RESUMO
BACKGROUND: Lung compliance, a biomarker of pulmonary fibrosis, is generally measured globally. Hyperpolarized 129Xe gas MRI offers the potential to evaluate lung compliance regionally, allowing for visualization of changes in lung compliance associated with fibrosis. PURPOSE: To assess global and regional lung compliance in a rat model of pulmonary fibrosis using hyperpolarized 129Xe gas MRI. STUDY TYPE: Prospective. ANIMAL MODEL: Twenty Sprague-Dawley male rats with bleomycin-induced fibrosis model (N = 10) and saline-treated controls (N = 10). FIELD STRENGTH/SEQUENCE: 7-T, fast low-angle shot (FLASH) sequence. ASSESSMENT: Lung compliance was determined by fitting lung volumes derived from segmented 129Xe MRI with an iterative selection method, to corresponding airway pressures. Similarly, lung compliance was obtained with computed tomography for cross-validation. Direction-dependencies of lung compliance were characterized by regional lung compliance ratios (R) in different directions. Pulmonary function tests (PFTs) and histological analysis were used to validate the pulmonary fibrosis model and assess its correlation with 129Xe lung compliance. STATISTICAL TESTS: Shapiro-Wilk tests, unpaired and paired t-tests, Mann-Whitney U and Wilcoxon signed-rank tests, and Pearson correlation coefficients. P < 0.05 was considered statistically significant. RESULTS: For the entire lung, the global and regional lung compliance measured with 129Xe gas MRI showed significant differences between the groups, and correlated with the global lung compliance measured using PFTs (global: r = 0.891; regional: r = 0.873). Additionally, for the control group, significant difference was found in mean regional compliance between areas, eg, 0.37 (0.32, 0.39) × 10-4 mL/cm H2O and 0.47 (0.41, 0.56) × 10-4 mL/cm H2O for apical and basal lung, respectively. The apical-basal direction R was 1.12 ± 0.09 and 1.35 ± 0.13 for fibrosis and control groups, respectively, indicating a significant difference. DATA CONCLUSION: Our findings demonstrate the feasibility of using hyperpolarized gas MRI to assess regional lung compliance. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 1.
RESUMO
PURPOSE: To demonstrate the feasibility of zigzag sampling for 3D rapid hyperpolarized 129Xe ventilation MRI in human. METHODS: Zigzag sampling in one direction was combined with gradient-recalled echo sequence (GRE-zigzag-Y) to acquire hyperpolarized 129Xe ventilation images. Image quality was compared with a balanced SSFP (bSSFP) sequence with the same spatial resolution for 12 healthy volunteers (HVs). For another 8 HVs and 9 discharged coronavirus disease 2019 subjects, isotropic resolution 129Xe ventilation images were acquired using zigzag sampling in two directions through GRE-zigzag-YZ. 129Xe ventilation defect percent (VDP) was quantified for GRE-zigzag-YZ and bSSFP acquisitions. Relationships and agreement between these VDP measurements were evaluated using Pearson correlation coefficient (r) and Bland-Altman analysis. RESULTS: For 12 HVs, GRE-zigzag-Y and bSSFP required 2.2 s and 10.5 s, respectively, to acquire 129Xe images with a spatial resolution of 3.96 × 3.96 × 10.5 mm3. Structural similarity index, mean absolute error, and Dice similarity coefficient between the two sets of images and ventilated lung regions were 0.85 ± 0.03, 0.0015 ± 0.0001, and 0.91 ± 0.02, respectively. For another 8 HVs and 9 coronavirus disease 2019 subjects, 129Xe images with a nominal spatial resolution of 2.5 × 2.5 × 2.5 mm3 were acquired within 5.5 s per subject using GRE-zigzag-YZ. VDP provided by GRE-zigzag-YZ was strongly correlated (R2 = 0.93, p < 0.0001) with that generated by bSSFP with minimal biases (bias = -0.005%, 95% limit-of-agreement = [-0.414%, 0.424%]). CONCLUSION: Zigzag sampling combined with GRE sequence provides a way for rapid 129Xe ventilation imaging.
