RESUMEN
BACKGROUND & AIMS: Accurate diagnosis of sarcopenia requires evaluation of muscle quality, which refers to the amount of fat infiltration in muscle tissue. In this study, we aim to investigate whether we can independently predict mortality risk in transcatheter aortic valve implantation (TAVI) patients, using automatic deep learning algorithms to assess muscle quality on procedural computed tomography (CT) scans. METHODS: This study included 1199 patients with severe aortic stenosis who underwent transcatheter aortic valve implantation (TAVI) between January 2010 and January 2020. A procedural CT scan was performed as part of the preprocedural-TAVI evaluation, and the scans were analyzed using deep-learning-based software to automatically determine skeletal muscle density (SMD) and intermuscular adipose tissue (IMAT). The association of SMD and IMAT with all-cause mortality was analyzed using a Cox regression model, adjusted for other known mortality predictors, including muscle mass. RESULTS: The mean age of the participants was 80 ± 7 years, 53% were female. The median observation time was 1084 days, and the overall mortality rate was 39%. We found that the lowest tertile of muscle quality, as determined by SMD, was associated with an increased risk of mortality (HR 1.40 [95%CI: 1.15-1.70], p < 0.01). Similarly, low muscle quality as defined by high IMAT in the lowest tertile was also associated with increased mortality risk (HR 1.24 [95%CI: 1.01-1.52], p = 0.04). CONCLUSIONS: Our findings suggest that deep learning-assessed low muscle quality, as indicated by fat infiltration in muscle tissue, is a practical, useful and independent predictor of mortality after TAVI.
RESUMEN
Label noise hampers supervised training of neural networks. However, data without label noise is often infeasible to attain, especially for medical tasks. Attaining high-quality medical labels would require a pool of experts and their consensus reading, which would be extremely costly. Several methods have been proposed to mitigate the adverse effects of label noise during training. State-of-the-art methods use multiple networks that exploit different decision boundaries to identify label noise. Among the best performing methods is co-teaching. However, co-teaching comes with the requirement of knowing label noise a priori. Hence, we propose a co-teaching method that does not require any prior knowledge about the level of label noise. We introduce stochasticity to select or reject training instances. We have extensively evaluated the method on synthetic experiments with extreme label noise levels and applied it to real-world medical problems of ECG classification and cardiac MRI segmentation. Results show that the approach is robust to its hyperparameter choice and applies to various classification tasks with unknown levels of label noise.
Asunto(s)
Efectos Colaterales y Reacciones Adversas Relacionados con Medicamentos , Humanos , Consenso , Conocimiento , Redes Neurales de la ComputaciónRESUMEN
AIMS: Left ventricular ejection fraction (LVEF) is suboptimal as a sole marker for predicting sudden cardiac death (SCD). Machine learning (ML) provides new opportunities for personalized predictions using complex, multimodal data. This study aimed to determine if risk stratification for implantable cardioverter-defibrillator (ICD) implantation can be improved by ML models that combine clinical variables with 12-lead electrocardiograms (ECG) time-series features. METHODS AND RESULTS: A multicentre study of 1010 patients (64.9 ± 10.8 years, 26.8% female) with ischaemic, dilated, or non-ischaemic cardiomyopathy, and LVEF ≤ 35% implanted with an ICD between 2007 and 2021 for primary prevention of SCD in two academic hospitals was performed. For each patient, a raw 12-lead, 10-s ECG was obtained within 90 days before ICD implantation, and clinical details were collected. Supervised ML models were trained and validated on a development cohort (n = 550) from Hospital A to predict ICD non-arrhythmic mortality at three-year follow-up (i.e. mortality without prior appropriate ICD-therapy). Model performance was evaluated on an external patient cohort from Hospital B (n = 460). At three-year follow-up, 16.0% of patients had died, with 72.8% meeting criteria for non-arrhythmic mortality. Extreme gradient boosting models identified patients with non-arrhythmic mortality with an area under the receiver operating characteristic curve (AUROC) of 0.90 [95% confidence intervals (CI) 0.80-1.00] during internal validation. In the external cohort, the AUROC was 0.79 (95% CI 0.75-0.84). CONCLUSIONS: ML models combining ECG time-series features and clinical variables were able to predict non-arrhythmic mortality within three years after device implantation in a primary prevention population, with robust performance in an independent cohort.
