A Clinical and Imaging Fused Deep Learning Model Matches Expert Clinician Prediction of 90-Day Stroke Outcomes

BACKGROUND AND PURPOSE

Predicting long-term clinical outcome in acute ischemic stroke is beneficial for prognosis, clinical trial design, resource management, and patient expectations. This study used a deep learning-based predictive model (DLPD) to predict 90-day mRS outcomes and compared its predictions with those made by physicians.

MATERIALS AND METHODS

A previously developed DLPD that incorporated DWI and clinical data from the acute period was used to predict 90-day mRS outcomes in 80 consecutive patients with acute ischemic stroke from a single-center registry. We assessed the predictions of the model alongside those of 5 physicians (2 stroke neurologists and 3 neuroradiologists provided with the same imaging and clinical information). The primary analysis was the agreement between the ordinal mRS predictions of the model or physician and the ground truth using the Gwet Agreement Coefficient. We also evaluated the ability to identify unfavorable outcomes (mRS >2) using the area under the curve, sensitivity, and specificity. Noninferiority analyses were undertaken using limits of 0.1 for the Gwet Agreement Coefficient and 0.05 for the area under the curve analysis. The accuracy of prediction was also assessed using the mean absolute error for prediction, percentage of predictions ±1 categories away from the ground truth (±1 accuracy [ACC]), and percentage of exact predictions (ACC).

RESULTS

To predict the specific mRS score, the DLPD yielded a Gwet Agreement Coefficient score of 0.79 (95% CI, 0.71-0.86), surpassing the physicians' score of 0.76 (95% CI, 0.67-0.84), and was noninferior to the readers (P < .001). For identifying unfavorable outcome, the model achieved an area under the curve of 0.81 (95% CI, 0.72-0.89), again noninferior to the readers' area under the curve of 0.79 (95% CI, 0.69-0.87) (P < .005). The mean absolute error, ±1ACC, and ACC were 0.89, 81%, and 36% for the DLPD.

CONCLUSIONS

A deep learning method using acute clinical and imaging data for long-term functional outcome prediction in patients with acute ischemic stroke, the DLPD, was noninferior to that of clinical readers.

Predicting FDG-PET Images From Multi-Contrast MRI Using Deep Learning in Patients With Brain Neoplasms

BACKGROUND

18 F-fluorodeoxyglucose (FDG) positron emission tomography (PET) is valuable for determining presence of viable tumor, but is limited by geographical restrictions, radiation exposure, and high cost.

PURPOSE

To generate diagnostic-quality PET equivalent imaging for patients with brain neoplasms by deep learning with multi-contrast MRI.

STUDY TYPE

Retrospective.

SUBJECTS

Patients (59 studies from 51 subjects; age 56 ± 13 years; 29 males) who underwent 18 F-FDG PET and MRI for determining recurrent brain tumor.

FIELD STRENGTH/SEQUENCE

3T; 3D GRE T1, 3D GRE T1c, 3D FSE T2-FLAIR, and 3D FSE ASL, 18 F-FDG PET imaging.

ASSESSMENT

Convolutional neural networks were trained using four MRIs as inputs and acquired FDG PET images as output. The agreement between the acquired and synthesized PET was evaluated by quality metrics and Bland-Altman plots for standardized uptake value ratio. Three physicians scored image quality on a 5-point scale, with score ≥3 as high-quality. They assessed the lesions on a 5-point scale, which was binarized to analyze diagnostic consistency of the synthesized PET compared to the acquired PET.

STATISTICAL TESTS

The agreement in ratings between the acquired and synthesized PET were tested with Gwet's AC and exact Bowker test of symmetry. Agreement of the readers was assessed by Gwet's AC. P = 0.05 was used as the cutoff for statistical significance.

RESULTS

The synthesized PET visually resembled the acquired PET and showed significant improvement in quality metrics (+21.7% on PSNR, +22.2% on SSIM, -31.8% on RSME) compared with ASL. A total of 49.7% of the synthesized PET were considered as high-quality compared to 73.4% of the acquired PET which was statistically significant, but with distinct variability between readers. For the positive/negative lesion assessment, the synthesized PET had an accuracy of 87% but had a tendency to overcall.

CONCLUSION

The proposed deep learning model has the potential of synthesizing diagnostic quality FDG PET images without the use of radiotracers.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

[Construction and preliminary validation of a risk prediction model for the recurrence of diabetic foot ulcer in diabetic patients]

Objective: To develop a risk prediction model for the recurrence of diabetic foot ulcer (DFU) in diabetic patients and primarily validate its predictive value. Methods: Meta-analysis combined with retrospective cohort study was conducted. The Chinese and English papers on risk factors related to DFU recurrence publicly published in China Biology Medicine disc, China National Knowledge Infrastructure, Wanfang Database, VIP Database, and PubMed, Embase, Cochrane Library, and Web of Science, and the search time was from the establishment date of each database until March 31st, 2022. The papers were screened and evaluated, the data were extracted, a meta-analysis was performed using RevMan 5.4.1 statistical software to screen risk factors for DFU recurrence, and Egger's linear regression was used to assess the publication bias of the study results. Risk factors for DFU recurrence mentioned in ≥3 studies and with statistically significant differences in the meta-analysis were selected as the independent variables to develop a logistic regression model for risk prediction of DFU recurrence. The medical records of 101 patients with DFU who met the inclusion criteria and were admitted to Affiliated Hospital of Guizhou Medical University from January 2019 to June 2022 were collected. There were 69 males and 32 females, aged (63±14) years. The receiver operating characteristic (ROC) curve of the predictive performance of the above constructed predictive model for DFU recurrence was drawn, and the area under the ROC curve, maximum Youden index, and sensitivity and specificity at the point were calculated. Dataset including data of 8 risk factors for DFU recurrence and the DFU recurrence rates of 10 000 cases was simulated using RStudio software and a scatter plot was drawn to determine two probabilities for risk division of DFU recurrence. Using the β coefficients corresponding to 8 DFU recurrence risk factors ×10 and taking the integer as the score of coefficient weight of each risk factor, the total score was obtained by summing up, and the cutoff scores for risk level division were calculated based on the total score × two probabilities for risk division of DFU recurrence. Results: Finally, 20 papers were included, including 3 case-control studies and 17 cohort studies, with a total of 4 238 cases and DFU recurrence rate of 22.7% to 71.2%. Meta-analysis showed that glycosylated hemoglobin >7.5% and with plantar ulcer, diabetic peripheral neuropathy, diabetic peripheral vascular disease, smoking, osteomyelitis, history of amputation/toe amputation, and multidrug-resistant bacterial infection were risk factors for the recurrence of DFU (with odds ratios of 3.27, 3.66, 4.05, 3.94, 1.98, 7.17, 11.96, 3.61, 95% confidence intervals of 2.79-3.84, 2.06-6.50, 2.50-6.58, 2.65-5.84, 1.65-2.38, 2.29-22.47, 4.60-31.14, 3.13-4.17, respectively, P<0.05). There were no statistically significant differences in publication biases of diabetic peripheral neuropathy, diabetic peripheral vascular disease, glycosylated hemoglobin >7.5%, plantar ulcer, smoking, multidrug-resistant bacterial infection, or osteomyelitis (P>0.05), but there was a statistically significant difference in the publication bias of amputation/toe amputation (t=-30.39, P<0.05). The area under the ROC curve of the predictive model was 0.81 (with 95% confidence interval of 0.71-0.91) and the maximum Youden index was 0.59, at which the sensitivity was 72% and the specificity was 86%. Ultimately, 29.0% and 44.8% were identified respectively as the cutoff for dividing the probability of low risk and medium risk, and medium risk and high risk for DFU recurrence, while the corresponding total scores of low, medium, and high risks of DFU recurrence were <37, 37-57, and 58-118, respectively. Conclusions: Eight risk factors for DFU recurrence are screened through meta-analysis and the risk prediction model for DFU recurrence is developed, which has moderate predictive accuracy and can provide guidance for healthcare workers to take interventions for patient with DFU recurrence risk.

