Artificial intelligence-assisted quantification of COVID-19 pneumonia burden from computed tomography improves prediction of adverse outcomes over visual scoring systems.

OBJECTIVE: We aimed to evaluate the effectiveness of utilizing artificial intelligence (AI) to quantify the extent of pneumonia from chest CT scans, and to determine its ability to predict clinical deterioration or mortality in patients admitted to the hospital with COVID-19 in comparison to semi-quantitative visual scoring systems. METHODS: A deep-learning algorithm was utilized to quantify the pneumonia burden, while semi-quantitative pneumonia severity scores were estimated through visual means. The primary outcome was clinical deterioration, the composite end point including admission to the intensive care unit, need for invasive mechanical ventilation, or vasopressor therapy, as well as in-hospital death. RESULTS: The final population comprised 743 patients (mean age 65  ±â€¯ 17 years, 55% men), of whom 175 (23.5%) experienced clinical deterioration or death. The area under the receiver operating characteristic curve (AUC) for predicting the primary outcome was significantly higher for AI-assisted quantitative pneumonia burden (0.739, p = 0.021) compared with the visual lobar severity score (0.711, p < 0.001) and visual segmental severity score (0.722, p = 0.042). AI-assisted pneumonia assessment exhibited lower performance when applied for calculation of the lobar severity score (AUC of 0.723, p = 0.021). Time taken for AI-assisted quantification of pneumonia burden was lower (38 ± 10 s) compared to that of visual lobar (328 ± 54 s, p < 0.001) and segmental (698 ± 147 s, p < 0.001) severity scores. CONCLUSION: Utilizing AI-assisted quantification of pneumonia burden from chest CT scans offers a more accurate prediction of clinical deterioration in patients with COVID-19 compared to semi-quantitative severity scores, while requiring only a fraction of the analysis time. ADVANCES IN KNOWLEDGE: Quantitative pneumonia burden assessed using AI demonstrated higher performance for predicting clinical deterioration compared to current semi-quantitative scoring systems. Such an AI system has the potential to be applied for image-based triage of COVID-19 patients in clinical practice.

Rapid quantification of COVID-19 pneumonia burden from computed tomography with convolutional long short-term memory networks.

Purpose: Quantitative lung measures derived from computed tomography (CT) have been demonstrated to improve prognostication in coronavirus disease 2019 (COVID-19) patients but are not part of clinical routine because the required manual segmentation of lung lesions is prohibitively time consuming. We aim to automatically segment ground-glass opacities and high opacities (comprising consolidation and pleural effusion). Approach: We propose a new fully automated deep-learning framework for fast multi-class segmentation of lung lesions in COVID-19 pneumonia from both contrast and non-contrast CT images using convolutional long short-term memory (ConvLSTM) networks. Utilizing the expert annotations, model training was performed using five-fold cross-validation to segment COVID-19 lesions. The performance of the method was evaluated on CT datasets from 197 patients with a positive reverse transcription polymerase chain reaction test result for SARS-CoV-2, 68 unseen test cases, and 695 independent controls. Results: Strong agreement between expert manual and automatic segmentation was obtained for lung lesions with a Dice score of 0.89 ± 0.07 ; excellent correlations of 0.93 and 0.98 for ground-glass opacity (GGO) and high opacity volumes, respectively, were obtained. In the external testing set of 68 patients, we observed a Dice score of 0.89 ± 0.06 as well as excellent correlations of 0.99 and 0.98 for GGO and high opacity volumes, respectively. Computations for a CT scan comprising 120 slices were performed under 3 s on a computer equipped with an NVIDIA TITAN RTX GPU. Diagnostically, the automated quantification of the lung burden % discriminate COVID-19 patients from controls with an area under the receiver operating curve of 0.96 (0.95-0.98). Conclusions: Our method allows for the rapid fully automated quantitative measurement of the pneumonia burden from CT, which can be used to rapidly assess the severity of COVID-19 pneumonia on chest CT.

Lung Ultrasound in Patients With SARS-COV-2 Pneumonia: Correlations With Chest Computed Tomography, Respiratory Impairment, and Inflammatory Cascade.