Asunto(s)
Desfibriladores Implantables , Humanos , Femenino , Masculino , Selección de Paciente , Volumen Sistólico , Función Ventricular Izquierda , Aprendizaje Automático , Muerte Súbita Cardíaca/etiología , Muerte Súbita Cardíaca/prevención & control , Prevención PrimariaRESUMEN
BACKGROUND: Body composition during childhood may predispose to negative health outcomes later in life. Automatic segmentation may assist in quantifying pediatric body composition in children. OBJECTIVE: To evaluate automatic segmentation for body composition on pediatric computed tomography (CT) scans and to provide normative data on muscle and fat areas throughout childhood using automatic segmentation. MATERIALS AND METHODS: In this pilot study, 537 children (ages 1-17 years) who underwent abdominal CT after high-energy trauma at a Dutch tertiary center (2002-2019) were retrospectively identified. Of these, the CT images of 493 children (66% boys) were used to establish normative data. Muscle (psoas, paraspinal and abdominal wall) and fat (subcutaneous and visceral) areas were measured at the third lumbar vertebral (L3) level by automatic segmentation. A representative subset of 52 scans was also manually segmented to evaluate the performance of automatic segmentation. RESULTS: For manually-segmented versus automatically-segmented areas (52 scans), mean Dice coefficients were high for muscle (0.87-0.90) and subcutaneous fat (0.88), but lower for visceral fat (0.60). In the control group, muscle area was comparable for both sexes until the age of 13 years, whereafter, boys developed relatively more muscle. From a young age, boys were more prone to visceral fat storage than girls. Overall, boys had significantly higher visceral-to-subcutaneous fat ratios (median 1.1 vs. 0.6, P<0.01) and girls higher fat-to-muscle ratios (median 1.0 vs. 0.7, P<0.01). CONCLUSION: Automatic segmentation of L3-level muscle and fat areas allows for accurate quantification of pediatric body composition. Using automatic segmentation, the development in muscle and fat distribution during childhood (in otherwise healthy) Dutch children was demonstrated.
Asunto(s)
Composición Corporal , Tomografía Computarizada por Rayos X , Masculino , Femenino , Humanos , Niño , Adolescente , Proyectos Piloto , Estudios Retrospectivos , Tomografía Computarizada por Rayos X/métodos , Grasa SubcutáneaRESUMEN
Since the onset of computer-aided diagnosis in medical imaging, voxel-based segmentation has emerged as the primary methodology for automatic analysis of left ventricle (LV) function and morphology in cardiac magnetic resonance images (CMRI). In standard clinical practice, simultaneous multi-slice 2D cine short-axis MR imaging is performed under multiple breath-holds resulting in highly anisotropic 3D images. Furthermore, sparse-view CMRI often lacks whole heart coverage caused by large slice thickness and often suffers from inter-slice misalignment induced by respiratory motion. Therefore, these volumes only provide limited information about the true 3D cardiac anatomy which may hamper highly accurate assessment of functional and anatomical abnormalities. To address this, we propose a method that learns a continuous implicit function representing 3D LV shapes by training an auto-decoder. For training, high-resolution segmentations from cardiac CT angiography are used. The ability of our approach to reconstruct and complete high-resolution shapes from manually or automatically obtained sparse-view cardiac shape information is evaluated by using paired high- and low-resolution CMRI LV segmentations. The results show that the reconstructed LV shapes have an unconstrained subvoxel resolution and appear smooth and plausible in through-plane direction. Furthermore, Bland-Altman analysis reveals that reconstructed high-resolution ventricle volumes are closer to the corresponding reference volumes than reference low-resolution volumes with bias of [limits of agreement] -3.51 [-18.87, 11.85] mL, and 12.96 [-10.01, 35.92] mL respectively. Finally, the results demonstrate that the proposed approach allows recovering missing shape information and can indirectly correct for limited motion-induced artifacts.