LSOR: Longitudinally-Consistent Self-Organized Representation Learning

Interpretability is a key issue when applying deep learning models to longitudinal brain MRIs. One way to address this issue is by visualizing the high-dimensional latent spaces generated by deep learning via self-organizing maps (SOM). SOM separates the latent space into clusters and then maps the cluster centers to a discrete (typically 2D) grid preserving the high-dimensional relationship between clusters. However, learning SOM in a high-dimensional latent space tends to be unstable, especially in a self-supervision setting. Furthermore, the learned SOM grid does not necessarily capture clinically interesting information, such as brain age. To resolve these issues, we propose the first self-supervised SOM approach that derives a high-dimensional, interpretable representation stratified by brain age solely based on longitudinal brain MRIs (i.e., without demographic or cognitive information). Called Longitudinally-consistent Self-Organized Representation learning (LSOR), the method is stable during training as it relies on soft clustering (vs. the hard cluster assignments used by existing SOM). Furthermore, our approach generates a latent space stratified according to brain age by aligning trajectories inferred from longitudinal MRIs to the reference vector associated with the corresponding SOM cluster. When applied to longitudinal MRIs of the Alzheimer's Disease Neuroimaging Initiative (ADNI, N = 632 ), LSOR generates an interpretable latent space and achieves comparable or higher accuracy than the state-of-the-art representations with respect to the downstream tasks of classification (static vs. progressive mild cognitive impairment) and regression (determining ADAS-Cog score of all subjects). The code is available at https://github.com/ouyangjiahong/longitudinal-som-single-modality.

Generative Adversarial Network-Enhanced Ultra-Low-Dose [18F]-PI-2620 τ PET/MRI in Aging and Neurodegenerative Populations

BACKGROUND AND PURPOSE

With the utility of hybrid τ PET/MR imaging in the screening, diagnosis, and follow-up of individuals with neurodegenerative diseases, we investigated whether deep learning techniques can be used in enhancing ultra-low-dose [18F]-PI-2620 τ PET/MR images to produce diagnostic-quality images.

MATERIALS AND METHODS

Forty-four healthy aging participants and patients with neurodegenerative diseases were recruited for this study, and [18F]-PI-2620 τ PET/MR data were simultaneously acquired. A generative adversarial network was trained to enhance ultra-low-dose τ images, which were reconstructed from a random sampling of 1/20 (approximately 5% of original count level) of the original full-dose data. MR images were also used as additional input channels. Region-based analyses as well as a reader study were conducted to assess the image quality of the enhanced images compared with their full-dose counterparts.

RESULTS

The enhanced ultra-low-dose τ images showed apparent noise reduction compared with the ultra-low-dose images. The regional standard uptake value ratios showed that while, in general, there is an underestimation for both image types, especially in regions with higher uptake, when focusing on the healthy-but-amyloid-positive population (with relatively lower τ uptake), this bias was reduced in the enhanced ultra-low-dose images. The radiotracer uptake patterns in the enhanced images were read accurately compared with their full-dose counterparts.

CONCLUSIONS

The clinical readings of deep learning-enhanced ultra-low-dose τ PET images were consistent with those performed with full-dose imaging, suggesting the possibility of reducing the dose and enabling more frequent examinations for dementia monitoring.

Functional Outcome Prediction in Acute Ischemic Stroke Using a Fused Imaging and Clinical Deep Learning Model

BACKGROUND

Predicting long-term clinical outcome based on the early acute ischemic stroke information is valuable for prognostication, resource management, clinical trials, and patient expectations. Current methods require subjective decisions about which imaging features to assess and may require time-consuming postprocessing. This study's goal was to predict ordinal 90-day modified Rankin Scale (mRS) score in acute ischemic stroke patients by fusing a Deep Learning model of diffusion-weighted imaging images and clinical information from the acute period.

METHODS

A total of 640 acute ischemic stroke patients who underwent magnetic resonance imaging within 1 to 7 days poststroke and had 90-day mRS follow-up data were randomly divided into 70% (n=448) for model training, 15% (n=96) for validation, and 15% (n=96) for internal testing. Additionally, external testing on a cohort from Lausanne University Hospital (n=280) was performed to further evaluate model generalization. Accuracy for ordinal mRS, accuracy within ±1 mRS category, mean absolute prediction error, and determination of unfavorable outcome (mRS score >2) were evaluated for clinical only, imaging only, and 2 fused clinical-imaging models.

RESULTS

The fused models demonstrated superior performance in predicting ordinal mRS score and unfavorable outcome in both internal and external test cohorts when compared with the clinical and imaging models. For the internal test cohort, the top fused model had the highest area under the curve of 0.92 for unfavorable outcome prediction and the lowest mean absolute error (0.96 [95% CI, 0.77-1.16]), with the highest proportion of mRS score predictions within ±1 category (79% [95% CI, 71%-88%]). On the external Lausanne University Hospital cohort, the best fused model had an area under the curve of 0.90 for unfavorable outcome prediction and outperformed other models with an mean absolute error of 0.90 (95% CI, 0.79-1.01), and the highest percentage of mRS score predictions within ±1 category (83% [95% CI, 78%-87%]).

CONCLUSIONS

A Deep Learning-based imaging model fused with clinical variables can be used to predict 90-day stroke outcome with reduced subjectivity and user burden.

[Summary of the best evidence on exercise for the prevention and treatment of diabetic foot]

Objective: To summarize the best evidence on exercise for the prevention and treatment of diabetic foot. Methods: A bibliometric approach was used. Systematic searches were carried out to retrieve all the publicly published evidences till July 2022 on exercise for the prevention and treatment of diabetic foot, including guidelines, evidence summary, recommended practices, expert consensus, systematic review, and original research, from foreign language databases including BMJ Best Practice, UpToDate, Joanna Briggs Institute Evidence-Based Practice Database, Cochrane Library, Embase, PubMed, Guideline International Network, National Guideline Clearinghouse, Chinese databases including China National Knowledge Infrastructure, Wanfang Database, VIP Database, China Biology Medicine disc, China Clinical Guidelines Library, and the official websites of relevant academic organizations including National Institute for Health and Care Excellence of the United Kingdom, Registered Nurses' Association of Ontario of Canada, the International Working Group on the Diabetic Foot, International Diabetes Federation, American College of Sports Medicine, American Diabetes Association, and Chinese Diabetes Society. The literature was screened and evaluated for the quality, from which the evidences were extracted and evaluated to summarize the best evidences. Results: Nine guidelines, three expert consensuses, one evidence summary (with two systematic reviews being traced), two systematic reviews, 6 randomized controlled trials were retrieved and included, with good quality of literature. Totally 33 pieces of best evidences on exercise for the prevention and treatment of diabetic foot were summarized from the aspects of appropriate exercise prevention of diabetic foot, exercise therapy of diabetic foot, precautions for exercise, health education, and establishment of a multidisciplinary limb salvage team. Conclusions: Totally 33 pieces of best evidences on exercise for the prevention and treatment of diabetic foot were summarized from 5 aspects, providing decision-making basis for clinical guidance on exercise practice for patients with diabetic foot.

Predicting Hypoperfusion Lesion and Target Mismatch in Stroke from Diffusion-weighted MRI Using Deep Learning

