Signal Intensity Trajectories Clustering for Liver Vasculature Segmentation and Labeling (LiVaS) on Contrast-Enhanced MR Images: A Feasibility Pilot Study.

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.

Mapping the Spatial Extent of Hypoperfusion in Chronic Thromboembolic Pulmonary Hypertension Using Multienergy CT.

Purpose: To assess if a novel automated method to spatially delineate and quantify the extent of hypoperfusion on multienergy CT angiograms can aid the evaluation of chronic thromboembolic pulmonary hypertension (CTEPH) disease severity. Materials and Methods: Multienergy CT angiograms obtained between January 2018 and December 2020 in 51 patients with CTEPH (mean age, 47 years ± 17 [SD]; 27 women) were retrospectively compared with those in 110 controls with no imaging findings suggestive of pulmonary vascular abnormalities (mean age, 51 years ± 16; 81 women). Parenchymal iodine values were automatically isolated using deep learning lobar lung segmentations. Low iodine concentration was used to delineate areas of hypoperfusion and calculate hypoperfused lung volume (HLV). Receiver operating characteristic curves, correlations with preoperative and postoperative changes in invasive hemodynamics, and comparison with visual assessment of lobar hypoperfusion by two expert readers were evaluated. Results: Global HLV correctly separated patients with CTEPH from controls (area under the receiver operating characteristic curve = 0.84; 10% HLV cutoff: 90% sensitivity, 72% accuracy, and 64% specificity) and correlated moderately with hemodynamic severity at time of imaging (pulmonary vascular resistance [PVR], ρ = 0.67; P < .001) and change after surgical treatment (∆PVR, ρ = -0.61; P < .001). In patients surgically classified as having segmental disease, global HLV correlated with preoperative PVR (ρ = 0.81) and postoperative ∆PVR (ρ = -0.70). Lobar HLV correlated moderately with expert reader lobar assessment (ρHLV = 0.71 for reader 1; ρHLV = 0.67 for reader 2). Conclusion: Automated quantification of hypoperfused areas in patients with CTEPH can be performed from clinical multienergy CT examinations and may aid clinical evaluation, particularly in patients with segmental-level disease.Keywords: CT-Spectral Imaging (Multienergy), Pulmonary, Pulmonary Arteries, Embolism/Thrombosis, Chronic Thromboembolic Pulmonary Hypertension, Multienergy CT, Hypoperfusion© RSNA, 2023.

Deep Learning for Inference of Hepatic Proton Density Fat Fraction From T1-Weighted In-Phase and Opposed-Phase MRI: Retrospective Analysis of Population-Based Trial Data.

BACKGROUND. The confounder-corrected chemical shift-encoded MRI (CSE-MRI) sequence used to determine proton density fat fraction (PDFF) for hepatic fat quantification is not widely available. As an alternative, hepatic fat can be assessed by a two-point Dixon method to calculate signal fat fraction (FF) from conventional T1-weighted in- and opposed-phase (IOP) images, although signal FF is prone to biases, leading to inaccurate quantification. OBJECTIVE. The purpose of this study was to compare hepatic fat quantification by use of PDFF inferred from conventional T1-weighted IOP images and deep-learning convolutional neural networks (CNNs) with quantification by use of two-point Dixon signal FF with CSE-MRI PDFF as the reference standard. METHODS. This study entailed retrospective analysis of data from 292 participants (203 women, 89 men; mean age, 53.7 ± 12.0 [SD] years) enrolled at two sites from September 1, 2017, to December 18, 2019, in the Strong Heart Family Study (a prospective population-based study of American Indian communities). Participants underwent liver MRI (site A, 3 T; site B, 1.5 T) including T1-weighted IOP MRI and CSE-MRI (used to reconstruct CSE PDFF and CSE R2* maps). With CSE PDFF as reference, a CNN was trained in a random sample of 218 (75%) participants to infer voxel-by-voxel PDFF maps from T1-weighted IOP images; testing was performed in the other 74 (25%) participants. Parametric values from the entire liver were automatically extracted. Per-participant median CNN-inferred PDFF and median two-point Dixon signal FF were compared with reference median CSE-MRI PDFF by means of linear regression analysis, intraclass correlation coefficient (ICC), and Bland-Altman analysis. The code is publicly available at github.com/kang927/CNN-inference-of-PDFF-from-T1w-IOP-MR. RESULTS. In the 74 test-set participants, reference CSE PDFF ranged from 1% to 32% (mean, 11.3% ± 8.3% [SD]); reference CSE R2* ranged from 31 to 457 seconds-1 (mean, 62.4 ± 67.3 seconds-1 [SD]). Agreement metrics with reference to CSE PDFF for CNN-inferred PDFF were ICC = 0.99, bias = -0.19%, 95% limits of agreement (LoA) = (-2.80%, 2.71%) and for two-point Dixon signal FF were ICC = 0.93, bias = -1.11%, LoA = (-7.54%, 5.33%). CONCLUSION. Agreement with reference CSE PDFF was better for CNN-inferred PDFF from conventional T1-weighted IOP images than for two-point Dixon signal FF. Further investigation is needed in individuals with moderate-to-severe iron overload. CLINICAL IMPACT. Measurement of CNN-inferred PDFF from widely available T1-weighted IOP images may facilitate adoption of hepatic PDFF as a quantitative bio-marker for liver fat assessment, expanding opportunities to screen for hepatic steatosis and nonalcoholic fatty liver disease.