Asunto(s)
Corazón , Imagen por Resonancia Cinemagnética , Imagen por Resonancia Cinemagnética/métodos , Corazón/diagnóstico por imagen , Imagen por Resonancia Magnética , Ventrículos Cardíacos , Función Ventricular IzquierdaRESUMEN
BACKGROUND: Arrhythmogenic right ventricular cardiomyopathy (ARVC) is diagnosed according to the Task Force Criteria (TFC) in which cardiovascular magnetic resonance (CMR) imaging plays an important role. Our study aims to apply an automatic deep learning-based segmentation for right and left ventricular CMR assessment and evaluate this approach for classification of the CMR TFC. METHODS: We included 227 subjects suspected of ARVC who underwent CMR. Subjects were classified into (1) ARVC patients fulfilling TFC; (2) at-risk family members; and (3) controls. To perform automatic segmentation, a Bayesian Dilated Residual Neural Network was trained and tested. Performance of automatic versus manual segmentation was assessed using Dice-coefficient and Hausdorff distance. Since automatic segmentation is most challenging in basal slices, manual correction of the automatic segmentation in the most basal slice was simulated (automatic-basal). CMR TFC calculated using manual and automatic-basal segmentation were compared using Cohen's Kappa (κ). RESULTS: Automatic segmentation was trained on CMRs of 70 subjects (39.6 ± 18.1 years, 47% female) and tested on 157 subjects (36.9 ± 17.6 years, 59% female). Dice-coefficient and Hausdorff distance showed good agreement between manual and automatic segmentations (≥ 0.89 and ≤ 10.6 mm, respectively) which further improved after simulated correction of the most basal slice (≥ 0.92 and ≤ 9.2 mm, p < 0.001). Pearson correlation of volumetric and functional CMR measurements was good to excellent (automatic (r = 0.78-0.99, p < 0.001) and automatic-basal (r = 0.88-0.99, p < 0.001) measurements). CMR TFC classification using automatic-basal segmentations was comparable to manual segmentations (κ 0.98 ± 0.02) with comparable diagnostic performance. CONCLUSIONS: Combining automatic segmentation of CMRs with correction of the most basal slice results in accurate CMR TFC classification of subjects suspected of ARVC.
Asunto(s)
Displasia Ventricular Derecha Arritmogénica , Humanos , Femenino , Masculino , Displasia Ventricular Derecha Arritmogénica/diagnóstico por imagen , Teorema de Bayes , Imagen por Resonancia Cinemagnética/métodos , Imagen por Resonancia Magnética , Ventrículos Cardíacos , Espectroscopía de Resonancia MagnéticaRESUMEN
Purpose: Coronary artery calcium (CAC) score, i.e., the amount of CAC quantified in CT, is a strong and independent predictor of coronary heart disease (CHD) events. However, CAC scoring suffers from limited interscan reproducibility, which is mainly due to the clinical definition requiring application of a fixed intensity level threshold for segmentation of calcifications. This limitation is especially pronounced in non-electrocardiogram-synchronized computed tomography (CT) where lesions are more impacted by cardiac motion and partial volume effects. Therefore, we propose a CAC quantification method that does not require a threshold for segmentation of CAC. Approach: Our method utilizes a generative adversarial network (GAN) where a CT with CAC is decomposed into an image without CAC and an image showing only CAC. The method, using a cycle-consistent GAN, was trained using 626 low-dose chest CTs and 514 radiotherapy treatment planning (RTP) CTs. Interscan reproducibility was compared to clinical calcium scoring in RTP CTs of 1662 patients, each having two scans. Results: A lower relative interscan difference in CAC mass was achieved by the proposed method: 47% compared to 89% manual clinical calcium scoring. The intraclass correlation coefficient of Agatston scores was 0.96 for the proposed method compared to 0.91 for automatic clinical calcium scoring. Conclusions: The increased interscan reproducibility achieved by our method may lead to increased reliability of CHD risk categorization and improved accuracy of CHD event prediction.
RESUMEN
Background: Manual muscle mass assessment based on Computed Tomography (CT) scans is recognized as a good marker for malnutrition, sarcopenia, and adverse outcomes. However, manual muscle mass analysis is cumbersome and time consuming. An accurate fully automated method is needed. In this study, we evaluate if manual psoas annotation can be substituted by a fully automatic deep learning-based method. Methods: This study included a cohort of 583 patients with severe aortic valve stenosis planned to undergo Transcatheter Aortic Valve Replacement (TAVR). Psoas muscle area was annotated manually on the CT scan at the height of lumbar vertebra 3 (L3). The deep learning-based method mimics this approach by first determining the L3 level and subsequently segmenting the psoas at that level. The fully automatic approach was evaluated as well as segmentation and slice selection, using average bias 95% limits of agreement, Intraclass Correlation Coefficient (ICC) and within-subject Coefficient of Variation (CV). To evaluate performance of the slice selection visual inspection was performed. To evaluate segmentation Dice index was computed between the manual and automatic segmentations (0 = no overlap, 1 = perfect overlap). Results: Included patients had a mean age of 81 ± 6 and 45% was female. The fully automatic method showed a bias and limits of agreement of -0.69 [-6.60 to 5.23] cm2, an ICC of 0.78 [95% CI: 0.74-0.82] and a within-subject CV of 11.2% [95% CI: 10.2-12.2]. For slice selection, 84% of the selections were on the same vertebra between methods, bias and limits of agreement was 3.4 [-24.5 to 31.4] mm. The Dice index for segmentation was 0.93 ± 0.04, bias and limits of agreement was -0.55 [1.71-2.80] cm2. Conclusion: Fully automatic assessment of psoas muscle area demonstrates accurate performance at the L3 level in CT images. It is a reliable tool that offers great opportunities for analysis in large scale studies and in clinical applications.
RESUMEN
High-resolution medical images are beneficial for analysis but their acquisition may not always be feasible. Alternatively, high-resolution images can be created from low-resolution acquisitions using conventional upsampling methods, but such methods cannot exploit high-level contextual information contained in the images. Recently, better performing deep-learning based super-resolution methods have been introduced. However, these methods are limited by their supervised character, i.e. they require high-resolution examples for training. Instead, we propose an unsupervised deep learning semantic interpolation approach that synthesizes new intermediate slices from encoded low-resolution examples. To achieve semantically smooth interpolation in through-plane direction, the method exploits the latent space generated by autoencoders. To generate new intermediate slices, latent space encodings of two spatially adjacent slices are combined using their convex combination. Subsequently, the combined encoding is decoded to an intermediate slice. To constrain the model, a notion of semantic similarity is defined for a given dataset. For this, a new loss is introduced that exploits the spatial relationship between slices of the same volume. During training, an existing in-between slice is generated using a convex combination of its neighboring slice encodings. The method was trained and evaluated using publicly available cardiac cine, neonatal brain and adult brain MRI scans. In all evaluations, the new method produces significantly better results in terms of Structural Similarity Index Measure and Peak Signal-to-Noise Ratio (p<0.001 using one-sided Wilcoxon signed-rank test) than a cubic B-spline interpolation approach. Given the unsupervised nature of the method, high-resolution training data is not required and hence, the method can be readily applied in clinical settings.
