CADA: phenotype-driven gene prioritization based on a case-enriched knowledge graph.

Many rare syndromes can be well described and delineated from other disorders by a combination of characteristic symptoms. These phenotypic features are best documented with terms of the Human Phenotype Ontology (HPO), which are increasingly used in electronic health records (EHRs), too. Many algorithms that perform HPO-based gene prioritization have also been developed; however, the performance of many such tools suffers from an over-representation of atypical cases in the medical literature. This is certainly the case if the algorithm cannot handle features that occur with reduced frequency in a disorder. With Cada, we built a knowledge graph based on both case annotations and disorder annotations. Using network representation learning, we achieve gene prioritization by link prediction. Our results suggest that Cada exhibits superior performance particularly for patients that present with the pathognomonic findings of a disease. Additionally, information about the frequency of occurrence of a feature can readily be incorporated, when available. Crucial in the design of our approach is the use of the growing amount of phenotype-genotype information that diagnostic labs deposit in databases such as ClinVar. By this means, Cada is an ideal reference tool for differential diagnostics in rare disorders that can also be updated regularly.

Identifying facial phenotypes of genetic disorders using deep learning.

Syndromic genetic conditions, in aggregate, affect 8% of the population1. Many syndromes have recognizable facial features2 that are highly informative to clinical geneticists3-5. Recent studies show that facial analysis technologies measured up to the capabilities of expert clinicians in syndrome identification6-9. However, these technologies identified only a few disease phenotypes, limiting their role in clinical settings, where hundreds of diagnoses must be considered. Here we present a facial image analysis framework, DeepGestalt, using computer vision and deep-learning algorithms, that quantifies similarities to hundreds of syndromes. DeepGestalt outperformed clinicians in three initial experiments, two with the goal of distinguishing subjects with a target syndrome from other syndromes, and one of separating different genetic subtypes in Noonan syndrome. On the final experiment reflecting a real clinical setting problem, DeepGestalt achieved 91% top-10 accuracy in identifying the correct syndrome on 502 different images. The model was trained on a dataset of over 17,000 images representing more than 200 syndromes, curated through a community-driven phenotyping platform. DeepGestalt potentially adds considerable value to phenotypic evaluations in clinical genetics, genetic testing, research and precision medicine.

Optimization of two-compartment-exchange-model analysis for dynamic contrast-enhanced mri incorporating bolus arrival time.

PURPOSE: To optimize the analysis of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) under the two-compartment-exchange-model (2CXM) and to incorporate voxelwise bolus-arrival-time (BAT). MATERIALS AND METHODS: The accuracy of the pharmacokinetic (PK) parameters, extracted from 3T DCE-MRI using 2CXM, was tested under several conditions: eight algorithms for data estimation; correction for BAT; using model selection; different temporal resolution and scan duration. Comparisons were performed on simulated data. The best algorithm was applied to seven patients with brain tumors or following stroke. The extracted perfusion parameters were compared to those of dynamic susceptibility contrast MRI (DSC-MRI). RESULTS: ACoPeD (AIF-corrected-perfusion-DCE-MRI), an analysis using a 2nd derivative regularized-spline and incorporating BAT, achieved the most accurate estimation in simulated data, mean-relative-error: Fp , F, vp , ve : 24.8%, 41.7%, 26.4%, 27.2% vs. 76.5%, 190.8%, 78.8%, 82.39% of the direct four parameters estimation (one-sided two-sample t-test, P < 0.001). Correction for BAT increased the estimation accuracy of the PK parameters by more than 30% and provided a supertemporal resolution estimation of the BAT (higher than the acquired resolution, mean-absolute-error 0.2 sec). High temporal resolution (∼2 sec) is required to avoid biased estimation of PK parameters, and long scan duration (∼20 min) is important for reliable permeability but not for perfusion estimations, mean-error-reduction: E: ∼12%, ve : ∼6%. Using ACoPeD, PK values from normal-appearing white matter, gray matter, and lesion were extracted from patients. Preliminary results showed significant voxelwise correlations to DSC-MRI, between flow values in a patient following stroke (r = 0.49, P < 0.001), and blood volume in a patient with a brain tumor (r = 0.62, P < 0.001). CONCLUSION: This study proposes an optimized analysis method, ACoPeD, for tissue perfusion and permeability estimation using DCE-MRI, to be used in clinical settings. LEVEL OF EVIDENCE: 1 J. Magn. Reson. Imaging 2017;45:237-249.

