Detection of diffusely abnormal white matter in multiple sclerosis on multiparametric brain MRI using semi-supervised deep learning.

In addition to focal lesions, diffusely abnormal white matter (DAWM) is seen on brain MRI of multiple sclerosis (MS) patients and may represent early or distinct disease processes. The role of MRI-observed DAWM is understudied due to a lack of automated assessment methods. Supervised deep learning (DL) methods are highly capable in this domain, but require large sets of labeled data. To overcome this challenge, a DL-based network (DAWM-Net) was trained using semi-supervised learning on a limited set of labeled data for segmentation of DAWM, focal lesions, and normal-appearing brain tissues on multiparametric MRI. DAWM-Net segmentation performance was compared to a previous intensity thresholding-based method on an independent test set from expert consensus (N = 25). Segmentation overlap by Dice Similarity Coefficient (DSC) and Spearman correlation of DAWM volumes were assessed. DAWM-Net showed DSC > 0.93 for normal-appearing brain tissues and DSC > 0.81 for focal lesions. For DAWM-Net, the DAWM DSC was 0.49 ± 0.12 with a moderate volume correlation (ρ = 0.52, p < 0.01). The previous method showed lower DAWM DSC of 0.26 ± 0.08 and lacked a significant volume correlation (ρ = 0.23, p = 0.27). These results demonstrate the feasibility of DL-based DAWM auto-segmentation with semi-supervised learning. This tool may facilitate future investigation of the role of DAWM in MS.

Parametric delineation uncertainties contouring (PDUC) modeling on CT scans of prostate cancer patients.

PURPOSE: Variability in contouring contributes to large variations in radiation therapy planning and treatment outcomes. The development and testing of tools to automatically detect contouring errors require a source of contours that includes well-understood and realistic errors. The purpose of this work was to develop a simulation algorithm that intentionally injects errors of varying magnitudes into clinically accepted contours and produces realistic contours with different levels of variability. METHODS: We used a dataset of CT scans from 14 prostate cancer patients with clinician-drawn contours of the regions of interest (ROI) of the prostate, bladder, and rectum. Using our newly developed Parametric Delineation Uncertainties Contouring (PDUC) model, we automatically generated alternative, realistic contours. The PDUC model consists of the contrast-based DU generator and a 3D smoothing layer. The DU generator transforms contours (deformation, contraction, and/or expansion) as a function of image contrast. The generated contours undergo 3D smoothing to obtain a realistic look. After model building, the first batch of auto-generated contours was reviewed. Editing feedback from the reviews was then used in a filtering model for the auto-selection of clinically acceptable (minor-editing) DU contours. RESULTS: Overall, C values of 5 and 50 consistently produced high proportions of minor-editing contours across all ROI compared to the other C values (0.936 ± $ \pm \;$ 0.111 and 0.552 ± $ \pm \;$ 0.228, respectively). The model performed best on the bladder, which had the highest proportion of minor-editing contours (0.606) of the three ROI. In addition, the classification AUC for the filtering model across all three ROI is 0.724 ± $ \pm \;$ 0.109. DISCUSSION: The proposed methodology and subsequent results are promising and could have a great impact on treatment planning by generating mathematically simulated alternative structures that are clinically relevant and realistic enough (i.e., similar to clinician-drawn contours) to be used in quality control of radiation therapy.

Characterization of Symptoms and Symptom Clusters for Type 2 Diabetes Using a Large Nationwide Electronic Health Record Database.