Asunto(s)
Corazón , Imagen por Resonancia Magnética , Adulto , Anisotropía , Encéfalo/diagnóstico por imagen , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Recién Nacido , Imagen por Resonancia Magnética/métodos , Relación Señal-RuidoRESUMEN
PURPOSE: To examine the prognostic value of location-specific arterial calcification quantities at lung screening low-dose CT for the prediction of cardiovascular disease (CVD) mortality. MATERIALS AND METHODS: This retrospective study included 5564 participants who underwent low-dose CT from the National Lung Screening Trial between August 2002 and April 2004, who were followed until December 2009. A deep learning network was trained to quantify six types of vascular calcification: thoracic aorta calcification (TAC); aortic and mitral valve calcification; and coronary artery calcification (CAC) of the left main, the left anterior descending, and the right coronary artery. TAC and CAC were determined in six evenly distributed slabs spatially aligned among chest CT images. CVD mortality prediction was performed with multivariable logistic regression using least absolute shrinkage and selection operator. The methods were compared with semiautomatic baseline prediction using self-reported participant characteristics, such as age, history of smoking, and history of illness. Statistical significance between the prediction models was tested using the nonparametric DeLong test. RESULTS: The prediction model was trained with data from 4451 participants (median age, 61 years; 37.9% women) and then tested on data from 1113 participants (median age, 61 years; 37.9% women). The prediction model using calcium scores achieved a C statistic of 0.74 (95% CI: 0.69, 0.79), and it outperformed the baseline model using only participant characteristics (C statistic, 0.69; P = .049). Best results were obtained when combining all variables (C statistic, 0.76; P < .001). CONCLUSION: Five-year CVD mortality prediction using automatically extracted image-based features is feasible at lung screening low-dose CT.© RSNA, 2021.
RESUMEN
Segmentation of cardiac anatomical structures in cardiac magnetic resonance images (CMRI) is a prerequisite for automatic diagnosis and prognosis of cardiovascular diseases. To increase robustness and performance of segmentation methods this study combines automatic segmentation and assessment of segmentation uncertainty in CMRI to detect image regions containing local segmentation failures. Three existing state-of-the-art convolutional neural networks (CNN) were trained to automatically segment cardiac anatomical structures and obtain two measures of predictive uncertainty: entropy and a measure derived by MC-dropout. Thereafter, using the uncertainties another CNN was trained to detect local segmentation failures that potentially need correction by an expert. Finally, manual correction of the detected regions was simulated in the complete set of scans of 100 patients and manually performed in a random subset of scans of 50 patients. Using publicly available CMR scans from the MICCAI 2017 ACDC challenge, the impact of CNN architecture and loss function for segmentation, and the uncertainty measure was investigated. Performance was evaluated using the Dice coefficient, 3D Hausdorff distance and clinical metrics between manual and (corrected) automatic segmentation. The experiments reveal that combining automatic segmentation with manual correction of detected segmentation failures results in improved segmentation and to 10-fold reduction of expert time compared to manual expert segmentation.
Asunto(s)
Enfermedades Cardiovasculares/diagnóstico por imagen , Corazón/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodos , Imagenología Tridimensional/métodos , Imagen por Resonancia Magnética/métodos , Corazón/anatomía & histología , Humanos , Redes Neurales de la ComputaciónRESUMEN
In this study, we propose a fast and accurate method to automatically localize anatomical landmarks in medical images. We employ a global-to-local localization approach using fully convolutional neural networks (FCNNs). First, a global FCNN localizes multiple landmarks through the analysis of image patches, performing regression and classification simultaneously. In regression, displacement vectors pointing from the center of image patches towards landmark locations are determined. In classification, presence of landmarks of interest in the patch is established. Global landmark locations are obtained by averaging the predicted displacement vectors, where the contribution of each displacement vector is weighted by the posterior classification probability of the patch that it is pointing from. Subsequently, for each landmark localized with global localization, local analysis is performed. Specialized FCNNs refine the global landmark locations by analyzing local sub-images in a similar manner, i.e. by performing regression and classification simultaneously and combining the results. Evaluation was performed through localization of 8 anatomical landmarks in CCTA scans, 2 landmarks in olfactory MR scans, and 19 landmarks in cephalometric X-rays. We demonstrate that the method performs similarly to a second observer and is able to localize landmarks in a diverse set of medical images, differing in image modality, image dimensionality, and anatomical coverage.