Convolutional Neural Network Algorithm to Determine Lateralization of Seizure Onset in Patients With Epilepsy: A Proof-of-Principle Study.

BACKGROUND AND OBJECTIVES: A new frontier in diagnostic radiology is the inclusion of machine-assisted support tools that facilitate the identification of subtle lesions often not visible to the human eye. Structural neuroimaging plays an essential role in the identification of lesions in patients with epilepsy, which often coincide with the seizure focus. In this study, we explored the potential for a convolutional neural network (CNN) to determine lateralization of seizure onset in patients with epilepsy using T1-weighted structural MRI scans as input. METHODS: Using a dataset of 359 patients with temporal lobe epilepsy (TLE) from 7 surgical centers, we tested whether a CNN based on T1-weighted images could classify seizure laterality concordant with clinical team consensus. This CNN was compared with a randomized model (comparison with chance) and a hippocampal volume logistic regression (comparison with current clinically available measures). Furthermore, we leveraged a CNN feature visualization technique to identify regions used to classify patients. RESULTS: Across 100 runs, the CNN model was concordant with clinician lateralization on average 78% (SD = 5.1%) of runs with the best-performing model achieving 89% concordance. The CNN outperformed the randomized model (average concordance of 51.7%) on 100% of runs with an average improvement of 26.2% and outperformed the hippocampal volume model (average concordance of 71.7%) on 85% of runs with an average improvement of 6.25%. Feature visualization maps revealed that in addition to the medial temporal lobe, regions in the lateral temporal lobe, cingulate, and precentral gyrus aided in classification. DISCUSSION: These extratemporal lobe features underscore the importance of whole-brain models to highlight areas worthy of clinician scrutiny during temporal lobe epilepsy lateralization. This proof-of-concept study illustrates that a CNN applied to structural MRI data can visually aid clinician-led localization of epileptogenic zone and identify extrahippocampal regions that may require additional radiologic attention. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that in patients with drug-resistant unilateral temporal lobe epilepsy, a convolutional neural network algorithm derived from T1-weighted MRI can correctly classify seizure laterality.

The Influence of Cannabinoids on Drosophila Behaviors, Longevity, and Traumatic Injury Responses of the Adult Nervous System.

