RESUMEN
Introduction: Hyperpolarized 129Xe MRI and spectroscopy is a rapidly growing technique for assessing lung function, with applications in a wide range of obstructive, restrictive, and pulmonary vascular disease. However, normal variations in 129Xe measures of gas exchange across healthy subjects are not well characterized, presenting an obstacle to differentiating disease processes from the consequences of expected physiological heterogeneity. Here, we use multivariate models to evaluate the role of age, sex, and BMI in a range of commonly used 129Xe measures of gas exchange. Materials and methods: Healthy subjects (N = 40, 16F, age 44.3 ± 17.8 yrs., min-max 22-87 years) with no history of cardiopulmonary disease underwent 129Xe gas exchange MRI and spectroscopy. We used multivariate linear models to assess the associations of age, sex, and body mass index (BMI) with the RBC:Membrane (RBC:M), membrane to gas (Mem:Gas), and red blood cell to gas (RBC:Gas) ratios, as well as measurements of RBC oscillation amplitude and RBC chemical shift. Results: Age, sex, and BMI were all significant covariates in the RBC:M model. Each additional 10 years of age was associated with a 0.05 decrease in RBC:M (p < 0.001), each additional 10 points of BMI was associated with a decrease of 0.07 (p = 0.02), and males were associated with a 0.17 higher RBC:M than females (p < 0.001). For Mem:Gas, male sex was associated with a decrease and BMI was associated with an increase. For RBC:Gas, age was associated with a decrease and male sex was associated with an increase. RBC oscillation amplitude increased with age and RBC chemical shift was not associated with any of the three covariates. Discussion: 129Xe MRI and spectroscopy measurements in healthy subjects, particularly the widely used RBC:M measurement, exhibit heterogeneity associated in part with variations in subject age, sex, and BMI. Elucidating the contributions of these and other factors to 129Xe gas exchange measurements is a critical component for differentiating disease processes from expected variation in healthy subjects. Notably, the Mem:Gas and RBC chemical shift appear to be stable with aging, suggesting that unexplained deviations in these metrics may be signs of underlying abnormalities.
RESUMEN
BACKGROUND: There is no consensus on the optimal allograft sizing strategy for lung transplantation in restrictive lung disease. Current methods that are based on predicted total lung capacity (pTLC) ratios do not account for the diminutive recipient chest size. The study investigators hypothesized that a new sizing ratio incorporating preoperative recipient computed tomographic lung volumes (CTVol) would be associated with postoperative outcomes. METHODS: A retrospective single-institution study was conducted of adults undergoing primary bilateral lung transplantation between January 2016 and July 2020 for restrictive lung disease. CTVol was computed for recipients by using advanced segmentation software. Two sizing ratios were calculated: pTLC ratio (pTLCdonor/pTLCrecipient) and a new volumetric ratio (pTLCdonor/CTVolrecipient). Patients were divided into reference, oversized, and undersized groups on the basis of ratio quintiles, and multivariable models were used to assess the effect of the ratios on primary graft dysfunction and survival. RESULTS: CTVol was successfully acquired in 218 of 220 (99.1%) patients. In adjusted analysis, undersizing on the basis of the volumetric ratio was independently associated with decreased primary graft dysfunction grade 2 or 3 within 72 hours (odds ratio, 0.42; 95% CI, 0.20-0.87; P =.02). The pTLC ratio was not significantly associated with primary graft dysfunction. Oversizing on the basis of the volumetric ratio was independently associated with an increased risk of death (hazard ratio, 2.27; 95% CI, 1.04-4.99; P =.04], whereas the pTLC ratio did not have a significant survival association. CONCLUSIONS: Using computed tomography-acquired lung volumes for donor-recipient size matching in lung transplantation is feasible with advanced segmentation software. This method may be more predictive of outcome compared with current sizing methods, which use gender and height only.
