Individual perceptions of community efficacy for non-communicable disease management in twelve communities in China: cross-sectional and longitudinal analyses

OBJECTIVES

This objective of this study was to use empirical data to assess cross-sectional variation singular and changes over time in community efficacy for non-communicable diseases (NCDs) management (COEN) and to examine individual factors associated with changes in COEN.

STUDY DESIGN

This was a longitudinal observational study.

METHODS

Participants with hypertension and diabetes were randomly selected from 12 communities from three cities in eastern China, and a baseline survey and a 1-year follow-up were conducted. The COEN scale has five dimensions: community physical environment (CPE), behavioral risk factors (BRF), mental health and social relationships (MHSR), community health management (CHM), and community organisations and activities (COA). Mixed-effects models were used to investigate the change in COEN over time and the association between individual factors and changes in COEN.

RESULTS

COEN scores showed significant variation singular among the 12 communities (P < 0.001) at the baseline. In the mixed-effects model, CPE (β coefficient: 1.62, P < 0.001), BRF (0.90, P < 0.001), MHSR (0.86, P < 0.001), CHM (0.46, P < 0.001), and total scores (β = 3.57, P < 0.001) increased significantly over time. The changes in COEN were associated with individual characteristics (e.g., older, men, more educated).

CONCLUSIONS

Cross-sectional variations and changes over time in COEN demonstrated the utility of a sensitive instrument. Factors such as age, gender, marriage, education level, and employment may affect the financial and social resources assignment for NCD management. Our findings suggest that further high-quality studies are needed to better evaluate the effect of community empowerment on the prevention and control of NCDs.

One Model to Synthesize Them All: Multi-Contrast Multi-Scale Transformer for Missing Data Imputation

Multi-contrast magnetic resonance imaging (MRI) is widely used in clinical practice as each contrast provides complementary information. However, the availability of each imaging contrast may vary amongst patients, which poses challenges to radiologists and automated image analysis algorithms. A general approach for tackling this problem is missing data imputation, which aims to synthesize the missing contrasts from existing ones. While several convolutional neural networks (CNN) based algorithms have been proposed, they suffer from the fundamental limitations of CNN models, such as the requirement for fixed numbers of input and output channels, the inability to capture long-range dependencies, and the lack of interpretability. In this work, we formulate missing data imputation as a sequence-to-sequence learning problem and propose a multi-contrast multi-scale Transformer (MMT), which can take any subset of input contrasts and synthesize those that are missing. MMT consists of a multi-scale Transformer encoder that builds hierarchical representations of inputs combined with a multi-scale Transformer decoder that generates the outputs in a coarse-to-fine fashion. The proposed multi-contrast Swin Transformer blocks can efficiently capture intra- and inter-contrast dependencies for accurate image synthesis. Moreover, MMT is inherently interpretable as it allows us to understand the importance of each input contrast in different regions by analyzing the in-built attention maps of Transformer blocks in the decoder. Extensive experiments on two large-scale multi-contrast MRI datasets demonstrate that MMT outperforms the state-of-the-art methods quantitatively and qualitatively.

Clinical Assessment of Deep Learning-based Super-Resolution for 3D Volumetric Brain MRI

Artificial intelligence (AI)-based image enhancement has the potential to reduce scan times while improving signal-to-noise ratio (SNR) and maintaining spatial resolution. This study prospectively evaluated AI-based image enhancement in 32 consecutive patients undergoing clinical brain MRI. Standard-of-care (SOC) three-dimensional (3D) T1 precontrast, 3D T2 fluid-attenuated inversion recovery, and 3D T1 postcontrast sequences were performed along with 45% faster versions of these sequences using half the number of phase-encoding steps. Images from the faster sequences were processed by a Food and Drug Administration-cleared AI-based image enhancement software for resolution enhancement. Four board-certified neuroradiologists scored the SOC and AI-enhanced image series independently on a five-point Likert scale for image SNR, anatomic conspicuity, overall image quality, imaging artifacts, and diagnostic confidence. While interrater κ was low to fair, the AI-enhanced scans were noninferior for all metrics and actually demonstrated a qualitative SNR improvement. Quantitative analyses showed that the AI software restored the high spatial resolution of small structures, such as the septum pellucidum. In conclusion, AI-based software can achieve noninferior image quality for 3D brain MRI sequences with a 45% scan time reduction, potentially improving the patient experience and scanner efficiency without sacrificing diagnostic quality. Keywords: MR Imaging, CNS, Brain/Brain Stem, Reconstruction Algorithms © RSNA, 2022.

Deep Learning Enables 60% Accelerated Volumetric Brain MRI While Preserving Quantitative Performance: A Prospective, Multicenter, Multireader Trial

BACKGROUND AND PURPOSE

In this prospective, multicenter, multireader study, we evaluated the impact on both image quality and quantitative image-analysis consistency of 60% accelerated volumetric MR imaging sequences processed with a commercially available, vendor-agnostic, DICOM-based, deep learning tool (SubtleMR) compared with that of standard of care.

MATERIALS AND METHODS

Forty subjects underwent brain MR imaging examinations on 6 scanners from 5 institutions. Standard of care and accelerated datasets were acquired for each subject, and the accelerated scans were enhanced with deep learning processing. Standard of care, accelerated scans, and accelerated-deep learning were subjected to NeuroQuant quantitative analysis and classified by a neuroradiologist into clinical disease categories. Concordance of standard of care and accelerated-deep learning biomarker measurements were assessed. Randomized, side-by-side, multiplanar datasets (360 series) were presented blinded to 2 neuroradiologists and rated for apparent SNR, image sharpness, artifacts, anatomic/lesion conspicuity, image contrast, and gray-white differentiation to evaluate image quality.

RESULTS

Accelerated-deep learning was statistically superior to standard of care for perceived quality across imaging features despite a 60% sequence scan-time reduction. Both accelerated-deep learning and standard of care were superior to accelerated scans for all features. There was no difference in quantitative volumetric biomarkers or clinical classification for standard of care and accelerated-deep learning datasets.

CONCLUSIONS

Deep learning reconstruction allows 60% sequence scan-time reduction while maintaining high volumetric quantification accuracy, consistent clinical classification, and what radiologists perceive as superior image quality compared with standard of care. This trial supports the reliability, efficiency, and utility of deep learning-based enhancement for quantitative imaging. Shorter scan times may heighten the use of volumetric quantitative MR imaging in routine clinical settings.