Introduction: The legalization of cannabis products has increased their usage in the United States. Among the ∼500 active compounds, this is especially true for cannabidiol (CBD)-based products, which are being used to treat a range of ailments. Research is ongoing regarding the safety, therapeutic potential, and molecular mechanism of cannabinoids. Drosophila (fruit flies) are widely used to model a range of factors that impact neural aging, stress responses, and longevity. Materials and Methods: Adult wild-type Drosophila melanogaster cohorts (w1118/+) were treated with different Δ9-tetrahydrocannabinol (THC) and CBD dosages and examined for neural protective properties using established neural aging and trauma models. The therapeutic potential of each compound was assessed using circadian and locomotor behavioral assays and longevity profiles. Changes to NF-κB pathway activation were assessed by measuring expression levels of downstream targets using quantitative real-time polymerase chain reaction analysis of neural cDNAs. Results: Flies exposed to different CBD or THC dosages showed minimal effects to sleep and circadian-based behaviors or the age-dependent decline in locomotion. The 2-week CBD (3 µM) treatment did significantly enhance longevity. Flies exposed to different CBD and THC dosages were also examined under stress conditions, using the Drosophila mild traumatic brain injury (mTBI) model (10×). Pretreatment with either compound did not alter baseline expression of key inflammatory markers (NF-κB targets), but did reduce neural mRNA profiles at a key 4-h time point following mTBI exposure. Locomotor responses were also significantly improved 1 and 2 weeks following mTBI. After mTBI (10×) exposure, the 48-h mortality rate improved for CBD (3 µM)-treated flies, as were global average longevity profiles for other CBD doses tested. While not significant, THC (0.1 µM)-treated flies show a net positive impact on acute mortality and longevity profiles following mTBI (10×) exposure. Conclusions: This study shows that the CBD and THC dosages examined had at most a modest impact on basal neural function, while demonstrating that CBD treatments had significant neural protective properties for flies following exposure to traumatic injury.

Erratum: Automated CT Staging of Chronic Obstructive Pulmonary Disease Severity for Predicting Disease Progression and Mortality with a Deep Learning Convolutional Neural Network.

[This corrects the article DOI: 10.1148/ryct.2021200477.].

Unsupervised Learning Identifies Computed Tomographic Measurements as Primary Drivers of Progression, Exacerbation, and Mortality in Chronic Obstructive Pulmonary Disease.

Rationale: Chronic obstructive pulmonary disease (COPD) is a heterogeneous syndrome with phenotypic manifestations that tend to be distributed along a continuum. Unsupervised machine learning based on broad selection of imaging and clinical phenotypes may be used to identify primary variables that define disease axes and stratify patients with COPD. Objectives: To identify primary variables driving COPD heterogeneity using principal component analysis and to define disease axes and assess the prognostic value of these axes across three outcomes: progression, exacerbation, and mortality. Methods: We included 7,331 patients between 39 and 85 years old, of whom 40.3% were Black and 45.8% were female smokers with a mean of 44.6 pack-years, from the COPDGene (Genetic Epidemiology of COPD) phase I cohort (2008-2011) in our analysis. Out of a total of 916 phenotypes, 147 continuous clinical, spirometric, and computed tomography (CT) features were selected. For each principal component (PC), we computed a PC score based on feature weights. We used PC score distributions to define disease axes along which we divided the patients into quartiles. To assess the prognostic value of these axes, we applied logistic regression analyses to estimate 5-year (n = 4,159) and 10-year (n = 1,487) odds of progression. Cox regression and Kaplan-Meier analyses were performed to estimate 5-year and 10-year risk of exacerbation (n = 6,532) and all-cause mortality (n = 7,331). Results: The first PC, accounting for 43.7% of variance, was defined by CT measures of air trapping and emphysema. The second PC, accounting for 13.7% of variance, was defined by spirometric and CT measures of vital capacity and lung volume. The third PC, accounting for 7.9% of the variance, was defined by CT measures of lung mass, airway thickening, and body habitus. Stratification of patients across each disease axis revealed up to 3.2-fold (95% confidence interval [CI] 2.4, 4.3) greater odds of 5-year progression, 5.4-fold (95% CI 4.6, 6.3) greater risk of 5-year exacerbation, and 5.0-fold (95% CI 4.2, 6.0) greater risk of 10-year mortality between the highest and lowest quartiles. Conclusions: Unsupervised learning analysis of the COPDGene cohort reveals that CT measurements may bolster patient stratification along the continuum of COPD phenotypes. Each of the disease axes also individually demonstrate prognostic potential, predictive of future forced expiratory volume in 1 second decline, exacerbation, and mortality.

Reader Perceptions and Impact of AI on CT Assessment of Air Trapping.

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.

CNN-based Deformable Registration Facilitates Fast and Accurate Air Trapping Measurements at Inspiratory and Expiratory CT.

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.

Automated CNN-Based Analysis Versus Manual Analysis for MR Elastography in Nonalcoholic Fatty Liver Disease: Intermethod Agreement and Fibrosis Stage Discriminative Performance.

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.