Asunto(s)
Enfermedades Pulmonares , Trasplante de Pulmón , Disfunción Primaria del Injerto , Adulto , Humanos , Pulmón/cirugía , Estudios Retrospectivos , Disfunción Primaria del Injerto/etiología , Tamaño de los Órganos , Trasplante de Pulmón/métodos , Enfermedades Pulmonares/cirugía , Donantes de Tejidos , Tomografía Computarizada por Rayos XRESUMEN
PURPOSE: To compare the immune response and survival after size-matched radiofrequency (RF) ablation and a proprietary form of pulsed electric field (PEF) ablation in murine tumors. MATERIAL AND METHODS: Orthotopically inoculated EMT6 or 4T1 murine tumors received sham, RF ablation, or PEF ablation. 4T1 tumor ablations included subgroups with intraperitoneal checkpoint inhibition immunotherapy (αPD-1). Blood was collected for cytokine profiling and flow cytometry. Tumor size was measured and survival was monitored. Tumor samples were processed for histology, immunohistochemistry, flow cytometry, and cytokine profiling. Lungs were collected from 4T1-bearing mice for hematoxylin and eosin histology to assess metastatic spread and abscopal effect induced by ablation. RESULTS: PEF elicited distinct immunomodulatory effects, with clear differences in serum and tumor cytokine profiles compared with RF ablation, including intratumoral downregulation of vascular endothelial growth factor, hypoxia-inducible factor 1α, c-MET, interleukin-10, Ki67, and tumor necrosis factor-α (all P < .05). PEF increased innate immune activation, with enhanced recruitment of dendritic cells, M1 macrophages, and natural killer cells coupled with a reduction in M2 macrophages and myeloid-derived suppressor cells (all P < .05). Concurrently, PEF strengthened adaptive immunity compared with RF ablation, characterized by increased antigen-specific T cells and decreased regulatory T cells (all P < .05). PEF stalled tumor growth and increased survival at the end of the study (≥4× versus RFA). Finally, PEF promoted an abscopal effect of clearing metastases in the lungs, which was stronger in combination with αPD-1 than with PEF alone. CONCLUSIONS: The proprietary form of PEF used in this study evoked a preferential immunostimulatory profile versus RF ablation thermal ablation in mice, with implications for enhancing the therapeutic effectiveness of checkpoint inhibition immunotherapy for immunotherapy-unresponsive tumors.
Asunto(s)
Neoplasias , Ablación por Radiofrecuencia , Ratones , Animales , Factor A de Crecimiento Endotelial Vascular/metabolismo , Linfocitos T/metabolismo , Citocinas/metabolismoRESUMEN
Patients with diffuse lung diseases require thorough medical and social history and physical examinations, coupled with a multitude of laboratory tests, pulmonary function tests, and radiologic imaging to discern and manage the specific disease. This review summarizes the current state of imaging of various diffuse lung diseases by hyperpolarized MR imaging. The potential of hyperpolarized MR imaging as a clinical tool is outlined as a novel imaging approach that enables further understanding of the cause of diffuse lung diseases, permits earlier detection of disease progression before that found with pulmonary function tests, and can delineate physiologic response to lung therapies.
Asunto(s)
Enfermedades Pulmonares , Isótopos de Xenón , Humanos , Pulmón/diagnóstico por imagen , Enfermedades Pulmonares/diagnóstico por imagen , Imagen por Resonancia Magnética/métodosRESUMEN
BACKGROUND: Pre-treatment FDG-PET/CT scans were analyzed with machine learning to predict progression of lung malignancies and overall survival (OS). METHODS: A retrospective review across three institutions identified patients with a pre-procedure FDG-PET/CT and an associated malignancy diagnosis. Lesions were manually and automatically segmented, and convolutional neural networks (CNNs) were trained using FDG-PET/CT inputs to predict malignancy progression. Performance was evaluated using area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Image features were extracted from CNNs and by radiomics feature extraction, and random survival forests (RSF) were constructed to predict OS. Concordance index (C-index) and integrated brier score (IBS) were used to evaluate OS prediction. FINDINGS: 1168 nodules (n=965 patients) were identified. 792 nodules had progression and 376 were progression-free. The most common malignancies were adenocarcinoma (n=740) and squamous cell carcinoma (n=179). For progression risk, the PET+CT ensemble model with manual segmentation (accuracy=0.790, AUC=0.876) performed similarly to the CT only (accuracy=0.723, AUC=0.888) and better compared to the PET only (accuracy=0.664, AUC=0.669) models. For OS prediction with deep learning features, the PET+CT+clinical RSF ensemble model (C-index=0.737) performed similarly to the CT only (C-index=0.730) and better than the PET only (C-index=0.595), and clinical only (C-index=0.595) models. RSF models constructed with radiomics features had comparable performance to those with CNN features. INTERPRETATION: CNNs trained using pre-treatment FDG-PET/CT and extracted performed well in predicting lung malignancy progression and OS. OS prediction performance with CNN features was comparable to a radiomics approach. The prognostic models could inform treatment options and improve patient care. FUNDING: NIH NHLBI training grant (5T35HL094308-12, John Sollee).