Assuntos
COVID-19 , Pulmão , Imageamento por Ressonância Magnética , SARS-CoV-2 , Isótopos de Xenônio , Humanos , COVID-19/diagnóstico por imagem , Imageamento por Ressonância Magnética/métodos , Masculino , Feminino , Adulto , Pulmão/diagnóstico por imagem , Pessoa de Meia-Idade , Imageamento Tridimensional/métodos , Estudos de ViabilidadeRESUMO
OBJECTIVE: To comprehensively assess the impact of aging, cigarette smoking, and chronic obstructive pulmonary disease (COPD) on pulmonary physiology using 129Xe MR. METHODS: A total of 90 subjects were categorized into four groups, including healthy young (HY, n = 20), age-matched control (AMC, n = 20), asymptomatic smokers (AS, n = 28), and COPD patients (n = 22). 129Xe MR was utilized to obtain pulmonary physiological parameters, including ventilation defect percent (VDP), alveolar sleeve depth (h), apparent diffusion coefficient (ADC), total septal wall thickness (d), and ratio of xenon signal from red blood cells and interstitial tissue/plasma (RBC/TP). RESULTS: Significant differences were found in the measured VDP (p = 0.035), h (p = 0.003), and RBC/TP (p = 0.003) between the HY and AMC groups. Compared with the AMC group, higher VDP (p = 0.020) and d (p = 0.048) were found in the AS group; higher VDP (p < 0.001), d (p < 0.001) and ADC (p < 0.001), and lower h (p < 0.001) and RBC/TP (p < 0.001) were found in the COPD group. Moreover, significant differences were also found in the measured VDP (p < 0.001), h (p < 0.001), ADC (p < 0.001), d (p = 0.008), and RBC/TP (p = 0.032) between the AS and COPD groups. CONCLUSION: Our findings indicate that pulmonary structure and functional changes caused by aging, cigarette smoking, and COPD are various, and show a progressive deterioration with the accumulation of these risk factors, including cigarette smoking and COPD. CLINICAL RELEVANCE STATEMENT: Pathophysiological changes can be difficult to comprehensively understand due to limitations in common techniques and multifactorial etiologies. 129Xe MRI can demonstrate structural and functional changes caused by several common factors and can be used to better understand patients' underlying pathology. KEY POINTS: Standard techniques for assessing pathophysiological lung function changes, spirometry, and chest CT come with limitations. 129Xe MR demonstrated progressive deterioration with accumulation of the investigated risk factors, without these limitations. 129Xe MR can assess lung changes related to these risk factors to stage and evaluate the etiology of the disease.
RESUMO
OBJECTIVE: Investigate the capacity of MRI to evaluate efficacy of radiofrequency (RF) ablations delivered to MRI-defined arrhythmogenic substrates. METHODS: Baseline MRI was performed at 3 T including 3D LGE in a swine model of chronic myocardial infarct (N = 8). MRI-derived maps of scar and heterogeneous tissue channels (HTCs) were generated using ADAS 3D. Animals underwent electroanatomic mapping and ablation of the left ventricle in CARTO3, guided by MRI-derived scar maps. Post-ablation MRI (in vivo at 3 T in 5/8 animals; ex vivo at 1.5 T in 3/8) included 3D native T1-weighted IR-SPGR (TI = 700-800 ms) to visualize RF lesions. T1-derived RF lesions were compared against excised tissue. The locations of T1-derived RF lesions were compared against CARTO ablation tags, and segment-wise sensitivity and specificity of lesion detection were calculated within the AHA 17-segment model. RESULTS: RF lesions were clearly visualized in HTCs, scar, and myocardium. Ablation patterns delivered in CARTO matched T1-derived RF lesion patterns with high sensitivity (88.9%) and specificity (94.7%), and were closely matched in registered MR-EP data sets, with a displacement of 5.4 ±3.8 mm (N = 152 ablation tags). CONCLUSION: Integrating MRI into ablative procedures for RF lesion assessment is feasible. Patterns of RF lesions created using a standard 3D EAM system are accurately reflected by MRI visualization in healthy myocardium, scar, and HTCs comprising the MRI-defined arrhythmia substrate. SIGNIFICANCE: MRI visualization of RF lesions can provide near-immediate ( 24 h) assessment of ablation, potentially indicating whether critical MRI-defined ventricular tachycardia substrates have been adequately ablated.
Assuntos
Ventrículos do Coração , Imageamento por Ressonância Magnética , Animais , Suínos , Ventrículos do Coração/diagnóstico por imagem , Ventrículos do Coração/cirurgia , Imageamento por Ressonância Magnética/métodos , Ablação por Cateter/métodos , Arritmias Cardíacas/diagnóstico por imagem , Arritmias Cardíacas/cirurgia , Cirurgia Assistida por Computador/métodos , Infarto do Miocárdio/diagnóstico por imagem , Infarto do Miocárdio/cirurgia , Ablação por Radiofrequência/métodos , Imageamento Tridimensional/métodos , Cicatriz/diagnóstico por imagemRESUMO
Magnetic resonance imaging (MRI) using hyperpolarized noble gases provides a way to visualize the structure and function of human lung, but the long imaging time limits its broad research and clinical applications. Deep learning has demonstrated great potential for accelerating MRI by reconstructing images from undersampled data. However, most existing deep convolutional neural networks (CNN) directly apply square convolution to k-space data without considering the inherent properties of k-space sampling, limiting k-space learning efficiency and image reconstruction quality. In this work, we propose an encoding enhanced (EN2) complex CNN for highly undersampled pulmonary MRI reconstruction. EN2 complex CNN employs convolution along either the frequency or phase-encoding direction, resembling the mechanisms of k-space sampling, to maximize the utilization of the encoding correlation and integrity within a row or column of k-space. We also employ complex convolution to learn rich representations from the complex k-space data. In addition, we develop a feature-strengthened modularized unit to further boost the reconstruction performance. Experiments demonstrate that our approach can accurately reconstruct hyperpolarized 129Xe and 1H lung MRI from 6-fold undersampled k-space data and provide lung function measurements with minimal biases compared with fully sampled images. These results demonstrate the effectiveness of the proposed algorithmic components and indicate that the proposed approach could be used for accelerated pulmonary MRI in research and clinical lung disease patient care.