Background Perfusion imaging is important to identify a target mismatch in stroke but requires contrast agents and postprocessing software. Purpose To use a deep learning model to predict the hypoperfusion lesion in stroke and identify patients with a target mismatch profile from diffusion-weighted imaging (DWI) and clinical information alone, using perfusion MRI as the reference standard. Materials and Methods Imaging data sets of patients with acute ischemic stroke with baseline perfusion MRI and DWI were retrospectively reviewed from multicenter data available from 2008 to 2019 (Imaging Collaterals in Acute Stroke, Diffusion and Perfusion Imaging Evaluation for Understanding Stroke Evolution 2, and University of California, Los Angeles stroke registry). For perfusion MRI, rapid processing of perfusion and diffusion software automatically segmented the hypoperfusion lesion (time to maximum, ≥6 seconds) and ischemic core (apparent diffusion coefficient [ADC], ≤620 × 10-6 mm2/sec). A three-dimensional U-Net deep learning model was trained using baseline DWI, ADC, National Institutes of Health Stroke Scale score, and stroke symptom sidedness as inputs, with the union of hypoperfusion and ischemic core segmentation serving as the ground truth. Model performance was evaluated using the Dice score coefficient (DSC). Target mismatch classification based on the model was compared with that of the clinical-DWI mismatch approach defined by the DAWN trial by using the McNemar test. Results Overall, 413 patients (mean age, 67 years ± 15 [SD]; 207 men) were included for model development and primary analysis using fivefold cross-validation (247, 83, and 83 patients in the training, validation, and test sets, respectively, for each fold). The model predicted the hypoperfusion lesion with a median DSC of 0.61 (IQR, 0.45-0.71). The model identified patients with target mismatch with a sensitivity of 90% (254 of 283; 95% CI: 86, 93) and specificity of 77% (100 of 130; 95% CI: 69, 83) compared with the clinical-DWI mismatch sensitivity of 50% (140 of 281; 95% CI: 44, 56) and specificity of 89% (116 of 130; 95% CI: 83, 94) (P < .001 for all). Conclusion A three-dimensional U-Net deep learning model predicted the hypoperfusion lesion from diffusion-weighted imaging (DWI) and clinical information and identified patients with a target mismatch profile with higher sensitivity than the clinical-DWI mismatch approach. ClinicalTrials.gov registration nos. NCT02225730, NCT01349946, NCT02586415 © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Kallmes and Rabinstein in this issue.

Disentangling Normal Aging From Severity of Disease via Weak Supervision on Longitudinal MRI

The continuous progression of neurological diseases are often categorized into conditions according to their severity. To relate the severity to changes in brain morphometry, there is a growing interest in replacing these categories with a continuous severity scale that longitudinal MRIs are mapped onto via deep learning algorithms. However, existing methods based on supervised learning require large numbers of samples and those that do not, such as self-supervised models, fail to clearly separate the disease effect from normal aging. Here, we propose to explicitly disentangle those two factors via weak-supervision. In other words, training is based on longitudinal MRIs being labelled either normal or diseased so that the training data can be augmented with samples from disease categories that are not of primary interest to the analysis. We do so by encouraging trajectories of controls to be fully encoded by the direction associated with brain aging. Furthermore, an orthogonal direction linked to disease severity captures the residual component from normal aging in the diseased cohort. Hence, the proposed method quantifies disease severity and its progression speed in individuals without knowing their condition. We apply the proposed method on data from the Alzheimer's Disease Neuroimaging Initiative (ADNI, N =632 ). We then show that the model properly disentangled normal aging from the severity of cognitive impairment by plotting the resulting disentangled factors of each subject and generating simulated MRIs for a given chronological age and condition. Moreover, our representation obtains higher balanced accuracy when used for two downstream classification tasks compared to other pre-training approaches. The code for our weak-supervised approach is available at https://github.com/ouyangjiahong/longitudinal-direction-disentangle.

Self-supervised learning of neighborhood embedding for longitudinal MRI

In recent years, several deep learning models recommend first to represent Magnetic Resonance Imaging (MRI) as latent features before performing a downstream task of interest (such as classification or regression). The performance of the downstream task generally improves when these latent representations are explicitly associated with factors of interest. For example, we derived such a representation for capturing brain aging by applying self-supervised learning to longitudinal MRIs and then used the resulting encoding to automatically identify diseases accelerating the aging of the brain. We now propose a refinement of this representation by replacing the linear modeling of brain aging with one that is consistent in local neighborhoods in the latent space. Called Longitudinal Neighborhood Embedding (LNE), we derive an encoding so that neighborhoods are age-consistent (i.e., brain MRIs of different subjects with similar brain ages are in close proximity of each other) and progression-consistent, i.e., the latent space is defined by a smooth trajectory field where each trajectory captures changes in brain ages between a pair of MRIs extracted from a longitudinal sequence. To make the problem computationally tractable, we further propose a strategy for mini-batch sampling so that the resulting local neighborhoods accurately approximate the ones that would be defined based on the whole cohort. We evaluate LNE on three different downstream tasks: (1) to predict chronological age from T1-w MRI of 274 healthy subjects participating in a study at SRI International; (2) to distinguish Normal Control (NC) from Alzheimer's Disease (AD) and stable Mild Cognitive Impairment (sMCI) from progressive Mild Cognitive Impairment (pMCI) based on T1-w MRI of 632 participants of the Alzheimer's Disease Neuroimaging Initiative (ADNI); and (3) to distinguish no-to-low from moderate-to-heavy alcohol drinkers based on fractional anisotropy derived from diffusion tensor MRIs of 764 adolescents recruited by the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA). Across the three data sets, the visualization of the smooth trajectory vector fields and superior accuracy on downstream tasks demonstrate the strength of the proposed method over existing self-supervised methods in extracting information related to brain aging, which could help study the impact of substance use and neurodegenerative disorders. The code is available at https://github.com/ouyangjiahong/longitudinal-neighbourhood-embedding.

Automated detection of arterial landmarks and vascular occlusions in patients with acute stroke receiving digital subtraction angiography using deep learning

BACKGROUND

Digital subtraction angiography (DSA) is the gold-standard method of assessing arterial blood flow and blockages prior to endovascular thrombectomy.

OBJECTIVE

To detect anatomical features and arterial occlusions with DSA using artificial intelligence techniques.

METHODS

We included 82 patients with acute ischemic stroke who underwent DSA imaging and whose carotid terminus was visible in at least one run. Two neurointerventionalists labeled the carotid location (when visible) and vascular occlusions on 382 total individual DSA runs. For detecting the carotid terminus, positive and negative image patches (either containing or not containing the internal carotid artery terminus) were extracted in a 1:1 ratio. Two convolutional neural network architectures (ResNet-50 pretrained on ImageNet and ResNet-50 trained from scratch) were evaluated. Area under the curve (AUC) of the receiver operating characteristic and pixel distance from the ground truth were calculated. The same training and analysis methods were used for detecting arterial occlusions.

RESULTS

The ResNet-50 trained from scratch most accurately detected the carotid terminus (AUC 0.998 (95% CI 0.997 to 0.999), p<0.00001) and arterial occlusions (AUC 0.973 (95% CI 0.971 to 0.975), p<0.0001). Average pixel distances from ground truth for carotid terminus and occlusion localization were 63±45 and 98±84, corresponding to approximately 1.26±0.90 cm and 1.96±1.68 cm for a standard angiographic field-of-view.

CONCLUSION

These results may serve as an unbiased standard for clinical stroke trials, as optimal standardization would be useful for core laboratories in endovascular thrombectomy studies, and also expedite decision-making during DSA-based procedures.

Mechanism of ALDH2 improves the neuronal damage caused by hypoxia/reoxygenation

OBJECTIVE

To investigate the protective effect and mechanism of ALDH2 on PC12 cells and brain nerve tissue injury under hypoxia.

MATERIALS AND METHODS

The hypoxia model of PC12 cells with low ALDH2 expression was established and screened. The eukaryotic expression vector of wild type pEGFP-N1-ALDH2 and blank plasmid pEGFP-N1 were constructed and transfected into PC12 hypoxia cells respectively. After reoxygenation culture, the morphology, quantity, ALDH2 expression level and apoptosis rate of the two groups were observed, and the role of ALDH2 in cell hypoxia injury was analyzed. Eighty SD rats were randomly divided into model group (ischemia-reperfusion injury group), Alda-1 group (intraperitoneal injection of alda-1 12 hours before and after modeling), DMSO group (intraperitoneal injection of dimethyl sulfoxide) and sham operation group, with 20 rats in each group. The neurobehavioral score, apoptosis rate of nerve cells, the content and activity of ALDH2 in active cerebral cortex and hippocampal CA1 area were compared.

RESULTS

The number of PC12 cells in hypoxia group was lower than that in control group. The expression level of ALDH2 protein in PC12 cells after 4 hours of hypoxia was lower than that in normal culture group. The number of PC12 cells transfected with wild-type recombinant plasmid was significantly more than that of blank plasmid group. Compared with the hypoxia group, the pre apoptotic and post apoptotic cells in wild type transfection group decreased after hypoxia treatment. Compared with sham operation group, nerve injury and apoptosis were increased in group M and DMSO, while ALDH2 activity and expression did not change significantly. Compared with M group and DMSO group, the nerve injury and apoptosis in Alda-1 group were improved, ALDH2 activity was increased, and ALDH2 expression was not significantly changed in Alda-1 group.

