital capacity (FVC); and diffusion capacity for carbon monoxide (DLco) were required for analysis of physiological decline. RESULTS: From 1513 cases, radiological ILA was present in 485 (32%). The cohort was 83.5% male with a median age of 68.3 years and a median (IQR) asbestos exposure of 0.7 (0.09-2.32) fiber/ml-year. A mixed occupation, mixed asbestos fiber cohort comprised the majority of the cohort (65.8%). Of those with ILA, 40 (8.2%) had an FVC decline of ≥10% and 30 (6.2%) had a DLco decline of ≥15% per year. Time since first exposure, increasing tobacco exposure and reported dyspnea were independently associated with the presence of ILA. CONCLUSIONS: In this population with relatively low asbestos exposure, LDCT-detected ILA that fits criteria for asbestosis is common, but physiological decline is not. This mild chronic stable phenotype of asbestos-associated ILA contrasts with the traditionally accepted views that asbestosis requires high exposures.
Asunto(s)
Amianto , Asbestosis , Exposición Profesional , Anciano , Amianto/toxicidad , Asbestosis/diagnóstico por imagen , Asbestosis/epidemiología , Femenino , Humanos , Pulmón/diagnóstico por imagen , Masculino , Exposición Profesional/efectos adversos , Tomografía Computarizada por Rayos XRESUMEN
INTRODUCTION: Deliberate exposure to medical ionising radiation should be as low as reasonably practicable but the reduction of radiation from CT should be balanced against diagnostic image quality. The ability of ultra-low-dose CT (uLDCT: similar radiation to chest X-ray) to demonstrate low contrast abnormalities (emphysema and interstitial lung abnormality (ILA)) is unclear.The aim of this cross-sectional study was to analyse the lung parenchymal findings from uLDCT scans against physiological measures of respiratory function. METHODS: WA Asbestos Review Programme participants were eligible if they had an uLDCT scan and lung function assessment between Janary and December 2018. All scans were performed using a single CT machine and reported using a standardised, semiquantitative synoptic report which includes emphysema and linear fibrosis (ILA) scores. RESULTS: Of 1344 participants, median (IQR) age was 72.0 (65.0-78.0) years, the majority were males (84.9%) with mixed occupational asbestos exposure (68.1%). There were 721 (53.6%) with no abnormality, 158 (11.8%) with emphysema, 465 (34.6%) with ILA. Mean radiation dose was 0.12 mSv. There was statistically significant between group differences for all physiological parameters of lung function compared with controls. For instance, the emphysema score significantly correlated with obstructive forced expiratory volume in 1 s (FEV1)/forced vital capacity ratio (r=0.512), per cent predicted FEV1 (r=0.24) and lower diffusion of carbon monoxide (DLCO) (r=0.337). Multivariate modelling demonstrated that increasing age, emphysema and fibrosis scores predicted reduced DLCO (adjusted R2=0.30). DISCUSSION: uLDCT-detected parenchymal lung abnormalities correlate strongly with significant changes on lung function testing suggesting the observed CT abnormalities are of physiological and clinical significance.
Asunto(s)
Amianto , Enfisema , Enfermedades Pulmonares , Enfisema Pulmonar , Masculino , Humanos , Anciano , Femenino , Estudios de Cohortes , Estudios Transversales , Tomografía Computarizada por Rayos X/métodos , Pulmón/diagnóstico por imagen , Enfisema Pulmonar/diagnóstico por imagen , Enfisema Pulmonar/etiología , Amianto/efectos adversos , FibrosisRESUMEN
STUDY DESIGN: Case-control study. OBJECTIVE: Investigate the association between lumbar spine magnetic resonance imaging (MRI) findings and 5-year trajectories of low back pain (LBP) in young Australian adults. SUMMARY OF BACKGROUND DATA: The association between lumbar spine imaging findings and LBP remains unclear due to important limitations of previous research, such as a lack of clearly defined LBP phenotypes and inadequate controlling for age, which may substantially affect the association. METHODS: Seventy-eight "case" participants with a previously identified "consistent high disabling LBP" trajectory from age 17 to 22âyears and 78 "control" participants from a trajectory with consistently low LBP over the same time period, matched for sex, body mass index, physical activity levels, and work physical demands, were identified from Gen2 Raine Study participants. At age 27, participants underwent a standardized lumbar MRI scan, from which 14 specific MRI phenotypes were identified. Primary analyses used unconditional logistic regression, adjusting for covariates used in the matching process, to investigate the relationship between presence of each imaging finding and being a case or control. Secondary analyses explored those relationships based on the number of spinal levels with each MRI finding. RESULTS: The odds for being a case compared with a control were higher in those with disc degeneration (Pfirrmann grade ≥ 3; ORâ=â3.21, 95% CI: 1.60-6.44; Pâ=â0.001) or those with a herniation (ORâ=â1.90, 95% CI: 0.96-3.74; P - 0.065). We also found that the association became substantially stronger when either disc degeneration or herniation was present at two or more spinal levels (ORâ=â5.56, 95% CI: 1.97-15.70; Pâ=â0.001, and ORâ=â5.85, 95% CI: 1.54-22.25; Pâ=â0.009, respectively). The other investigated MRI findings were not associated with greater odds of being a case. CONCLUSION: Lumbar disc degeneration and herniation may be important contributors to disabling LBP in young adults. Further investigation of their potential prognostic and causal roles is indicated.Level of Evidence: 4.
Asunto(s)
Degeneración del Disco Intervertebral , Dolor de la Región Lumbar , Adolescente , Adulto , Australia/epidemiología , Estudios de Casos y Controles , Humanos , Degeneración del Disco Intervertebral/diagnóstico por imagen , Degeneración del Disco Intervertebral/epidemiología , Dolor de la Región Lumbar/diagnóstico por imagen , Dolor de la Región Lumbar/epidemiología , Vértebras Lumbares/diagnóstico por imagen , Región Lumbosacra , Imagen por Resonancia Magnética , Adulto JovenRESUMEN
We present a case of a 70-year-old Caucasian woman with multisystem granulomatous disease involving her lungs, bones and lymph nodes. The patient initially presented with cervical lymphadenopathy and subsequently developed progressive breathlessness. Imaging revealed extensive mediastinal, hilar and intra-abdominal lymphadenopathy as well as bilateral pulmonary parenchymal infiltrates. Lymph node and lung biopsy confirmed non-necrotising granulomatous inflammation while a BAL showed scanty growth of Cryptococcus neoformans and moderate growth of Staphylococcus aureus The patient received intravenous ceftriaxone and had a good response to treatment. She also completed 3 months of oral fluconazole. Although a diagnosis of sarcoidosis was considered most likely, the patient was not initially started on systemic corticosteroids due to concern around possible infection and initial response to antimicrobials. However, her exercise tolerance gradually deteriorated. A craniofacial CT revealed multiple lytic lesions involving the skull and visualised cervical spine. Biopsy of a clivus lesion revealed non-necrotising granulomatous inflammation while fungal cultures and histopathological stains were negative. The patient was diagnosed with widespread sarcoidosis and she was initiated on prednisolone and methotrexate which led to marked clinical and radiological improvement.