scholarly journals Crowd Annotations Can Approximate Clinical Autism Impressions from Short Home Videos with Privacy Protections

2021 ◽  
Author(s):  
Peter Washington ◽  
Emilie Leblanc ◽  
Kaitlyn Dunlap ◽  
Aaron Kline ◽  
Cezmi Mutlu ◽  
...  
Keyword(s):  
Optical Flow ◽  
Reliable Estimate ◽  
Clinical Impression ◽  
Home Videos ◽  
Dense Optical Flow ◽  
Behavioral Pediatrics ◽  
Item Level ◽  
The Mean ◽  
Visual Privacy ◽  
Image Transformations

Artificial Intelligence (A.I.) solutions are increasingly considered for telemedicine. For these methods to adapt to the field of behavioral pediatrics, serving children and their families in home settings, it will be crucial to ensure the privacy of the child and parent subjects in the videos. To address this challenge in A.I. for healthcare, we explore the potential for global image transformations to provide privacy while preserving behavioral annotation quality. Crowd workers have previously been shown to reliably annotate behavioral features in unstructured home videos, allowing machine learning classifiers to detect autism using the annotations as input. We evaluate this method with videos altered via pixelation, dense optical flow, and Gaussian blurring. On a balanced test set of 30 videos of children with autism and 30 neurotypical controls, we find that the visual privacy alterations do not drastically alter any individual behavioral annotation at the item level. The AUROC on the evaluation set was 90.0% +/- 7.5% for the unaltered condition, 85.0% +/- 9.0% for pixelation, 85.0% +/- 9.0% for optical flow, and 83.3% +/- 9.3% for blurring, demonstrating that an aggregation of small changes across multiple behavioral questions can collectively result in increased misdiagnosis rates. We also compare crowd answers against clinicians who provided the same annotations on the same videos and find that clinicians are more sensitive to autism-related symptoms. We also find that there is a linear correlation (r=0.75, p<0.0001) between the mean Clinical Global Impression (CGI) score provided by professional clinicians and the corresponding classifier score emitted by the logistic regression classifier with crowd inputs, indicating that the classifier's output probability is a reliable estimate of clinical impression of autism from home videos. A significant correlation is maintained with privacy alterations, indicating that crowd annotations can approximate clinician-provided autism impression from home videos in a privacy-preserved manner.

MODIFIED METHOD FOR REAL-TIME COMPUTING DENSE OPTICAL FLOW ON FPGA

2019 ◽  
Vol 70 ◽  
pp. 146-157
Author(s):  
A. V. Bratulin ◽  
◽  
M. B. Nikiforov ◽  
A. I. Efimov ◽  
◽  
...  
Keyword(s):  
Optical Flow ◽  
Real Time ◽  
Modified Method ◽  
Dense Optical Flow ◽  
Real Time Computing

scholarly journals Groups and Individuals: Optical Flow Patterns of Broiler Chicken Flocks Are Correlated with the Behavior of Individual Birds

Animals ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 568
Author(s):  
Sabine G. Gebhardt-Henrich ◽  
Ariane Stratmann ◽  
Marian Stamp Dawkins
Keyword(s):  
Optical Flow ◽  
Broiler Chicken ◽  
Average Length ◽  
Flow Patterns ◽  
Group Level ◽  
Positive Correlation ◽  
Water Test ◽  
Mean And Variance ◽  
The Mean

Group level measures of welfare flocks have been criticized on the grounds that they give only average measures and overlook the welfare of individual animals. However, we here show that the group-level optical flow patterns made by broiler flocks can be used to deliver information not just about the flock averages but also about the proportion of individuals in different movement categories. Mean optical flow provides information about the average movement of the whole flock while the variance, skew and kurtosis quantify the variation between individuals. We correlated flock optical flow patterns with the behavior and welfare of a sample of 16 birds per flock in two runway tests and a water (latency-to-lie) test. In the runway tests, there was a positive correlation between the average time taken to complete the runway and the skew and kurtosis of optical flow on day 28 of flock life (on average slow individuals came from flocks with a high skew and kurtosis). In the water test, there was a positive correlation between the average length of time the birds remained standing and the mean and variance of flock optical flow (on average, the most mobile individuals came from flocks with the highest mean). Patterns at the flock level thus contain valuable information about the activity of different proportions of the individuals within a flock.