CONCLUSIONS

Increasing the expression of ALDH2 or enhancing the activity of ALDH2 can improve the injury of neurons induced by hypoxia/reoxygenation.

Abstract 8: Hypoperfusion Lesion And Target Mismatch Prediction In Acute Ischemic Stroke From Baseline Mr Diffusion Imaging Using A 3d Convolutional Neural Network

Purpose: Perfusion imaging assesses target mismatch but requires contrast and processing software. Clinical/diffusion mismatch can miss cases that have target mismatch and could benefit from thrombectomy. We explored whether a neural network can predict hypoperfusion and identify target mismatch from diffusion-weighted imaging (DWI) and clinical information alone.

Methods: Acute ischemic stroke cases with baseline MR perfusion and DWI were included from two multi-center trials and one registry for model development and a separate randomized trial for external validation. MR perfusion images were processed by RAPID, which segments Tmax lesion (Tmax≥6s) and the ischemic core lesion (apparent diffusion coefficient [ADC]≤ 620). A 3D U-Net was trained using baseline DWI, ADC, NIH stroke scale, and side of stroke as input, and the union of Tmax and ischemic core segmentation as the ground truth. 5-fold cross-validation was performed for model development cohort. Model performance was evaluated by Dice score coefficient (DSC) and volume difference. Sensitivity and specificity of model target mismatch and clinical/diffusion mismatch criteria from the DAWN were compared, using the DEFUSE 3 target mismatch as reference.

Results: 413 patients were included for model development and 46 for external validation. In model development and external validation cohort, the model achieved median DSC of 0.61 (IQR 0.45, 0.71) and 0.62 (IQR 0.53, 0.72); and volume difference of 3 ml (IQR -37, 41) and 7 ml (IQR -24, 32), respectively. Compared to the clinical/diffusion mismatch approach, the model identified target mismatch with a sensitivity of 89.5% vs 49.3%, a specificity of 77.5% vs 89.2% in the model development cohort, and a sensitivity of 95.6% vs 41.3% in external validation cohort.

Conclusion: A 3D U-Net can predict hypoperfusion lesions from baseline DWI and clinical information, with more sensitive classification of target mismatch than clinical/diffusion mismatch.

Deep learning evaluation of biomarkers from echocardiogram videos

BACKGROUND

Laboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos can provide additional value in understanding disease states and can evaluate common biomarkers results.

METHODS

We developed EchoNet-Labs, a video-based deep learning algorithm to detect evidence of anemia, elevated B-type natriuretic peptide (BNP), troponin I, and blood urea nitrogen (BUN), as well as values of ten additional lab tests directly from echocardiograms. We included patients (n = 39,460) aged 18 years or older with one or more apical-4-chamber echocardiogram videos (n = 70,066) from Stanford Healthcare for training and internal testing of EchoNet-Lab's performance in estimating the most proximal biomarker result. Without fine-tuning, the performance of EchoNet-Labs was further evaluated on an additional external test dataset (n = 1,301) from Cedars-Sinai Medical Center. We calculated the area under the curve (AUC) of the receiver operating characteristic curve for the internal and external test datasets.

FINDINGS

On the held-out test set of Stanford patients not previously seen during model training, EchoNet-Labs achieved an AUC of 0.80 (0.79-0.81) in detecting anemia (low hemoglobin), 0.86 (0.85-0.88) in detecting elevated BNP, 0.75 (0.73-0.78) in detecting elevated troponin I, and 0.74 (0.72-0.76) in detecting elevated BUN. On the external test dataset from Cedars-Sinai, EchoNet-Labs achieved an AUC of 0.80 (0.77-0.82) in detecting anemia, of 0.82 (0.79-0.84) in detecting elevated BNP, of 0.75 (0.72-0.78) in detecting elevated troponin I, and of 0.69 (0.66-0.71) in detecting elevated BUN. We further demonstrate the utility of the model in detecting abnormalities in 10 additional lab tests. We investigate the features necessary for EchoNet-Labs to make successful detection and identify potential mechanisms for each biomarker using well-known and novel explainability techniques.

INTERPRETATION

These results show that deep learning applied to diagnostic imaging can provide additional clinical value and identify phenotypic information beyond current imaging interpretation methods.

FUNDING

J.W.H. and B.H. are supported by the NSF Graduate Research Fellowship. D.O. is supported by NIH K99 HL157421-01. J.Y.Z. is supported by NSF CAREER 1942926, NIH R21 MD012867-01, NIH P30AG059307 and by a Chan-Zuckerberg Biohub Fellowship.

Self-Supervised Longitudinal Neighbourhood Embedding

Longitudinal MRIs are often used to capture the gradual deterioration of brain structure and function caused by aging or neurological diseases. Analyzing this data via machine learning generally requires a large number of ground-truth labels, which are often missing or expensive to obtain. Reducing the need for labels, we propose a self-supervised strategy for representation learning named Longitudinal Neighborhood Embedding (LNE). Motivated by concepts in contrastive learning, LNE explicitly models the similarity between trajectory vectors across different subjects. We do so by building a graph in each training iteration defining neighborhoods in the latent space so that the progression direction of a subject follows the direction of its neighbors. This results in a smooth trajectory field that captures the global morphological change of the brain while maintaining the local continuity. We apply LNE to longitudinal T1w MRIs of two neuroimaging studies: a dataset composed of 274 healthy subjects, and Alzheimer's Disease Neuroimaging Initiative (ADNI, N = 632). The visualization of the smooth trajectory vector field and superior performance on downstream tasks demonstrate the strength of the proposed method over existing self-supervised methods in extracting information associated with normal aging and in revealing the impact of neurodegenerative disorders. The code is available at https://github.com/ouyangjiahong/longitudinal-neighbourhood-embedding.

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.

Longitudinal Pooling & Consistency Regularization to Model Disease Progression From MRIs

Many neurological diseases are characterized by gradual deterioration of brain structure andfunction. Large longitudinal MRI datasets have revealed such deterioration, in part, by applying machine and deep learning to predict diagnosis. A popular approach is to apply Convolutional Neural Networks (CNN) to extract informative features from each visit of the longitudinal MRI and then use those features to classify each visit via Recurrent Neural Networks (RNNs). Such modeling neglects the progressive nature of the disease, which may result in clinically implausible classifications across visits. To avoid this issue, we propose to combine features across visits by coupling feature extraction with a novel longitudinal pooling layer and enforce consistency of the classification across visits in line with disease progression. We evaluate the proposed method on the longitudinal structural MRIs from three neuroimaging datasets: Alzheimer's Disease Neuroimaging Initiative (ADNI, N=404), a dataset composed of 274 normal controls and 329 patients with Alcohol Use Disorder (AUD), and 255 youths from the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA). In allthree experiments our method is superior to other widely used approaches for longitudinal classification thus making a unique contribution towards more accurate tracking of the impact of conditions on the brain. The code is available at https://github.com/ouyangjiahong/longitudinal-pooling.