Applying Deep Learning to Accelerated Clinical Brain Magnetic Resonance Imaging for Multiple Sclerosis

Background: Magnetic resonance (MR) scans are routine clinical procedures for monitoring people with multiple sclerosis (PwMS). Patient discomfort, timely scheduling, and financial burden motivate the need to accelerate MR scan time. We examined the clinical application of a deep learning (DL) model in restoring the image quality of accelerated routine clinical brain MR scans for PwMS.

Methods: We acquired fast 3D T1w BRAVO and fast 3D T2w FLAIR MRI sequences (half the phase encodes and half the number of slices) in parallel to conventional parameters. Using a subset of the scans, we trained a DL model to generate images from fast scans with quality similar to the conventional scans and then applied the model to the remaining scans. We calculated clinically relevant T1w volumetrics (normalized whole brain, thalamic, gray matter, and white matter volume) for all scans and T2 lesion volume in a sub-analysis. We performed paired t-tests comparing conventional, fast, and fast with DL for these volumetrics, and fit repeated measures mixed-effects models to test for differences in correlations between volumetrics and clinically relevant patient-reported outcomes (PRO).

Results: We found statistically significant but small differences between conventional and fast scans with DL for all T1w volumetrics. There was no difference in the extent to which the key T1w volumetrics correlated with clinically relevant PROs of MS symptom burden and neurological disability.

Conclusion: A deep learning model that improves the image quality of the accelerated routine clinical brain MR scans has the potential to inform clinically relevant outcomes in MS.

Low-count whole-body PET with deep learning in a multicenter and externally validated study

More widespread use of positron emission tomography (PET) imaging is limited by its high cost and radiation dose. Reductions in PET scan time or radiotracer dosage typically degrade diagnostic image quality (DIQ). Deep-learning-based reconstruction may improve DIQ, but such methods have not been clinically evaluated in a realistic multicenter, multivendor environment. In this study, we evaluated the performance and generalizability of a deep-learning-based image-quality enhancement algorithm applied to fourfold reduced-count whole-body PET in a realistic clinical oncologic imaging environment with multiple blinded readers, institutions, and scanner types. We demonstrate that the low-count-enhanced scans were noninferior to the standard scans in DIQ (p < 0.05) and overall diagnostic confidence (p < 0.001) independent of the underlying PET scanner used. Lesion detection for the low-count-enhanced scans had a high patient-level sensitivity of 0.94 (0.83-0.99) and specificity of 0.98 (0.95-0.99). Interscan kappa agreement of 0.85 was comparable to intrareader (0.88) and pairwise inter-reader agreements (maximum of 0.72). SUV quantification was comparable in the reference regions and lesions (lowest p-value=0.59) and had high correlation (lowest CCC = 0.94). Thus, we demonstrated that deep learning can be used to restore diagnostic image quality and maintain SUV accuracy for fourfold reduced-count PET scans, with interscan variations in lesion depiction, lower than intra- and interreader variations. This method generalized to an external validation set of clinical patients from multiple institutions and scanner types. Overall, this method may enable either dose or exam-duration reduction, increasing safety and lowering the cost of PET imaging.

Tissue at Risk and Ischemic Core Estimation Using Deep Learning in Acute Stroke

BACKGROUND AND PURPOSE

In acute stroke patients with large vessel occlusions, it would be helpful to be able to predict the difference in the size and location of the final infarct based on the outcome of reperfusion therapy. Our aim was to demonstrate the value of deep learning-based tissue at risk and ischemic core estimation. We trained deep learning models using a baseline MR image in 3 multicenter trials.

MATERIALS AND METHODS

Patients with acute ischemic stroke from 3 multicenter trials were identified and grouped into minimal (≤20%), partial (20%-80%), and major (≥80%) reperfusion status based on 4- to 24-hour follow-up MR imaging if available or into unknown status if not. Attention-gated convolutional neural networks were trained with admission imaging as input and the final infarct as ground truth. We explored 3 approaches: 1) separate: train 2 independent models with patients with minimal and major reperfusion; 2) pretraining: develop a single model using patients with partial and unknown reperfusion, then fine-tune it to create 2 separate models for minimal and major reperfusion; and 3) thresholding: use the current clinical method relying on apparent diffusion coefficient and time-to-maximum of the residue function maps. Models were evaluated using area under the curve, the Dice score coefficient, and lesion volume difference.

RESULTS

Two hundred thirty-seven patients were included (minimal, major, partial, and unknown reperfusion: n = 52, 80, 57, and 48, respectively). The pretraining approach achieved the highest median Dice score coefficient (tissue at risk = 0.60, interquartile range, 0.43-0.70; core = 0.57, interquartile range, 0.30-0.69). This was higher than the separate approach (tissue at risk = 0.55; interquartile range, 0.41-0.69; P = .01; core = 0.49; interquartile range, 0.35-0.66; P = .04) or thresholding (tissue at risk = 0.56; interquartile range, 0.42-0.65; P = .008; core = 0.46; interquartile range, 0.16-0.54; P < .001).

CONCLUSIONS

Deep learning models with fine-tuning lead to better performance for predicting tissue at risk and ischemic core, outperforming conventional thresholding methods.

A generic deep learning model for reduced gadolinium dose in contrast-enhanced brain MRI

PURPOSE

With rising safety concerns over the use of gadolinium-based contrast agents (GBCAs) in contrast-enhanced MRI, there is a need for dose reduction while maintaining diagnostic capability. This work proposes comprehensive technical solutions for a deep learning (DL) model that predicts contrast-enhanced images of the brain with approximately 10% of the standard dose, across different sites and scanners.

METHODS

The proposed DL model consists of a set of methods that improve the model robustness and generalizability. The steps include multi-planar reconstruction, 2.5D model, enhancement-weighted L1, perceptual, and adversarial losses. The proposed model predicts contrast-enhanced images from corresponding pre-contrast and low-dose images. With IRB approval and informed consent, 640 heterogeneous patient scans (56 train, 13 validation, and 571 test) from 3 institutions consisting of 3D T1-weighted brain images were used. Quantitative metrics were computed and 50 randomly sampled test cases were evaluated by 2 board-certified radiologists. Quantitative tumor segmentation was performed on cases with abnormal enhancements. Ablation study was performed for systematic evaluation of proposed technical solutions.

