Dataset Information

Video-based evaluation of infant crawling toward quantitative assessment of motor development.

ABSTRACT: This study proposes a quantitative evaluation support system for infant motor development and uses the system to analyze hands-and-knees creeping and belly crawling. This system measures movements using two video cameras and extracts movement features via background and inter-frame subtractions of original images. Eight evaluation indices for each crawling cycle are calculated, enabling markerless movement analysis of infants. Cross-sectional analysis of 16 10-month-olds confirmed significant differences between hands-and-knees creeping and belly crawling in five of the eight indices, demonstrating the system capability to quantitatively differentiate between creeping and crawling. Longitudinal analysis of one infant (aged 7-10 months) also suggested that the proposed quantitative indices can follow changes in crawling characteristics and evaluate infants' motor development process. The results from the experiments suggest that the proposed system may enable diagnosis support in clinical practice.

SUBMITTER: Kawashima K

PROVIDER: S-EPMC7347929 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Video-based evaluation of infant crawling toward quantitative assessment of motor development.

Kawashima Katsuaki K Funabiki Yasuko Y Ogawa Shino S Hayashi Hideaki H Soh Zu Z Furui Akira A Sato Ayumi A Shiwa Taiko T Mori Hiroki H Shimatani Koji K Mogami Haruta H Konishi Yukuo Y Tsuji Toshio T

Scientific reports 20200709 1

This study proposes a quantitative evaluation support system for infant motor development and uses the system to analyze hands-and-knees creeping and belly crawling. This system measures movements using two video cameras and extracts movement features via background and inter-frame subtractions of original images. Eight evaluation indices for each crawling cycle are calculated, enabling markerless movement analysis of infants. Cross-sectional analysis of 16 10-month-olds confirmed significant di ...[more]

PMID: 32647233

Similar Datasets

Project description:BACKGROUND:Current use of smartphone cameras by parents create opportunities for longitudinal home-video-assessments to monitor infant development. We developed and validated a home-video method for parents, enabling Pediatric Physical Therapists to assess infants' gross motor development with the Alberta Infant Motor Scale (AIMS). The objective of the present study was to investigate the feasibility of this home-video method from the parents' perspective. METHODS:Parents of 59 typically developing infants (0-19?months) were recruited, 45 parents participated in the study. Information about dropout was collected. A sequential mixed methods design was used to examine feasibility, including questionnaires and semi-structured interviews. While the questionnaires inquired after the practical feasibility of the home-video method, the interviews also allowed parents to comment on their feelings and thoughts using the home-video method. RESULTS:Of 45 participating parents, 34 parents returned both questionnaires and eight parents agreed to an interview. Parent reported effort by the infants was very low: the home-video method is perceived as similar to the normal routine of playing. The parental effort level was acceptable. The main constraint parents reported was time planning. Parents noted it was sometimes difficult to find the right moment to record the infant's motor behavior, that is, when parents were both at home and their baby was in the appropriate state. Technical problems with the web portal, reported by 28% of the parents were also experienced as a constraint. Positive factors mentioned by parents were: the belief that the home videos are valuable for family use, receiving feedback from a professional, the moments of one-on-one attention and interaction with their babies. Moreover, the process of recording the home videos resulted in an increased parental awareness of, and insight into, the gross motor development of their infant. CONCLUSION:The AIMS home-video method is feasible for parents of typically developing children. Most constraints are of a practical nature that can be addressed in future applications. Future research is needed to show whether the home-video method is also applicable for parents with an infant at risk of motor development problems.

Project description:AimTo examine the effects of an early home-based 8-week crawling intervention performed by trained therapists on the motor and general development of very premature infants during the first year of life.MethodsAt term-equivalent age, immediately following discharge from the Neonatal Intensive Care Unit (NICU), we randomly allocated 44 premature infants born before 32 weeks' gestation without major brain damage to one of three conditions in our intervention study: crawling on a mini-skateboard, the Crawliskate (Crawli), prone positioning control (Mattress), or standard care (Control). The Crawli and Mattress groups received 5 min daily at-home training administered by trained therapists for 8 consecutive weeks upon discharge from the NICU. The outcomes of greatest interest included gross motor development (Bayley-III) at 2, 6, 9, and 12 months (primary outcome) corrected age (CA), mature crawling at 9 months CA and general development at 9 and 12 months CA [Ages and Stages Questionnaires-3 (ASQ-3)]. The study was registered at www.clinicaltrials.gov; registration number: NCT05278286.ResultsA 3 (Condition) × 4 (Age) repeated measures ANOVA revealed that Crawli group infants had significantly higher Bayley-III gross motor development scores than Mattress and Control group infants. Crawli group infants also scored significantly higher on groups of Bayley-III items related to specific motor skills than infants in the other groups, including crawling at 9 months CA. We found significant differences in favor of the Crawli group in separate one-way ANOVAs at each of the ages we examined. A 3 (Condition) × 2 (Age) repeated measures ANOVA revealed that the Crawli group scored significantly higher than the Control group for the ASQ-3 total score and communication score and significantly higher for the fine motor score than the Control and Mattress groups. We found additional significant differences in favor of the Crawli group for other dimensions of the ASQ-3 in separate one-way ANOVAs at 9 and 12 months CA.InterpretationEarly crawling training on a Crawliskate provides an effective way to promote motor and general development in very premature infants. The findings also provide clear evidence for a link between newborn crawling and more mature crawling later in development.

Project description:PurposeSurgeons' skill in the operating room is a major determinant of patient outcomes. Assessment of surgeons' skill is necessary to improve patient outcomes and quality of care through surgical training and coaching. Methods for video-based assessment of surgical skill can provide objective and efficient tools for surgeons. Our work introduces a new method based on attention mechanisms and provides a comprehensive comparative analysis of state-of-the-art methods for video-based assessment of surgical skill in the operating room.MethodsUsing a dataset of 99 videos of capsulorhexis, a critical step in cataract surgery, we evaluated image feature-based methods and two deep learning methods to assess skill using RGB videos. In the first method, we predict instrument tips as keypoints and predict surgical skill using temporal convolutional neural networks. In the second method, we propose a frame-wise encoder (2D convolutional neural network) followed by a temporal model (recurrent neural network), both of which are augmented by visual attention mechanisms. We computed the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and predictive values through fivefold cross-validation.ResultsTo classify a binary skill label (expert vs. novice), the range of AUC estimates was 0.49 (95% confidence interval; CI = 0.37 to 0.60) to 0.76 (95% CI = 0.66 to 0.85) for image feature-based methods. The sensitivity and specificity were consistently high for none of the methods. For the deep learning methods, the AUC was 0.79 (95% CI = 0.70 to 0.88) using keypoints alone, 0.78 (95% CI = 0.69 to 0.88) and 0.75 (95% CI = 0.65 to 0.85) with and without attention mechanisms, respectively.ConclusionDeep learning methods are necessary for video-based assessment of surgical skill in the operating room. Attention mechanisms improved discrimination ability of the network. Our findings should be evaluated for external validity in other datasets.

Dataset Information

Video-based evaluation of infant crawling toward quantitative assessment of motor development.

Publications

Video-based evaluation of infant crawling toward quantitative assessment of motor development.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets