Synthesizing Contrast-Enhanced MR Images from Noncontrast MR Images Using Deep Learning

BACKGROUND AND PURPOSE

Recent developments in deep learning methods offer a potential solution to the need for alternative imaging methods due to concerns about the toxicity of gadolinium-based contrast agents. The purpose of the study was to synthesize virtual gadolinium contrast-enhanced T1-weighted MR images from noncontrast multiparametric MR images in patients with primary brain tumors by using deep learning.

MATERIALS AND METHODS

We trained and validated a deep learning network by using MR images from 335 subjects in the Brain Tumor Segmentation Challenge 2019 training data set. A held out set of 125 subjects from the Brain Tumor Segmentation Challenge 2019 validation data set was used to test the generalization of the model. A residual inception DenseNet network, called T1c-ET, was developed and trained to simultaneously synthesize virtual contrast-enhanced T1-weighted (vT1c) images and segment the enhancing portions of the tumor. Three expert neuroradiologists independently scored the synthesized vT1c images by using a 3-point Likert scale, evaluating image quality and contrast enhancement against ground truth T1c images (1 = poor, 2 = good, 3 = excellent).

RESULTS

The synthesized vT1c images achieved structural similarity index, peak signal-to-noise ratio, and normalized mean square error scores of 0.91, 64.35, and 0.03, respectively. There was moderate interobserver agreement between the 3 raters, regarding the algorithm's performance in predicting contrast enhancement, with a Fleiss kappa value of 0.61. Our model was able to accurately predict contrast enhancement in 88.8% of the cases (scores of 2 to 3 on the 3-point scale).

CONCLUSIONS

We developed a novel deep learning architecture to synthesize virtual postcontrast enhancement by using only conventional noncontrast brain MR images. Our results demonstrate the potential of deep learning methods to reduce the need for gadolinium contrast in the evaluation of primary brain tumors.

QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at https://github.com/RagMeh11/QU-BraTS.

Deep Learning-Based Electrocardiogram Signal Analysis for Abnormalities Detection Using Hybrid Cascade Feed Forward Backpropagation with Ant Colony Optimization Technique

In this paper, a time series data mining models is introduced for analysis of ECG data for prior identification of heart attacks. The ECG data sets extracted from Physionet are simulated in MATLAB. The Data used for model are preprocessed so that missing data are fulfilled. In this work cascade feedforward NN which is similar to Multilayer Perceptron (MLP) architecture is proposed along with Swarm Intelligence. A hybrid method combining cascade-Forward NN Classifier and Ant colony optimization is proposed in this paper. The swarm-based intelligence method optimizes the weight adjustment of neural network and enhances the convergence behavior. The novelty is on the optimization of the NN parameters for narrowing down the convergence with ACO implementation. Ant colony optimization is used here for choosing the optimized hidden node. The combined use of machine learning algorithm with neural network enhances the performance of the system. The performance is evaluated using parameters like True Positive (TP), True Negative (TN), False Positive (FP), and False Negative (FN) respectively. The Improved accuracy of proposed Classifier model raises the speed. In addition, the proposed method uses minimum memory. The implementation was done in MATLAB tool. Real time data was used.

BrainNET: Inference of Brain Network Topology Using Machine Learning

Background: To develop a new functional magnetic resonance image (fMRI) network inference method, BrainNET, that utilizes an efficient machine learning algorithm to quantify contributions of various regions of interests (ROIs) in the brain to a specific ROI. Methods: BrainNET is based on extremely randomized trees to estimate network topology from fMRI data and modified to generate an adjacency matrix representing brain network topology, without reliance on arbitrary thresholds. Open-source simulated fMRI data of 50 subjects in 28 different simulations under various confounding conditions with known ground truth were used to validate the method. Performance was compared with correlation and partial correlation (PC). The real-world performance was then evaluated in a publicly available attention-deficit/hyperactivity disorder (ADHD) data set, including 134 typically developing children (mean age: 12.03, males: 83), 75 ADHD inattentive (mean age: 11.46, males: 56), and 93 ADHD combined (mean age: 11.86, males: 77) subjects. Network topologies in ADHD were inferred using BrainNET, correlation, and PC. Graph metrics were extracted to determine differences between the ADHD groups. Results: BrainNET demonstrated excellent performance across all simulations and varying confounders in identifying the true presence of connections. In the ADHD data set, BrainNET was able to identify significant changes (p < 0.05) in graph metrics between groups. No significant changes in graph metrics between ADHD groups were identified using correlation and PC. Conclusion: We describe BrainNET, a new network inference method to estimate fMRI connectivity that was adapted from gene regulatory methods. BrainNET out-performed Pearson correlation and PC in fMRI simulation data and real-world ADHD data. BrainNET can be used independently or combined with other existing methods as a useful tool to understand network changes and to determine the true network topology of the brain under various conditions and disease states. Impact statement Developed a new functional magnetic resonance image (fMRI) network inference method named as BrainNET using machine learning. BrainNET out-performed Pearson correlation and partial correlation in fMRI simulation data and real-world attention-deficit/hyperactivity disorder data. BrainNET does not need to be pretrained and can be applied to infer fMRI network topology independently on individual subjects and for varying number of nodes.

Detection of Adherence of Enterococcus faecalis in Infected Dentin of Extracted Human Teeth Using Confocal Laser Scanning Microscope: An In vitro Study

AIM

The aim of this study is to detect in vitro adherence of Enterococcus faecalis to the infected dentinal tubules of human extracted teeth using confocal laser scanning microscope.