RESULTS

The average peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) between full-dose and model prediction were 35.07 ± 3.84 dB and 0.92 ± 0.02 , respectively. Radiologists found the same enhancing pattern in 45/50 (90%) cases; discrepancies were minor differences in contrast intensity and artifacts, with no effect on diagnosis. The average segmentation Dice score between full-dose and synthesized images was 0.88 ± 0.06 (median = 0.91).

CONCLUSIONS

We have proposed a DL model with technical solutions for low-dose contrast-enhanced brain MRI with potential generalizability under diverse clinical settings.

Abstract P325: Validation of Deep Learning Based Critical Hypoperfusion and Ischemic Core Prediction in a Multicenter External Randomized Controlled Trial

Objective: We previously developed two separate deep learning (DL) models to segment the ischemic core and critically hypoperfused tissue on baseline imaging of acute ischemic stroke patients. We aimed to validate the models in an external, multi-center randomized clinical trial (DEFUSE3) and compare with the current clinical standard.

Methods: The DL models were previously trained in a separate dataset in which follow-up MRI, obtained at 3-7 days, was used as the reference for critically hypoperfused tissue in patients who did not reperfuse and as the reference for the ischemic core in patients who did reperfuse. For validation, we included DEFUSE3 patients with adequate quality baseline MR perfusion and a 24-hour follow-up DWI scan. The 24-hour DWI lesion served as the reference for ischemic core in patients in the thrombectomy arm and for critically hypoperfused tissue for patients in the medical arm. RAPID was used to generate perfusion maps (Tmax, cerebral blood flow, cerebral blood volume, and mean transient time). The accuracy of segmenting the ischemic core and critically hypoperfused tissue on baseline imaging was compared between the DL approach and the traditional thresholding approach implemented in RAPID.

Results: In the 46 patients included for analysis, 24 were in the medical arm and 22 in the thrombectomy arm. Compared to a traditional thresholding method, the DL model segmented the ischemic core more accurately (AUC of 0.92 vs 0.72, p=0.0001 and volume difference of -8ml vs -21ml, p=0.001). Similarly, the DL model segmented critically hypoperfused tissue more accurately (AUC of 0.93 vs 0.80, p<0.0001; volume difference 14ml vs. 55ml, p=0.0005). However, great heterogeneity in final infarct was noticed in medical arm. See tables and figures.

Conclusions: The DL-based critical hypoperfusion and ischemic core prediction provides more accurate prediction on final infarct than a commonly used thresholding method in this external validation.

Abstract P319: Can Deep Learning Find the Ischemic Core on CT? Transfer Learning From Pre-Trained MRI-Based Networks

Objective: Ischemic core prediction from CT perfusion (CTP) remains inaccurate compared with gold standard diffusion-weighted imaging (DWI). We evaluated if a deep learning model to predict the DWI lesion from MR perfusion (MRP) could facilitate ischemic core prediction on CTP.

Method: Using the multi-center CRISP cohort of acute ischemic stroke patient with CTP before thrombectomy, we included patients with major reperfusion (TICI score≥2b), adequate image quality, and follow-up MRI at 3-7 days. Perfusion parameters including Tmax, mean transient time, cerebral blood flow (CBF), and cerebral blood volume were reconstructed by RAPID software. Core lab experts outlined the stroke lesion on the follow-up MRI. A previously trained MRI model in a separate group of patients was used as a starting point, which used MRP parameters as input and RAPID ischemic core on DWI as ground truth. We fine-tuned this model, using CTP parameters as input, and follow-up MRI as ground truth. Another model was also trained from scratch with only CTP data. 5-fold cross validation was used. Performance of the models was compared with ischemic core (rCBF≤30%) from RAPID software to identify the presence of a large infarct (volume>70 or >100ml).

Results: 94 patients in the CRISP trial met the inclusion criteria (mean age 67±15 years, 52% male, median baseline NIHSS 18, median 90-day mRS 2). Without fine-tuning, the MRI model had an agreement of 73% in infarct >70ml, and 69% in >100ml; the MRI model fine-tuned on CT improved the agreement to 77% and 73%; The CT model trained from scratch had agreements of 73% and 71%; All of the deep learning models outperformed the rCBF segmentation from RAPID, which had agreements of 51% and 64%. See Table and figure.

Conclusions: It is feasible to apply MRP-based deep learning model to CT. Fine-tuning with CTP data further improves the predictions. All deep learning models predict the stroke lesion after major recanalization better than thresholding approaches based on rCBF.

Predicting 15O-Water PET cerebral blood flow maps from multi-contrast MRI using a deep convolutional neural network with evaluation of training cohort bias

To improve the quality of MRI-based cerebral blood flow (CBF) measurements, a deep convolutional neural network (dCNN) was trained to combine single- and multi-delay arterial spin labeling (ASL) and structural images to predict gold-standard ¹⁵O-water PET CBF images obtained on a simultaneous PET/MRI scanner. The dCNN was trained and tested on 64 scans in 16 healthy controls (HC) and 16 cerebrovascular disease patients (PT) with 4-fold cross-validation. Fidelity to the PET CBF images and the effects of bias due to training on different cohorts were examined. The dCNN significantly improved CBF image quality compared with ASL alone (mean ± standard deviation): structural similarity index (0.854 ± 0.036 vs. 0.743 ± 0.045 [single-delay] and 0.732 ± 0.041 [multi-delay], P < 0.0001); normalized root mean squared error (0.209 ± 0.039 vs. 0.326 ± 0.050 [single-delay] and 0.344 ± 0.055 [multi-delay], P < 0.0001). The dCNN also yielded mean CBF with reduced estimation error in both HC and PT (P < 0.001), and demonstrated better correlation with PET. The dCNN trained with the mixed HC and PT cohort performed the best. The results also suggested that models should be trained on cases representative of the target population.