HEAD CIRCUMFERENCE, MENTAL RETARDATION, AND GROWTH FAILURE

PEDIATRICS ◽  
1965 ◽  
Vol 36 (1) ◽  
pp. 62-66
Author(s):  
Edward J. O'Connell ◽  
Robert H. Feldt ◽  
Gunnar B. Stickler
Keyword(s):  
Mental Retardation ◽  
Head Circumference ◽  
Growth Failure ◽  
Clinical Impression ◽  
Severe Mental Retardation ◽  
Small Head ◽  
The Mean ◽  
Standard Deviations ◽  
Mental Subnormality ◽  
Age And Sex

The purpose of this study was to re-affirm our clinical impression that non-institutionalized children whose head circumference was below minus 2 standard deviations were mentally subnormal and frequently had growth failure. A group of 134 children with a head circumference below minus 2 standard deviations from the mean were studied, and all but one were mentally subnormal. The most severe mental retardation was noted in the group of children with a head circumference of minus 4 standard deviations or below. We found, as have others, that children with mental retardation have height and weights below the expected norm and that children with a head circumference below minus 2 standard deviations have even lower mean heights and weights. The head circumference of 31 children with growth failure and normal intelligence was normal for age and sex, therefore disproving the concept that the abnormally small child has a proportionally small head. In the child with growth failure, should the head be proportionally small (below minus 2 standard deviations), mental subnormality should be suspected. We feel that the head circumference measurement has taken on new clinical significance in that our data support its use in suspecting the association of mental subnormality in children with growth failure and a head circumference of below minus 2 standard deviations from the mean for age and sex.

Abstract P403: Seasonal Variation in the Daily Urinary Sodium Excretion in Outpatients From the Northern Japan

Hypertension ◽  
2017 ◽  
Vol 70 (suppl_1) ◽  
Author(s):  
Tomoko Hashimoto
Keyword(s):  
Seasonal Variation ◽  
Sodium Excretion ◽  
Salt Intake ◽  
Sodium Intake ◽  
Urinary Sodium Excretion ◽  
Urinary Sodium ◽  
Reliable Estimate ◽  
Significant Difference ◽  
The Mean ◽  
Northern Japan

Although the daily urinary sodium excretion (UNaV) is considered to provide the most reliable estimate of the daily sodium intake, it may be affected by salt loss due to sweating in summer. However, theseasonal variation in the daily UNaV associated with a normal lifestyle is unknown. This study was performed in 348 outpatients from the Morioka region during three seasons: summer(summer 1), winter, and the following summer (summer 2). The daily UNaV (g salt/day) was estimated by the second morning urine method three times during each season. Seasonal variation was defined as a significant trend across the three seasons together with a significant difference between winter and both summers. In women, the daily UNaV was higher in winter (11.8±3.0 g salt/day) than in summer 1 (11.2±2.9g salt/day) or summer 2 (11.0±2.9 g salt/day). In contrast, there was no marked seasonal variation in men. An analysis stratified by age (4 quartiles) identified seasonal variation in the older 2 quartiles of women (aged ≧68 years). In these women, the mean seasonal difference in the daily UNaV was 0.9 g of salt/day for both winter vs. summer 1 and winter vs. summer 2, while it was 0.1-0.8 g of salt/day in the other groups. Seasonal variation in the daily UNaV only occurred in older female patients and was relatively small. This is evidence for restricting salt intake throughout the year and should reassure patients who are anxious about salt loss due to sweating in summer.

Image Stabilization Based on Panoramic Dense Optical Flow Matching for Camera on Flapping Wing

2021 ◽  
Author(s):  
Tian Shen ◽  
Cui Long ◽  
Liu Zhaoming ◽  
Wang Hongwei ◽  
Zhang Feng ◽  
...  
Keyword(s):  
Optical Flow ◽  
Flapping Wing ◽  
Image Stabilization ◽  
Dense Optical Flow

Challenges of medical residency. Are they perceived and addressed differently by international medical graduates, Canadian medical graduates, and preceptors?