Optimization of DCE-MRI protocol for the assessment of patients with brain tumors.

The interstitium-to-plasma rate constant (kep), extracted from dynamic contrast enhancement (DCE-MRI) MRI data, seems to have an important role in the assessment of patients with brain tumors. This parameter is affected by the slow behavior of the system, and thus is expected to be highly dependent on acquisition duration. The aim of this study was to optimize the scan duration and protocol of DCE-MRI for accurate estimation of the kep parameter in patients with high grade brain tumors. The effects of DCE-MRI scan duration and protocol design (continuous vs integrated scanning) on the estimated pharmacokinetic (PK) parameters and on model selection, were studied using both simulated and patient data. Scan duration varied, up to 60min for simulated data, and up to 25min in 25 MRI scans obtained from patients with high grade brain tumors, with continuous and integrated scanning protocols. Converging results were obtained from simulated and real data. Significant effect of scan duration was detected on kep. Scan duration of 9min, with integrated protocol in which the data are acquired continuously for 5min, and additional volumes at 7 and 9min, was sufficient for accurate estimation of even low kep values, with an average error of 3%. Over-estimation of the PK parameters was detected for scan duration <12min, being more pronounced at low kep values (<0.1min-1). For the model selection maps, significantly lower percentage of the full extended-Tofts-model (ETM) was selected in patients at scan duration of 5min compared to >12min. An integrated protocol of 9min is suggested as optimal for clinical use in patients with high grade brain tumors. Lower acquisition time may result in over-estimation of kep when using ETM, and therefore care should be taken using model selection.

Differentiation between treatment-related changes and progressive disease in patients with high grade brain tumors using support vector machine classification based on DCE MRI.

Differentiation between treatment-related changes and progressive disease (PD) remains a major clinical challenge in the follow-up of patients with high grade brain tumors. The aim of this study was to differentiate between treatment-related changes and PD using dynamic contrast enhanced (DCE) MRI. Twenty patients were scanned using conventional, DCE-MRI and MR spectroscopy (total of 44 MR scans). The enhanced lesion area was extracted using independent components analysis of the DCE data. Pharmacokinetic parameters were estimated from the DCE data based on the Extended-Tofts-Model. Voxel based classification for treatment-related changes versus PD was performed in a patient-wise leave-one-out manner, using a support vector machine classifier. DCE parameters, K (trans), v e, k ep and v p, significantly differentiated between the tissue types. Classification results were validated using spectroscopy data showing significantly higher choline/creatine values in the extracted PD component compared to areas with treatment-related changes and normal appearing white matter, and high correlation between choline/creatine values and the percentage of the identified PD component within the lesion area (r = 0.77, p < 0.001). On the training data the sensitivity and specificity were 98 and 97 %, respectively, for the treatment-related changes component and 97 and 98 % for the PD component. This study proposes a methodology based on DCE-MRI to differentiate lesion areas into treatment-related changes versus PD, prospectively in each scan. Results may have major clinical importance for pre-operative planning, guidance for targeting biopsy, and early prediction of radiological outcomes in patients with high grade brain tumors.

DUSTER: dynamic contrast enhance up-sampled temporal resolution analysis method.

Dynamic contrast enhanced (DCE) MRI using Tofts' model for estimating vascular permeability is widely accepted, yet inter-tissue differences in bolus arrival time (BAT) are generally ignored. In this work we propose a method, incorporating the BAT in the analysis, demonstrating its applicability and advantages in healthy subjects and patients. A method for DCE Up Sampled TEmporal Resolution (DUSTER) analysis is proposed which includes: baseline T1 map using DESPOT1 analyzed with flip angle (FA) correction; preprocessing; raw-signal-to-T1-to-concentration time curves (CTC) conversion; automatic arterial input function (AIF) extraction at temporal super-resolution; model fitting with model selection while incorporating BAT in the pharmacokinetic (PK) model, and fits contrast agent CTC while using exhaustive search in the BAT dimension in super-resolution. The method was applied to simulated data and to human data from 17 healthy subjects, six patients with glioblastoma, and two patients following stroke. BAT values were compared to time-to-peak (TTP) values extracted from dynamic susceptibility contrast imaging. Results show that the method improved the AIF estimation and allowed extraction of the BAT with a resolution of 0.8 s. In simulations, lower mean relative errors were detected for all PK parameters extracted using DUSTER compared to analysis without BAT correction (vp:5% vs. 20%, Ktrans: 9% vs. 24% and Kep: 8% vs. 17%, respectively), and BAT estimates demonstrated high correlations (r = 0.94, p < 1e− 10) with true values. In real data, high correlations between BAT values were detected when extracted from data acquired with high temporal resolution (2 s) and sub-sampled standard resolution data (6 s) (mean r = 0.85,p < 1e− 10). BAT and TTP values were significantly correlated in the different brain regions in healthy subjects (mean r = 0.72,p = < 1e− 3), as were voxel-wise comparisons in patients (mean r = 0.89, p < 1e− 10). In conclusion, incorporating BAT in DCE analysis improves estimation accuracy for the AIF and the PK parameters while providing an additional clinically important parameter.

Human cerebral blood volume measurements using dynamic contrast enhancement in comparison to dynamic susceptibility contrast MRI.

INTRODUCTION: Cerebral blood volume (CBV) is an important parameter for the assessment of brain tumors, usually obtained using dynamic susceptibility contrast (DSC) MRI. However, this method often suffers from low spatial resolution and high sensitivity to susceptibility artifacts and usually does not take into account the effect of tissue permeability. The plasma volume (vp) can also be extracted from dynamic contrast enhancement (DCE) MRI. The aim of this study was to investigate whether DCE can be used for the measurement of cerebral blood volume in place of DSC for the assessment of patients with brain tumors. METHODS: Twenty-eight subjects (17 healthy subjects and 11 patients with glioblastoma) were scanned using DCE and DSC. vp and CBV values were measured and compared in different brain components in healthy subjects and in the tumor area in patients. RESULTS: Significant high correlations were detected between vp and CBV in healthy subjects in the different brain components; white matter, gray matter, and arteries, correlating with the known increased tissue vascularity, and within the tumor area in patients. CONCLUSION: This work proposes the use of DCE as an alternative method to DSC for the assessment of blood volume, given the advantages of its higher spatial resolution, its lower sensitivity to susceptibility artifacts, and its ability to provide additional information regarding tissue permeability.

Classification of tumor area using combined DCE and DSC MRI in patients with glioblastoma.

This study proposes an automatic method for identification and quantification of different tissue components: the non-enhanced infiltrative tumor, vasogenic edema and enhanced tumor areas, at the subject level, in patients with glioblastoma (GB) based on dynamic contrast enhancement (DCE) and dynamic susceptibility contrast (DSC) MRI. Nineteen MR data sets, obtained from 12 patients with GB, were included. Seven patients were scanned before and 8 weeks following bevacizumab initiation. Segmentation of the tumor area was performed based on the temporal data of DCE and DSC at the group-level using k-means algorithm, and further at the subject-level using support vector machines algorithm. The obtained components were associated to different tissues types based on their temporal characteristics, calculated perfusion and permeability values and MR-spectroscopy. The method enabled the segmentation of the tumor area into the enhancing permeable component; the non-enhancing hypoperfused component, associated with vasogenic edema; and the non-enhancing hyperperfused component, associated with infiltrative tumor. Good agreement was obtained between the group-level, unsupervised and subject-level, supervised classification results, with significant correlation (r = 0.93, p < 0.001) and average symmetric root-mean-square surface distance of 2.5 ± 5.1 mm. Longitudinal changes in the volumes of the three components were assessed alongside therapy. Tumor area segmentation using DCE and DSC can be used to differentiate between vasogenic edema and infiltrative tumors in patients with GB, which is of major clinical importance in therapy response assessment.