Synthesize High-Quality Multi-Contrast Magnetic Resonance Imaging From Multi-Echo Acquisition Using Multi-Task Deep Generative Model

Multi-echo saturation recovery sequence can provide redundant information to synthesize multi-contrast magnetic resonance imaging. Traditional synthesis methods, such as GE's MAGiC platform, employ a model-fitting approach to generate parameter-weighted contrasts. However, models' over-simplification, as well as imperfections in the acquisition, can lead to undesirable reconstruction artifacts, especially in T2-FLAIR contrast. To improve the image quality, in this study, a multi-task deep learning model is developed to synthesize multi-contrast neuroimaging jointly using both signal relaxation relationships and spatial information. Compared with previous deep learning-based synthesis, the correlation between different destination contrast is utilized to enhance reconstruction quality. To improve model generalizability and evaluate clinical significance, the proposed model was trained and tested on a large multi-center dataset, including healthy subjects and patients with pathology. Results from both quantitative comparison and clinical reader study demonstrate that the multi-task formulation leads to more efficient and accurate contrast synthesis than previous methods.

[A retrospective analysis of single preterm birth incidence and high-risk factors based on maternal age stratification]

Objective: To compare the preterm birth rate among different age groups and analyze relative high-risk factors of preterm birth. Methods: A retrospective analysis was conducted on clinical data of single pregnant women ≥28 gestational weeks from January 2013 to May 2019 in the First Affiliated Hospital of Chongqing Medical Hospital. All involved women were divided into three groups according to age, Group 1 (aged<35 years), Group 2 (aged 35-39 years), and Group 3 (aged ≥40 years). The preterm birth rate among 3 groups was compared and their high-risk factors were analyzed. Results: There were 48 288 singleton pregnancies during the study period, of which 3 351 were preterm births， preterm birth rate was 6.94% (3 351/48 288). In Group 1, there were 42 020 women, of which 2 699 were preterm births (6.42%, 2 699/42 020); in Group 2, there were 5 061 women, of which 491 were preterm births (9.70%, 491/5 061); and in Group 3, there were 1 207 women, of which 161 were preterm births (13.34%, 161/1 207). Comparing the spontaneous preterm birth rates among the three groups, Group 1 was the lowest one and Group 3 was the highest one (3.72% vs 4.51% vs 5.88%); comparing the medical preterm birth rates among the three groups, Group 1 also was the lowest one and Group 3 also was the highest one (2.70% vs 5.20% vs 7.46%); the differences were statistically significant (P<0.05). The incidence of spontaneous and medical preterm birth according gestational weeks were compared among three groups and there were no significant differences (P>0.05). Comparing and analyzing the high-risk factors of medical preterm birth, the incidence of intrahepatic cholestasis of pregnancy and fetal distress in Group 1 were higher than those in Group 2 and 3; the incidence of placenta praevia were significantly higher in Group 2 and 3 than that in Group 1; the differences were statistically significant (P<0.05). Conclusions: Maternal age is a significant high-risk factor of both spontaneous preterm birth and medical preterm birth, and the risk of preterm birth increases with age. For medical preterm birth, compared with right-age pregnant women, placenta praevia is the high-risk factor for women in advanced maternal age(AMA), which have great effect on medical preterm birth rate of AMA.

Joint multi-contrast variational network reconstruction (jVN) with application to rapid 2D and 3D imaging

PURPOSE

To improve the image quality of highly accelerated multi-channel MRI data by learning a joint variational network that reconstructs multiple clinical contrasts jointly.

METHODS

Data from our multi-contrast acquisition were embedded into the variational network architecture where shared anatomical information is exchanged by mixing the input contrasts. Complementary k-space sampling across imaging contrasts and Bunch-Phase/Wave-Encoding were used for data acquisition to improve the reconstruction at high accelerations. At 3T, our joint variational network approach across T1w, T2w and T2-FLAIR-weighted brain scans was tested for retrospective under-sampling at R = 6 (2D) and R = 4 × 4 (3D) acceleration. Prospective acceleration was also performed for 3D data where the combined acquisition time for whole brain coverage at 1 mm isotropic resolution across three contrasts was less than 3 min.

RESULTS

Across all test datasets, our joint multi-contrast network better preserved fine anatomical details with reduced image-blurring when compared to the corresponding single-contrast reconstructions. Improvement in image quality was also obtained through complementary k-space sampling and Bunch-Phase/Wave-Encoding where the synergistic combination yielded the overall best performance as evidenced by exemplary slices and quantitative error metrics.

CONCLUSION

By leveraging shared anatomical structures across the jointly reconstructed scans, our joint multi-contrast approach learnt more efficient regularizers, which helped to retain natural image appearance and avoid over-smoothing. When synergistically combined with advanced encoding techniques, the performance was further improved, enabling up to R = 16-fold acceleration with good image quality. This should help pave the way to very rapid high-resolution brain exams.

Use of Deep Learning to Predict Final Ischemic Stroke Lesions From Initial Magnetic Resonance Imaging

IMPORTANCE

Predicting infarct size and location is important for decision-making and prognosis in patients with acute stroke.

OBJECTIVES

To determine whether a deep learning model can predict final infarct lesions using magnetic resonance images (MRIs) acquired at initial presentation (baseline) and to compare the model with current clinical prediction methods.

DESIGN, SETTING, AND PARTICIPANTS

In this multicenter prognostic study, a specific type of neural network for image segmentation (U-net) was trained, validated, and tested using patients from the Imaging Collaterals in Acute Stroke (iCAS) study from April 14, 2014, to April 15, 2018, and the Diffusion Weighted Imaging Evaluation for Understanding Stroke Evolution Study-2 (DEFUSE-2) study from July 14, 2008, to September 17, 2011 (reported in October 2012). Patients underwent baseline perfusion-weighted and diffusion-weighted imaging and MRI at 3 to 7 days after baseline. Patients were grouped into unknown, minimal, partial, and major reperfusion status based on 24-hour imaging results. Baseline images acquired at presentation were inputs, and the final true infarct lesion at 3 to 7 days was considered the ground truth for the model. The model calculated the probability of infarction for every voxel, which can be thresholded to produce a prediction. Data were analyzed from July 1, 2018, to March 7, 2019.

MAIN OUTCOMES AND MEASURES

Area under the curve, Dice score coefficient (DSC) (a metric from 0-1 indicating the extent of overlap between the prediction and the ground truth; a DSC of ≥0.5 represents significant overlap), and volume error. Current clinical methods were compared with model performance in subgroups of patients with minimal or major reperfusion.