Asunto(s)
Neoplasias Pulmonares , Tomografía Computarizada por Tomografía de Emisión de Positrones , Fluorodesoxiglucosa F18 , Humanos , Neoplasias Pulmonares/diagnóstico por imagen , Neoplasias Pulmonares/terapia , Aprendizaje Automático , Tomografía Computarizada por Tomografía de Emisión de Positrones/métodos , Tomografía de Emisión de PositronesRESUMEN
Background: The diagnosis of pulmonary hypertension (PH) remains challenging. Pre- and post-capillary PH have different signatures on noninvasive 129Xe gas-exchange magnetic resonance imaging (MRI) and dynamic MR spectroscopy (MRS). We tested the accuracy of 129Xe MRI/MRS to diagnose PH status compared to right heart catheterisation (RHC). Methods: 129Xe MRI/MRS from 93 subjects was used to develop a diagnostic algorithm, which was tested in 32 patients undergoing RHC on the same day (n=20) or within 5â months (42±40â days) (n=12). Three expert readers, blinded to RHC, used 129Xe MRI/MRS to classify subjects as pre-capillary PH, post-capillary PH, no PH and no interstitial lung disease (ILD), or ILD. Results: For pre-capillary PH, 129Xe MRI/MRS diagnostic accuracy was 75% (95% CI 66-84) with a sensitivity of 67% (95% CI 54-79) and a specificity of 86% (95% CI 75-96); for post-capillary PH accuracy was 69% (95% CI 59-78) with sensitivity of 54% (95% CI 34-74) and specificity of 74% (95% CI 63-84). The model performed well in straightforward cases of pre-capillary PH but was less accurate in its diagnosis in the presence of mixed disease, particularly in the presence of ILD or combined post- and pre-capillary PH. Conclusion: This study demonstrates the potential to develop 129Xe MRI/MRS into a modality with good accuracy in detecting pre- and post-capillary PH. Furthermore, the combination of 129Xe dynamic MRS and gas-exchange MRI uniquely provide concurrent, noninvasive assessment of both haemodynamics and gas-exchange impairment that may aid in the detection of PH.