Assuntos
Processamento de Imagem Assistida por Computador , Pulmão , Imageamento por Ressonância Magnética , Redes Neurais de Computação , Imageamento por Ressonância Magnética/métodos , Pulmão/diagnóstico por imagem , Humanos , Processamento de Imagem Assistida por Computador/métodos , Algoritmos , Imagens de Fantasmas , Aprendizado Profundo , Isótopos de Xenônio/químicaRESUMO
OBJECTIVE: Convolutional neural networks (CNNs) have demonstrated promise in automated cardiac magnetic resonance image segmentation. However, when using CNNs in a large real-world dataset, it is important to quantify segmentation uncertainty and identify segmentations which could be problematic. In this work, we performed a systematic study of Bayesian and non-Bayesian methods for estimating uncertainty in segmentation neural networks. METHODS: We evaluated Bayes by Backprop, Monte Carlo Dropout, Deep Ensembles, and Stochastic Segmentation Networks in terms of segmentation accuracy, probability calibration, uncertainty on out-of-distribution images, and segmentation quality control. RESULTS: We observed that Deep Ensembles outperformed the other methods except for images with heavy noise and blurring distortions. We showed that Bayes by Backprop is more robust to noise distortions while Stochastic Segmentation Networks are more resistant to blurring distortions. For segmentation quality control, we showed that segmentation uncertainty is correlated with segmentation accuracy for all the methods. With the incorporation of uncertainty estimates, we were able to reduce the percentage of poor segmentation to 5% by flagging 31-48% of the most uncertain segmentations for manual review, substantially lower than random review without using neural network uncertainty (reviewing 75-78% of all images). CONCLUSION: This work provides a comprehensive evaluation of uncertainty estimation methods and showed that Deep Ensembles outperformed other methods in most cases. SIGNIFICANCE: Neural network uncertainty measures can help identify potentially inaccurate segmentations and alert users for manual review.
Assuntos
Benchmarking , Redes Neurais de Computação , Incerteza , Imageamento por Ressonância Magnética/métodos , Radiografia , Processamento de Imagem Assistida por Computador/métodosRESUMO
It has been a great challenge to prepare high-expansion-ratio polylactide (PLA) foam with eminent thermal insulation and compression performance in packaging field. Herein, a naturally formed nanofiller halloysite nanotube (HNT) and stereocomplex (SC) crystallites were introduced into PLA with a supercritical CO2 foaming method to improve foaming behavior and physical properties. The compressive performance and thermal insulation properties of the obtained poly(L-lactic acid) (PLLA)/poly(D-lactic acid) (PDLA)/HNT composite foams were successfully investigated. At a HNT content of 1 wt%, the PLLA/PDLA/HNT blend foam with an expansion ratio of 36.7 folds showed a thermal conductivity as low as 30.60 mW/(m·K). Meanwhile, the compressive modulus of PLLA/PDLA/HNT foam was 115% higher than that of PLLA/PDLA foam without HNT. Moreover, the crystallinity of PLLA/PDLA/HNT foam was dramatically improved after annealing, thus the results showed that compressive modulus of the annealed foam increased by as high as 72%, while it still maintained good heat insulation with the thermal conductivity of 32.63 mW/(m·K). This work provides a green method for the preparation of biodegradable PLA foams with admirable heat resistance and mechanical performance.
Assuntos
Dióxido de Carbono , Nanotubos , Poliésteres , Temperatura Alta , Ácido LácticoRESUMO
Vessel wall volume (VWV) is a 3-D ultrasound measurement for the assessment of therapy in patients with carotid atherosclerosis. Deep learning can be used to segment the media-adventitia boundary (MAB) and lumen-intima boundary (LIB) and to quantify VWV automatically; however, it typically requires large training data sets with expert manual segmentation, which are difficult to obtain. In this study, a UNet++ ensemble approach was developed for automated VWV measurement, trained on five small data sets (n = 30 participants) and tested on 100 participants with clinically diagnosed coronary artery disease enrolled in a multicenter CAIN trial. The Dice similarity coefficient (DSC), average symmetric surface distance (ASSD), Pearson correlation coefficient (r), Bland-Altman plots and coefficient of variation (CoV) were used to evaluate algorithm segmentation accuracy, agreement and reproducibility. The UNet++ ensemble yielded DSCs of 91.07%-91.56% and 87.53%-89.44% and ASSDs of 0.10-0.11 mm and 0.33-0.39 mm for the MAB and LIB, respectively; the algorithm VWV measurements were correlated (r = 0.763-0.795, p < 0.001) with manual segmentations, and the CoV for VWV was 8.89%. In addition, the UNet++ ensemble trained on 30 participants achieved a performance similar to that of U-Net and Voxel-FCN trained on 150 participants. These results suggest that our approach could provide accurate and reproducible carotid VWV measurements using relatively small training data sets, supporting deep learning applications for monitoring atherosclerosis progression in research and clinical trials.
