RESUMEN
BACKGROUND. Histologic fibrosis stage is the most important prognostic factor in chronic liver disease. MR elastography (MRE) is the most accurate noninvasive method for detecting and staging liver fibrosis. Although accurate, manual ROI-based MRE analysis is complex, time-consuming, requires specialized readers, and is prone to methodologic variability and suboptimal interreader agreement. OBJECTIVE. The purpose of this study was to develop an automated convolutional neural network (CNN)-based method for liver MRE analysis, evaluate its agreement with manual ROI-based analysis, and assess its performance for classifying dichotomized fibrosis stages using histology as the reference standard. METHODS. In this retrospective cross-sectional study, 675 participants who underwent MRE using different MRI systems and field strengths at 28 imaging sites from five multicenter international clinical trials of nonalcoholic steatohepatitis were included for algorithm development and internal testing of agreement between automated CNN-based and manual ROI-based analyses. Eighty-one patients (52 women, 29 men; mean age, 54 years) who underwent MRE using a single 3-T system and liver biopsy for clinical purposes at a single institution were included for external testing of agreement between the two analysis methods and assessment of fibrosis stage discriminative performance. Agreement was evaluated using intraclass correlation coefficients (ICCs). Bootstrapping was used to compute 95% CIs. Discriminative performance of each method for dichotomized histologic fibrosis stage was evaluated by AUC and compared using bootstrapping. RESULTS. Mean CNN- and manual ROI-based stiffness measurements ranged from 3.21 to 3.34 kPa in trial participants and from 3.21 to 3.30 kPa in clinical patients. ICC for CNN- and manual ROI-based measurements was 0.98 (95% CI, 0.97-0.98) in trial participants and 0.99 (95% CI, 0.98-0.99) in clinical patients. AUCs for classification of dichotomized fibrosis stage ranged from 0.89 to 0.93 for CNN-based analysis and 0.87 to 0.93 for manual ROI-based analysis (p = .23-.75). CONCLUSION. Stiffness measurements using the automated CNN-based method agreed strongly with manual ROI-based analysis across MRI systems and field strengths, with excellent discriminative performance for histology-determined dichotomized fibrosis stages in external testing. CLINICAL IMPACT. Given the high incidence of chronic liver disease worldwide, it is important that noninvasive tools to assess fibrosis are applied reliably across different settings. CNN-based analysis is feasible and may reduce reliance on expert image analysts.
Asunto(s)
Diagnóstico por Imagen de Elasticidad , Enfermedad del Hígado Graso no Alcohólico , Estudios Transversales , Diagnóstico por Imagen de Elasticidad/métodos , Femenino , Fibrosis , Humanos , Hígado/diagnóstico por imagen , Hígado/patología , Cirrosis Hepática/diagnóstico por imagen , Cirrosis Hepática/patología , Imagen por Resonancia Magnética/métodos , Masculino , Persona de Mediana Edad , Enfermedad del Hígado Graso no Alcohólico/diagnóstico por imagen , Enfermedad del Hígado Graso no Alcohólico/patología , Reproducibilidad de los Resultados , Estudios RetrospectivosRESUMEN
OBJECTIVES: According to LI-RADS, a major discriminating feature between hepatocellular carcinoma (HCC) and non-HCC malignancies is the subtype of arterial phase hyperenhancement (APHE). The aim of this study was to investigate whether APHE subtypes are consistent across multi-arterial phase (mHAP) MRI acquisitions while evaluating reader agreement. Secondarily, we investigated factors that may affect reader agreement for APHE subtype. METHODS: In this retrospective study, consecutive patients with liver cirrhosis and focal observations who underwent mHAP were included. Five radiologists reviewed MR images in 2 reading sessions. In reading session 1, individual AP series were reviewed and scored for presence of APHE and subtype. In reading session 2, readers scored observations' major and ancillary features and LI-RADS category in the complete MRI examination. Reader agreement was calculated using Fleiss' kappa for binary outcomes and Kendall's coefficient of concordance for LI-RADS categories. Univariate mixed effects logistic regressions were performed to investigate factors affecting agreement. RESULTS: In total, 61 patients with 77 focal observations were analyzed. Of observations unanimously scored as having APHE, 27.7% showed both rim and nonrim subtypes on mHAP. Inter-reader agreement for APHE subtype ranged from 0.49 (95% CI: 0.33, 0.64) to 0.57 (95% CI: 0.40, 0.74) between reading sessions. Observation size had a trend level effect on rim APHE agreement (p = 0.052). CONCLUSION: Approximately 1/3 of observations demonstrated inconsistent APHE subtype during mHAP acquisition. Small lesions were particularly challenging. Further guidance on APHE subtype classification, especially when applied to mHAP, could be a focus of LI-RADS refinement. KEY POINTS: ⢠In a cohort of patients at risk for HCC, 28% of the observations showed inconsistent arterial phase hyperenhancement (APHE) subtypes (rim and nonrim) on multi-arterial phase imaging according to the majority score of 5 independent readers. ⢠Inconsistent APHE subtypes may challenge reliable imaging diagnosis, i.e., LI-RADS categorization, of focal liver observations in patients at risk for HCC.