RESUMEN
Background Recent studies demonstrate that antifibrotic drugs previously reserved for idiopathic pulmonary fibrosis (IPF) may slow progression in other interstitial lung diseases (ILDs), creating an urgent need for tools that can sensitively assess disease activity, progression, and therapy response across ILDs. Hyperpolarized xenon 129 (129Xe) MRI and spectroscopy have provided noninvasive measurements of regional gas-exchange abnormalities in IPF. Purpose To assess gas exchange function using 129Xe MRI in a group of study participants with nonspecific interstitial pneumonia (NSIP) compared with healthy control participants. Materials and Methods In this prospective study, participants with NSIP and healthy control participants were enrolled between November 2017 and February 2020 and underwent 129Xe MRI and spectroscopy. Quantitative imaging provided three-dimensional maps of ventilation, interstitial barrier uptake, and transfer into the red blood cell (RBC) compartment. Spectroscopy provided parameters of the static RBC and barrier uptake compartments, as well as cardiogenic oscillations in RBC signal amplitude and chemical shift. Differences between NSIP and healthy control participants were assessed using the Wilcoxon rank-sum test. Results Thirty-six participants with NSIP (mean age, 57 years ± 11 [standard deviation]; 27 women) and 15 healthy control participants (mean age, 39 years ± 18; two women) were evaluated. Participants with NSIP had no difference in ventilation compared with healthy control participants (median, 4.4% [first quartile, 1.5%; third quartile, 8.7%] vs 6.0% [first quartile, 2.8%; third quartile, 6.9%]; P = .91), but they had a higher barrier uptake (median, 6.2% [first quartile, 1.8%; third quartile, 23.9%] vs 0.53% [first quartile, 0.33%; third quartile, 2.9%]; P = .003) and an increased RBC transfer defect (median, 20.6% [first quartile, 11.6%; third quartile, 27.8%] vs 2.8% [first quartile, 2.3%; third quartile, 4.9%]; P < .001). NSIP participants also had a reduced ratio of RBC-to-barrier peaks (median, 0.24 [first quartile, 0.19; third quartile, 0.31] vs 0.57 [first quartile, 0.52; third quartile, 0.67]; P < .001) and a reduced RBC chemical shift (median, 217.5 ppm [first quartile, 217.0 ppm; third quartile, 218.0 ppm] vs 218.2 ppm [first quartile, 217.9 ppm; third quartile, 218.6 ppm]; P = .001). Conclusion Participants with nonspecific interstitial pneumonia had increased barrier uptake and decreased red blood cell (RBC) transfer compared with healthy controls measured using xenon 129 gas-exchange MRI and reduced RBC-to-barrier ratio and RBC chemical shift measured using spectroscopy. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Wild in this issue.
Asunto(s)
Enfermedades Pulmonares Intersticiales/diagnóstico por imagen , Imagen por Resonancia Magnética/métodos , Intercambio Gaseoso Pulmonar , Isótopos de Xenón , Adulto , Estudios Transversales , Femenino , Humanos , Pulmón/diagnóstico por imagen , Pulmón/fisiopatología , Masculino , Persona de Mediana Edad , Estudios Prospectivos , Análisis Espectral/métodosRESUMEN
Hyperpolarized 129Xe MRI has emerged as a novel means to evaluate pulmonary function via 3D mapping of ventilation, interstitial barrier uptake, and RBC transfer. However, the physiological interpretation of these measurements has yet to be firmly established. Here, we propose a model that uses the three components of 129Xe gas-exchange MRI to estimate accessible alveolar volume (VA), membrane conductance, and capillary blood volume contributions to DLCO. 129Xe ventilated volume (VV) was related to VA by a scaling factor kV = 1.47 with 95% confidence interval [1.42, 1.52], relative 129Xe barrier uptake (normalized by the healthy reference value) was used to estimate the membrane-specific conductance coefficient kB = 10.6 [8.6, 13.6] mL/min/mmHg/L, whereas normalized RBC transfer was used to calculate the capillary blood volume-specific conductance coefficient kR = 13.6 [11.4, 16.7] mL/min/mmHg/L. In this way, the barrier and RBC transfer per unit volume determined the transfer coefficient KCO, which was then multiplied by image-estimated VA to obtain DLCO. The model was built on a cohort of 41 healthy subjects and 101 patients with pulmonary disorders. The resulting 129Xe-derived DLCO correlated strongly (R2 = 0.75, P < 0.001) with the measured values, a finding that was preserved within each individual disease cohort. The ability to use 129Xe MRI measures of ventilation, barrier uptake, and RBC transfer to estimate each of the underlying constituents of DLCO clarifies the interpretation of these images while enabling their use to monitor these aspects of gas exchange independently and regionally.NEW & NOTEWORTHY The diffusing capacity for carbon monoxide (DLCO) is perhaps one of the most comprehensive physiological measures used in pulmonary medicine. Here, we spatially resolve and estimate its key components-accessible alveolar volume, membrane, and capillary blood volume conductances-using hyperpolarized 129Xe MRI of ventilation, interstitial barrier uptake, and red blood cell transfer. This image-derived DLCO correlates strongly with measured values in 142 subjects with a broad range of pulmonary disorders.
