Video analysis-based newborn pain expression identification method

Abstract

The present invention relates to a video analysis-based newborn pain expression identification method. According to the present invention, by introducing a deep learning method based on a three dimensional convolutional neural network and applying to the newborn pain expression identification work, the expressions when the newborns are in the peaceful and crying states and the expressions, such as the mild pain, the severe pain, etc., caused by the painful operations can be identified effectively, and a new path is provided for developing a newborn pain automatic assessment system. Concretely, by introducing the three dimensional convolutional neural network, and using a 3D convolution kernel to extract the time domain and spatial domain features of the video fragments, the tedious operation of extracting the features artificially is avoided, the extracted features are preferable, and the newborn pain expressions are learned and identified automatically on a deep learning platform. Compared with a conventional artificial assessment mode, the video analysis-based newborn pain expression identification method is more objective and accurate, and saves a lot of manpower resources.

Description

technical field [0001] The invention relates to a newborn pain expression recognition method based on video analysis, which belongs to the technical field of video analysis and pattern recognition. Background technique [0002] In the past, the medical community believed that newborns had no pain, so newborn pain has not been taken seriously. However, medical research in recent years has confirmed that repeated painful stimulation will have some short-term and long-term effects on newborns, especially premature and critically ill infants. Pain is a subjective experience, and self-assessment is considered the most reliable method of assessing pain. However, since neonates cannot verbally express pain feelings like adults, it is of great clinical significance to correctly assess and actively deal with neonatal pain. Among the commonly used neonatal pain assessment tools, "facial expression" is considered to be the most reliable indicator of pain monitoring. [0003] At pres...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a newborn pain expression recognition method based on video analysis, which can solve the problem that the existing technology cannot effectively recognize the newborn pain expression, and provide a new method for developing an objective and accurate newborn pain automatic assessment system. way

Images