Erratum: CNN-based Deformable Registration Facilitates Fast and Accurate Air Trapping Measurements at Inspiratory and Expiratory CT.

[This corrects the article DOI: 10.1148/ryai.2021210211.].

Automated CT Staging of Chronic Obstructive Pulmonary Disease Severity for Predicting Disease Progression and Mortality with a Deep Learning Convolutional Neural Network.

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.

Multi-arterial phase MRI depicts inconsistent arterial phase hyperenhancement (APHE) subtypes in liver observations of patients at risk for hepatocellular carcinoma.

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.

CNN color-coded difference maps accurately display longitudinal changes in liver MRI-PDFF.

OBJECTIVES: To assess the feasibility of a CNN-based liver registration algorithm to generate difference maps for visual display of spatiotemporal changes in liver PDFF, without needing manual annotations. METHODS: This retrospective exploratory study included 25 patients with suspected or confirmed NAFLD, who underwent PDFF-MRI at two time points at our institution. PDFF difference maps were generated by applying a CNN-based liver registration algorithm, then subtracting follow-up from baseline PDFF maps. The difference maps were post-processed by smoothing (5 cm2 round kernel) and applying a categorical color scale. Two fellowship-trained abdominal radiologists and one radiology resident independently reviewed difference maps to visually determine segmental PDFF change. Their visual assessment was compared with manual ROI-based measurements of each Couinaud segment and whole liver PDFF using intraclass correlation (ICC) and Bland-Altman analysis. Inter-reader agreement for visual assessment was calculated (ICC). RESULTS: The mean patient age was 49 years (12 males). Baseline and follow-up PDFF ranged from 2.0 to 35.3% and 3.5 to 32.0%, respectively. PDFF changes ranged from - 20.4 to 14.1%. ICCs against the manual reference exceeded 0.95 for each reader, except for segment 2 (2 readers ICC = 0.86-0.91) and segment 4a (reader 3 ICC = 0.94). Bland-Altman limits of agreement were within 5% across all three readers. Inter-reader agreement for visually assessed PDFF change (whole liver and segmental) was excellent (ICCs > 0.96), except for segment 2 (ICC = 0.93). CONCLUSIONS: Visual assessment of liver segmental PDFF changes using a CNN-generated difference map strongly agreed with manual estimates performed by an expert reader and yielded high inter-reader agreement. KEY POINTS: • Visual assessment of longitudinal changes in quantitative liver MRI can be performed using a CNN-generated difference map and yields strong agreement with manual estimates performed by expert readers.

Comparison of handcrafted features and convolutional neural networks for liver MR image adequacy assessment.

We propose a random forest classifier for identifying adequacy of liver MR images using handcrafted (HC) features and deep convolutional neural networks (CNNs), and analyze the relative role of these two components in relation to the training sample size. The HC features, specifically developed for this application, include Gaussian mixture models, Euler characteristic curves and texture analysis. Using HC features outperforms the CNN for smaller sample sizes and with increased interpretability. On the other hand, with enough training data, the combined classifier outperforms the models trained with HC features or CNN features alone. These results illustrate the added value of HC features with respect to CNNs, especially when insufficient data is available, as is often found in clinical studies.

Convolutional neural network-automated hepatobiliary phase adequacy evaluation may optimize examination time.

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.

Fully automated convolutional neural network-based affine algorithm improves liver registration and lesion co-localization on hepatobiliary phase T1-weighted MR images.

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.

Association of Macular and Circumpapillary Microvasculature with Visual Field Sensitivity in Advanced Glaucoma.

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.

Measurement Floors and Dynamic Ranges of OCT and OCT Angiography in Glaucoma.

