Resarch topics

A Clinical Diagnosis Support System for General Movements Evaluation to Assess Spontaneous Movements in Infants

Bioelectric signal group

This study proposed a markerless infant movement assessment system for GM evaluation. This system calculates 25 evaluation indices related to the movements of an infant, such as the movement frequency and rhythm of movement, from binary images extracted from the background difference and frame difference of video images. Movement discrimination based on GMs is also performed using a neural network. The distinctive features of this system are that the movements of infants can be measured without using any markers for motion capture and can discriminate movements based on GMs automatically using a neural network. In the experiments conducted during the study, the evaluation and classification of infant movements based on GMs are demonstrated using the proposed system for full-term and low-birth-weight infants. The results reveal that the proposed system can evaluate infant movements similarly to a licensed evaluator and can classify GMs accurately (average classification rates: 76.2 ± 2.83% for four types of GM classification, 92.9 ± 1.98% for normal/abnormal classification).

References

1.A Motion-based Evaluation System for Infant Movements Using Real-time Video Analysis
Yuko Osawa, Keisuke Shima, Nan Bu, Tokuo Tsuji,Toshio Tsuji, Idaku Ishii, Hiroshi Matsuda, Kensuke Orito, Tomoaki Ikeda and Shunichi Noda
ICBME2008 – 13th International Conference on Biomedical Engineering (IFMBE Proceedings, Vol. 23), pp. 2043-2047, Singapore, December 3 – 6, 2008.

2.Change over time of infants’ movements based on motion analysis: Comparison with changes in General Movements and the body sway
Koji Shimatani, Taro Shibanoki, Keisuke Shima, Yuichi Kurita, Akira Otsuka, Maura Casadio, Psiche Giannoni, Paolo Moretti, Pietro Morasso, and Toshio Tsuji
Physiotherapy, Volume 101, Supplement 1, Page e1388, May 2015.
World Confederation for Physical Therapy Congress 2015 Abstracts, Singapore, 1-4 May 2015

3.A Neural Network Based Infant Monitoring System to Facilitate Diagnosis of Epileptic Seizures
Yuya Ogura, Hideaki Hayashi, Shota Nakashima, Zu Soh, Taro Shibanoki, Koji Shimatani, Akihito Takeuchi, Makoto Nakamura, Akihisa Okumura, Yuichi Kurita, and Toshio Tsuji
Proceedings of 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’15), pp. 5614-5617, Milano, Italy, August 25th-29th, 2015.