SUBJECTS AND METHODS

Roots from human premolar teeth (n = 40) were infected with E. faecalis strain the American Type Culture Collection 29212 in brain heart infusion for 21 days. After the experimental period, specimens were divided into two groups, Group A (n = 20), Group B (n = 20), and Group A specimens were stained with fluorescein diacetate dye for the detection of viability and adherence Group B were stained with acridine orange dye for detection of metabolic activity and adherence. Samples were washed, thoroughly sectioned and examined by confocal laser scanning microscopy. Computer-assisted determinants of fluorescence, bacterial viability, metabolic activity, and adherence were compared statistically.

RESULTS

E. faecalis was able to invade the dentinal tubules to a depth of 1-400 μm and adhere to 1-200 μm depth. Adherence (90%) was significantly higher in 1-100 μm using fluorescein diacetate and acridine orange dye.

CONCLUSION

Adherence of E. faecalis as evaluated by confocal laser scanning microscope was highest at the depth of 1-100 μm which may have an impact on the shaping and cleaning procedures on the root canal.

Lymphangioma circumscriptum in an adult: an unusual oral presentation

Lymphangioma is a benign hamartomatous tumor of lymphatic vessels. This lymphatic malformation is characterized by an abnormal proliferation of lymphatic vessels. Extra-oral lymphangiomas occur more frequently in the neck region predominantly in the posterior triangle, while intra-oral lymphangiomas are commonly seen in the tongue mainly on the dorsum surface. Various imaging modalities such as ultrasound and color Doppler are very useful in viewing the extent of the lesion. In most of the cases, surgical excision is the treatment of choice. The prognosis is good for most patients, but recurrence has also been reported in some cases, presumably because the lesion is interwoven between muscle fibers, preventing complete removal. This case report discusses the clinical features, color Doppler imaging, histopathology, and treatment of lymphangioma.

Reversible formation of on-pathway macroscopic aggregates during the folding of maltose binding protein

Maltose binding protein (MBP) is widely used as a model for protein folding and export studies. We show here that macroscopic aggregates form transiently during the refolding of MBP at micromolar protein concentrations. Disaggregation occurs spontaneously without any aid, and the refolded material has structure and activity identical to those of the native, nondenatured protein. A considerable fraction of protein undergoing folding partitions into the aggregate phase and can be manually separated from the soluble phase by centrifugation. The separated MBP precipitate can be resolubilized and yields active, refolded protein. This demonstrates that both the soluble and aggregate phases contribute to the final yield of refolded protein. SecB, the cognate Escherichia coli cytosolic chaperone in vivo for MBP, reduces but does not entirely prevent aggregation, whereas GroEL and a variety of other control proteins have no effect. Kinetic studies using a variety of spectroscopic probes show that aggregation occurs through a collapsed intermediate with some secondary structure. The aggregate formed during refolding can convert directly to a near native state without going through the unfolded state. Further, optical and electron microscopic studies indicate that the MBP precipitate is not an amyloid.

Disordered N-terminal residues affect the folding thermodynamics and kinetics of maltose binding protein

Maltose binding protein (MBP) exhibits a slow phase of folding at pH 7.4, 298 K. The kinetics of this phase has been characterized as a function of denaturant concentration and temperature. Denaturant double-jump experiments and the activation energy for folding indicate that the slow phase involves processes other than proline isomerization. Although the first five N-terminal residues are disordered in the MBP crystal structure, mutations in this region slow down folding and destabilize the native structure. This is the first report showing that disordered N-terminal residues can affect folding kinetics and stability.

Prediction of the maximal stability temperature of monomeric globular proteins solely from amino acid sequence

Globular protein thermostability is characterized the cold denaturation, maximal stability (Tms) and heat denaturation temperatures. For mesophilic globular proteins, Tms typically ranges from -25 degrees C to +35 degrees C. We show that the indirect estimate of Tms from calorimetry and the direct estimate from chemical denaturation performed in a range of temperatures are in close agreement. The heat capacity change of unfolding per mol residue (delta Cp) alone is shown to accurately predict Tms. Delta Cp and hence Tms can be predicted solely from the protein sequence. The average difference in free energy of unfolding at the observed and predicted values of Tms is 1.0 kcal mol(-1), which is small compared to typical values of the total free energy of unfolding.

Thermodynamic characterization of the reversible, two-state unfolding of maltose binding protein, a large two-domain protein

The folding and stability of maltose binding protein (MBP) have been investigated as a function of pH and temperature by intrinsic tryptophan fluorescence, far- and near-UV circular dichroism, and high-sensitivity differential scanning calorimetric measurements. MBP is a monomeric, two-domain protein containing 370 amino acids. The protein is stable in the pH range of 4-10.5 at 25 degrees C. The protein exhibits reversible, two-state, thermal and guanidine hydrochloride-mediated denaturation at neutral pH. The thermostability of MBP is maximal at pH 6, with a Tm of 64.9 degrees C and a deltaHm of 259.7 kcal mol(-1). The linear dependence of deltaHm on Tm was used to estimate a value of deltaCp of 7.9 kcal mol(-1) K(-1) or 21.3 cal (mol of residue)(-1) K(-1). These values are higher than the corresponding deltaCp's for most globular proteins studied to date. However, the extrapolated values of deltaH and deltaS (per mole of residue) at 110 degrees C are similar to those of other globular proteins. These data have been used to show that the temperature at which a protein undergoes cold denaturation depends primarily on the deltaCp (per mol of residue) and that this temperature increases with an increase in deltaCp. The predicted decrease in stability of MBP at low temperatures was experimentally confirmed by carrying out denaturant-mediated unfolding studies at neutral pH at 2 and 28 degrees C.