Asunto(s)
Carcinoma Hepatocelular , Neoplasias Hepáticas , Carcinoma Hepatocelular/diagnóstico por imagen , Medios de Contraste , Humanos , Hígado , Neoplasias Hepáticas/diagnóstico por imagen , Imagen por Resonancia Magnética , Estudios Retrospectivos , Sensibilidad y EspecificidadRESUMEN
This study aims to develop a semiautomated pipeline and user interface (LiVaS) for rapid segmentation and labeling of MRI liver vasculature and evaluate its time efficiency and accuracy against manual reference standard. Retrospective feasibility pilot study. Liver MR images from different scanners from 36 patients were included, and 4/36 patients were randomly selected for manual segmentation as referenced standard. The liver was segmented in each contrast phase and masks registered to the pre-contrast segmentation. Voxel-wise signal trajectories were clustered using the k-means algorithm. Voxel clusters that best segment the liver vessels were selected and labeled by three independent radiologists and a research scientist using LiVaS. Segmentation times were compared using a paired-sample t-test on log-transformed data. The agreement was analyzed qualitatively and quantitatively using DSC for hepatic and portal vein segmentations. The mean segmentation time among four readers was significantly shorter than manual (3.6 ± 1.4 vs. 70.0 ± 29.2 min; p < 0.001), even when using a higher number of clusters to enhance accuracy. The DSC for portal and hepatic veins reached up to 0.69 and 0.70, respectively. LiVaS segmentations were overall of good quality, with variations in performance related to the presence/severity of liver disease, acquisition timing, and image quality. Our semi-automated pipeline was robust to different MRI vendors in producing segmentation and labeling of liver vasculature in agreement with expert manual annotations, with significantly higher time efficiency. LiVaS could facilitate the creation of large, annotated datasets for training and validation of neural networks for automated MRI liver vascularity segmentation. HIGHLIGHTS: Key Finding: In this pilot feasibility study, our semiautomated pipeline for segmentation of liver vascularity (LiVaS) on MR images produced segmentations with simultaneous labeling of portal and hepatic veins in good agreement with the manual reference standard but at significantly shorter times (mean LiVaS 3.6 ± 1.4 vs. mean manual 70.0 ± 29.2 min; p < 0.001). Importance: LiVaS was robust in producing liver MRI vascular segmentations across images from different scanners in agreement with expert manual annotations, with significant ly higher time efficiency, and therefore potential scalability.