Asunto(s)
Enfermedades Pulmonares , Isótopos de Xenón , Monóxido de Carbono , Humanos , Pulmón , Imagen por Resonancia Magnética , Capacidad de Difusión Pulmonar , RespiraciónRESUMEN
PURPOSE: Incidental pulmonary embolism (IPE) can be found on body CT. The aim of this study was to evaluate the feasibility of using artificial intelligence to identify missed IPE on a large number of CT examinations. METHODS: This retrospective analysis included all single-phase chest, abdominal, and pelvic (CAP) and abdominal and pelvic (AP) CT examinations performed at a single center over 1 year, for indications other than identification of PE. Proprietary visual classification and natural language processing software was used to analyze images and reports from all CT examinations, followed by a two-step human adjudication process to classify cases as true positive, false positive, true negative, or false negative. Descriptive statistics were assessed for prevalence of IPE and features (subsegmental versus central, unifocal versus multifocal, right heart strain or not) of missed IPE. Interrater agreement for radiologist readers was also calculated. RESULTS: A total of 11,913 CT examinations (6,398 CAP, 5,515 AP) were included. Thirty false-negative examinations were identified on CAP (0.47%; 95% confidence interval [CI], 0.32%-0.67%) and nineteen false-negative studies on AP (0.34%; 95% CI, 0.21%-0.54%) studies. During manual review, readers showed substantial agreement for identification of IPE on CAP (κ = 0.76; 95% CI, 0.66-0.86) and nearly perfect agreement for identification of IPE on AP (κ = 0.86; 95% CI, 0.76-0.97). Forty-nine missed IPEs (0.41%; 95% CI, 0.30%-0.54%) were ultimately identified, compared with seventy-nine IPEs (0.66%; 95% CI, 0.53%-0.83%) identified at initial clinical interpretation. CONCLUSIONS: Artificial intelligence can efficiently analyze CT examinations to identify potential missed IPE. These results can inform peer-review efforts and quality control and could potentially be implemented in a prospective fashion.
Asunto(s)
Inteligencia Artificial , Embolia Pulmonar , Humanos , Prevalencia , Estudios Prospectivos , Embolia Pulmonar/diagnóstico por imagen , Embolia Pulmonar/epidemiología , Mejoramiento de la Calidad , Estudios Retrospectivos , Tomografía Computarizada por Rayos XRESUMEN
INTRODUCTION: There is mounting evidence of respiratory problems related to military service in the Middle East in the past two decades due to environmental exposures during deployment (eg, sand storms and burn pits). This pilot study tests the hypothesis that regional lung function in subjects with prior deployment in Iraq and/or Afghanistan with suspected War Lung Injury (WLI) would be worse than subjects with normal lung function. MATERIALS AND METHODS: Five subjects meeting the inclusion and exclusion criteria were recruited for this pilot study. All subjects underwent spirometry, high-resolution chest computed tomography imaging, and 19F MRI. RESULTS: While the WLI subjects had normal pulmonary function tests and normal high-resolution chest computed tomography evaluations, their regional lung function from 19F MRI was abnormal with compartments with poor function showing slower filling time constants for ventilation. The scans of suspected WLI subjects show higher fractional lung volume with slow filling compartments similar to patients with chronic obstructive pulmonary disease in contrast to normal subjects. CONCLUSIONS: This is consistent with our premise that WLI results in abnormal lung function and reflects small airways dysfunction and suggests that we may be able to provide a more sensitive tool for evaluation of WLI suspected cases.