RESULTS

Among the 182 patients included in the model (97 women [53.3%]; mean [SD] age, 65 [16] years), the deep learning model achieved a median area under the curve of 0.92 (interquartile range [IQR], 0.87-0.96), DSC of 0.53 (IQR, 0.31-0.68), and volume error of 9 (IQR, -14 to 29) mL. In subgroups with minimal (DSC, 0.58 [IQR, 0.31-0.67] vs 0.55 [IQR, 0.40-0.65]; P = .37) or major (DSC, 0.48 [IQR, 0.29-0.65] vs 0.45 [IQR, 0.15-0.54]; P = .002) reperfusion for which comparison with existing clinical methods was possible, the deep learning model had comparable or better performance.

CONCLUSIONS AND RELEVANCE

The deep learning model appears to have successfully predicted infarct lesions from baseline imaging without reperfusion information and achieved comparable performance to existing clinical methods. Predicting the subacute infarct lesion may help clinicians prepare for decompression treatment and aid in patient selection for neuroprotective clinical trials.

Abstract WP79: The Value of Pre-Training for Deep Learning Acute Stroke Triaging Models

Objective: We investigated if deep learning models are able to define the penumbra and ischemic core by comparing models from two training strategies (with and without pre-training) and clinical thresholding criteria (MRI parameter time-to-peak of the residue function [Tmax] and apparent diffusion coefficient [ADC]).

Methods: We selected patients from two multicenter stroke trials, with baseline perfusion-weighted imaging (PWI) and diffusion-weighted imaging (DWI) and 3-7 day T2-FLAIR. Based on reperfusion rate calculated from baseline and 24 hr PWI, patients were grouped into unknown (no 24 hr PWI scan), minimal (≤20%), partial (20%-80%), and major (≥80%) reperfusion. Attention-gated U-net structure was selected for training, with eight image channels from baseline PWI/DWI as inputs and the infarct lesion manually segmented on T2-FLAIR as ground truth. Two training strategies were used: (1) training two models separately in minimal and major reperfusion patients; (2) pre-training a model using patients with partial and unknown reperfusion, then fine-tuning two models using minimal and major reperfusion patients, respectively. Prediction was evaluated by Dice score coefficient (DSC), and lesion volume error at an optimal threshold. In minimal and major reperfusion patients, the deep learning models and Tmax and ADC thresholding were compared using paired sample Wilcoxon test.

Results: 182 patients were included (85 males, age 65±16 yrs, baseline NIHSS 15 IQR 10-19), with a breakdown of minimal/major/partial/unknown reperfusion status of 32/65/43/42 patients, respectively. The pre-training approach performed the best among all approaches (Table 1, Figure 1).

Conclusion: Deep learning models to predict penumbra and ischemic core are best trained using general pre-training on a wide range of stroke cases followed by fine-tuning on the extreme cases. This method outperforms conventional DWI-PWI mismatch inspired thresholding approaches.

Ultra-low-dose PET reconstruction using generative adversarial network with feature matching and task-specific perceptual loss

PURPOSE

Our goal was to use a generative adversarial network (GAN) with feature matching and task-specific perceptual loss to synthesize standard-dose amyloid Positron emission tomography (PET) images of high quality and including accurate pathological features from ultra-low-dose PET images only.

METHODS

Forty PET datasets from 39 participants were acquired with a simultaneous PET/MRI scanner following injection of 330 ± 30 MBq of the amyloid radiotracer 18F-florbetaben. The raw list-mode PET data were reconstructed as the standard-dose ground truth and were randomly undersampled by a factor of 100 to reconstruct 1% low-dose PET scans. A 2D encoder-decoder network was implemented as the generator to synthesize a standard-dose image and a discriminator was used to evaluate them. The two networks contested with each other to achieve high-visual quality PET from the ultra-low-dose PET. Multi-slice inputs were used to reduce noise by providing the network with 2.5D information. Feature matching was applied to reduce hallucinated structures. Task-specific perceptual loss was designed to maintain the correct pathological features. The image quality was evaluated by peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and root mean square error (RMSE) metrics with and without each of these modules. Two expert radiologists were asked to score image quality on a 5-point scale and identified the amyloid status (positive or negative).

RESULTS

With only low-dose PET as input, the proposed method significantly outperformed Chen et al.'s method (Chen et al. Radiology. 2018;290:649-656) (which shows the best performance in this task) with the same input (PET-only model) by 1.87 dB in PSNR, 2.04% in SSIM, and 24.75% in RMSE. It also achieved comparable results to Chen et al.'s method which used additional magnetic resonance imaging (MRI) inputs (PET-MR model). Experts' reading results showed that the proposed method could achieve better overall image quality and maintain better pathological features indicating amyloid status than both PET-only and PET-MR models proposed by Chen et al. CONCLUSION: Standard-dose amyloid PET images can be synthesized from ultra-low-dose images using GAN. Applying adversarial learning, feature matching, and task-specific perceptual loss are essential to ensure image quality and the preservation of pathological features.

Ultra-Low-Dose 18F-Florbetaben Amyloid PET Imaging Using Deep Learning with Multi-Contrast MRI Inputs

Purpose To reduce radiotracer requirements for amyloid PET/MRI without sacrificing diagnostic quality by using deep learning methods. Materials and Methods Forty data sets from 39 patients (mean age ± standard deviation [SD], 67 years ± 8), including 16 male patients and 23 female patients (mean age, 66 years ± 6 and 68 years ± 9, respectively), who underwent simultaneous amyloid (fluorine 18 [18F]-florbetaben) PET/MRI examinations were acquired from March 2016 through October 2017 and retrospectively analyzed. One hundredth of the raw list-mode PET data were randomly chosen to simulate a low-dose (1%) acquisition. Convolutional neural networks were implemented with low-dose PET and multiple MR images (PET-plus-MR model) or with low-dose PET alone (PET-only) as inputs to predict full-dose PET images. Quality of the synthesized images was evaluated while Bland-Altman plots assessed the agreement of regional standard uptake value ratios (SUVRs) between image types. Two readers scored image quality on a five-point scale (5 = excellent) and determined amyloid status (positive or negative). Statistical analyses were carried out to assess the difference of image quality metrics and reader agreement and to determine confidence intervals (CIs) for reading results. Results The synthesized images (especially from the PET-plus-MR model) showed marked improvement on all quality metrics compared with the low-dose image. All PET-plus-MR images scored 3 or higher, with proportions of images rated greater than 3 similar to those for the full-dose images (-10% difference [eight of 80 readings], 95% CI: -15%, -5%). Accuracy for amyloid status was high (71 of 80 readings [89%]) and similar to intrareader reproducibility of full-dose images (73 of 80 [91%]). The PET-plus-MR model also had the smallest mean and variance for SUVR difference to full-dose images. Conclusion Simultaneously acquired MRI and ultra-low-dose PET data can be used to synthesize full-dose-like amyloid PET images. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Catana in this issue.