PURPOSE: To determine if OCT angiography (OCTA)-derived vessel density measurements can extend the available dynamic range for detecting glaucoma compared with spectral-domain (SD) OCT-derived thickness measurements. DESIGN: Observational, cross-sectional study. PARTICIPANTS: A total of 509 eyes from 38 healthy participants, 63 glaucoma suspects, and 193 glaucoma patients enrolled in the Diagnostic Innovations in Glaucoma Study. METHODS: Relative vessel density and tissue thickness measurement floors of perifoveal vessel density (pfVD), circumpapillary capillary density (cpCD), circumpapillary retinal nerve fiber (cpRNFL) thickness, ganglion cell complex (GCC) thickness, and visual field (VF) mean deviation (MD) were investigated and compared with a previously reported linear change point model (CPM) and locally weighted scatterplot smoothing curves. MAIN OUTCOME MEASURES: Estimated vessel density and tissue thickness measurement floors and corresponding dynamic ranges. RESULTS: Visual field MD ranged from -30.1 to 2.8 decibels (dB). No measurement floor was found for pfVD, which continued to decrease constantly until very advanced disease. A true floor (i.e., slope of approximately 0 after observed CPM change point) was detected for cpRNFL thickness only. The post-CPM estimated floors were 49.5±2.6 µm for cpRNFL thickness, 70.7±1.0 µm for GCC thickness, and 31.2±1.1% for cpCD. Perifoveal vessel density reached the post-CPM estimated floor later in the disease (VF MD, -25.8±3.8 dB) than cpCD (VF MD, -19.3±2.4 dB), cpRNFL thickness (VF MD, -17.5±3.3 dB), and GCC thickness (VF MD, -13.9±1.8 dB; P < 0.001). The number of available measurement steps from normal values to the CPM estimated floor was greatest for cpRNFL thickness (8.9), followed by GCC thickness (7.4), cpCD (4.5), and pfVD (3.8). CONCLUSIONS: In late-stage glaucoma, particularly when VF MD is worse than -14 dB, OCTA-measured pfVD is a promising tool for monitoring progression because it does not have a detectable measurement floor. However, the number of steps within the dynamic range of a parameter also needs to be considered. Although thickness parameters reached the floor earlier than OCTA-measured pfVD, there are more such steps with thickness than OCTA parameters.

Association Between Lamina Cribrosa Defects and Progressive Retinal Nerve Fiber Layer Loss in Glaucoma.

Importance: Certain features of the lamina cribrosa may be associated with increased risk of glaucoma progression. Objectives: To compare the rates of retinal nerve fiber layer (RNFL) thinning in patients with open-angle glaucoma with or without lamina cribrosa (LC) defects and to evaluate factors associated with the rate of glaucoma progression in eyes with LC defects. Design, Setting, and Participants: This longitudinal cohort study designed in September 2017 and conducted at a tertiary glaucoma center in California included 51 eyes of 43 patients with LC defects and 83 eyes of 68 patients without LC defects followed up for a mean (SD) of 3.5 (0.8) years from April 2012 to May 2017. Main Outcomes and Measures: Focal LC defects were detected using swept-source optical coherence tomographic images. All participants underwent visual field testing and spectral-domain optical coherence tomography for RNFL thickness measurements every 6 months. Univariate and multivariable random-effects models were used to compare the rate of local and global RNFL loss. Results: The mean (95% CI) age at baseline for individuals with LC defects was 69.5 (65.4 to 73.6) years, and for those without LC defects, it was 69.6 (67.2-72.0) years; 18 individuals (41%) with LC defects and 35 individuals (51%) without LC defects were men; 6 individuals (14%) with LC defects and 17 individuals (25%) without were African American. The mean (95% CI) rate of global RNFL loss in eyes with LC defects was 2-fold faster than that in eyes without LC defects (-0.91 [-1.20 to -0.62] vs -0.48 [-0.65 to -0.31] µm/y; difference, -0.43 [-0.76 to -0.09] µm/y; P = .01). The rate of RNFL thinning was faster in the LC defect sectors than that in the unaffected sectors (difference, -0.90 [95% CI, -1.68 to -0.12] µm/y, P = .02). Thinner corneal thickness was the only factor that was associated with a faster rate of RNFL loss in eyes with LC defects (ß2 = -0.09 [95% CI, -0.14 to -0.04], P = .001). No association was found between mean intraocular pressure during follow-up and the mean rate of RNFL thinning in eyes with LC defects (ß2, -0.05 [95% CI, -0.17 to 0.06], P = .36). Conclusions and Relevance: These data suggest that LC defects are an independent risk factor for RNFL thinning and that glaucoma progression may correspond topographically to the LC defect location. Thinner corneal thickness in eyes with LC defects was associated with faster further glaucoma progression. In the management of open-angle glaucoma, LC findings may inform the likelihood and rate of glaucoma progression.