Asunto(s)
Imagen por Resonancia Magnética con Fluor-19/métodos , Lesión Pulmonar/diagnóstico por imagen , Adulto , Campaña Afgana 2001- , Femenino , Imagen por Resonancia Magnética con Fluor-19/instrumentación , Imagen por Resonancia Magnética con Fluor-19/estadística & datos numéricos , Humanos , Guerra de Irak 2003-2011 , Masculino , Persona de Mediana Edad , Terapia por Inhalación de Oxígeno/métodos , Proyectos Piloto , Sistema de Registros/estadística & datos numéricos , Encuestas y Cuestionarios , Estados UnidosRESUMEN
HistoryA 47-year-old Sudanese man without a known remarkable medical history presented to the emergency department for a syncopal episode. The patient denied chest pain, dyspnea, focal weakness, or prior similar episodes. He was originally from north Sudan and eventually moved to Saudi Arabia, where he worked as a farm manager before emigrating to the United States years ago. Physical examination findings and routine laboratory values, including complete blood count and basic metabolic panels, were normal. Electrocardiography revealed nonspecific T-wave inversions, and a series of cardiac biomarkers were negative. A contrast material-enhanced CT angiography pulmonary embolism protocol and cardiac MRI were performed for further evaluation.
Asunto(s)
Angiografía por Tomografía Computarizada/métodos , Equinococosis/diagnóstico por imagen , Cardiopatías/diagnóstico por imagen , Cardiopatías/patología , Imagen por Resonancia Magnética/métodos , Animales , Procedimientos Quirúrgicos Cardíacos , Medios de Contraste , Diagnóstico Diferencial , Equinococosis/cirugía , Echinococcus , Electrocardiografía/métodos , Corazón/diagnóstico por imagen , Corazón/parasitología , Cardiopatías/cirugía , Humanos , Masculino , Persona de Mediana Edad , Intensificación de Imagen RadiográficaRESUMEN
PURPOSE: To assess the diagnostic performance of ferumoxytol-enhanced MR venography for the detection of thoracic central vein stenosis or occlusion with conventional venography as the reference standard. MATERIALS AND METHODS: In this retrospective study, consecutive patients from May 2012 to December 2018 underwent dedicated ferumoxytol-enhanced MR venography of the thoracic central veins and conventional venography within 6 months for detecting central venous stenosis. The central veins were divided into seven segments for evaluation. MR venography images were evaluated by three radiologists for presence of stenosis or occlusion. Interobserver agreement was assessed using Fleiss κ. RESULTS: A total of 35 patients were included (mean age, 49 years; age range, 12-75 years; 18 females). Of the 122 total venous segments with corresponding conventional venography, 73 were stenotic or occluded. The sensitivity and specificity for detection of stenosis or occlusion was 99% and 98%, respectively. The sensitivity and specificity for detecting occlusion alone was 96% and 98%, respectively. MR venography readers demonstrated moderate agreement in their ability to grade stenosis or occlusion (κ = 0.59). There were no adverse events related to contrast agent administration. CONCLUSION: Ferumoxytol-enhanced MR venography demonstrated excellent sensitivity and specificity for detection of thoracic central vein stenosis or occlusion.© RSNA, 2020See also the commentary by Finn in this issue.
RESUMEN
RATIONALE: Hyperpolarized 129Xe ventilation MRI is typically acquired using multislice fast gradient recalled echo (GRE), but interleaved 3D radial 129Xe gas transfer MRI now provides dissolved-phase and ventilation images from a single breath. To investigate whether these ventilation images provide equivalent quantitative metrics, we introduce generalized linear binning analysis. METHODS: This study included 36 patients who had undergone both multislice GRE ventilation and 3D radial gas exchange imaging. Images were then quantified by linear binning to classify voxels into one of four clusters: ventilation defect percentage (VDP), Low-, Medium- or High-ventilation percentage (LVP, MVP, HVP). For 3D radial images, linear binning thresholds were generalized using a Box-Cox rescaled reference histogram. We compared the cluster populations from the two ventilation acquisitions both numerically and spatially. RESULTS: Interacquisition Bland-Altman limits of agreement for the clusters between 3D radial vs GRE were (-7% to 5%) for VDP, (-10% to 14%) for LVP, and (-8% to 8%) for HVP. While binning maps were qualitatively similar between acquisitions, their spatial overlap was modest for VDP (Diceâ¯=â¯0.5 ± 0.2), and relatively poor for LVP (0.3 ± 0.1) and HVP (0.2 ± 0.1). CONCLUSION: Both acquisitions yield reasonably concordant VDP and qualitatively similar maps. However, poor regional agreement (Dice) suggests that the two acquisitions cannot yet be used interchangeably. However, further improvements in 3D radial resolution and reconciliation of bias field correction may well obviate the need for a dedicated ventilation scan in many cases.