2020 ◽  
Author(s):  
Neda Abedi ◽  
Michelle McCarren ◽  
Farzaneh Sheidaei ◽  
Andriyka L. Papish
Keyword(s):  
English Language ◽  
Multivariate Analyses ◽  
International Medical ◽  
International Medical Graduates ◽  
Residency Programs ◽  
Program Coordinators ◽  
Medical Graduates ◽  
Item Level ◽  
Scale Scores ◽  
The Mean

Abstract Background: Residency is an important and challenging part of medical education. Some of these challenges are common to all residents and some are specific to a particular group of residents. A number of studies have addressed the challenges of residency. To our knowledge, the experience of challenges from the perspective of international medical graduates (IMGs), Canadian medical graduates (CMGs), and their preceptors has not been studied in a single residency cohort. This study represents a valuable step in addressing the differential needs of international and Canadian medical graduates and in identifying the way different groups of residents can support each other to function better during residency.Methods: We surveyed residents and preceptors to determine what they perceive to be the greatest challenges for each group during residency. The survey was sent to the program coordinators of all English language psychiatry residency programs in Canada to be distributed to all residents and preceptors. Three reminders were sent, and a prize draw was offered to participants. Mean scale scores were calculated. One-way analyses of variance (ANOVAs) were calculated to compare resident self-ratings between groups, preceptors' ratings of each resident group's challenges, and all four groups' perceptions of the challenges experienced by different groups. To determine the particular types of challenges that residents experience, multivariate analyses of variance (MANOVAs) were also used for item-level comparisons.Results: 177 residents and 82 preceptors completed the survey. We found no significant differences in the mean scale scores for how each group rated their own challenges though the most challenging area was different for each group of residents. Preceptors viewed FIMGs as experiencing the greatest challenges (M = 3.27, SD = 0.066, 95% CI [3.11, 3.41]) and CMGs, the least (M = 2.02, SD = 0.59, 95% CI [1.89, 2.16]; F (2, 227) = 88.030, p < 0.001).Conclusion: Although the degree of challenge perceived by all groups of residents was relatively similar in general, different groups of residents identified different areas of challenges from their own perspective, and these areas differed from those identified by their resident colleagues and preceptors as being challenging for each group. This study highlights the necessity for reviewing the needs, strengths, and challenges of each group of residents and the importance of better communication between preceptors and residents regarding the different areas of challenges.

scholarly journals A Hardware-Friendly Optical Flow-Based Time-to-Collision Estimation Algorithm

Sensors ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 807
Author(s):  
Cong Shi ◽  
Zhuoran Dong ◽  
Shrinivas Pundlik ◽  
Gang Luo
Keyword(s):  
Embedded System ◽  
Optical Flow ◽  
Random Forests ◽  
Visual Motion ◽  
Hardware Acceleration ◽  
Ground Truth ◽  
Estimation Algorithm ◽  
Estimation Accuracy ◽  
Time To Collision ◽  
Dense Optical Flow

This work proposes a hardware-friendly, dense optical flow-based Time-to-Collision (TTC) estimation algorithm intended to be deployed on smart video sensors for collision avoidance. The algorithm optimized for hardware first extracts biological visual motion features (motion energies), and then utilizes a Random Forests regressor to predict robust and dense optical flow. Finally, TTC is reliably estimated from the divergence of the optical flow field. This algorithm involves only feed-forward data flows with simple pixel-level operations, and hence has inherent parallelism for hardware acceleration. The algorithm offers good scalability, allowing for flexible tradeoffs among estimation accuracy, processing speed and hardware resource. Experimental evaluation shows that the accuracy of the optical flow estimation is improved due to the use of Random Forests compared to existing voting-based approaches. Furthermore, results show that estimated TTC values by the algorithm closely follow the ground truth. The specifics of the hardware design to implement the algorithm on a real-time embedded system are laid out.

Sign in / Sign up

Export Citation Format

Share Document