Assuntos
Artérias Carótidas , Imageamento Tridimensional , Humanos , Reprodutibilidade dos Testes , Imageamento Tridimensional/métodos , Artérias Carótidas/diagnóstico por imagem , Ultrassonografia/métodos , AlgoritmosRESUMO
Purpose: To design and evaluate an automated deep learning method for segmentation and analysis of cardiac MRI T1 maps with use of synthetic T1-weighted images for MRI relaxation-based contrast augmentation. Materials and Methods: This retrospective study included MRI scans acquired between 2016 and 2019 from 100 patients (mean age ± SD, 55 years ± 13; 72 men) across various clinical abnormalities with use of a modified Look-Locker inversion recovery, or MOLLI, sequence to quantify native T1 (T1native), postcontrast T1 (T1post), and extracellular volume (ECV). Data were divided into training (n = 60) and internal (n = 40) test subsets. "Synthetic" T1-weighted images were generated from the T1 exponential inversion-recovery signal model at a range of optimal inversion times, yielding high blood-myocardium contrast, and were used for contrast-based image augmentation during training and testing of a convolutional neural network for myocardial segmentation. Automated segmentation, T1, and ECV were compared with experts with use of Dice similarity coefficients (DSCs), correlation coefficients, and Bland-Altman analysis. An external test dataset (n = 147) was used to assess model generalization. Results: Internal testing showed high myocardial DSC relative to experts (0.81 ± 0.08), which was similar to interobserver DSC (0.81 ± 0.08). Automated segmental measurements strongly correlated with experts (T1native, R = 0.87; T1post, R = 0.91; ECV, R = 0.92), which were similar to interobserver correlation (T1native, R = 0.86; T1post, R = 0.94; ECV, R = 0.95). External testing showed strong DSC (0.80 ± 0.09) and T1native correlation (R = 0.88) between automatic and expert analysis. Conclusion: This deep learning method leveraging synthetic contrast augmentation may provide accurate automated T1 and ECV analysis for cardiac MRI data acquired across different abnormalities, centers, scanners, and T1 sequences.Keywords: MRI, Cardiac, Tissue Characterization, Segmentation, Convolutional Neural Network, Deep Learning Algorithms, Machine Learning Algorithms, Supervised Learning Supplemental material is available for this article. © RSNA, 2022.
RESUMO
Pulmonary functional magnetic resonance imaging (PfMRI) provides a way to non-invasively map and measure the spatial distribution of pulmonary ventilation, perfusion and gas-exchange abnormalities with unprecedented detail of functional processes at the level of airways, alveoli and the alveolar-capillary membrane. Current PfMRI approaches are dominated by hyperpolarized helium-3 (3He) and xenon-129 (129Xe) gases, which both provide rapid (8-15 s) and well-tolerated imaging examinations in patients with severe pulmonary diseases and pediatric populations, whilst employing no ionizing radiation. While a number of review papers summarize the required image acquisition hardware and software requirements needed to enable PfMRI, here we focus on the image analysis and processing methods required for reproducible measurements using hyperpolarized gas ventilation MRI. We start with the transition in the literature from qualitative and subjective scoring systems to quantitative and objective measurements which enable precise quantification of the lung's critical structure-function relationship. We provide an overview of quantitative biomarkers and the relevant respiratory system parameters that may be measured using PfMRI methods, outlining the history of developments in the field, current methods and then knowledge gaps and typical limitations. We focus on hyperpolarized noble gas MR image processing methods used for quantifying ventilation and gas distribution in the lungs, and discuss the utility and applications of imaging biomarkers generated through these techniques. We conclude with a summary of the current and future directions to further the development of image processing methods, and discuss the remaining challenges for potential clinical translation of these approaches and their integration into standard clinical workflows.
Assuntos
Hélio , Imageamento por Ressonância Magnética , Criança , Humanos , Imageamento por Ressonância Magnética/métodos , Pulmão/diagnóstico por imagem , Processamento de Imagem Assistida por Computador , Ventilação PulmonarRESUMO
The performance of deep learning for cardiac magnetic resonance imaging (MRI) segmentation is oftentimes degraded when using small datasets and sparse annotations for training or adapting a pre-trained model to previously unseen datasets. Here, we developed and evaluated an approach to addressing some of these issues to facilitate broader use of deep learning for short-axis cardiac MRI segmentation. We developed a globally optimal label fusion (GOLF) algorithm that enforced spatial smoothness to generate consensus segmentation from segmentation predictions provided by a deep learning ensemble algorithm. The GOLF consensus was entered into an uncertainty-guided coupled continuous kernel cut (ugCCKC) algorithm that employed normalized cut, image-grid continuous regularization, and "nesting" and circular shape priors of the left ventricular myocardium (LVM) and cavity (LVC). In addition, the uncertainty measurements derived from the segmentation predictions were used to constrain the similarity of GOLF and final segmentation. We optimized ugCCKC through upper bound relaxation, for which we developed an efficient coupled continuous max-flow algorithm implemented in an iterative manner. We showed that GOLF yielded average symmetric surface distance (ASSD) 0.2-0.8 mm lower than an averaging method with higher or similar Dice similarity coefficient (DSC). We also demonstrated that ugCCKC incorporating the shape priors improved DSC by 0.01-0.05 and reduced ASSD by 0.1-0.9 mm. In addition, we integrated GOLF and ugCCKC into a deep learning ensemble algorithm by refining the segmentation of an unannotated dataset and using the refined segmentation to update the trained models. With the proposed framework, we demonstrated the capability of using relatively small datasets (5-10 subjects) with sparse (5-25% slices labeled) annotations to train a deep learning algorithm, while achieving DSC of 0.871-0.893 for LVM and 0.933-0.959 for LVC on the LVQuan dataset, and these were 0.844-0.871 for LVM and 0.923-0.931 for LVC on the ACDC dataset. Furthermore, we showed that the proposed approach can be adapted to substantially alleviate the domain shift issue. Moreover, we calculated a number of commonly used LV function measurements using the derived segmentation and observed strong correlations (Pearson r=0.77-1.00, p<0.001) between algorithm and manual LV function analyses. These results suggest that the developed approaches can be used to facilitate broader application of deep learning in research and clinical cardiac MR imaging workflow.