Asunto(s)
Ventilación Pulmonar , Isótopos de Xenón , Humanos , Pulmón , Imagen por Resonancia Magnética , RespiraciónAsunto(s)
Fibrosis Pulmonar Idiopática/diagnóstico por imagen , Aumento de la Imagen/métodos , Pulmón/diagnóstico por imagen , Imagen por Resonancia Magnética/métodos , Xenón , Adolescente , Adulto , Anciano , Estudios de Casos y Controles , Femenino , Humanos , Modelos Logísticos , Masculino , Persona de Mediana Edad , Adulto JovenRESUMEN
[This corrects the article DOI: 10.1038/s41746-019-0189-7.].
RESUMEN
Human-in-the-loop (HITL) AI may enable an ideal symbiosis of human experts and AI models, harnessing the advantages of both while at the same time overcoming their respective limitations. The purpose of this study was to investigate a novel collective intelligence technology designed to amplify the diagnostic accuracy of networked human groups by forming real-time systems modeled on biological swarms. Using small groups of radiologists, the swarm-based technology was applied to the diagnosis of pneumonia on chest radiographs and compared against human experts alone, as well as two state-of-the-art deep learning AI models. Our work demonstrates that both the swarm-based technology and deep-learning technology achieved superior diagnostic accuracy than the human experts alone. Our work further demonstrates that when used in combination, the swarm-based technology and deep-learning technology outperformed either method alone. The superior diagnostic accuracy of the combined HITL AI solution compared to radiologists and AI alone has broad implications for the surging clinical AI deployment and implementation strategies in future practice.
RESUMEN
BACKGROUND: As an increasing number of patients exhibit concomitant cardiac and pulmonary disease, limitations of standard diagnostic criteria are more frequently encountered. Here, we apply noninvasive 129Xe magnetic resonance imaging (MRI) and spectroscopy to identify patterns of regional gas transfer impairment and haemodynamics that are uniquely associated with chronic obstructive pulmonary disease (COPD), idiopathic pulmonary fibrosis (IPF), left heart failure (LHF) and pulmonary arterial hypertension (PAH). METHODS: Healthy volunteers (n=23) and patients with COPD (n=8), IPF (n=12), LHF (n=6) and PAH (n=10) underwent 129Xe gas transfer imaging and dynamic spectroscopy. For each patient, three-dimensional maps were generated to depict ventilation, barrier uptake (129Xe dissolved in interstitial tissue) and red blood cell (RBC) transfer (129Xe dissolved in RBCs). Dynamic 129Xe spectroscopy was used to quantify cardiogenic oscillations in the RBC signal amplitude and frequency shift. RESULTS: Compared with healthy volunteers, all patient groups exhibited decreased ventilation and RBC transfer (both p≤0.01). Patients with COPD demonstrated more ventilation and barrier defects compared with all other groups (both p≤0.02). In contrast, IPF patients demonstrated elevated barrier uptake compared with all other groups (p≤0.007), and increased RBC amplitude and shift oscillations compared with healthy volunteers (p=0.007 and p≤0.01, respectively). Patients with COPD and PAH both exhibited decreased RBC amplitude oscillations (p=0.02 and p=0.005, respectively) compared with healthy volunteers. LHF was distinguishable from PAH by enhanced RBC amplitude oscillations (p=0.01). CONCLUSION: COPD, IPF, LHF and PAH each exhibit unique 129Xe MRI and dynamic spectroscopy signatures. These metrics may help with diagnostic challenges in cardiopulmonary disease and increase understanding of regional lung function and haemodynamics at the alveolar-capillary level.