[Association of hyperuricemia-induced renal damage with sirtuin 1 and endothelial nitric oxide synthase in rats]

Objective: To investigate the association of hyperuricemia-induced renal damage with sirtuin 1 (SIRT1) and endothelial nitric oxide synthase (eNOS) in rats. Methods: Using the random number table method, 32 Sprague-Dawley rats were randomly divided into 4 groups: control group, model A group (the model was generated using oxonic acid potassium salt alone), model B group (hyperuricemia model was generated using oxonic acid potassium salt combined with uric acid) and resveratrol group, with 8 rats in each group. The experiment lasted 12 weeks. Serum uric acid and cystatin C levels were monitored regularly. In week 12, serum creatinine and urea nitrogen levels were measured, and the kidneys were extracted. The expression of SIRT1 and eNOS in renal tissues was measured and determined by immunohistochemistry, quantitative reverse-transcription polymerase chain reaction (RT-qPCR) and western blotting. Immunohistochemistry of alpha-smooth muscle actin combined with Masson staining was employed to evaluate the degree of renal fibrosis, and pathological changes were observed based on hematoxylin and eosin staining. Results: In week 12, the uric acid levels in both the model A and model B groups were higher than those in the control group [(316±43) μmol/L, (297±40) μmol/L vs (118±44) μmol/L, both P<0.05]. The levels of cystatin C in the model A, model B, and resveratrol groups were all higher than those in the control group [(156±20) ng/ml, (143±29) ng/ml, (128±26) ng/ml vs (62±18) ng/ml, all P<0.05]. Creatinine levels were higher in the model A and model B groups than those in the control group [(68.5±10.3) μmol/L, (64.5±13.9) μmol/L vs (43.2±10.6) μmol/L, both P<0.05]. The levels of uric acid, cystatin C and creatinine in the resveratrol group were lower than those in the model A group (all P<0.05). Immunohistochemistry, RT-qPCR, and Western blotting for renal SIRT1 and eNOS showed that the expression in the model A and model B groups was inhibited, while the expression in the resveratrol group was not significantly inhibited, compared with that in the control group. Microscopically, obvious abnormalities were not found in the renal tissue of the control group. Renal inflammatory cell aggregation and edema occurred, and interstitial fibrosis was obvious in both the model A and model B groups, while these lesions in the resveratrol group were significantly improved. Conclusions: Hyperuricemia may cause renal injury by inhibiting the expression of SIRT1 and eNOS.

Generalization of deep learning models for ultra-low-count amyloid PET/MRI using transfer learning

PURPOSE

We aimed to evaluate the performance of deep learning-based generalization of ultra-low-count amyloid PET/MRI enhancement when applied to studies acquired with different scanning hardware and protocols.

METHODS

Eighty simultaneous [18F]florbetaben PET/MRI studies were acquired, split equally between two sites (site 1: Signa PET/MRI, GE Healthcare, 39 participants, 67 ± 8 years, 23 females; site 2: mMR, Siemens Healthineers, 64 ± 11 years, 23 females) with different MRI protocols. Twenty minutes of list-mode PET data (90-110 min post-injection) were reconstructed as ground-truth. Ultra-low-count data obtained from undersampling by a factor of 100 (site 1) or the first minute of PET acquisition (site 2) were reconstructed for ultra-low-dose/ultra-short-time (1% dose and 5% time, respectively) PET images. A deep convolution neural network was pre-trained with site 1 data and either (A) directly applied or (B) trained further on site 2 data using transfer learning. Networks were also trained from scratch based on (C) site 2 data or (D) all data. Certified physicians determined amyloid uptake (+/-) status for accuracy and scored the image quality. The peak signal-to-noise ratio, structural similarity, and root-mean-squared error were calculated between images and their ground-truth counterparts. Mean regional standardized uptake value ratios (SUVR, reference region: cerebellar cortex) from 37 successful site 2 FreeSurfer segmentations were analyzed.

RESULTS

All network-synthesized images had reduced noise than their ultra-low-count reconstructions. Quantitatively, image metrics improved the most using method B, where SUVRs had the least variability from the ground-truth and the highest effect size to differentiate between positive and negative images. Method A images had lower accuracy and image quality than other methods; images synthesized from methods B-D scored similarly or better than the ground-truth images.

CONCLUSIONS

Deep learning can successfully produce diagnostic amyloid PET images from short frame reconstructions. Data bias should be considered when applying pre-trained deep ultra-low-count amyloid PET/MRI networks for generalization.

Evaluation of four disease management programs: evidence from blue cross blue shield of Louisiana

Aims: Chronic diseases impose a substantial healthcare burden. This study sought to evaluate the clinical and economic impact of new disease management (DM) programs, targeting four major chronic disease groups: diabetes, coronary heart disease (CHD)/hypertension (HTN), asthma/chronic obstructive pulmonary disease (COPD), and congestive heart failure (CHF)/chronic kidney disease (CKD).Materials and methods: Between March 1, 2015, and February 28, 2018, members with Blue Cross Blue Shield of Louisiana insurance were contacted and enrolled in a DM program if they were aged 18 years through 64 years, eligible for a DM program, and had not been previously enrolled in a DM program. Active enrollees of a DM program ("IN" group) were compared to members who were not yet enrolled ("OUT" group). Average per member per month (PMPM) costs were aggregated annually to document any descriptive trends. Multivariable model estimates were used to compare PMPM costs for all IN subjects and all OUT subjects. Total medical savings were evaluated for the following time intervals: 1-12 months, 13-24 months, and 25-36 months.Results: For all four DM programs, average costs PMPM trended upward over time for the OUT cohort, while they remained relatively stable for the IN cohort. Some evidence also showed that DM programs improved clinical outcomes, such as hemoglobin A1c values. A difference in difference analysis showed PMPM savings for all four programs combined of $31.61, $50.45, and $53.72 after 1, 2, and 3 years, respectively. Multivariable modeling results showed total savings after 3 years of $14,460,174 for all DM programs combined.Limitations: Although multivariable models adjusted for several clinical, demographic, and economic characteristics; it is possible that some important confounders were missing due to lack of data.Conclusions: DM programs implemented to control diabetes, CHD/HTN, CHF/CKD, and asthma/COPD are cost-effective and show some evidence of improved clinical outcomes.

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.

Homocysteine induced oxidative stress in human umbilical vein endothelial cells via regulating methylation of SORBS1

OBJECTIVE

The aim of the present study was to investigate the mechanism of homocysteine (Hcy) induced oxidative stress in the human umbilical vein endothelial cells (HUVECs).

PATIENTS AND METHODS

The HUVECs were isolated from umbilical vein vascular wall of 12 patients and treated with Hcy. The malondialdehyde (MDA) level was measured using the thiobarbituric acid (TBA) method. The expressions of superoxide dismutase 2 (SOD2), endothelial nitric oxide synthase (eNOS), and intercellular adhesion molecule 1 (ICAM-1) were detected by Western blot and RT-PCR. The genome-wide DNA methylation assay was performed using the Infinium Human Methylation 450 BeadChip. The specific DNA methylation was determined using bisulfite sequencing analysis. To evaluate the role of sorbin and SH3 domain-containing protein 1 (SORBS1), the HUVECs were transfected with small interfere RNA (siRNA) targeting SORBS1 (SORBS1-siRNA).

RESULTS

Hcy induced MDA level in HUVECs, and increased ICAM-1 expression both in protein and mRNA levels. The protein and mRNA levels of SOD2 and eNOS were inhibited by Hcy induction. However, the effects of Hcy on MDA level and expressions of SOD2, eNOS, and ICAM-1 were attenuated by folic acid (Fc) and vitamin B12 (B12) treatment. DNA total methylation level in Hcy treated cells was significantly decreased compared to the control group, while the DNA total methylation levels were increased after treatment with Fc and B12. The methylation level of SORBS1 in Hcy treatment group was higher than that of control group. And the methylation level of SORBS1 induced by Hcy was attenuated by Fc and B12 treatment. SORBS1-siRNA transfection induced the MDA levels and reduced the expressions of SOD2 in HUVECs.

CONCLUSIONS

We indicated that Hcy induced oxidative stress in HUVECs via regulating methylation of SORBS1. We also found that Fc and B12 treatment attenuated the oxidative stress and inflammation induced by Hcy in HUVECs. The findings indicated that Fc and B12 might be effective agents for the treatment of Hcy induced AS.

MR-based cardiac and respiratory motion correction of PET: application to static and dynamic cardiac 18F-FDG imaging

Motion of the myocardium deteriorates the quality and quantitative accuracy of cardiac PET images. We present a method for MR-based cardiac and respiratory motion correction of cardiac PET data and evaluate its impact on estimation of activity and kinetic parameters in human subjects. Three healthy subjects underwent simultaneous dynamic ¹⁸F-FDG PET and MRI on a hybrid PET/MR scanner. A cardiorespiratory motion field was determined for each subject using navigator, tagging and golden-angle radial MR acquisitions. Acquired coincidence events were binned into cardiac and respiratory phases using electrocardiogram and list mode-driven signals, respectively. Dynamic PET images were reconstructed with MR-based motion correction (MC) and without motion correction (NMC). Parametric images of ¹⁸F-FDG consumption rates (K_i) were estimated using Patlak's method for both MC and NMC images. MC alleviated motion artifacts in PET images, resulting in improved spatial resolution, improved recovery of activity in the myocardium wall and reduced spillover from the myocardium to the left ventricle cavity. Significantly higher myocardium contrast-to-noise ratio and lower apparent wall thickness were obtained in MC versus NMC images. Likewise, parametric images of K_i calculated with MC data had improved spatial resolution as compared to those obtained with NMC. Consistent with an increase in reconstructed activity concentration in the frames used during kinetic analyses, MC led to the estimation of higher K_i values almost everywhere in the myocardium, with up to 18% increase (mean across subjects) in the septum as compared to NMC. This study shows that MR-based motion correction of cardiac PET results in improved image quality that can benefit both static and dynamic studies.