Assuntos
Aprendizado Profundo , Processamento de Imagem Assistida por Computador , Coração/diagnóstico por imagem , Humanos , Processamento de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos , IncertezaRESUMO
Three-dimensional (3D) transrectal ultrasound (TRUS) is utilized in prostate cancer diagnosis and treatment, necessitating time-consuming manual prostate segmentation. We have previously developed an automatic 3D prostate segmentation algorithm involving deep learning prediction on radially sampled 2D images followed by 3D reconstruction, trained on a large, clinically diverse dataset with variable image quality. As large clinical datasets are rare, widespread adoption of automatic segmentation could be facilitated with efficient 2D-based approaches and the development of an image quality grading method. The complete training dataset of 6761 2D images, resliced from 206 3D TRUS volumes acquired using end-fire and side-fire acquisition methods, was split to train two separate networks using either end-fire or side-fire images. Split datasets were reduced to 1000, 500, 250, and 100 2D images. For deep learning prediction, modified U-Net and U-Net++ architectures were implemented and compared using an unseen test dataset of 40 3D TRUS volumes. A 3D TRUS image quality grading scale with three factors (acquisition quality, artifact severity, and boundary visibility) was developed to assess the impact on segmentation performance. For the complete training dataset, U-Net and U-Net++ networks demonstrated equivalent performance, but when trained using split end-fire/side-fire datasets, U-Net++ significantly outperformed the U-Net. Compared to the complete training datasets, U-Net++ trained using reduced-size end-fire and side-fire datasets demonstrated equivalent performance down to 500 training images. For this dataset, image quality had no impact on segmentation performance for end-fire images but did have a significant effect for side-fire images, with boundary visibility having the largest impact. Our algorithm provided fast (<1.5 s) and accurate 3D segmentations across clinically diverse images, demonstrating generalizability and efficiency when employed on smaller datasets, supporting the potential for widespread use, even when data is scarce. The development of an image quality grading scale provides a quantitative tool for assessing segmentation performance.
Assuntos
Aprendizado Profundo , Neoplasias da Próstata , Humanos , Masculino , Pelve , Próstata/diagnóstico por imagem , Neoplasias da Próstata/diagnóstico por imagem , UltrassonografiaRESUMO
Ultra-short echo-time (UTE) magnetic resonance imaging (MRI) provides enhanced visualization of pulmonary structural and functional abnormalities and has shown promise in phenotyping lung disease. Here, we describe the development and evaluation of a lung segmentation approach to facilitate UTE MRI methods for patient-based imaging. The proposed approach employs a k-means algorithm in kernel space for pair-wise feature clustering and imposes image domain continuous regularization, coined as continuous kernel k-means (CKKM). The high-order CKKM algorithm was simplified through upper bound relaxation and solved within an iterative continuous max-flow framework. We combined the CKKM with U-net and atlas-based approaches and comprehensively evaluated the performance on 100 images from 25 patients with asthma and bronchial pulmonary dysplasia enrolled at Robarts Research Institute (Western University, London, Canada) and Centre Hospitalier Universitaire (Sainte-Justine, Montreal, Canada). For U-net, we trained the network five times on a mixture of five different images with under-annotations and applied the model to 64 images from the two centres. We also trained a U-net on five images with full and brush annotations from one centre, and tested the model on 32 images from the other centre. For an atlas-based approach, we employed three atlas images to segment 64 target images from the two centres through straightforward atlas registration and label fusion. We applied the CKKM algorithm to the baseline U-net and atlas outputs and refined the initial segmentation through multi-volume image fusion. The integration of CKKM substantially improved baseline results and yielded, with minimal computational cost, segmentation accuracy, and precision that were greater than some state-of-the-art deep learning models and similar to experienced observer manual segmentation. This suggests that deep learning and atlas-based approaches may be utilized to segment UTE MRI datasets using relatively small training datasets with under-annotations.
