An Extensive-Form Game Paradigm for Visual Field Testing via Deep Reinforcement Learning.

Glaucoma is the leading cause of irreversible but preventable blindness worldwide, and visual field testing is an important tool for its diagnosis and monitoring. Testing using standard visual field thresholding procedures is time-consuming, and prolonged test duration leads to patient fatigue and decreased test reliability. Different visual field testing algorithms have been developed to shorten testing time while maintaining accuracy. However, the performance of these algorithms depends heavily on prior knowledge and manually crafted rules that determine the intensity of each light stimulus as well as the termination criteria, which is suboptimal. We leverage deep reinforcement learning to find improved decision strategies for visual field testing. In our proposed algorithms, multiple intelligent agents are employed to interact with the patient in an extensive-form game fashion, with each agent controlling the test on one of the testing locations in the patient's visual field. Through training, each agent learns an optimized policy that determines the intensities of light stimuli and the termination criteria, which minimizes the error in sensitivity estimation and test duration at the same time. In simulation experiments, we compare the performance of our algorithms against baseline visual field testing algorithms and show that our algorithms achieve a better trade-off between estimation accuracy and test duration. By retaining testing accuracy with reduced test duration, our algorithms improve test reliability, clinic efficiency, and patient satisfaction, and translationally affect clinical outcomes.

RGC-Net: An Automatic Reconstruction and Quantification Algorithm for Retinal Ganglion Cells Based on Deep Learning.

Purpose: The purpose of this study was to develop a deep learning-based fully automated reconstruction and quantification algorithm which automatically delineates the neurites and somas of retinal ganglion cells (RGCs). Methods: We trained a deep learning-based multi-task image segmentation model, RGC-Net, that automatically segments the neurites and somas in RGC images. A total of 166 RGC scans with manual annotations from human experts were used to develop this model, whereas 132 scans were used for training, and the remaining 34 scans were reserved as testing data. Post-processing techniques removed speckles or dead cells in soma segmentation results to further improve the robustness of the model. Quantification analyses were also conducted to compare five different metrics obtained by our automated algorithm and manual annotations. Results: Quantitatively, our segmentation model achieves average foreground accuracy, background accuracy, overall accuracy, and dice similarity coefficient of 0.692, 0.999, 0.997, and 0.691 for the neurite segmentation task, and 0.865, 0.999, 0.997, and 0.850 for the soma segmentation task, respectively. Conclusions: The experimental results demonstrate that RGC-Net can accurately and reliably reconstruct neurites and somas in RGC images. We also demonstrate our algorithm is comparable to human manually curated annotations in quantification analyses. Translational Relevance: Our deep learning model provides a new tool that can trace and analyze the RGC neurites and somas efficiently and faster than manual analysis.

Objective Measurement of Social Gaze and Smile Behaviors in Children with Suspected Autism Spectrum Disorder During Administration of the Autism Diagnostic Observation Schedule, 2nd Edition.

Best practice for the assessment of autism spectrum disorder (ASD) symptom severity relies on clinician ratings of the Autism Diagnostic Observation Schedule, 2nd Edition (ADOS-2), but the association of these ratings with objective measures of children's social gaze and smiling is unknown. Sixty-six preschool-age children (49 boys, M = 39.97 months, SD = 10.58) with suspected ASD (61 confirmed ASD) were administered the ADOS-2 and provided social affect calibrated severity scores (SA CSS). Children's social gaze and smiling during the ADOS-2, captured with a camera contained in eyeglasses worn by the examiner and parent, were obtained via a computer vision processing pipeline. Children who gazed more at their parents (p = .04) and whose gaze at their parents involved more smiling (p = .02) received lower social affect severity scores, indicating fewer social affect symptoms, adjusted R2 = .15, p = .003.

United States Federal Emergency Management Agency regional clustering by disaster exposure: a new paradigm for disaster response.

The Federal Emergency Management Agency (FEMA) divides the United States (US) into ten standard regions to promote local partnerships and priorities. These divisions, while longstanding, do not adequately address known hazard risk as reflected in past federal disaster declarations. From FEMA's inception in 1979 until 2020, the OpenFEMA dataset reports 4127 natural disaster incidents declared by 53 distinct state-level jurisdictions, listed by disaster location, type, and year. An unsupervised spectral clustering (SC) algorithm was applied to group these jurisdictions into regions based on affinity scores assigned to each pair of jurisdictions accounting for both geographic proximity and historical disaster exposures. Reassigning jurisdictions to ten regions using the proposed SC algorithm resulted in an adjusted Rand index (ARI) of 0.43 when compared with the existing FEMA regional structure, indicating little similarity between the current FEMA regions and the clustering results. Reassigning instead into six regions substantially improved cluster quality with a maximized silhouette score of 0.42, compared to a score of 0.34 for ten regions. In clustering US jurisdictions not only by geographic proximity but also by the myriad hazards faced in relation to one another, this study demonstrates a novel method for FEMA regional allocation and design that may ultimately improve FEMA disaster specialization and response.