Accurate tissue interface segmentation via adversarial pre-segmentation of anterior segment OCT images

Optical Coherence Tomography (OCT) is an imaging modality that has been widely adopted for visualizing corneal, retinal and limbal tissue structure with micron resolution. It can be used to diagnose pathological conditions of the eye, and for developing pre-operative surgical plans. In contrast to the posterior retina, imaging the anterior tissue structures, such as the limbus and cornea, results in B-scans that exhibit increased speckle noise patterns and imaging artifacts. These artifacts, such as shadowing and specularity, pose a challenge during the analysis of the acquired volumes as they substantially obfuscate the location of tissue interfaces. To deal with the artifacts and speckle noise patterns and accurately segment the shallowest tissue interface, we propose a cascaded neural network framework, which comprises of a conditional Generative Adversarial Network (cGAN) and a Tissue Interface Segmentation Network (TISN). The cGAN pre-segments OCT B-scans by removing undesired specular artifacts and speckle noise patterns just above the shallowest tissue interface, and the TISN combines the original OCT image with the pre-segmentation to segment the shallowest interface. We show the applicability of the cascaded framework to corneal datasets, demonstrate that it precisely segments the shallowest corneal interface, and also show its generalization capacity to limbal datasets. We also propose a hybrid framework, wherein the cGAN pre-segmentation is passed to a traditional image analysis-based segmentation algorithm, and describe the improved segmentation performance. To the best of our knowledge, this is the first approach to remove severe specular artifacts and speckle noise patterns (prior to the shallowest interface) that affects the interpretation of anterior segment OCT datasets, thereby resulting in the accurate segmentation of the shallowest tissue interface. To the best of our knowledge, this is the first work to show the potential of incorporating a cGAN into larger deep learning frameworks for improved corneal and limbal OCT image segmentation. Our cGAN design directly improves the visualization of corneal and limbal OCT images from OCT scanners, and improves the performance of current OCT segmentation algorithms.

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.

[Clinical characteristics and prognosis of 34 cases of acute myeloid leukemia with FLT3 internal tandem duplication and MLL gene rearrangement]

目的

探讨同时伴FLT3-ITD突变及MLL基因异常的急性髓系白血病（AML）患者的临床特征及转归。

方法

回顾性分析34例同时伴FLT3-ITD突变及MLL基因异常的AML患者的临床资料，比较化疗、化疗加靶向药物治疗及allo-HSCT的疗效及影响因素。

结果

34例同时伴FLT3-ITD突变及MLL基因异常的AML患者占同期住院AML患者的2.02%。入院时WBC>30×10⁹/L的患者占63.6%，其中WBC>50×10⁹/L者占39.4%。FAB亚型中以M₅比例最高，占35.3%，染色体核型异常者达63.6%，其中复杂异常占12.1%。34例患者中仅有FLT3-ITD及MLL基因异常（双基因异常）者11例（32.4%），具FLT3及MLL以外的1种及1种以上的基因异常（多基因异常）者23例（67.6%）。34例患者2个疗程完全缓解（CR）率为29.4%，7例（20.6%）化疗≥3个疗程后CR，CR患者的早期复发率为52.9%。WBC>50×10⁹/L以及多基因异常的患者2个疗程CR率较低（7.7%、5.4%），其中具有3种以上基因异常的患者无一例CR。34例患者2年总生存（OS）率为28.8%（95%CI 13.5%~46.0%），2年无病生存（DFS）率为27.1%（95% CI 12.5%~44.0%）。18例仅使用化疗或化疗加靶向药物治疗的患者，17例在2年内死亡，1例放弃治疗后失访。接受allo-HSCT治疗的患者3年OS率为43.4%（95%CI 13.7%~70.4%），3年DFS率为42.7%（95% CI 13.4%~69.7%）。

结论

同时伴FLT3-ITD突变及MLL基因异常的AML患者FAB分型以M₅多见，常伴高白细胞血症、细胞遗传学异常及多基因异常。患者化疗缓解率低，早期复发率高，长期生存率低。高白细胞血症、多基因异常可能是此类患者疗效差的重要原因，allo-HSCT可改善患者的转归。

[Efficacy and safety of IA regimen containing different doses of idarubicin in de-novo acute myeloid leukemia for adult patients]

目的

探讨含不同剂量去甲氧柔红霉素（IDA 8、10、12 mg/m²）的IA方案诱导治疗成人初发急性髓系白血病（AML）（非急性早幼粒细胞白血病）的临床疗效和安全性。

方法

采用多中心、单盲、非随机、临床对照研究，纳入2011年5月至2015年3月苏州大学附属第一医院及其他36家单位收治的1 215例成人初发AML患者，根据诱导化疗方案中IDA的剂量对患者进行分组，分析不同剂量IDA联合阿糖胞苷（100 mg/m²）组成的IA方案在成人初发AML诱导治疗中的完全缓解（CR）率、血液学及非血液学不良事件。

结果

可纳入缓解率分析的AML患者共1 207例，IDA 8 mg/m²、10 mg/m²和12 mg/m²组的CR率分别为73.6%（215/292）、84.1%（662/787）和86.7%（111/128），差异有统计学意义（P<0.001）；以IDA 8 mg/m²组为参照组，在调整了年龄、骨髓原始细胞比例、FAB分型、危险度分层后，IDA 10 mg/m²和IDA 12 mg/m²为影响患者CR的有利因素[OR=0.49（95% CI 0.34~0.70），P<0.001；OR=0.36（95%CI 0.18~0.71），P=0.003]。在中、低危组中三组CR率分别为76.5%（163/213）、86.9%（506/582）和86.1%（68/79），差异有统计学意义（P=0.007）；在调整了年龄、骨髓原始细胞比例、FAB分型因素后，IDA 10 mg/m²为影响患者CR的有利因素[OR=0.47（95% CI 0.31~0.71），P<0.001]。在高危组中，三组CR率分别为50.0%（18/36）、60.6%（43/71）和81.8%（18/22），差异无统计学意义（P=0.089），但在调整了年龄、骨髓原始细胞比例、FAB分型因素后，IDA 12 mg/m²为影响患者CR的有利因素[OR=0.22（95% CI 0.06~0.80），P=0.022]。8 mg/m²、10 mg/m²和12 mg/m²组中性粒细胞≤0.5×10⁹/L的中位持续时间分别为14（11~18）、15（11~20）和18（14~22）d，差异有统计学意义（P=0.012）；三组PLT≤20×10⁹/L的中位持续时间分别为14（7~17）、15（11~20）和17（15~21）d，差异有统计学意义（P=0.001）；三组肺部感染发生率分别为9.8%、13.5%和25.2%，差异有统计学意义（P<0.001）。

结论

在中国成人（18~60岁）初发AML中，建议中、低危组患者采用含IDA 10 mg/m²的IA方案进行诱导治疗；而高危组AML建议选择含IDA 12 mg/m²的IA方案进行诱导治疗。

Giant Magneto-Impedance (GMI) Effect in Single-Layer Soft Magnetic Film Under Stress

The stress-induced magnetic anisotropy can significantly affect giant magneto-impedance (GMI) effect of the soft magnetic film. This paper is devoted to the GMI effect of the single layer soft magnetic film implied without and with a stress. By simulating a physical model with MATLAB and COMSOL software, the impedance expression of the single layer soft magnetic film and the relation between external magnetic field and magnetic permeability are deduced. We observed that, without a stress, the sensitive region increased firstly and then decreased with the increasing of the excitation current frequency from 1 MHz to 200 MHz. While the film was subjected to the stress in the direction of the current with one end stressed, the stress on the film was gradually reduced from stressed end to free end. Also, the impedance change rate of the film changed when the stress was added, which is similar to the effect of adding a bias magnetic field on the film. More importantly, the addition of stress σ can induce the bias of the GMI measurement range and improve its sensitivity near zero magnetic fields. This may provide a new way for designing a GMI sensor with higher sensitivity and adjustable measurement range.