OBJECTIVES: Lung ultrasound (LUS) might be comparable to chest computed tomography (CT) in detecting parenchymal and pleural pathology, and in monitoring interstitial lung disease. We aimed to describe LUS characteristics of patients during the hospitalization for COVID-19 pneumonia, and to compare the extent of lung involvement at LUS and chest-CT with inflammatory response and the severity of respiration impairment. METHODS: During a 2-week period, we performed LUS and chest CT in hospitalized patients affected by COVID-19 pneumonia. Dosages of high sensitivity C-reactive protein (HS-CRP), d-dimer, and interleukin-6 (IL-6) were also obtained. The index of lung function (P/F ratio) was calculated from the blood gas test. LUS and CT scoring were assessed using previously validated scores. RESULTS: Twenty-six consecutive patients (3 women) underwent LUS 34 ± 14 days from the early symptoms. Among them, 21 underwent CT on the same day of LUS. A fair association was found between LUS and CT scores (R = 0.45, P = .049), which became stronger if the B-lines score on LUS was not considered (R = 0.57, P = .024). LUS B-lines score correlated with IL-6 levels (R = 0.75, P = .011), and the number of involved lung segments detected by LUS correlated with the P/F ratio (R = 0.60, P = .019) but not with HS-CRP and d-Dimer levels. No correlations were found between CT scores and inflammations markers or P/F. CONCLUSION: In patients with COVID-19 pneumonia, LUS was correlated with both the extent of the inflammatory response and the P/F ratio.

Effective Study: Development and Application of a Question-Driven, Time-Effective Cardiac Magnetic Resonance Scanning Protocol.

Background Long scanning times impede cardiac magnetic resonance (CMR) clinical uptake. A "one-size-fits-all" shortened, focused protocol (eg, only function and late-gadolinium enhancement) reduces scanning time and costs, but provides less information. We developed 2 question-driven CMR and stress-CMR protocols, including tailored advanced tissue characterization, and tested their effectiveness in reducing scanning time while retaining the diagnostic performances of standard protocols. Methods and Results Eighty three consecutive patients with cardiomyopathy or ischemic heart disease underwent the tailored CMR. Each scan consisted of standard cines, late-gadolinium enhancement imaging, native T1-mapping, and extracellular volume. Fat/edema modules, right ventricle cine, and in-line quantitative perfusion mapping were performed as clinically required. Workflow was optimized to avoid gaps. Time target was <30 minutes for a CMR and <35 minutes for a stress-CMR. CMR was considered impactful when its results drove changes in diagnosis or management. Advanced tissue characterization was considered impactful when it changed the confidence level in the diagnosis. The quality of the images was assessed. A control group of 137 patients was identified among scans performed before February 2020. Compared with standard protocols, the average scan duration dropped by >30% (CMR: from 42±8 to 28±6 minutes; stress-CMR: from 50±10 to 34±6 minutes, both P<0.0001). Independent on the protocol, CMR was impactful in ≈60% cases, and advanced tissue characterization was impactful in >45% of cases. Quality grading was similar between the 2 protocols. Tailored protocols did not require additional staff. Conclusions Tailored CMR and stress-CMR protocols including advanced tissue characterization are accurate and time-effective for cardiomyopathies and ischemic heart disease.

Recent advances in multimodality imaging of the tricuspid valve.

INTRODUCTION: The tricuspid valve (TV) and the right heart chambers are complex three-dimensional structures that are difficult to assess using tomographic imaging techniques. The progressive aging of the general population and the advancements in treating left-sided heart diseases by transcatheter procedures have contributed to the tricuspid regurgitation (TR) becoming a major public health problem associated with progression to refractory heart failure and poor outcome. Recent advances in multimodality cardiac imaging allow a better understanding of the pathophysiology of TR that may translate in better management of patients. AREAS COVERED: Three-dimensional echocardiography, cardiac magnetic resonance, and computed tomography provide complementary information to i. assess the TV complex; ii. identify the etiology and the mechanisms of TR; iii. evaluate its severity and hemodynamic consequences; iv. explore the remodeling of the right heart chambers; and v. properly plan, guide, and monitor the transcatheter interventions aimed to reduce the severity of TR. EXPERT OPINION: We need thorough understanding of both the TV and the right heart chamber geometry and function to understand the pathophysiology of TR. The integrated use of multimodality cardiac imaging is pivotal to assess patients with TR and to identify tailored and timely treatment of TR in properly selected patients.

Rapid quantification of COVID-19 pneumonia burden from computed tomography with convolutional LSTM networks.

Quantitative lung measures derived from computed tomography (CT) have been demonstrated to improve prognostication in Coronavirus disease 2019 (COVID-19) patients, but are not part of the clinical routine since required manual segmentation of lung lesions is prohibitively time-consuming. We propose a new fully automated deep learning framework for quantification and differentiation between lung lesions in COVID-19 pneumonia from both contrast and non-contrast CT images using convolutional Long Short-Term Memory (LSTM) networks. Utilizing the expert annotations, model training was performed using 5-fold cross-validation to segment ground-glass opacity and high opacity (including consolidation and pleural effusion). The performance of the method was evaluated on CT data sets from 197 patients with positive reverse transcription polymerase chain reaction test result for SARS-CoV-2. Strong agreement between expert manual and automatic segmentation was obtained for lung lesions with a Dice score coefficient of 0.876 ± 0.005; excellent correlations of 0.978 and 0.981 for ground-glass opacity and high opacity volumes. In the external validation set of 67 patients, there was dice score coefficient of 0.767 ± 0.009 as well as excellent correlations of 0.989 and 0.996 for ground-glass opacity and high opacity volumes. Computations for a CT scan comprising 120 slices were performed under 2 seconds on a personal computer equipped with NVIDIA Titan RTX graphics processing unit. Therefore, our deep learning-based method allows rapid fully-automated quantitative measurement of pneumonia burden from CT and may generate the big data with an accuracy similar to the expert readers.