Objective quantification of homophily in children with and without disabilities in naturalistic contexts.

Homophily, the tendency for individuals to preferentially interact with others similar to themselves is typically documented via self-report and, for children, adult report. Few studies have investigated homophily directly using objective measures of social movement. We quantified homophily in children with developmental disabilities (DD) and typical development (TD) using objective measures of position/orientation in preschool inclusion classrooms, designed to promote interaction between these groups of children. Objective measurements were collected using ultra-wideband radio-frequency tracking to determine social approach and social contact, measures of social movement and interaction. Observations of 77 preschoolers (47 with DD, and 30 TD) were conducted in eight inclusion classrooms on a total of 26 days. We compared DD and TD groups with respect to how children approached and shared time in social contact with peers using mixed-effects models. Children in concordant dyads (DD-DD and TD-TD) both moved toward each other at higher velocities and spent greater time in social contact than discordant dyads (DD-TD), evidencing homophily. DD-DD dyads spent less time in social contact than TD-TD dyads but were comparable to TD-TD dyads in their social approach velocities. Children's preference for similar peers appears to be a pervasive feature of their naturalistic interactions.

Objective measurement of vocalizations in the assessment of autism spectrum disorder symptoms in preschool age children.

Assessment of autism spectrum disorder (ASD) relies on expert clinician observation and judgment, but objective measurement tools have the potential to provide additional information on ASD symptom severity. Diagnostic evaluations for ASD typically include the autism diagnostic observation schedule (ADOS-2), a semi-structured assessment composed of a series of social presses. The current study examined associations between concurrent objective features of child vocalizations during the ADOS-2 and examiner-rated autism symptom severity. The sample included 66 children (49 male; M = 40 months, SD = 10.58) evaluated in a university-based clinic, 61 of whom received an ASD diagnosis. Research reliable administration of the ADOS-2 provided social affect (SA) and restricted and repetitive behavior (RRB) calibrated severity scores (CSS). Audio was recorded from examiner-worn eyeglasses during the ADOS-2 and child and adult speech were differentiated with LENA SP Hub. PRAAT was used to ascertain acoustic features of the audio signal, specifically the mean fundamental vocal frequency (F0) of LENA-identified child speech-like vocalizations (those with phonemic content), child cry vocalizations, and adult speech. Sphinx-4 was employed to estimate child and adult phonological features indexed by the average consonant and vowel count per vocalization. More than a quarter of the variance in ADOS-2 RRB CSS was predicted by the combination of child phoneme count per vocalization and child vocalization F0. Findings indicate that both acoustic and phonological features of child vocalizations are associated with expert clinician ratings of autism symptom severity. LAY SUMMARY: Determination of the severity of autism spectrum disorder is based in part on expert (but subjective) clinician observations during the ADOS-2. Two characteristics of child vocalizations-a smaller number of speech-like sounds per vocalization and higher pitched vocalizations (including cries)-were associated with greater autism symptom severity. The results suggest that objectively ascertained characteristics of children's vocalizations capture variance in children's restricted and repetitive behaviors that are reflected in clinician severity indices.

Simulating COVID19 transmission from observed movement.

Current models of COVID-19 transmission predict infection from reported or assumed interactions. Here we leverage high-resolution observations of interaction to simulate infectious processes. Ultra-Wide Radio Frequency Identification (RFID) systems were employed to track the real-time physical movements and directional orientation of children and their teachers in 4 preschool classes over a total of 34 observations. An agent-based transmission model combined observed interaction patterns (individual distance and orientation) with CDC-published risk guidelines to estimate the transmission impact of an infected patient zero attending class on the proportion of overall infections, the average transmission rate, and the time lag to the appearance of symptomatic individuals. These metrics highlighted the prophylactic role of decreased classroom density and teacher vaccinations. Reduction of classroom density to half capacity was associated with an 18.2% drop in overall infection proportion while teacher vaccination receipt was associated with a 25.3% drop. Simulation results of classroom transmission dynamics may inform public policy in the face of COVID-19 and similar infectious threats.

Objectively measured teacher and preschooler vocalizations: Phonemic diversity is associated with language abilities.