Deep Generative Adversarial Neural Networks for Compressive Sensing MRI

Undersampled magnetic resonance image (MRI) reconstruction is typically an ill-posed linear inverse task. The time and resource intensive computations require tradeoffs between accuracy and speed. In addition, state-of-the-art compressed sensing (CS) analytics are not cognizant of the image diagnostic quality. To address these challenges, we propose a novel CS framework that uses generative adversarial networks (GAN) to model the (low-dimensional) manifold of high-quality MR images. Leveraging a mixture of least-squares (LS) GANs and pixel-wise l1/l2 cost, a deep residual network with skip connections is trained as the generator that learns to remove the aliasing artifacts by projecting onto the image manifold. The LSGAN learns the texture details, while the l1/l2 cost suppresses high-frequency noise. A discriminator network, which is a multilayer convolutional neural network (CNN), plays the role of a perceptual cost that is then jointly trained based on high-quality MR images to score the quality of retrieved images. In the operational phase, an initial aliased estimate (e.g., simply obtained by zero-filling) is propagated into the trained generator to output the desired reconstruction. This demands a very low computational overhead. Extensive evaluations are performed on a large contrast-enhanced MR dataset of pediatric patients. Images rated by expert radiologists corroborate that GANCS retrieves higher quality images with improved fine texture details compared with conventional Wavelet-based and dictionary-learning-based CS schemes as well as with deep-learning-based schemes using pixel-wise training. In addition, it offers reconstruction times of under a few milliseconds, which are two orders of magnitude faster than the current state-of-the-art CS-MRI schemes.

Deep Learning in Neuroradiology

Deep learning is a form of machine learning using a convolutional neural network architecture that shows tremendous promise for imaging applications. It is increasingly being adapted from its original demonstration in computer vision applications to medical imaging. Because of the high volume and wealth of multimodal imaging information acquired in typical studies, neuroradiology is poised to be an early adopter of deep learning. Compelling deep learning research applications have been demonstrated, and their use is likely to grow rapidly. This review article describes the reasons, outlines the basic methods used to train and test deep learning models, and presents a brief overview of current and potential clinical applications with an emphasis on how they are likely to change future neuroradiology practice. Facility with these methods among neuroimaging researchers and clinicians will be important to channel and harness the vast potential of this new method.

ISLES 2016 and 2017-Benchmarking Ischemic Stroke Lesion Outcome Prediction Based on Multispectral MRI

Performance of models highly depend not only on the used algorithm but also the data set it was applied to. This makes the comparison of newly developed tools to previously published approaches difficult. Either researchers need to implement others' algorithms first, to establish an adequate benchmark on their data, or a direct comparison of new and old techniques is infeasible. The Ischemic Stroke Lesion Segmentation (ISLES) challenge, which has ran now consecutively for 3 years, aims to address this problem of comparability. ISLES 2016 and 2017 focused on lesion outcome prediction after ischemic stroke: By providing a uniformly pre-processed data set, researchers from all over the world could apply their algorithm directly. A total of nine teams participated in ISLES 2015, and 15 teams participated in ISLES 2016. Their performance was evaluated in a fair and transparent way to identify the state-of-the-art among all submissions. Top ranked teams almost always employed deep learning tools, which were predominately convolutional neural networks (CNNs). Despite the great efforts, lesion outcome prediction persists challenging. The annotated data set remains publicly available and new approaches can be compared directly via the online evaluation system, serving as a continuing benchmark (www.isles-challenge.org).

Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI

BACKGROUND

There are concerns over gadolinium deposition from gadolinium-based contrast agents (GBCA) administration.

PURPOSE

To reduce gadolinium dose in contrast-enhanced brain MRI using a deep learning method.

STUDY TYPE

Retrospective, crossover.

POPULATION

Sixty patients receiving clinically indicated contrast-enhanced brain MRI.

SEQUENCE

3D T₁ -weighted inversion-recovery prepped fast-spoiled-gradient-echo (IR-FSPGR) imaging was acquired at both 1.5T and 3T. In 60 brain MRI exams, the IR-FSPGR sequence was obtained under three conditions: precontrast, postcontrast images with 10% low-dose (0.01mmol/kg) and 100% full-dose (0.1 mmol/kg) of gadobenate dimeglumine. We trained a deep learning model using the first 10 cases (with mixed indications) to approximate full-dose images from the precontrast and low-dose images. Synthesized full-dose images were created using the trained model in two test sets: 20 patients with mixed indications and 30 patients with glioma.

ASSESSMENT

For both test sets, low-dose, true full-dose, and the synthesized full-dose postcontrast image sets were compared quantitatively using peak-signal-to-noise-ratios (PSNR) and structural-similarity-index (SSIM). For the test set comprised of 20 patients with mixed indications, two neuroradiologists scored blindly and independently for the three postcontrast image sets, evaluating image quality, motion-artifact suppression, and contrast enhancement compared with precontrast images.

STATISTICAL ANALYSIS

Results were assessed using paired t-tests and noninferiority tests.

RESULTS

The proposed deep learning method yielded significant (n = 50, P < 0.001) improvements over the low-dose images (>5 dB PSNR gains and >11.0% SSIM). Ratings on image quality (n = 20, P = 0.003) and contrast enhancement (n = 20, P < 0.001) were significantly increased. Compared to true full-dose images, the synthesized full-dose images have a slight but not significant reduction in image quality (n = 20, P = 0.083) and contrast enhancement (n = 20, P = 0.068). Slightly better (n = 20, P = 0.039) motion-artifact suppression was noted in the synthesized images. The noninferiority test rejects the inferiority of the synthesized to true full-dose images for image quality (95% CI: -14-9%), artifacts suppression (95% CI: -5-20%), and contrast enhancement (95% CI: -13-6%).

DATA CONCLUSION

With the proposed deep learning method, gadolinium dose can be reduced 10-fold while preserving contrast information and avoiding significant image quality degradation.