Asunto(s)
Insuficiencia Cardíaca/diagnóstico por imagen , Fibrosis Pulmonar Idiopática/diagnóstico por imagen , Hipertensión Arterial Pulmonar/diagnóstico por imagen , Enfermedad Pulmonar Obstructiva Crónica/diagnóstico por imagen , Adulto , Anciano , Estudios de Casos y Controles , Femenino , Humanos , Imagenología Tridimensional , Imagen por Resonancia Magnética , Masculino , Persona de Mediana Edad , Isótopos de Xenón , Adulto JovenRESUMEN
History A 47-year-old Sudanese man without a known remarkable medical history presented to the emergency department for a syncopal episode. The patient denied chest pain, dyspnea, focal weakness, or prior similar episodes. He was originally from north Sudan and eventually moved to Saudi Arabia, where he worked as a farm manager before emigrating to the United States years ago. Physical examination findings and routine laboratory values, including complete blood count and basic metabolic panels, were normal. Electrocardiography revealed nonspecific T-wave inversions, and a series of cardiac biomarkers were negative. A contrast material-enhanced CT angiography pulmonary embolism protocol and cardiac MRI were performed for further evaluation (Figs 1-4). [Figure: see text] [Figure: see text] [Figure: see text] [Figure: see text] [Figure: see text] [Figure: see text].
RESUMEN
OBJECTIVE: The primary objective of this study was to estimate the percentage of individuals possibly eligible for lung cancer screening that report having discussed screening with a health care provider. The secondary objective was to investigate the associated factors of having patient-provider lung cancer screening discussion. METHODS: Data from the Health Information National Trends Survey 2017 were used (n = 3217). Lung cancer screening eligibility was based on the criteria utilized by the Centers for Medicare and Medicaid Services. Gender, race, educational attainment, health insurance coverage, and usual source of health care were covariates. Current or former smokers ages 55-77 (n = 706) were considered potentially eligible for lung cancer screening (dependent variable). RESULTS: Only 12.24% of individuals potentially eligible for lung cancer screening report prior discussion regarding lung cancer screening with a health care provider. Being eligible for lung cancer screening based on Centers for Medicare and Medicaid Services eligibility criteria was positively associated with the odds of a patient-provider lung cancer screening discussion (odds ratio = 3.95, 95% confidence interval = 2.48-6.30). Unlike gender, race, education, or insurance coverage, a usual source of health care was positively associated with a patient-provider screening discussion (odds ratio = 2.48, 95% confidence interval = 1.31-4.70). CONCLUSION: Individuals potentially eligible for lung cancer screening are more likely to have screening discussions with a health care provider. Having a usual source of health care may increase the odds of such a discussion, while patients are not discriminated based on race, gender, education, and insurance coverage. However, the relatively low rate (12.24%) of reported patient-provider lung cancer screening discussion indicates that significant barriers still remain.
RESUMEN
Idiopathic pulmonary fibrosis (IPF) is a progressive pulmonary disease that is ultimately fatal. Although the diagnosis of IPF has been revolutionized by high-resolution computed tomography, this imaging modality still exhibits significant limitations, particularly in assessing disease progression and therapy response. The need for noninvasive regional assessment has become more acute in light of recently introduced novel therapies and numerous others in the pipeline. Thus, it will likely be valuable to complement 3-dimensional imaging of lung structure with 3-dimensional regional assessment of function. This challenge is well addressed by hyperpolarized (HP) Xe magnetic resonance imaging (MRI), exploiting the unique properties of this inert gas to image its distribution, not only in the airspaces, but also in the interstitial barrier tissues and red blood cells. This single-breath imaging exam could ultimately become the ideal, noninvasive tool to assess pulmonary gas-exchange impairment in IPF. This review article will detail the evolution of HP Xe MRI from its early development to its current state as a clinical research platform. It will detail the key imaging biomarkers that can be generated from the Xe MRI examination, as well as their potential in IPF for diagnosis, prognosis, and assessment of therapeutic response. We conclude by discussing the types of studies that must be performed for HP Xe MRI to be incorporated into the IPF clinical algorithm and begin to positively impact IPF disease diagnosis and management.