Assuntos
Algoritmos , Imageamento por Ressonância Magnética , Humanos , Processamento de Imagem Assistida por Computador , Pulmão/diagnóstico por imagemRESUMO
Automatic quantification of the left ventricle (LV) from cardiac magnetic resonance (CMR) images plays an important role in making the diagnosis procedure efficient, reliable, and alleviating the laborious reading work for physicians. Considerable efforts have been devoted to LV quantification using different strategies that include segmentation-based (SG) methods and the recent direct regression (DR) methods. Although both SG and DR methods have obtained great success for the task, a systematic platform to benchmark them remains absent because of differences in label information during model learning. In this paper, we conducted an unbiased evaluation and comparison of cardiac LV quantification methods that were submitted to the Left Ventricle Quantification (LVQuan) challenge, which was held in conjunction with the Statistical Atlases and Computational Modeling of the Heart (STACOM) workshop at the MICCAI 2018. The challenge was targeted at the quantification of 1) areas of LV cavity and myocardium, 2) dimensions of the LV cavity, 3) regional wall thicknesses (RWT), and 4) the cardiac phase, from mid-ventricle short-axis CMR images. First, we constructed a public quantification dataset Cardiac-DIG with ground truth labels for both the myocardium mask and these quantification targets across the entire cardiac cycle. Then, the key techniques employed by each submission were described. Next, quantitative validation of these submissions were conducted with the constructed dataset. The evaluation results revealed that both SG and DR methods can offer good LV quantification performance, even though DR methods do not require densely labeled masks for supervision. Among the 12 submissions, the DR method LDAMT offered the best performance, with a mean estimation error of 301 mm 2 for the two areas, 2.15 mm for the cavity dimensions, 2.03 mm for RWTs, and a 9.5% error rate for the cardiac phase classification. Three of the SG methods also delivered comparable performances. Finally, we discussed the advantages and disadvantages of SG and DR methods, as well as the unsolved problems in automatic cardiac quantification for clinical practice applications.
Assuntos
Ventrículos do Coração , Imagem Cinética por Ressonância Magnética , Coração , Ventrículos do Coração/diagnóstico por imagem , Humanos , Imageamento por Ressonância MagnéticaRESUMO
Measurement of total-plaque-area (TPA) is important for determining long term risk for stroke and monitoring carotid plaque progression. Since delineation of carotid plaques is required, a deep learning method can provide automatic plaque segmentations and TPA measurements; however, it requires large datasets and manual annotations for training with unknown performance on new datasets. A UNet++ ensemble algorithm was proposed to segment plaques from 2D carotid ultrasound images, trained on three small datasets (n = 33, 33, 34 subjects) and tested on 44 subjects from the SPARC dataset (n = 144, London, Canada). The ensemble was also trained on the entire SPARC dataset and tested with a different dataset (n = 497, Zhongnan Hospital, China). Algorithm and manual segmentations were compared using Dice-similarity-coefficient (DSC), and TPAs were compared using the difference ( ∆TPA), Pearson correlation coefficient (r) and Bland-Altman analyses. Segmentation variability was determined using the intra-class correlation coefficient (ICC) and coefficient-of-variation (CoV). For 44 SPARC subjects, algorithm DSC was 83.3-85.7%, and algorithm TPAs were strongly correlated (r = 0.985-0.988; p < 0.001) with manual results with marginal biases (0.73-6.75) mm 2 using the three training datasets. Algorithm ICC for TPAs (ICC = 0.996) was similar to intra- and inter-observer manual results (ICC = 0.977, 0.995). Algorithm CoV = 6.98% for plaque areas was smaller than the inter-observer manual CoV (7.54%). For the Zhongnan dataset, DSC was 88.6% algorithm and manual TPAs were strongly correlated (r = 0.972, p < 0.001) with ∆TPA = -0.44 ±4.05 mm 2 and ICC = 0.985. The proposed algorithm trained on small datasets and segmented a different dataset without retraining with accuracy and precision that may be useful clinically and for research.
Assuntos
Artérias Carótidas/diagnóstico por imagem , Aprendizado Profundo , Algoritmos , Feminino , Humanos , Masculino , Infarto do Miocárdio/diagnóstico por imagem , Infarto do Miocárdio/patologia , Placa Aterosclerótica/diagnóstico , Acidente Vascular Cerebral/diagnóstico por imagem , Acidente Vascular Cerebral/patologia , UltrassonografiaRESUMO
PURPOSE: Cardiac relaxometry techniques, particularly T1 mapping, have recently gained clinical importance in various cardiac pathologies. Myocardial T1 and extracellular volume are usually calculated from manual identification of left ventricular epicardial and endocardial regions. This is a laborious process, particularly for large volume studies. Here we present a fully automated relaxometry framework (FASTR) for segmental analysis of T1 maps (both native and postcontrast) and partition coefficient (λ). METHODS: Patients (N = 11) were imaged postacute myocardial infarction on a 1.5T clinical scanner. The scan protocol involved CINE-SSFP imaging, native, and post-contrast T1 mapping using the Modified Look-Locker Inversion (MOLLI) recovery sequence. FASTR consisted of automatic myocardial segmentation of spatio-temporally coregistered CINE images as an initial guess, followed by refinement of the contours on the T1 maps to derive segmental T1 and λ. T1 and λ were then compared to those obtained from two trained expert observers. RESULTS: Robust endocardial and epicardial contours were achieved on T1 maps despite the presence of infarcted tissue. Relative to experts, FASTR resulted in myocardial Dice coefficients (native T1: 0.752 ± 0.041; postcontrast T1: 0.751 ± 0.057) that were comparable to interobserver Dice (native T1: 0.803 ± 0.045; postcontrast T1: 0.799 ± 0.054). There were strong correlations observed for T1 and λ derived from experts and FASTR (native T1: r = 0.83; postcontrast T1: r = 0.87; λ: r = 0.78; P < 0.0001), which were comparable to inter-expert correlation coefficients (native T1: r = 0.90; postcontrast T1: r = 0.93; λ: r = 0.80; P < 0.0001). CONCLUSIONS: Our fully automated framework, FASTR, can generate accurate myocardial segmentations for native and postcontrast MOLLI T1 analysis without the need for manual intervention. Such a design is appealing for high volume clinical protocols.
