A markerless pipeline to analyze spontaneous movements of preterm infants
Matteo Moro1, Vito Paolo Pastore2, Chaira Tacchino3
1Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS), University of Genova, via Dodecaneso 35, Genova 16146, Italy; Machine Learning Genoa (MaLGa) Center, via Dodecaneso 35, Genova 16146, Italy.
Insights
Early detection of neurological disorders in preterm infants is crucial. This study presents a computer-aided pipeline using AI to analyze infant movements from videos, achieving 85.7% accuracy in identifying abnormal motion patterns.
Area of Science:
- Medical technology
- Computer vision
- Developmental neuroscience
Background:
- Anomalous spontaneous movements in preterm infants can indicate neurological disorders.
- Early diagnosis is critical for timely rehabilitation interventions.
- Current assessment methods are operator-dependent and may be cumbersome.
Purpose of the Study:
- To develop a computer-aided pipeline for characterizing and classifying infant motion from 2D video recordings.
- To detect anomalous motion patterns indicative of neurological issues.
- To provide an objective and accessible tool for early detection.
Main Methods:
- A pipeline utilizing computer vision and machine learning algorithms was developed.
- Body keypoints were detected using a deep learning-based semantic features detector.
- Quantitative motion parameters were extracted and used to classify movements as normal or abnormal via various classifiers (SVM, Random Forest, NN, LSTM).
Main Results:
- The pipeline was tested on 142 infants (59 with diagnosed neuromotor disorders).
- It successfully discriminated between normal and anomalous motion patterns.
- A maximum accuracy of 85.7% was achieved in classification.
Conclusions:
- The proposed pipeline shows potential as a supportive tool for early detection of abnormal motion patterns in preterm infants.
- This technology can aid in identifying infants who may require further neurological assessment.
- The computer-aided approach offers a more objective and potentially scalable method for motion analysis.
Background And Objective:
The analysis of spontaneous movements of preterm infants is important because anomalous motion patterns can be a sign of neurological disorders caused by lesions in the developing brain. A diagnosis in the first weeks of child's life is crucial to plan timely and appropriate rehabilitative interventions. An accurate visual assessment of infants' spontaneous movements requires highly specialized personnel, not always available, and it is operator dependent. Motion capture systems, markers and wearable sensors are commonly used for human motion analysis, but they can be cumbersome, limiting their use in the study of infants' movements.
Methods:
In this paper we propose a computer-aided pipeline to characterize and classify infants' motion from 2D video recordings. The final goal is detecting anomalous motion patterns. The implemented pipeline is based on computer vision and machine learning algorithms and includes a specific step to increase the interpretability of the results. Specifically, it can be summarized by the following steps: (i) body keypoints detection: we rely on a deep learning-based semantic features detector to localize the positions of meaningful landmark points on infants' bodies; (ii) parameters extraction: starting from the trajectories of the detected landmark points, we extract quantitative parameters describing infants motion patterns; (iii) classification: we implement different classifiers (Support Vector Machines, Random Forest, fully connected Neural Network, Long Short Term Memory) that, starting from the motion parameters, classify between normal or abnormal motion patterns.
Results:
We tested the proposed pipeline on a dataset, recorded at the 40th gestational week, of 142 infants, 59 with evidence of neuromotor disorders according to a medical assessment carried out a posteriori. Our procedure successfully discriminates normal and anomalous motion patterns with a maximum accuracy of 85.7%.
Conclusions:
In conclusion, our pipeline has the potential to be adopted as a tool to support the early detection of abnormal motion patterns in preterm infants.