Over half of US children are enrolled in preschools, where the quantity and quality of language input from teachers are likely to affect children's language development. Leveraging repeated objective measurements, we examined the rate per minute and phonemic diversity of child and teacher speech-related vocalizations in preschool classrooms and their association with children's end-of-year receptive and expressive language abilities measured with the Preschool Language Scales (PLS-5). Phonemic diversity was computed as the number of unique consonants and vowels in a speech-related vocalization. We observed three successive cohorts of 2.5-3.5-year-old children enrolled in an oral language classroom that included children with and without hearing loss (N = 29, 16 girls, 14 Hispanic). Vocalization data were collected using child-worn audio recorders over 34 observations spanning three successive school years, yielding 21.53 mean hours of audio recording per child. The rate of teacher vocalizations positively predicted the rate of children's speech-related vocalizations while the phonemic diversity of teacher vocalizations positively predicted the phonemic diversity of children's speech-related vocalizations. The phonemic diversity of children's speech-related vocalizations was a stronger predictor of end-of-year language abilities than the rate of children's speech-related vocalizations. Mediation analyses indicated that the phonemic diversity of teacher vocalizations was associated with children's receptive and expressive language abilities to the extent that it influenced the phonemic diversity of children's own speech-related vocalizations. The results suggest that qualitatively richer language input expands the phonemic diversity of children's speech, which in turn is associated with language abilities.

Deep Learning-Based Retinal Nerve Fiber Layer Thickness Measurement of Murine Eyes.

Purpose: To design a robust and automated estimation method for measuring the retinal nerve fiber layer (RNFL) thickness using spectral domain optical coherence tomography (SD-OCT). Methods: We developed a deep learning-based image segmentation network for automated segmentation of the RNFL in SD-OCT B-scans of mouse eyes. In total, 5500 SD-OCT B-scans (5200 B-scans were used as training data with the remaining 300 B-scans used as testing data) were used to develop this segmentation network. Postprocessing operations were then applied on the segmentation results to fill any discontinuities or remove any speckles in the RNFL. Subsequently, a three-dimensional retina thickness map was generated by z-stacking 100 segmentation processed thickness B-scan images together. Finally, the average absolute difference between algorithm predicted RNFL thickness compared to the ground truth manual human segmentation was calculated. Results: The proposed method achieves an average dice similarity coefficient of 0.929 in the SD-OCT segmentation task and an average absolute difference of 0.0009 mm in thickness estimation task on the basis of the testing dataset. We also evaluated our segmentation algorithm on another biological dataset with SD-OCT volumes for RNFL thickness after the optic nerve crush injury. Results were shown to be comparable between the predicted and manually measured retina thickness values. Conclusions: Experimental results demonstrate that our automated segmentation algorithm reliably predicts the RNFL thickness in SD-OCT volumes of mouse eyes compared to laborious and more subjective manual SD-OCT RNFL segmentation. Translational Relevance: Automated segmentation using a deep learning-based algorithm for murine eye OCT effectively and rapidly produced nerve fiber layer thicknesses comparable to manual segmentation.

Continuous measurement of attachment behavior: A multimodal view of the strange situation procedure.

Infant attachment is a critical indicator of healthy infant social-emotional functioning, which is typically measured using the gold-standard Strange Situation Procedure (SSP). However, expert-based attachment classifications from the SSP are time-intensive (with respect both to expert training and rating), and do not provide an objective, continuous record of infant behavior. To continuously quantify predictors of key attachment behaviors and dimensions, multimodal movement and audio data were collected during the SSP. Forty-nine 1-year-olds and their mothers participated in the SSP and were tracked in three-dimensional space using five synchronized Kinect sensors; LENA recordings were used to quantify crying duration. Theoretically-informed multimodal measures of attachment-related behavior (e.g., dyadic contact duration, infant velocity of approach toward the mother, and infant crying) were used to predict expert rating scales and dimensional summaries of attachment outcomes. Stepwise regressions identified sets of multimodal objective measures that were significant predictors of eight of nine of the expert ratings of infant attachment behaviors in the SSP's two reunions. These multimodal measures predicted approximately half of the variance in the summary approach/avoidance and resistance/disorganization attachment dimensions. Incorporating all objective measures as predictors regardless of significance levels, predicted individual ratings within an average of one point on the original Likert scales. The results indicate that relatively inexpensive Kinect and LENA sensors can be harnessed to quantify attachment behavior in a key assessment protocol, suggesting the promise of objective measurement to understanding infant-parent interaction.