OBJECTIVE: A variety of symptoms may be associated with type 2 diabetes and its complications. Symptoms in chronic diseases may be described in terms of prevalence, severity, and trajectory and often co-occur in groups, known as symptom clusters, which may be representative of a common etiology. The purpose of this study was to characterize type 2 diabetes-related symptoms using a large nationwide electronic health record (EHR) database. Methods: We acquired the Cerner Health Facts, a nationwide EHR database. The type 2 diabetes cohort (n = 1,136,301 patients) was identified using a rule-based phenotype method. A multistep procedure was then used to identify type 2 diabetes-related symptoms based on International Classification of Diseases, 9th and 10th revisions, diagnosis codes. Type 2 diabetes-related symptoms and co-occurring symptom clusters, including their temporal patterns, were characterized based the longitudinal EHR data. Results: Patients had a mean age of 61.4 years, 51.2% were female, and 70.0% were White. Among 1,136,301 patients, there were 8,008,276 occurrences of 59 symptoms. The most frequently reported symptoms included pain, heartburn, shortness of breath, fatigue, and swelling, which occurred in 21-60% of the patients. We also observed over-represented type 2 diabetes symptoms, including difficulty speaking, feeling confused, trouble remembering, weakness, and drowsiness/sleepiness. Some of these are rare and difficult to detect by traditional patient-reported outcomes studies. Conclusion: To the best of our knowledge, this is the first study to use a nationwide EHR database to characterize type 2 diabetes-related symptoms and their temporal patterns. Fifty-nine symptoms, including both over-represented and rare diabetes-related symptoms, were identified.

Water and Meadow Views Both Afford Perceived but Not Performance-Based Attention Restoration: Results From Two Experimental Studies.

Attention Restoration Theory proposes that exposure to natural environments helps to restore attention. For sustained attention-the ongoing application of focus to a task, the effect appears to be modest, and the underlying mechanisms of attention restoration remain unclear. Exposure to nature may improve attention performance through many means: modulation of alertness and one's connection to nature were investigated here, in two separate studies. In both studies, participants performed the Sustained Attention to Response Task (SART) before and immediately after viewing a meadow, ocean, or urban image for 40 s, and then completed the Perceived Restorativeness Scale. In Study 1 (n = 68), an eye-tracker recorded the participants' tonic pupil diameter during the SARTs, providing a measure of alertness. In Study 2 (n = 186), the effects of connectedness to nature on SART performance and perceived restoration were studied. In both studies, the image viewed was not associated with participants' sustained attention performance; both nature images were perceived as equally restorative, and more restorative than the urban image. The image viewed was not associated with changes in alertness. Connectedness to nature was not associated with sustained attention performance, but it did moderate the relation between viewing the natural images and perceived restorativeness; participants reporting a higher connection to nature also reported feeling more restored after viewing the nature, but not the urban, images. Dissociation was found between the physiological and behavioral measures and the perceived restorativeness of the images. The results suggest that restoration associated with nature exposure is not associated with modulation of alertness but is associated with connectedness with nature.

Developing a Search Engine for Precision Medicine.

Precision medicine focuses on developing new treatments based on an individual's genetic, environmental, and lifestyle profile. While this data-driven approach has led to significant advances, retrieving information specific to a patient's condition has proved challenging for oncologists due to the large volume of data. In this paper, we propose the PRecIsion Medicine Robust Oncology Search Engine (PRIMROSE) for cancer patients that retrieves scientific articles and clinical trials based on a patient's condition, genetic profile, age, and gender. Our search engine utilizes Elasticsearch indexes for information storage and retrieval, and we developed a knowledge graph for query expansion in order to improve recall. Additionally, we experimented with machine learning and learning-to-rank components to the search engine and compared the results of the two approaches. Finally, we developed a front-facing ReactJS website and a REST API for connecting with our search engine. The development of this front-facing website allows for easy access to our system by healthcare providers.

Accurate prediction of boundaries of high resolution topologically associated domains (TADs) in fruit flies using deep learning.

Genomes are organized into self-interacting chromatin regions called topologically associated domains (TADs). A significant number of TAD boundaries are shared across multiple cell types and conserved across species. Disruption of TAD boundaries may affect the expression of nearby genes and could lead to several diseases. Even though detection of TAD boundaries is important and useful, there are experimental challenges in obtaining high resolution TAD locations. Here, we present computational prediction of TAD boundaries from high resolution Hi-C data in fruit flies. By extensive exploration and testing of several deep learning model architectures with hyperparameter optimization, we show that a unique deep learning model consisting of three convolution layers followed by a long short-term-memory layer achieves an accuracy of 96%. This outperforms feature-based models' accuracy of 91% and an existing method's accuracy of 73-78% based on motif TRAP scores. Our method also detects previously reported motifs such as Beaf-32 that are enriched in TAD boundaries in fruit flies and also several unreported motifs.