RESUMEN
PURPOSE: To develop a convolutional neural network (CNN)-based deformable lung registration algorithm to reduce computation time and assess its potential for lobar air trapping quantification. MATERIALS AND METHODS: In this retrospective study, a CNN algorithm was developed to perform deformable registration of lung CT (LungReg) using data on 9118 patients from the COPDGene Study (data collected between 2007 and 2012). Loss function constraints included cross-correlation, displacement field regularization, lobar segmentation overlap, and the Jacobian determinant. LungReg was compared with a standard diffeomorphic registration (SyN) for lobar Dice overlap, percentage voxels with nonpositive Jacobian determinants, and inference runtime using paired t tests. Landmark colocalization error (LCE) across 10 patients was compared using a random effects model. Agreement between LungReg and SyN air trapping measurements was assessed using intraclass correlation coefficient. The ability of LungReg versus SyN emphysema and air trapping measurements to predict Global Initiative for Chronic Obstructive Lung Disease (GOLD) stages was compared using area under the receiver operating characteristic curves. RESULTS: Average performance of LungReg versus SyN showed lobar Dice overlap score of 0.91-0.97 versus 0.89-0.95, respectively (P < .001); percentage voxels with nonpositive Jacobian determinant of 0.04 versus 0.10, respectively (P < .001); inference run time of 0.99 second (graphics processing unit) and 2.27 seconds (central processing unit) versus 418.46 seconds (central processing unit) (P < .001); and LCE of 7.21 mm versus 6.93 mm (P < .001). LungReg and SyN whole-lung and lobar air trapping measurements achieved excellent agreement (intraclass correlation coefficients > 0.98). LungReg versus SyN area under the receiver operating characteristic curves for predicting GOLD stage were not statistically different (range, 0.88-0.95 vs 0.88-0.95, respectively; P = .31-.95). CONCLUSION: CNN-based deformable lung registration is accurate and fully automated, with runtime feasible for clinical lobar air trapping quantification, and has potential to improve diagnosis of small airway diseases.Keywords: Air Trapping, Convolutional Neural Network, Deformable Registration, Small Airway Disease, CT, Lung, Semisupervised Learning, Unsupervised Learning Supplemental material is available for this article. © RSNA, 2021 An earlier incorrect version of this article appeared online. This article was corrected on December 22, 2021.
RESUMEN
[This corrects the article DOI: 10.1148/ryai.2021210211.].
RESUMEN
Quantitative imaging measurements can be facilitated by artificial intelligence (AI) algorithms, but how they might impact decision-making and be perceived by radiologists remains uncertain. After creation of a dedicated inspiratory-expiratory CT examination and concurrent deployment of a quantitative AI algorithm for assessing air trapping, five cardiothoracic radiologists retrospectively evaluated severity of air trapping on 17 examination studies. Air trapping severity of each lobe was evaluated in three stages: qualitatively (visually); semiquantitatively, allowing manual region-of-interest measurements; and quantitatively, using results from an AI algorithm. Readers were surveyed on each case for their perceptions of the AI algorithm. The algorithm improved interreader agreement (intraclass correlation coefficients: visual, 0.28; semiquantitative, 0.40; quantitative, 0.84; P < .001) and improved correlation with pulmonary function testing (forced expiratory volume in 1 second-to-forced vital capacity ratio) (visual r = -0.26, semiquantitative r = -0.32, quantitative r = -0.44). Readers perceived moderate agreement with the AI algorithm (Likert scale average, 3.7 of 5), a mild impact on their final assessment (average, 2.6), and a neutral perception of overall utility (average, 3.5). Though the AI algorithm objectively improved interreader consistency and correlation with pulmonary function testing, individual readers did not immediately perceive this benefit, revealing a potential barrier to clinical adoption. Keywords: Technology Assessment, Quantification © RSNA, 2021.
RESUMEN
[This corrects the article DOI: 10.1148/ryct.2021200477.].
RESUMEN
PURPOSE: To develop a deep learning-based algorithm to stage the severity of chronic obstructive pulmonary disease (COPD) through quantification of emphysema and air trapping on CT images and to assess the ability of the proposed stages to prognosticate 5-year progression and mortality. MATERIALS AND METHODS: In this retrospective study, an algorithm using co-registration and lung segmentation was developed in-house to automate quantification of emphysema and air trapping from inspiratory and expiratory CT images. The algorithm was then tested in a separate group of 8951 patients from the COPD Genetic Epidemiology study (date range, 2007-2017). With measurements of emphysema and air trapping, bivariable thresholds were determined to define CT stages of severity (mild, moderate, severe, and very severe) and were evaluated for their ability to prognosticate disease progression and mortality using logistic regression and Cox regression. RESULTS: On the basis of CT stages, the odds of disease progression were greatest among patients with very severe disease (odds ratio [OR], 2.67; 95% CI: 2.02, 3.53; P < .001) and were elevated in patients with moderate disease (OR, 1.50; 95% CI: 1.22, 1.84; P = .001). The hazard ratio of mortality for very severe disease at CT was 2.23 times the normal ratio (95% CI: 1.93, 2.58; P < .001). When combined with Global Initiative for Chronic Obstructive Lung Disease (GOLD) staging, patients with GOLD stage 2 disease had the greatest odds of disease progression when the CT stage was severe (OR, 4.48; 95% CI: 3.18, 6.31; P < .001) or very severe (OR, 4.72; 95% CI: 3.13, 7.13; P < .001). CONCLUSION: Automated CT algorithms can facilitate staging of COPD severity, have diagnostic performance comparable with that of spirometric GOLD staging, and provide further prognostic value when used in conjunction with GOLD staging.Supplemental material is available for this article.© RSNA, 2021See also commentary by Kalra and Ebrahimian in this issue.