Asunto(s)
Algoritmos , Aprendizaje Profundo , Puntos Anatómicos de Referencia/diagnóstico por imagen , Redes Neurales de la Computación , Reproducibilidad de los ResultadosRESUMEN
Cardiovascular imaging is going to change substantially in the next decade, fueled by the deep learning revolution. For medical professionals, it is important to keep track of these developments to ensure that deep learning can have meaningful impact on clinical practice. This review aims to be a stepping stone in this process. The general concepts underlying most successful deep learning algorithms are explained, and an overview of the state-of-the-art deep learning in cardiovascular imaging is provided. This review discusses >80 papers, covering modalities ranging from cardiac magnetic resonance, computed tomography, and single-photon emission computed tomography, to intravascular optical coherence tomography and echocardiography. Many different machines learning algorithms were used throughout these papers, with the most common being convolutional neural networks. Recent algorithms such as generative adversarial models were also used. The potential implications of deep learning algorithms on clinical practice, now and in the near future, are discussed.
Asunto(s)
Técnicas de Imagen Cardíaca , Enfermedades Cardiovasculares/diagnóstico por imagen , Aprendizaje Profundo , Interpretación de Imagen Asistida por Computador , Humanos , Valor Predictivo de las Pruebas , Reproducibilidad de los ResultadosRESUMEN
Cardiovascular disease (CVD) is the global leading cause of death. A strong risk factor for CVD events is the amount of coronary artery calcium (CAC). To meet the demands of the increasing interest in quantification of CAC, i.e., coronary calcium scoring, especially as an unrequested finding for screening and research, automatic methods have been proposed. The current automatic calcium scoring methods are relatively computationally expensive and only provide scores for one type of CT. To address this, we propose a computationally efficient method that employs two convolutional neural networks: the first performs registration to align the fields of view of input CTs and the second performs direct regression of the calcium score, thereby circumventing time-consuming intermediate CAC segmentation. Optional decision feedback provides insight into the regions that are contributed to the calcium score. Experiments were performed using 903 cardiac CT and 1687 chest CT scans. The method predicted calcium scores in less than 0.3 s. The intra-class correlation coefficient between predicted and manual calcium scores was 0.98 for both cardiac and chest CT. The method showed almost perfect agreement between automatic and manual CVD risk categorization in both the datasets, with a linearly weighted Cohen's kappa of 0.95 in cardiac CT and 0.93 in chest CT. Performance is similar to that of the state-of-the-art methods, but the proposed method is hundreds of times faster. By providing visual feedback, insight is given in the decision process, making it readily implementable in clinical and research settings.
Asunto(s)
Enfermedad de la Arteria Coronaria/diagnóstico por imagen , Interpretación de Imagen Asistida por Computador/métodos , Tomografía Computarizada por Rayos X/métodos , Calcificación Vascular/diagnóstico por imagen , Vasos Coronarios/diagnóstico por imagen , Aprendizaje Profundo , Técnicas de Diagnóstico Cardiovascular , Humanos , Radiografía TorácicaRESUMEN
Image registration, the process of aligning two or more images, is the core technique of many (semi-)automatic medical image analysis tasks. Recent studies have shown that deep learning methods, notably convolutional neural networks (ConvNets), can be used for image registration. Thus far training of ConvNets for registration was supervised using predefined example registrations. However, obtaining example registrations is not trivial. To circumvent the need for predefined examples, and thereby to increase convenience of training ConvNets for image registration, we propose the Deep Learning Image Registration (DLIR) framework for unsupervised affine and deformable image registration. In the DLIR framework ConvNets are trained for image registration by exploiting image similarity analogous to conventional intensity-based image registration. After a ConvNet has been trained with the DLIR framework, it can be used to register pairs of unseen images in one shot. We propose flexible ConvNets designs for affine image registration and for deformable image registration. By stacking multiple of these ConvNets into a larger architecture, we are able to perform coarse-to-fine image registration. We show for registration of cardiac cine MRI and registration of chest CT that performance of the DLIR framework is comparable to conventional image registration while being several orders of magnitude faster.