Epicardial adipose tissue is associated with extent of pneumonia and adverse outcomes in patients with COVID-19.

AIM: We sought to examine the association of epicardial adipose tissue (EAT) quantified on chest computed tomography (CT) with the extent of pneumonia and adverse outcomes in patients with coronavirus disease 2019 (COVID-19). METHODS: We performed a post-hoc analysis of a prospective international registry comprising 109 consecutive patients (age 64 ±â€¯16 years; 62% male) with laboratory-confirmed COVID-19 and noncontrast chest CT imaging. Using semi-automated software, we quantified the burden (%) of lung abnormalities associated with COVID-19 pneumonia. EAT volume (mL) and attenuation (Hounsfield units) were measured using deep learning software. The primary outcome was clinical deterioration (intensive care unit admission, invasive mechanical ventilation, or vasopressor therapy) or in-hospital death. RESULTS: In multivariable linear regression analysis adjusted for patient comorbidities, the total burden of COVID-19 pneumonia was associated with EAT volume (ß = 10.6, p = 0.005) and EAT attenuation (ß = 5.2, p = 0.004). EAT volume correlated with serum levels of lactate dehydrogenase (r = 0.361, p = 0.001) and C-reactive protein (r = 0.450, p < 0.001). Clinical deterioration or death occurred in 23 (21.1%) patients at a median of 3 days (IQR 1-13 days) following the chest CT. In multivariable logistic regression analysis, EAT volume (OR 5.1 [95% CI 1.8-14.1] per doubling p = 0.011) and EAT attenuation (OR 3.4 [95% CI 1.5-7.5] per 5 Hounsfield unit increase, p = 0.003) were independent predictors of clinical deterioration or death, as was total pneumonia burden (OR 2.5, 95% CI 1.4-4.6, p = 0.002), chronic lung disease (OR 1.3 [95% CI 1.1-1.7], p = 0.011), and history of heart failure (OR 3.5 [95% 1.1-8.2], p = 0.037). CONCLUSIONS: EAT measures quantified from chest CT are independently associated with extent of pneumonia and adverse outcomes in patients with COVID-19, lending support to their use in clinical risk stratification.

Quantitative Burden of COVID-19 Pneumonia on Chest CT Predicts Adverse Outcomes: A Post-Hoc Analysis of a Prospective International Registry.

PURPOSE: To examine the independent and incremental value of CT-derived quantitative burden and attenuation of COVID-19 pneumonia for the prediction of clinical deterioration or death. METHODS: This was a retrospective analysis of a prospective international registry of consecutive patients with laboratory-confirmed COVID-19 and chest CT imaging, admitted to four centers between January 10 and May 6, 2020. Total burden (expressed as a percentage) and mean attenuation of ground glass opacities (GGO) and consolidation were quantified from CT using semi-automated research software. The primary outcome was clinical deterioration (intensive care unit admission, invasive mechanical ventilation, or vasopressor therapy) or in-hospital death. Logistic regression was performed to assess the predictive value of clinical and CT parameters for the primary outcome. RESULTS: The final population comprised 120 patients (mean age 64 ± 16 years, 78 men), of whom 39 (32.5%) experienced clinical deterioration or death. In multivariable regression of clinical and CT parameters, consolidation burden (odds ratio [OR], 3.4; 95% confidence interval [CI]: 1.7, 6.9 per doubling; P = .001) and increasing GGO attenuation (OR, 3.2; 95% CI: 1.3, 8.3 per standard deviation, P = .02) were independent predictors of deterioration or death; as was C-reactive protein (OR, 2.1; 95% CI: 1.3, 3.4 per doubling; P = .004), history of heart failure (OR 1.3; 95% CI: 1.1, 1.6, P = .01), and chronic lung disease (OR, 1.3; 95% CI: 1.0, 1.6; P = .02). Quantitative CT measures added incremental predictive value beyond a model with only clinical parameters (area under the curve, 0.93 vs 0.82, P = .006). The optimal prognostic cutoffs for burden of COVID-19 pneumonia as determined by Youden's index were consolidation of greater than or equal to 1.8% and GGO of greater than or equal to 13.5%. CONCLUSIONS: Quantitative burden of consolidation or GGO on chest CT independently predict clinical deterioration or death in patients with COVID-19 pneumonia. CT-derived measures have incremental prognostic value over and above clinical parameters, and may be useful for risk stratifying patients with COVID-19.