Using Deep Convolutional Neural Networks for Neonatal Brain Image Segmentation

INTRODUCTION

Deep learning neural networks are especially potent at dealing with structured data, such as images and volumes. Both modified LiviaNET and HyperDense-Net performed well at a prior competition segmenting 6-month-old infant magnetic resonance images, but neonatal cerebral tissue type identification is challenging given its uniquely inverted tissue contrasts. The current study aims to evaluate the two architectures to segment neonatal brain tissue types at term equivalent age.

METHODS

Both networks were retrained over 24 pairs of neonatal T1 and T2 data from the Developing Human Connectome Project public data set and validated on another eight pairs against ground truth. We then reported the best-performing model from training and its performance by computing the Dice similarity coefficient (DSC) for each tissue type against eight test subjects.

RESULTS

During the testing phase, among the segmentation approaches tested, the dual-modality HyperDense-Net achieved the best statistically significantly test mean DSC values, obtaining 0.94/0.95/0.92 for the tissue types and took 80 h to train and 10 min to segment, including preprocessing. The single-modality LiviaNET was better at processing T2-weighted images than processing T1-weighted images across all tissue types, achieving mean DSC values of 0.90/0.90/0.88 for gray matter, white matter, and cerebrospinal fluid, respectively, while requiring 30 h to train and 8 min to segment each brain, including preprocessing.

DISCUSSION

Our evaluation demonstrates that both neural networks can segment neonatal brains, achieving previously reported performance. Both networks will be continuously retrained over an increasingly larger repertoire of neonatal brain data and be made available through the Canadian Neonatal Brain Platform to better serve the neonatal brain imaging research community.

Prediction of Vestibular Dysfunction by Applying Machine Learning Algorithms to Postural Instability

Objective: To evaluate various machine learning algorithms in predicting peripheral vestibular dysfunction using the dataset of the center of pressure (COP) sway during foam posturography measured from patients with dizziness.

Study Design: Retrospective study.

Setting: Tertiary referral center.

Patients: Seventy-five patients with vestibular dysfunction and 163 healthy controls were retrospectively recruited. The dataset included the velocity, the envelopment area, the power spectrum of the COP for three frequency ranges and the presence of peripheral vestibular dysfunction evaluated by caloric testing in 75 patients with vestibular dysfunction and 163 healthy controls.

Main Outcome Measures: Various forms of machine learning algorithms including the Gradient Boosting Decision Tree, Bagging Classifier, and Logistic Regression were trained. Validation and comparison were performed using the area under the curve (AUC) of the receiver operating characteristic curve (ROC) and the recall of each algorithm using K-fold cross-validation.

Results: The AUC (0.90 ± 0.06) and the recall (0.84 ± 0.07) of the Gradient Boosting Decision Tree were the highest among the algorithms tested, and both of them were significantly higher than those of the logistic regression (AUC: 0.85 ± 0.08, recall: 0.78 ± 0.07). The recall of the Bagging Classifier (0.82 ± 0.07) was also significantly higher than that of logistic regression.

Conclusion: Machine learning algorithms can be successfully used to predict vestibular dysfunction as identified using caloric testing with the dataset of the COP sway during posturography. The multiple algorithms should be evaluated in each clinical dataset since specific algorithm does not always fit to any dataset. Optimization of the hyperparameters in each algorithm are necessary to obtain the highest accuracy.

Machine Learning of Stem Cell Identities From Single-Cell Expression Data via Regulatory Network Archetypes

The molecular regulatory network underlying stem cell pluripotency has been intensively studied, and we now have a reliable ensemble model for the "average" pluripotent cell. However, evidence of significant cell-to-cell variability suggests that the activity of this network varies within individual stem cells, leading to differential processing of environmental signals and variability in cell fates. Here, we adapt a method originally designed for face recognition to infer regulatory network patterns within individual cells from single-cell expression data. Using this method we identify three distinct network configurations in cultured mouse embryonic stem cells-corresponding to naïve and formative pluripotent states and an early primitive endoderm state-and associate these configurations with particular combinations of regulatory network activity archetypes that govern different aspects of the cell's response to environmental stimuli, cell cycle status and core information processing circuitry. These results show how variability in cell identities arise naturally from alterations in underlying regulatory network dynamics and demonstrate how methods from machine learning may be used to better understand single cell biology, and the collective dynamics of cell communities.

Machine Learning in Acute Ischemic Stroke Neuroimaging

Machine Learning (ML) through pattern recognition algorithms is currently becoming an essential aid for the diagnosis, treatment, and prediction of complications and patient outcomes in a number of neurological diseases. The evaluation and treatment of Acute Ischemic Stroke (AIS) have experienced a significant advancement over the past few years, increasingly requiring the use of neuroimaging for decision-making. In this review, we offer an insight into the recent developments and applications of ML in neuroimaging focusing on acute ischemic stroke.