Asunto(s)
Aprendizaje Profundo , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Cinemagnética/métodos , Tomografía Computarizada por Rayos X/métodos , Aprendizaje Automático no Supervisado , Cardiopatías/diagnóstico por imagen , Humanos , Imagenología Tridimensional , Redes Neurales de la Computación , Radiografía Torácica/métodosRESUMEN
INTRODUCTION: The amount of coronary artery calcium determined in CT scans is a well established predictor of cardiovascular events. However, high interscan variability of coronary calcium quantification may lead to incorrect cardiovascular risk assignment. Partial volume effect contributes to high interscan variability. Hence, we propose a method for coronary calcium quantification employing partial volume correction. METHODS: Two phantoms containing artificial coronary artery calcifications and 293 subject chest CT scans were used. The first and second phantom contained nine calcifications and the second phantom contained three artificial arteries with three calcifications of different volumes, shapes and densities. The first phantom was scanned five times with and without extension rings. The second phantom was scanned three times without and with simulated cardiac motion (10 and 30 mm/s). Chest CT scans were acquired without ECG-synchronization and reconstructed using sharp and soft kernels. Coronary calcifications were annotated employing the clinically used intensity value thresholding (130 HU). Thereafter, a threshold separating each calcification from its background was determined using an Expectation-Maximization algorithm. Finally, for each lesion the partial content of calcification in each voxel was determined depending on its intensity and the determined threshold. RESULTS: Clinical calcium scoring resulted in overestimation of calcium volume for medium and high density calcifications in the first phantom, and overestimation of calcium volume for high density and underestimation for low density calcifications in the second phantom. With induced motion these effects were further emphasized. The proposed quantification resulted in better accuracy and substantially lower over- and underestimation of calcium volume even in presence of motion. In chest CT, the agreement between calcium scores from the two reconstructions improved when proposed method was used. CONCLUSION: Compared with clinical calcium scoring, proposed quantification provides a better estimate of the true calcium volume in phantoms and better agreement in calcium scores between different subject scan reconstructions.
Asunto(s)
Calcio/metabolismo , Enfermedad de la Arteria Coronaria/diagnóstico por imagen , Enfermedad de la Arteria Coronaria/metabolismo , Vasos Coronarios/diagnóstico por imagen , Vasos Coronarios/metabolismo , Calcificación Vascular/diagnóstico por imagen , Calcificación Vascular/metabolismo , Algoritmos , Humanos , Fantasmas de Imagen , Interpretación de Imagen Radiográfica Asistida por Computador/estadística & datos numéricos , Reproducibilidad de los Resultados , Tórax/diagnóstico por imagen , Tomografía Computarizada por Rayos X/estadística & datos numéricosRESUMEN
Heavy smokers undergoing screening with low-dose chest CT are affected by cardiovascular disease as much as by lung cancer. Low-dose chest CT scans acquired in screening enable quantification of atherosclerotic calcifications and thus enable identification of subjects at increased cardiovascular risk. This paper presents a method for automatic detection of coronary artery, thoracic aorta, and cardiac valve calcifications in low-dose chest CT using two consecutive convolutional neural networks. The first network identifies and labels potential calcifications according to their anatomical location and the second network identifies true calcifications among the detected candidates. This method was trained and evaluated on a set of 1744 CT scans from the National Lung Screening Trial. To determine whether any reconstruction or only images reconstructed with soft tissue filters can be used for calcification detection, we evaluated the method on soft and medium/sharp filter reconstructions separately. On soft filter reconstructions, the method achieved F1 scores of 0.89, 0.89, 0.67, and 0.55 for coronary artery, thoracic aorta, aortic valve, and mitral valve calcifications, respectively. On sharp filter reconstructions, the F1 scores were 0.84, 0.81, 0.64, and 0.66, respectively. Linearly weighted kappa coefficients for risk category assignment based on per subject coronary artery calcium were 0.91 and 0.90 for soft and sharp filter reconstructions, respectively. These results demonstrate that the presented method enables reliable automatic cardiovascular risk assessment in all low-dose chest CT scans acquired for lung cancer screening.
