Search

Sensor-based remote monitoring could help us better track Parkinson’s disease (PD) progression, and measure patients’ response to putative disease-modifying therapeutic interventions. To be useful, the remotely-collected measurements should be valid, reliable and sensitive to change, and people with PD must engage with the technology.We developed a smartwatch-based active assessment that enables unsupervised measurement of motor signs of PD. 388 study participants with early-stage PD (Personalized Parkinson Project, 64% men, average age 63 years) wore a smartwatch for a median of 390 days, allowing for continuous passive monitoring. Participants performed unsupervised motor tasks both in the clinic (once) and remotely (twice weekly for one year). Dropout rate was 2% at the end of follow-up. Median wear-time was 21.1 hours/day, and 59% of per-protocol remote assessments were completed.In-clinic performance of the virtual exam verified that most participants correctly followed watch-based instructions. Analytical validation was established for in-clinic measurements, which showed moderate-to-strong correlations with consensus MDS-UPDRS Part III ratings for rest tremor (ρ=0.70), bradykinesia (ρ=-0.62), and gait (ρ=-0.46). Test-retest reliability of remote measurements, aggregated monthly, was good-to-excellent (ICC: 0.75 - 0.96). Remote measurements were sensitive to the known effects of dopaminergic medication (on vs off Cohen’s d: 0.19 - 0.54). Of note, in-clinic assessments often did not reflect the patients’ typical status at home.This demonstrates the feasibility of using smartwatch-based unsupervised active tests, and establishes the analytical validity of associated digital measurements. Weekly measurements can create a more complete picture of patient functioning by providing a real-life distribution of disease severity, as it fluctuates over time. Sensitivity to medication-induced change, together with the improvement in test-retest reliability from temporal aggregation implies that these methods could help reduce sample sizes needed to demonstrate a response to therapeutic intervention or disease progression.

Current clinical practice relies on clinical history to determine the time since stroke (TSS) onset. Imaging-based determination of acute stroke onset time could provide critical information to clinicians in deciding stroke treatment options, such as thrombolysis. The patients with unknown or unwitnessed TSS are usually excluded from thrombolysis, even if their symptoms began within the therapeutic window. In this paper, we demonstrate a machine learning approach for TSS classification using routinely acquired imaging sequences. We develop imaging features from the magnetic resonance (MR) images and train machine learning models to classify the TSS. We also propose a deep-learning model to extract hidden representations for the MR perfusion-weighted images and demonstrate classification improvement by incorporating these additional deep features. The cross-validation results show that our best classifier achieved an area under the curve of 0.765, with a sensitivity of 0.788 and a negative predictive value of 0.609, outperforming existing methods. We show that the features generated by our deep-learning algorithm correlate with the MR imaging features, and validate the robustness of the model on imaging parameter variations (e.g., year of imaging). This paper advances magnetic resonance imaging analysis one-step-closer to an operational decision support tool for stroke treatment guidance.

Prostate cancer is the most common and second most deadly form of cancer in men in the United States. The classification of prostate cancers based on Gleason grading using histological images is important in risk assessment and treatment planning for patients. Here, we demonstrate a new region-based convolutional neural network framework for multi-task prediction using an epithelial network head and a grading network head. Compared with a single-task model, our multi-task model can provide complementary contextual information, which contributes to better performance. Our model is achieved a state-of-the-art performance in epithelial cells detection and Gleason grading tasks simultaneously. Using fivefold cross-validation, our model is achieved an epithelial cells detection accuracy of 99.07% with an average area under the curve of 0.998. As for Gleason grading, our model is obtained a mean intersection over union of 79.56% and an overall pixel accuracy of 89.40%.

Gleason grading of histological images is important in risk assessment and treatment planning for prostate cancer patients. Much research has been done in classifying small homogeneous cancer regions within histological images. However, semi-supervised methods published to date depend on pre-selected regions and cannot be easily extended to an image of heterogeneous tissue composition. In this paper, we propose a multi-scale U-Net model to classify images at the pixel-level using 224 histological image tiles from radical prostatectomies of 20 patients. Our model was evaluated by a patient-based 10-fold cross validation, and achieved a mean Jaccard index of 65.8% across 4 classes (stroma, Gleason 3, Gleason 4 and benign glands), and 75.5% for 3 classes (stroma, benign glands, prostate cancer), outperforming other methods.

Automated Gleason grading is an important preliminary step for quantitative histopathological feature extraction. Different from the traditional task of classifying small pre-selected homogeneous regions, semantic segmentation provides pixel-wise Gleason predictions across an entire slide. Deep learning-based segmentation models can automatically learn visual semantics from data, which alleviates the need for feature engineering. However, performance of deep learning models is limited by the scarcity of large-scale fully annotated datasets, which can be both expensive and time-consuming to create. One way to address this problem is to leverage external weakly labeled datasets to augment models trained on the limited data. In this paper, we developed an expectation maximization-based approach constrained by an approximated prior distribution in order to extract useful representations from a large number of weakly labeled images generated from low-magnification annotations. This method was utilized to improve the performance of a model trained on a limited fully annotated dataset. Our semi-supervised approach trained with 135 fully annotated and 1,800 weakly annotated tiles achieved a mean Jaccard Index of 49.5% on an independent test set, which was 14% higher than the initial model trained only on the fully annotated dataset.