Assuntos
Infarto do Miocárdio , Miocárdio , Meios de Contraste , Coração/diagnóstico por imagem , Ventrículos do Coração/diagnóstico por imagem , Humanos , Imageamento por Ressonância Magnética , Imagem Cinética por Ressonância Magnética , Espectroscopia de Ressonância Magnética , Infarto do Miocárdio/diagnóstico por imagem , Valor Preditivo dos Testes , Reprodutibilidade dos TestesRESUMO
PURPOSE: To develop an approach for automated quantification of myocardial infarct heterogeneity in late gadolinium enhancement (LGE) cardiac MRI. METHODS: We acquired 2D short-axis cine and 3D LGE in 10 pigs with myocardial infarct. The 2D cine myocardium was segmented and registered to the LGE images. LGE image signal intensities within the warped cine myocardium masks were analyzed to determine the thresholds of infarct core (IC) and gray zone (GZ) for the standard-deviation (SD) and full-width-at-halfmaximum (FWHM) methods. The initial IC, GZ, and IC + GZ segmentations were postprocessed using a normalized cut approach. Cine segmentation and cine-LGE registration accuracies were evaluated using dice similarity coefficient and average symmetric surface distance. Automated IC, GZ, and IC + GZ volumes were compared with manual results using Pearson correlation coefficient (r), Bland-Altman analyses, and intraclass correlation coefficient. RESULTS: For n = 87 slices containing scar, we achieved cine segmentation dice similarity coefficient = 0.87 ± 0.12, average symmetric surface distance = 0.94 ± 0.74 mm (epicardium), and 1.03 ± 0.82 mm (endocardium) in the scar region. For cine-LGE registration, dice similarity coefficient was 0.90 ± 0.06 and average symmetric surface distance was 0.72 ± 0.39 mm (epicardium) and 0.86 ± 0.53 mm (endocardium) in the scar region. For both SD and FWHM methods, automated IC, GZ, and IC + GZ volumes were strongly (r > 0.70) correlated with manual measurements, and the correlations were not significantly different from interobserver correlations (P > .05). The agreement between automated and manual scar volumes (intraclass correlation coefficient = 0.85-0.96) was similar to that between two observers (intraclass correlation coefficient = 0.81-0.99); automated scar segmentation errors were not significantly different from interobserver segmentation differences (P > .05). CONCLUSIONS: Our approach provides fully automated cine-LGE MRI registration and LGE myocardial infarct heterogeneity quantification in preclinical studies.
Assuntos
Gadolínio , Infarto do Miocárdio , Animais , Meios de Contraste , Imageamento Tridimensional , Imageamento por Ressonância Magnética , Imagem Cinética por Ressonância Magnética , Infarto do Miocárdio/diagnóstico por imagem , Miocárdio , Reprodutibilidade dos Testes , SuínosRESUMO
Background Hyperpolarized noble gas MRI helps measure lung ventilation, but clinical translation remains limited. Free-breathing proton MRI may help quantify lung function using existing MRI systems without contrast material and may assist in providing information about ventilation not visible to the eye or easily extracted with segmentation methods. Purpose To explore the use of deep convolutional neural networks (DCNNs) to generate synthetic MRI ventilation scans from free-breathing MRI (deep learning [DL] ventilation MRI)-derived specific ventilation maps as a surrogate of noble gas MRI and to validate this approach across a wide range of lung diseases. Materials and Methods In this secondary analysis of prospective trials, 114 paired noble gas MRI and two-dimensional free-breathing MRI scans were obtained in healthy volunteers with no history of chronic or acute respiratory disease and in study participants with a range of different obstructive lung diseases, including asthma, bronchiectasis, chronic obstructive pulmonary disease, and non-small-cell lung cancer between September 2013 and April 2018 (ClinicalTrials.gov identifiers: NCT03169673, NCT02351141, NCT02263794, NCT02282202, NCT02279329, and NCT02002052). A U-Net-based DCNN model was trained to map free-breathing proton MRI to hyperpolarized helium 3 (3He) MRI ventilation and validated using a sixfold validation. During training, the DCNN ventilation maps were compared with noble gas MRI scans using the Pearson correlation coefficient (r) and mean absolute error. DCNN ventilation images were segmented for ventilation and ventilation defects and were compared with noble gas MRI scans using the Dice similarity coefficient (DSC). Relationships were evaluated with the Spearman correlation coefficient (rS). Results One hundred fourteen study participants (mean age, 56 years ± 15 [standard deviation]; 66 women) were evaluated. As compared with 3He MRI, DCNN model ventilation maps had a mean r value of 0.87 ± 0.08. The mean DSC for DL ventilation MRI and 3He MRI ventilation was 0.91 ± 0.07. The ventilation defect percentage for DL ventilation MRI was highly correlated with 3He MRI ventilation defect percentage (rS = 0.83, P < .001, mean bias = -2.0% ± 5). Both DL ventilation MRI (rS = -0.51, P < .001) and 3He MRI (rS = -0.61, P < .001) ventilation defect percentage were correlated with the forced expiratory volume in 1 second. The DCNN model required approximately 2 hours for training and approximately 1 second to generate a ventilation map. Conclusion In participants with diverse pulmonary pathologic findings, deep convolutional neural networks generated ventilation maps from free-breathing proton MRI trained with a hyperpolarized noble-gas MRI ventilation map data set. The maps showed correlation with noble gas MRI ventilation and pulmonary function measurements. © RSNA, 2020 See also the editorial by Vogel-Claussen in this issue.