Joint reconstruction of rest/stress myocardial perfusion SPECT

Myocardial perfusion imaging (MPI) using rest/stress single photon emission computed tomography (SPECT) allows non-invasive assessment of reversible cardiac perfusion defects. Conventionally, reversible defects are identified using a difference image, called reversible map, obtained by subtracting the stress image from the rest image after registration and normalization of the two images. The identification of reversible defects using the conventional subtraction method is however limited by noise. We propose to jointly reconstruct rest and stress projection data to directly obtain the reversible map in a single reconstruction framework to improve the detectability of reversible defects. To evaluate the performance of the proposed method, we performed phantom studies to mimic reversible defects with different levels of severity and doses. As compared to the conventional subtraction method, the joint method yielded reversible maps with much lower noise and improved defect detectability. At a normal clinical dose level, the joint method improved the signal to noise ratio (SNR) of defect contrast in reversible maps from 13.2 to 66.4, 9.7 to 35.0, 6.1 to 13.2, and 3.1 to 6.5, for defect to normal myocardium concentration ratios of 0%, 25%, 50%, and 75%, respectively. The SNRs obtained using the joint method were improved from 6.1 to 13.2, 3.9 to 9.4, 3.0 to 8.0, and 2.1 to 7.1, for 100%, 75%, 50%, and 25% of the normal clinical dose as compared to the conventional subtraction method. To access clinical feasibility, we applied the joint method to a rest/stress SPECT MPI patient study. The joint method yielded a reversible map with much lower noise, translating into a much higher defect detectability as compared to the conventional subtraction method. Our results indicate that the joint method has the potential to improve radiologists' performance for assessing defects in rest/stress SPECT MPI. In addition, the joint method can be used to reduce dose or imaging time.

A comparison of the biomechanical stability of pedicle-lengthening screws and traditional pedicle screws: an in vitro instant and fatigue-resistant pull-out test

Aims

The aim of this study was to compare the peak pull-out force (PPF) of pedicle-lengthening screws (PLS) and traditional pedicle screws (TPS) using instant and cyclic fatigue testing.

Materials and Methods

A total of 60 lumbar vertebrae were divided into six groups: PLS submitted to instant pull-out and fatigue-resistance testing (groups A1 and A2, respectively), TPS submitted to instant pull-out and fatigue-resistance testing (groups B1 and B2, respectively) and PLS augmented with 2 ml polymethylmethacrylate, submitted to instant pull-out and fatigue-resistance testing (groups C1 and C2, respectively). The PPF and normalized PPF (PPFn) for bone mineral density (BMD) were compared within and between all groups.

Results

In all groups, BMD was significantly correlated with PPF (r = 0.83, p < 0.001). The PPFn in A1 was significantly less than in B1 (p = 0.006) and C1 (p = 0.002). The PPFn of A2 was significantly less than in B2 (p < 0.001) and C2 (p < 0.001). The PPFn in A1, B1, and C1 was significantly greater than in A2 (p = 0.002), B2 (p = 0.027), and C2 (p = 0.003). There were no significant differences in PPFn between B1 and C1, or between B2 and C2.

Conclusion

Pedicle lengthening screws with cement augmentation can provide the same fixation stability as traditional pedicle screws and may be a viable clinical option. Cite this article: Bone Joint J 2018;100-B:516-21.

[Distribution and drug resistance of pathogens at hematology department of Jiangsu Province from 2014 to 2015: results from a multicenter, retrospective study]

Objective: To describe the distribution and drug resistance of pathogens at hematology department of Jiangsu Province from 2014 to 2015 to provide reference for empirical anti-infection treatment. Methods: Pathogens were from hematology department of 26 tertiary hospitals in Jiangsu Province from 2014 to 2015. Antimicrobial susceptibility testing was carried out according to a unified protocol using Kirby-Bauer method or agar dilution method. Collection of drug susceptibility results and corresponding patient data were analyzed. Results: The separated pathogens amounted to 4 306. Gram-negative bacteria accounted for 64.26%, while the proportions of gram-positive bacteria and funguses were 26.99% and 8.75% respectively. Common gram-negative bacteria were Escherichia coli (20.48%) , Klebsiella pneumonia (15.40%) , Pseudomonas aeruginosa (8.50%) , Acinetobacter baumannii (5.04%) and Stenotropho-monas maltophilia (3.41%) respectively. CRE amounted to 123 (6.68%) . Common gram-positive bacteria were Staphylococcus aureus (4.92%) , Staphylococcus hominis (4.88%) and Staphylococcus epidermidis (4.71%) respectively. Candida albicans were the main fungus which accounted for 5.43%. The rates of Escherichia coli and Klebsiella pneumonia resistant to carbapenems were 3.5%-6.1% and 5.0%-6.3% respectively. The rates of Pseudomonas aeruginosa resistant to tobramycin and amikacin were 3.2% and 3.3% respectively. The resistant rates of Acinetobacter baumannii towards tobramycin and cefoperazone/sulbactam were both 19.2%. The rates of Stenotrophomonas maltophilia resistant to minocycline and sulfamethoxazole were 3.5% and 9.3% respectively. The rates of Staphylococcus aureus, Enterococcus faecium and Enterococcus faecalis resistant wards vancomycin were 0, 6.4% and 1.4% respectively; also, the rates of them resistant to linezolid were 1.2%, 0 and 1.6% respectively; in addition, the rates of them resistant to teicoplanin were 2.8%, 14.3% and 8.0% respectively. Furthermore, MRSA accounted for 39.15% (83/212) . Conclusions: Pathogens were mainly gram-negative bacteria. CRE accounted for 6.68%. The rates of Escherichia coli and Klebsiella pneumonia resistant to carbapenems were lower compared with other antibacterial agents. The rates of gram-positive bacteria resistant to vancomycin, linezolid and teicoplanin were still low. MRSA accounted for 39.15%.

mTORC1 activation downregulates FGFR3 and PTH/PTHrP receptor in articular chondrocytes to initiate osteoarthritis

OBJECTIVE

Articular chondrocyte activation, involving aberrant proliferation and prehypertrophic differentiation, is essential for osteoarthritis (OA) initiation and progression. Disruption of mechanistic target of rapamycin complex 1 (mTORC1) promotes chondrocyte autophagy and survival, and decreases the severity of experimental OA. However, the role of cartilage mTORC1 activation in OA initiation is unknown. In this study, we elucidated the specific role of mTORC1 activation in OA initiation, and identify the underlying mechanisms.

METHOD

Expression of mTORC1 in articular cartilage of OA patients and OA mice was assessed by immunostaining. Cartilage-specific tuberous sclerosis complex 1 (Tsc1, mTORC1 upstream inhibitor) knockout (TSC1CKO) and inducible Tsc1 KO (TSC1CKO^ER) mice were generated. The functional effects of mTORC1 in OA initiation and development on its downstream targets were examined by immunostaining, western blotting and qPCR.

RESULTS

Articular chondrocyte mTORC1 was activated in early-stage OA and in aged mice. TSC1CKO mice exhibited spontaneous OA, and TSC1CKO^ER mice (from 2 months) exhibited accelerated age-related and DMM-induced OA phenotypes, with aberrant chondrocyte proliferation and hypertrophic differentiation. This was associated with hyperactivation of mTORC1 and dramatic downregulation of FGFR3 and PPR, two receptors critical for preventing chondrocyte proliferation and differentiation. Rapamycin treatment reversed these phenotypes in KO mice. Furthermore, in vitro rescue experiments demonstrated that p73 and ERK1/2 may mediate the negative regulation of FGFR3 and PPR by mTORC1.

CONCLUSION

mTORC1 activation stimulates articular chondrocyte proliferation and differentiation to initiate OA, in part by downregulating FGFR3 and PPR.