LEVEL OF EVIDENCE

3 Technical Efficacy: Stage 5 J. MAGN. RESON. IMAGING 2018;48:330-340.

Abstract WP53: Improved Prediction of the Final Infarct From Acute Stroke Neuroimaging Using Deep Learning

Introduction: Predicting the final infarct for acute stroke from acute imaging is valuable for triage and prognosis (1). We developed and tested a Deep Learning model, based on a 3D Convolutional Neural Network (CNN) architecture, to predict the lesion based on a 30-90 day scan from acute images.

Method: The model has 3 advantages compared with traditional CNN (Figure):

1. 3D CNN more efficiently utilizes spatial information across multiple slices.

2. Patches instead of entire images are used as inputs. With a patch-based approach, we avoid the impact of minimally-relevant information from distant voxels. Training on patches also prevents over-fitting by augmenting each image into thousands of samples.

3. Multi-scale structure is used by processing patches with different resolutions. Segmentation based on a single scale image cannot fully capture varying local information and may miss contextual information. We use two scales of patches to learn both local and global context.

The model was trained and tested using the MICCAI ISLES 2017 challenge dataset (2), which consists of 43 cases with acute ADC and PWI maps paired with annotated final infarct segmentations at day 30-90. Dice score coefficient (DSC) and AUC for segmentation were used as quality metrics.

Results: Using 70% of dataset for training and rest for testing, we achieved a DSC of 0.43±0.18 and 0.90 for AUC. As a comparison, the winning entry for the ISLES 2016 challenge achieved a DSC of 0.31, while several previous research works (threshold based, cluster based, Generalized Linear Model, etc.) achieve up to 0.84 AUC (1).

Conclusion: We demonstrate that a deep learning approach can predict the final stroke lesion based on acute diffusion and perfusion neuroimaging data. Given its inherent speed, high performance, and capacity for further training, deep learning is a promising method for stroke lesion outcome prediction.

References

1. Rekik et al., Neuroimage Clin 2012;

2. http://www.isles-challenge.org/

Spoken sentences decoding based on intracranial high gamma response using dynamic time warping

In this study, we explore the discriminability of high gamma activities from speech production cortex during the overt articulation of two sentences. Neural activities were recorded from one intracranial electrode placed approximately over the posterior part of the inferior frontal gyrus. By employing a dynamic time warping (DTW) method to realign single-trial high gamma response during speech productions, averaged temporal activation patterns corresponding to the two spoken sentences were obtained. Single-trial ECoG responses were subsequently classified according to their correlations with these two temporal activation patterns. On average, 77.5% of the trials were correctly classified, which was much higher than the chance-level performance of the SVM classifier without DTW. Our preliminary results shed light on the construction of cortical speech brain-computer interfaces on the sentence level.

Relationship between expression levels and atherogenesis in scavenger receptor class B, type I transgenics

Both in vitro and in vivo studies of scavenger receptor class B type I (SR-BI) have implicated it as a likely participant in the metabolism of HDL cholesterol. To investigate the effect of SR-BI on atherogenesis, we examined two lines of SR-BI transgenic mice with high (10-fold increases) and low (2-fold increases) SR-BI expression in an inbred mouse background hemizygous for a human apolipoprotein (apo) B transgene. Unlike non-HDL cholesterol levels that minimally differed in the various groups of animals, HDL cholesterol levels were inversely related to SR-BI expression. Mice with the low expression SR-BI transgene had a 50% reduction in HDL cholesterol, whereas the high expression SR-BI transgene was associated with 2-fold decreases in HDL cholesterol as well as dramatic alterations in HDL composition and size including the near absence of alpha-migrating particles as determined by two-dimensional electrophoresis. The low expression SR-BI/apo B transgenics had more than a 2-fold decrease in the development of diet-induced fatty streak lesions compared with the apo B transgenics (4448 +/- 1908 micrometer(2)/aorta to 10133 +/- 4035 micrometer (2)/aorta; p < 0.001), whereas the high expression SR-BI/apo B transgenics had an atherogenic response similar to that of the apo B transgenics (14692 +/- 7238 micrometer(2)/aorta) but 3-fold greater than the low SR-BI/apo B mice (p < 0.001). The prominent anti-atherogenic effect of moderate SR-BI expression provides in vivo support for the hypothesis that HDL functions to inhibit atherogenesis through its interactions with SR-BI in facilitating reverse cholesterol transport. The failure of the high SR-BI/apo B transgenics to have similar or even greater reductions in atherogenesis suggests that the changes resulting from extremely high SR-BI expression including dramatic changes in lipoproteins may have both pro- and anti-atherogenic consequences, illustrating the complexity of the relationship between SR-BI and atherogenesis.

Genomic interval engineering of mice identifies a novel modulator of triglyceride production

To accelerate the biological annotation of novel genes discovered in sequenced regions of mammalian genomes, we are creating large deletions in the mouse genome targeted to include clusters of such genes. Here we describe the targeted deletion of a 450-kb region on mouse chromosome 11, which, based on computational analysis of the deleted murine sequences and human 5q orthologous sequences, codes for nine putative genes. Mice homozygous for the deletion had a variety of abnormalities, including severe hypertriglyceridemia, hepatic and cardiac enlargement, growth retardation, and premature mortality. Analysis of triglyceride metabolism in these animals demonstrated a several-fold increase in hepatic very-low density lipoprotein triglyceride secretion, the most prevalent mechanism responsible for hypertriglyceridemia in humans. A series of mouse BAC and human YAC transgenes covering different intervals of the 450-kb deleted region were assessed for their ability to complement the deletion induced abnormalities. These studies revealed that OCTN2, a gene recently shown to play a role in carnitine transport, was able to correct the triglyceride abnormalities. The discovery of this previously unappreciated relationship between OCTN2, carnitine, and hepatic triglyceride production is of particular importance because of the clinical consequence of hypertriglyceridemia and the paucity of genes known to modulate triglyceride secretion.