RESUMEN
PURPOSE: To develop and evaluate the performance of a fully-automated convolutional neural network (CNN)-based algorithm to evaluate hepatobiliary phase (HBP) adequacy of gadoxetate disodium (EOB)-enhanced MRI. Secondarily, we explored the potential of the proposed CNN algorithm to reduce examination length by applying it to EOB-MRI examinations. METHODS: We retrospectively identified EOB-enhanced MRI-HBP series from examinations performed 2011-2018 (internal and external datasets). Our algorithm, comprising a liver segmentation and classification CNN, produces an adequacy score. Two abdominal radiologists independently classified series as adequate or suboptimal. The consensus determination of HBP adequacy was used as ground truth for CNN model training and validation. Reader agreement was evaluated with Cohen's kappa. Performance of the algorithm was assessed by receiver operating characteristics (ROC) analysis and computation of the area under the ROC curve (AUC). Potential examination duration reduction was evaluated descriptively. RESULTS: 1408 HBP series from 484 patients were included. Reader kappa agreement was 0.67 (internal dataset) and 0.80 (external dataset). AUCs were 0.97 (0.96-0.99) for internal and 0.95 (0.92-96) for external and were not significantly different from each other (p = 0.24). 48 % (50/105) examinations could have been shorter by applying the algorithm. CONCLUSION: A proposed CNN-based algorithm achieves higher than 95 % AUC for classifying HBP images as adequate versus suboptimal. The application of this algorithm could potentially shorten examination time and aid radiologists in recognizing technically suboptimal images, avoiding diagnostic pitfalls.
Asunto(s)
Medios de Contraste/farmacocinética , Gadolinio DTPA/farmacocinética , Interpretación de Imagen Asistida por Computador/métodos , Neoplasias Hepáticas/diagnóstico por imagen , Imagen por Resonancia Magnética/métodos , Redes Neurales de la Computación , Adulto , Anciano , Algoritmos , Área Bajo la Curva , Eficiencia , Femenino , Humanos , Hígado/diagnóstico por imagen , Masculino , Persona de Mediana Edad , Curva ROC , Estudios Retrospectivos , Tiempo , Flujo de TrabajoRESUMEN
BACKGROUND: Liver alignment between series/exams is challenged by dynamic morphology or variability in patient positioning or motion. Image registration can improve image interpretation and lesion co-localization. We assessed the performance of a convolutional neural network algorithm to register cross-sectional liver imaging series and compared its performance to manual image registration. METHODS: Three hundred fourteen patients, including internal and external datasets, who underwent gadoxetate disodium-enhanced magnetic resonance imaging for clinical care from 2011 to 2018, were retrospectively selected. Automated registration was applied to all 2,663 within-patient series pairs derived from these datasets. Additionally, 100 within-patient series pairs from the internal dataset were independently manually registered by expert readers. Liver overlap, image correlation, and intra-observation distances for manual versus automated registrations were compared using paired t tests. Influence of patient demographics, imaging characteristics, and liver uptake function was evaluated using univariate and multivariate mixed models. RESULTS: Compared to the manual, automated registration produced significantly lower intra-observation distance (p < 0.001) and higher liver overlap and image correlation (p < 0.001). Intra-exam automated registration achieved 0.88 mean liver overlap and 0.44 mean image correlation for the internal dataset and 0.91 and 0.41, respectively, for the external dataset. For inter-exam registration, mean overlap was 0.81 and image correlation 0.41. Older age, female sex, greater inter-series time interval, differing uptake, and greater voxel size differences independently reduced automated registration performance (p ≤ 0.020). CONCLUSION: A fully automated algorithm accurately registered the liver within and between examinations, yielding better liver and focal observation co-localization compared to manual registration.