Asunto(s)
Calcinosis/diagnóstico por imagen , Redes Neurales de la Computación , Radiografía Torácica/métodos , Tomografía Computarizada por Rayos X/métodos , Anciano , Algoritmos , Válvula Aórtica/diagnóstico por imagen , Válvula Aórtica/patología , Estenosis de la Válvula Aórtica/diagnóstico por imagen , Enfermedad de la Arteria Coronaria/diagnóstico por imagen , Vasos Coronarios/diagnóstico por imagen , Humanos , Neoplasias Pulmonares/diagnóstico por imagen , Persona de Mediana EdadRESUMEN
The amount of coronary artery calcification (CAC) quantified in computed tomography (CT) scans enables prediction of cardiovascular disease (CVD) risk. However, interscan variability of CAC quantification is high, especially in scans made without ECG synchronization. We propose a method for automatic detection of CACs that are severely affected by cardiac motion. Subsequently, we evaluate the impact of such CACs on CAC quantification and CVD risk determination. This study includes 1000 baseline and 585 one-year follow-up low-dose chest CTs from the National Lung Screening Trial. About 415 baseline scans are used to train and evaluate a convolutional neural network that identifies observer determined CACs affected by severe motion artifacts. Therefore, 585 paired scans acquired at baseline and follow-up were used to evaluate the impact of severe motion artifacts on CAC quantification and risk categorization. Based on the CAC amount, the scans were categorized into four standard CVD risk categories. The method identified CACs affected by severe motion artifacts with 85.2% accuracy. Moreover, reproducibility of CAC scores in scan pairs is higher in scans containing mostly CACs not affected by severe cardiac motion. Hence, the proposed method enables identification of scans affected by severe cardiac motion, where CAC quantification may not be reproducible.
RESUMEN
BACKGROUND: We investigated fully automatic coronary artery calcium (CAC) scoring and cardiovascular disease (CVD) risk categorization from CT attenuation correction (CTAC) acquired at rest and stress during cardiac PET/CT and compared it with manual annotations in CTAC and with dedicated calcium scoring CT (CSCT). METHODS AND RESULTS: We included 133 consecutive patients undergoing myocardial perfusion 82Rb PET/CT with the acquisition of low-dose CTAC at rest and stress. Additionally, a dedicated CSCT was performed for all patients. Manual CAC annotations in CTAC and CSCT provided the reference standard. In CTAC, CAC was scored automatically using a previously developed machine learning algorithm. Patients were assigned to a CVD risk category based on their Agatston score (0, 1-10, 11-100, 101-400, >400). Agreement in CVD risk categorization between manual and automatic scoring in CTAC at rest and stress resulted in Cohen's linearly weighted κ of 0.85 and 0.89, respectively. The agreement between CSCT and CTAC at rest resulted in κ of 0.82 and 0.74, using manual and automatic scoring, respectively. For CTAC at stress, these were 0.79 and 0.70, respectively. CONCLUSION: Automatic CAC scoring from CTAC PET/CT may allow routine CVD risk assessment from the CTAC component of PET/CT without any additional radiation dose or scan time.
Asunto(s)
Enfermedades Cardiovasculares/etiología , Imagen de Perfusión Miocárdica/métodos , Tomografía Computarizada por Tomografía de Emisión de Positrones/métodos , Tomografía de Emisión de Positrones/métodos , Adulto , Anciano , Anciano de 80 o más Años , Calcio/análisis , Enfermedades Cardiovasculares/diagnóstico por imagen , Vasos Coronarios/diagnóstico por imagen , Femenino , Humanos , Masculino , Persona de Mediana Edad , Radioisótopos de RubidioRESUMEN
Regrettably an error was introduced in Table 3 during the article's production. The very first cell (row: Very low 0; column: Very low) should read '12' and not '21' as originally published.