Lower plasma levels and accelerated clearance of high density lipoprotein (HDL) and non-HDL cholesterol in scavenger receptor class B type I transgenic mice

Recent studies have indicated that the scavenger receptor class B type I (SR-BI) may play an important role in the uptake of high density lipoprotein (HDL) cholesteryl ester in liver and steroidogenic tissues. To investigate the in vivo effects of liver-specific SR-BI overexpression on lipid metabolism, we created several lines of SR-BI transgenic mice with an SR-BI genomic construct where the SR-BI promoter region had been replaced by the apolipoprotein (apo)A-I promoter. The effect of constitutively increased SR-BI expression on plasma HDL and non-HDL lipoproteins and apolipoproteins was characterized. There was an inverse correlation between SR-BI expression and apoA-I and HDL cholesterol levels in transgenic mice fed either mouse chow or a diet high in fat and cholesterol. An unexpected finding in the SR-BI transgenic mice was the dramatic impact of the SR-BI transgene on non-HDL cholesterol and apoB whose levels were also inversely correlated with SR-BI expression. Consistent with the decrease in plasma HDL and non-HDL cholesterol was an accelerated clearance of HDL, non-HDL, and their major associated apolipoproteins in the transgenics compared with control animals. These in vivo studies of the effect of SR-BI overexpression on plasma lipoproteins support the previously proposed hypothesis that SR-BI accelerates the metabolism of HDL and also highlight the capacity of this receptor to participate in the metabolism of non-HDL lipoproteins.

Apolipoprotein(a) yeast artificial chromosome transgenic rabbits. Lipoprotein(a) assembly with human and rabbit apolipoprotein B

The in vivo analysis of lipoprotein(a) (Lp(a)), an independent atherosclerosis risk factor in humans, has been limited in part by its restricted distribution among mammals. Although transgenic mice have been created containing Lp(a), the relatively small size of the mouse has precluded some studies. To examine the properties of this molecule in a significantly larger mammal, we have used a 270-kilobase yeast artificial chromosome clone containing the human apolipoprotein(a) (apo(a)) gene and a 90-kilobase P1 phagemid clone containing the human apolipoprotein B (apoB) gene to create transgenic rabbits that express either or both transgenes. Expression of both transgenes was tissue specific and localized predominantly to the liver. Average apolipoprotein plasma levels in the rabbits were 2.5 mg/dl for apo(a) and 17.6 mg/dl for human apoB. In contrast to observations in apo(a) transgenic mice, we found that apo(a) plasma levels in the rabbits were stable throughout sexual maturity. Also, apo(a) formed a covalent association with the endogenous rabbit apoB albeit with a lower efficiency than its association with human apoB. The analysis of Lp(a) transgenic rabbits has provided new insights into apo(a) expression and Lp(a) assembly. In addition, these transgenic rabbits potentially will provide an improved experimental model for the in vivo analysis of Lp(a) and its role in promoting atherosclerosis and restenosis.

Apolipoprotein A-IMilano. Correlation between high density lipoprotein subclass distribution and triglyceridemia

Carriers of the apolipoprotein A-IMilano (apo A-IM) variant represent a selected group of subjects showing low levels of high density lipoprotein (HDL), variable hypertriglyceridemia, and low prevalence of atherosclerotic vascular disease. The distribution of HDL subfractions and the correlation with abnormalities in triglyceride transport were determined in these subjects. Sera from 24 apo A-IM carriers (A-IM+ and from age- and sex-matched normolipidemic controls (A-IM-) were analyzed by rate zonal ultracentrifugation. The A-IM+ subjects showed a marked decrease of HDL3 mass with reduced flotation rates and major compositional alterations; the HDL2 were nearly absent. The HDL subclasses from 10 A-IM+ subjects were resolved according to particle size by gradient gel electrophoresis (GGE). The HDL patterns detected in the carriers were unique in exhibiting a distinct peak in the (HDL3b)gge interval, undetectable in the controls. Three patterns reflecting the relative contributions of smaller (HDL3b)gge and larger (HDL3a)gge particles could be distinguished in the carriers, and these were clearly related to different triglyceride and HDL cholesterol levels in plasma. These findings in a highly selected group of subjects with generally low HDL levels and quite variable triglyceridemia confirmed the existence of relationships between alterations in triglyceride transport and abnormalities in the HDL subclass distribution, possibly reflecting the variable atherosclerotic risk in hypertriglyceridemic subjects.

Follow-up of adolescent trauma victims: a new model of care

A comprehensive model of service delivery for the rehabilitative care of adolescents with closed head injuries is presented. Our data show that the Glasgow Coma Scale score on hospital admission correlates with the length of time required for follow-up. Adolescents with mild closed head injuries require more follow-up than adults with comparable injuries because of adolescent developmental stages that complicate the recovery process. Anticipatory guidance has helped the patient and family cope with stresses. Finally, we have identified a typical pattern of difficulties during the recovery process including: impaired judgment, reduced attention span, irritability, short-term memory loss, and ongoing memory deficits.

Expression of carbohydrate antigen 19-9 and stage-specific embryonic antigen 1 in nontumorous and tumorous epithelia of the human colon and rectum

The expression of carbohydrate antigen 19-9 (CA 19-9) and stage-specific embryonic antigen 1 (SSEA-1) in various human colorectal epithelia was examined by an immunohistochemical method. In mucosa remote from the carcinoma, CA 19-9 was not expressed, whereas SSEA-1 was only faintly expressed in lower crypts in all cases. In mucosa adjacent to the carcinoma, CA 19-9 was weakly expressed in upper crypts in 20% of the cases, whereas SSEA-1 was expressed not only in lower crypts in all cases but also in upper crypts in 93.3% of the cases. In adenoma, CA 19-9 was expressed in 80.6% of the cases, and SSEA-1 was expressed in all cases. The expression of both antigens was to some extent related to the degree of cellular atypia. In focal carcinoma in adenoma, CA 19-9 was strongly and diffusely expressed in 50% of the cases, and SSEA-1 was strongly and diffusely expressed in all cases. In advanced carcinoma, CA 19-9 was homogeneously or heterogeneously expressed in 82.2% of the cases, and SSEA-1 was homogeneously or heterogeneously expressed in all cases, but lower intensity of SSEA-1 staining was associated with a decrease in the degree of carcinoma differentiation. These results show that the expression of both CA 19-9 and SSEA-1 changes along with neoplastic transformation and progression in the colon and rectum. Immunohistochemical studies of SSEA-1 in flat colorectal mucosa might be a useful approach for detecting foci with preneoplastic change in the general population, whereas those of SSEA-1 and CA 19-9 could be a useful method for detecting focal carcinoma in adenoma.