Asunto(s)
Algoritmos , Hígado/diagnóstico por imagen , Imagen por Resonancia Magnética/métodos , Redes Neurales de la Computación , Adulto , Anciano , Femenino , Humanos , Masculino , Persona de Mediana Edad , Estudios RetrospectivosRESUMEN
PURPOSE: To evaluate the association between optical coherence tomography angiography (OCTA) macular and circumpapillary vessel density and visual field mean deviation (MD) in advanced primary open angle glaucoma. DESIGN: Cross-sectional study. METHODS: Macula (superficial layer) and optic nerve head (ONH) with capillary density (CD) and without vessel density (VD) automated removal of large vessels OCTA of 34 eyes (34 patients, MD < -10 dB) were investigated as macula whole image VD (wiVD), parafoveal VD (pfVD), ONH wiVD, wiCD, circumpapillary VD, and cpCD. Spectral domain OCT circumpapillary retinal nerve fiber layer, macular ganglion cell complex, and ganglion cell inner plexiform layer were also analyzed. RESULTS: Macular and ONH VD decreased significantly with worsening MD. Each 1-dB decrease in MD was associated with a reduction of 0.43% and 0.46% for macular wiVD and pfVD with R2 of 0.28 and 0.27, respectively (all P < .01). The association between MD and VD was strongest for measures of ONH with large vessels removed, wiCD, and cpCD, followed by wiVD and circumpapillary VD with R2 of 0.26, 0.22, 0.17, 0.14, and a VD reduction of 0.43%, 0.51%, 0.33%, and 0.40%, respectively (all P < .02). There was a reduction of 1.19 µm in Avanti parafoveal ganglion cell complex, 1.13 µm in Spectralis ganglion cell inner plexiform layer, and 1.01 µm in Spectralis circumpapillary retinal nerve fiber layer, with R2 of 0.19 (P = .006), 0.23 (P = .002), and 0.24 (P = .002), respectively. CONCLUSIONS: ONH and macula OCTA VD and thickness are associated with the severity of visual field damage in advanced primary open angle glaucoma.
Asunto(s)
Glaucoma de Ángulo Abierto/diagnóstico , Mácula Lútea/irrigación sanguínea , Microvasos/patología , Disco Óptico/irrigación sanguínea , Células Ganglionares de la Retina/patología , Vasos Retinianos/patología , Campos Visuales/fisiología , Anciano , Estudios Transversales , Femenino , Angiografía con Fluoresceína/métodos , Fondo de Ojo , Glaucoma de Ángulo Abierto/fisiopatología , Humanos , Presión Intraocular/fisiología , Mácula Lútea/patología , Masculino , Fibras Nerviosas/patología , Tomografía de Coherencia Óptica/métodos , Pruebas del Campo VisualRESUMEN
PURPOSE: To compare optical coherence tomography angiography (OCTA) measured macular vessel density and spectral domain optical coherence tomography (SDOCT) measured macular ganglion cell complex (GCC) thickness in primary open-angle glaucoma eyes with and without focal lamina cribrosa (LC) defects. METHODS: In this cross-sectional, case-control study of patients with primary open-angle glaucoma, 46 eyes of 46 patients with LC defects and 54 eyes of 54 patients without observable LC defects were included. OCTA and SDOCT imaging were performed on the same day by the same operator. Perimetry and swept-source OCT testing used to identify LC defects were conducted within 6 months of OCTA and SDOCT testing. Global and local parafoveal vessel density and macular GCC thickness were compared between study groups. RESULTS: Glaucoma severity was similar between groups (SAP mean deviation=-5.63 and -4.64 dB for eyes with and without LC defects, respectively; P=0.40). Global and local measured parafoveal vessel density was similar between groups (all P≥0.11). GCC focal loss volume was higher in eyes with LC defects than eyes without LC defects (7.2% and 4.97%, respectively; P=0.03). In addition, GCC focal loss volume was topographically related to defect location in LC defect eyes. CONCLUSIONS: Although OCTA macular vessel density was not significantly different between eyes with and without LC defects, focal GCC loss in eyes with LC defects was different. This highlights the importance of not relying solely on vessel density measurements for determining macular changes for diagnosing and detecting glaucomatous progression.