Assuntos
Interpretação de Imagem Assistida por Computador/métodos , Pneumopatias/diagnóstico por imagem , Imageamento por Ressonância Magnética/métodos , Redes Neurais de Computação , Ventilação Pulmonar , Adulto , Idoso , Feminino , Humanos , Pulmão/diagnóstico por imagem , Masculino , Pessoa de Meia-Idade , Estudos Prospectivos , PrótonsRESUMO
Vessel-wall-volume (VWV) is an important three-dimensional ultrasound (3DUS) metric used in the assessment of carotid plaque burden and monitoring changes in carotid atherosclerosis in response to medical treatment. To generate the VWV measurement, we proposed an approach that combined a voxel-based fully convolution network (Voxel-FCN) and a continuous max-flow module to automatically segment the carotid media-adventitia (MAB) and lumen-intima boundaries (LIB) from 3DUS images. Voxel-FCN includes an encoder consisting of a general 3D CNN and a 3D pyramid pooling module to extract spatial and contextual information, and a decoder using a concatenating module with an attention mechanism to fuse multi-level features extracted by the encoder. A continuous max-flow algorithm is used to improve the coarse segmentation provided by the Voxel-FCN. Using 1007 3DUS images, our approach yielded a Dice-similarity-coefficient (DSC) of 93.2±3.0% for the MAB in the common carotid artery (CCA), and 91.9±5.0% in the bifurcation by comparing algorithm and expert manual segmentations. We achieved a DSC of 89.5±6.7% and 89.3±6.8% for the LIB in the CCA and the bifurcation respectively. The mean errors between the algorithm-and manually-generated VWVs were 0.2±51.2 mm3 for the CCA and -4.0±98.2 mm3 for the bifurcation. The algorithm segmentation accuracy was comparable to intra-observer manual segmentation but our approach required less than 1s, which will not alter the clinical work-flow as 10s is required to image one side of the neck. Therefore, we believe that the proposed method could be used clinically for generating VWV to monitor progression and regression of carotid plaques.
Assuntos
Doenças das Artérias Carótidas , Placa Aterosclerótica , Algoritmos , Artérias Carótidas/diagnóstico por imagem , Doenças das Artérias Carótidas/diagnóstico por imagem , Humanos , Imageamento Tridimensional , UltrassonografiaRESUMO
Cardiac magnetic resonance imaging (MRI) provides a wealth of imaging biomarkers for cardiovascular disease care and segmentation of cardiac structures is required as a first step in enumerating these biomarkers. Deep convolutional neural networks (CNNs) have demonstrated remarkable success in image segmentation but typically require large training datasets and provide suboptimal results that require further improvements. Here, we developed a way to enhance cardiac MRI multi-class segmentation by combining the strengths of CNN and interpretable machine learning algorithms. We developed a continuous kernel cut segmentation algorithm by integrating normalized cuts and continuous regularization in a unified framework. The high-order formulation was solved through upper bound relaxation and a continuous max-flow algorithm in an iterative manner using CNN predictions as inputs. We applied our approach to two representative cardiac MRI datasets across a wide range of cardiovascular pathologies. We comprehensively evaluated the performance of our approach for two CNNs trained with various small numbers of training cases, tested on the same and different datasets. Experimental results showed that our approach improved baseline CNN segmentation by a large margin, reduced CNN segmentation variability substantially, and achieved excellent segmentation accuracy with minimal extra computational cost. These results suggest that our approach provides a way to enhance the applicability of CNN by enabling the use of smaller training datasets and improving the segmentation accuracy and reproducibility for cardiac MRI segmentation in research and clinical patient care.