The segment-dependent changes in lumbar intervertebral space height during flexion-extension motion

Objectives

Many studies have investigated the kinematics of the lumbar spine and the morphological features of the lumbar discs. However, the segment-dependent immediate changes of the lumbar intervertebral space height during flexion-extension motion are still unclear. This study examined the changes of intervertebral space height during flexion-extension motion of lumbar specimens.

Methods

First, we validated the accuracy and repeatability of a custom-made mechanical loading equipment set-up. Eight lumbar specimens underwent CT scanning in flexion, neural, and extension positions by using the equipment set-up. The changes in the disc height and distance between adjacent two pedicle screw entry points (DASEP) of the posterior approach at different lumbar levels (L3/4, L4/5 and L5/S1) were examined on three-dimensional lumbar models, which were reconstructed from the CT images.

Results

All the vertebral motion segments (L3/4, L4/5 and L5/S1) had greater changes in disc height and DASEP from neutral to flexion than from neutral to extension. The change in anterior disc height gradually increased from upper to lower levels, from neutral to flexion. The changes in anterior and posterior disc heights were similar at the L4/5 level from neutral to extension, but the changes in anterior disc height were significantly greater than those in posterior disc height at the L3/4 and L5/S1 levels, from neutral to extension.

Conclusions

The lumbar motion segment showed level-specific changes in disc height and DASEP. The data may be helpful in understanding the physiologic dynamic characteristics of the lumbar spine and in optimising the parameters of lumbar surgical instruments.

Cite this article: M. Fu, Q. Ye, C. Jiang, L. Qian, D. Xu, Y. Wang, P. Sun, J. Ouyang. The segment-dependent changes in lumbar intervertebral space height during flexion-extension motion. Bone Joint Res 2017;6:245–252. DOI: 10.1302/2046-3758.64.BJR-2016-0245.R1.

A Bayesian spatial temporal mixtures approach to kinetic parametric images in dynamic positron emission tomography

PURPOSE

Estimation of parametric maps is challenging for kinetic models in dynamic positron emission tomography. Since voxel kinetics tend to be spatially contiguous, the authors consider groups of homogeneous voxels together. The authors propose a novel algorithm to identify the groups and estimate kinetic parameters simultaneously. Uncertainty estimates for kinetic parameters are also obtained.

METHODS

Mixture models were used to fit the time activity curves. In order to borrow information from spatially nearby voxels, the Potts model was adopted. A spatial temporal model was built incorporating both spatial and temporal information in the data. Markov chain Monte Carlo was used to carry out parameter estimation. Evaluation and comparisons with existing methods were carried out on cardiac studies using both simulated data sets and a pig study data. One-compartment kinetic modeling was used, in which K1 is the parameter of interest, providing a measure of local perfusion.

RESULTS

Based on simulation experiments, the median standard deviation across all image voxels, of K1 estimates were 0, 0.13, and 0.16 for the proposed spatial mixture models (SMMs), standard curve fitting, and spatial K-means methods, respectively. The corresponding median mean squared biases for K1 were 0.04, 0.06, and 0.06 for abnormal region of interest (ROI); 0.03, 0.03, and 0.04 for normal ROI; and 0.007, 0.02, and 0.05 for the noise region.

CONCLUSIONS

SMM is a fully Bayesian algorithm which determines the optimal number of homogeneous voxel groups, voxel group membership, parameter estimation, and parameter uncertainty estimation simultaneously. The voxel membership can also be used for classification purposes. By borrowing information from spatially nearby voxels, SMM substantially reduces the variability of parameter estimates. In some ROIs, SMM also reduces mean squared bias.

[Gene diagnosis of four patients with protein C deficiency]

目的

探讨蛋白C缺陷症的分子发病机制。

方法

对4例蛋白C缺陷症患者进行常规诊断和基因分析。

结果

①例1，女，40岁。临床诊断：左下肢深静脉血栓形成。蛋白C活性（PC∶C）48%，蛋白S活性（PS∶C）26.3%，抗凝血酶活性（AT∶C) 75.6%。基因检测结果：蛋白C基因（PROC）启动子C5156T杂合突变、2号外显子区域存在A6578T杂合突变。给予抗凝、溶栓、滤器植入等治疗，症状好转出院。②例2，女，32岁。临床诊断：双下肢深静脉血栓，双上、下肢缺血，双下肢皮肤软组织感染。PC∶C 27%，PS∶C 22.9%，AT∶C 86.7%。基因检测结果：PROC基因启动子C5156T杂合突变、A5045T杂合突变。给予抗凝、抗感染等治疗，因呼吸衰竭、感染性休克、DIC死亡。③例3，女，28岁。临床诊断：右髂静脉及股深静脉血栓。PC∶C 58%，PS∶C 57.3%，AT∶C 80.8%。基因检测结果：PROC启动子C4867T杂合突变，7号外显子12702-12704 AGA (Arg192）或12705-12707 AGA（Arg193）杂合缺失，9号外显子G15240A杂合突变。给予抗凝、溶栓、滤器植入等治疗，症状好转出院。④例4，男，30岁。临床诊断：左下肢深静脉血栓，双下肺动脉栓塞伴双下肺梗死。PC∶C 50%，PS∶C 75.0%，AT∶C 89.1%。基因检测结果：PROC启动子C4867T纯合突变、G4880A纯合突变和A5045T杂合突变，2号外显子T6589C杂合突变。给予抗凝、溶栓、滤器植入等相关治疗，症状好转出院。⑤多态性分析：PROC基因启动子C4867T杂合突变、G4880A纯合突变、C5156T杂合突变为PROC启动子多态性位点。

结论

PROC启动子多态性位点G4880A、C4867T、C5156T，错义突变A5045T、A6578T、G15240A，缺失突变AGA12702-12704del或12705-12707del可能与蛋白C缺陷症有关。PROC启动子错义突变A5045T、A6578T、G15240A，缺失突变AGA12702-12704del或12705-12706del是国际首次报告。

Impact of pedicle-lengthening osteotomy on spinal canal volume and neural foramen size in three types of lumbar spinal stenosis

Objectives

Pedicle-lengthening osteotomy is a novel surgery for lumbar spinal stenosis (LSS), which achieves substantial enlargement of the spinal canal by expansion of the bilateral pedicle osteotomy sites. Few studies have evaluated the impact of this new surgery on spinal canal volume (SCV) and neural foramen dimension (NFD) in three different types of LSS patients.

Methods

CT scans were performed on 36 LSS patients (12 central canal stenosis (CCS), 12 lateral recess stenosis (LRS), and 12 foraminal stenosis (FS)) at L4-L5, and on 12 normal (control) subjects. Mimics 14.01 workstation was used to reconstruct 3D models of the L4-L5 vertebrae and discs. SCV and NFD were measured after 1 mm, 2 mm, 3 mm, 4 mm, or 5 mm pedicle-lengthening osteotomies at L4 and/or L5. One-way analysis of variance was used to examine between-group differences.

Results

In the intact state, SVC and NFD were significantly larger in the control group compared with the LSS groups (P<0.05). After lengthening at L4, the percentage increase in SCV (per millimetre) was LRS>CCS>FS>Control. After lengthening at L5 and L4-L5, the percentage increase in SCV (per millimetre) was LRS>FS>CCS>Control. After lengthening at L4 and L4-L5, the percentage increase in NFD (per millimetre) was FS>CCS>LRS>Control. After lengthening at L5, the percentage increase in NFD (per millimetre) was CCS>LRS>control>FS.

Conclusions

LRS patients are the most suitable candidates for treatment with pedicle-lengthening osteotomy. Lengthening L4 pedicles produced larger percentage increases in NFD than lengthening L5 pedicles (p < 0.05). Lengthening L4 pedicles may be the most effective option for relieving foraminal compression in LSS patients.

Cite this article: P. Li, L. Qian, W. D. Wu, C. F. Wu, J. Ouyang. Impact of pedicle-lengthening osteotomy on spinal canal volume and neural foramen size in three types of lumbar spinal stenosis. Bone Joint Res 2016;5:239–246. DOI: 10.1302/2046-3758.56.2000469.