Predicting infarct volume from magnetic resonance perfusion-weighted imaging can provide helpful information to clinicians in deciding how aggressively to treat acute stroke patients. Models have been developed to predict tissue fate, yet these models are mostly built using hand-crafted features (e.g., time-to-maximum) derived from perfusion images, which are sensitive to deconvolution methods. We demonstrate the application of deep convolution neural networks (CNNs) on predicting final stroke infarct volume using only the source perfusion images. We propose a deep CNN architecture that improves feature learning and achieves an area under the curve of [Formula: see text] , outperforming existing tissue fate models. We further validate the proposed deep CNN with existing 2-D and 3-D deep CNNs for images/video classification, showing the importance of the proposed architecture. Our work leverages deep learning techniques in stroke tissue outcome prediction, advancing magnetic resonance imaging perfusion analysis one step closer to an operational decision support tool for stroke treatment guidance.

Introduction: Perfusion MR and CT parameters are widely used during the assessment of acute ischemic strokes to evaluate the likely lesion growth. However, such perfusion parameters and derived ratios are sensitive to the choice of arterial input function or deconvolution method. Studies have shown that various deconvolution algorithms can lead to inconsistent values and also introduce distortions that influence measurement. In this work, we propose a deep convolutional neural network (CNN) to learn imaging features from source magnetic resonance perfusion images that are best predictive of tissue outcome. Methods: We developed a deep CNN for voxel-by-voxel prediction. Perfusion-weighted images (PWIs), diffusion-weighted images (DWIs), and apparent diffusion coefficient (ADC) maps were obtained in five ischemic stroke patients (mean age: 69; mean NIHSS: 12) within 6.5 hours of stroke onset from UCLA stroke center database. The final infarct volumes were evaluated in the 5-7 days post-treatment FLAIR images. 53,000 training data were generated; each training data consisted of the raw voxel values obtained across the MR images. The CNN has three separate convolutional and pooling layers for each imaging channel; 128 combined features were learned in the final fully-connected layer, which were fitted to a logistic classifier for single voxel infarct prediction. Results: The model achieved an area under the curve (AUC) of 0.941 +/- 0.002 (95% CI) in ten-fold cross validation, outperforming existing models with perfusion parameters. With a cut-off threshold of 0.5, the model achieved an accuracy of 0.865, a precision of 0.836, and a recall of 0.910. The model automatically learned spatio-temporal filters that detected temporal and spatial changes in the PWIs. Conclusion: This pilot study showed that the deep CNN is capable of generating automatically learned features from source perfusion images that are predictive of tissue outcome, providing a potential alternative for stroke image analysis. Our future work includes experimenting on a larger dataset, and optimizing model parameters with pre-training and fine-tuning.

Several models have been developed to predict stroke outcomes (e.g., stroke mortality, patient dependence, etc.) in recent decades. However, there is little discussion regarding the problem of between-class imbalance in stroke datasets, which leads to prediction bias and decreased performance. In this paper, we demonstrate the use of the Synthetic Minority Over-sampling Technique to overcome such problems. We also compare state of the art machine learning methods and construct a six-variable support vector machine (SVM) model to predict stroke mortality at discharge. Finally, we discuss how the identification of a reduced feature set allowed us to identify additional cases in our research database for validation testing. Our classifier achieved a c-statistic of 0.865 on the cross-validated dataset, demonstrating good classification performance using a reduced set of variables.

While phytoplankton diversity and productivity in the Southern Ocean has been widely studied in recent years, most attention has been given to elucidating environmental factors that affect the dynamics of micro-plankton (mainly diatoms) and nano-plankton (mainly Phaeocystis antarctica). Only limited effects have been given to studying the occurrence and the potential risks associated with the blooming of dinoflagellates in the relevant waters. This study focused on the appearance and toxicological characteristics of a toxic dinoflagellate, Alexandrium tamarense, identified and isolated from the Drake Passage in a research cruise from November to December 2001 The appearance of A. tamarense in the Southern Ocean indicates the risk of a paralytic shellfish poisoning (PSP) outbreak there and is therefore of scientific concern. Results showed that while the overall quantity of A. tamarense in water samples from 30meters below the sea surface often comprised less than 0.1% of the total population of phytoplankton, the highest concentration of A. tamarense (20 cells ) was recorded in the portion of the Southern Ocean between the southern end of South America and the Falkland Islands. Waters near the Polar Front contained the second highest concentrations of 10-15 cells . A. tamarense was however rarely found in waters near the southern side of the Polar Front, indicating that cold sea temperatures near the Antarctic ice does not favor the growth of this dinoflagellate. One strain of A. tamarense from this cruise was isolated and cultured for further study in the laboratory. Experiments showed that this strain of A. tamarense has a high tolerance to temperature variations and could survive at temperatures ranging from . This shows the cosmopolitan nature off. tamarense. With regard to the algal toxins produced, this strain of A. tamarense produced mainly C-2 toxins but very little saxitoxin and gonyailtoxin. The toxicological property of this A. tamarense strain coincided with a massive death of penguins in the Falkland Islands in December 2002 to January 2003.