Automated movement recognition to predict motor impairment in high-risk infants: a systematic review of diagnostic test accuracy and meta-analysis

Intelligence Sparse Sensor Network for Automatic Early Evaluation of General Movements in Infants

General movements (GMs) have been widely used for the early clinical evaluation of infant brain development, allowing immediate evaluation of potential development disorders and timely rehabilitation. The infants' general movements can be captured digitally, but the lack of quantitative assessment and well-trained clinical pediatricians presents an obstacle for many years to achieve wider deployment, especially in low-resource settings. There is a high potential to explore wearable sensors for movement analysis due to outstanding privacy, low cost, and easy-to-use features. This work presents a sparse sensor network with soft wireless IMU devices (SWDs) for automatic early evaluation of general movements in infants. The sparse network consisting of only five sensor nodes (SWDs) with robust mechanical properties and excellent biocompatibility continuously and stably captures full-body motion data. The proof-of-the-concept clinical testing with 23 infants showcases outstanding performance in recognizing neonatal activities, confirming the reliability of the system. Taken together with a tiny machine learning algorithm, the system can automatically identify risky infants based on the GMs, with an accuracy of up to 100% (99.9%). The wearable sparse sensor network with an artificial intelligence-based algorithm facilitates intelligent evaluation of infant brain development and early diagnosis of development disorders.

Predictive value of the General Movements Assessment and Standardized Infant NeuroDevelopmental Assessment in infants at high risk of neurodevelopmental disorders

AIM

To compare the predictive values of the General Movements Assessment (GMA) and the Standardized Infant NeuroDevelopmental Assessment (SINDA) neurological scale for atypical neurodevelopmental outcome in 3-month-old at-risk infants.

METHOD

A total of 109 infants (gestational age 30 weeks; range: 24-41; 52 males) attending a non-academic outpatient clinic were assessed with the GMA and the SINDA at 3 (2-4) months corrected age. The GMA pays attention to the complexity of general movements and presence of fidgety movements. Atypical neurodevelopmental outcome at 24 months corrected age (and older) implied cerebral palsy (CP) or a Bayley Mental Development Index or Bayley Psychomotor Development Index lower than 70.

RESULTS

At 24 months corrected (and older) age, 16 children had an atypical outcome, including 14 children with CP. Regarding markedly reduced general movement complexity in combination with absent or sporadic fidgety movements, the GMA predicted an atypical outcome with specificity, positive, and negative predictive values greater than 0.900, and sensitivity of 0.687 (95% confidence interval [CI] = 0.460-0.915). SINDA predicted an atypical outcome with sensitivity, specificity, and negative predictive value greater than 0.900 and a positive predictive value of 0.652 (95% CI = 0.457-0.847). Regarding absent fidgety movements only or markedly reduced general movement complexity, the GMA predicted the outcome less well than both general movement criteria.

INTERPRETATION

The SINDA and GMA both predict neurodevelopmental outcome well, but SINDA is easier to learn than the GMA; being a non-video-based assessment, it allows caregiver feedback during the consultation whereas the GMA usually does not.

Machine learning approaches to evaluate infants' general movements in the writhing stage-a pilot study

The goals of this study are to describe machine learning techniques employing computer-vision movement algorithms to automatically evaluate infants' general movements (GMs) in the writhing stage. This is a retrospective study of infants admitted 07/2019 to 11/2021 to a level IV neonatal intensive care unit (NICU). Infant GMs, classified by certified expert, were analyzed in two-steps (1) determination of anatomic key point location using a NICU-trained pose estimation model [accuracy determined using object key point similarity (OKS)]; (2) development of a preliminary movement model to distinguish normal versus cramped-synchronized (CS) GMs using cosine similarity and autocorrelation of major joints. GMs were analyzed using 85 videos from 74 infants; gestational age at birth 28.9 ± 4.1 weeks and postmenstrual age (PMA) at time of video 35.9 ± 4.6 weeks The NICU-trained pose estimation model was more accurate (0.91 ± 0.008 OKS) than a generic model (0.83 ± 0.032 OKS, p < 0.001). Autocorrelation values in the lower limbs were significantly different between normal (5 videos) and CS GMs (5 videos, p < 0.05). These data indicate that automated pose estimation of anatomical key points is feasible in NICU patients and that a NICU-trained model can distinguish between normal and CS GMs. These preliminary data indicate that machine learning techniques may represent a promising tool for earlier CP risk assessment in the writhing stage and prior to hospital discharge.

Automated Prediction of Infant Cognitive Development Risk by Video: A Pilot Study

OBJECTIVE

Cognition is an essential human function, and its development in infancy is crucial. Traditionally, pediatricians used clinical observation or medical imaging to assess infants' current cognitive development (CD) status. The object of pediatricians' greater concern is however their future outcomes, because high-risk infants can be identified early in life for intervention. However, this opportunity has not yet been realized. Fortunately, some recent studies have shown that the general movement (GM) performance of infants around 3-4 months after birth might reflect their future CD status, which gives us an opportunity to achieve this goal by cameras and artificial intelligence.

METHODS

First, infants' GM videos were recorded by cameras, from which a series of features reflecting their bilateral movement symmetry (BMS) were extracted. Then, after at least eight months of natural growth, the infants' CD status was evaluated by the Bayley Infant Development Scale, and they were divided into high-risk and low-risk groups. Finally, the BMS features extracted from the early recorded GM videos were fed into the classifiers, using late infant CD risk assessment as the prediction target.

RESULTS

The area under the curve, recall and precision values reached 0.830, 0.832, and 0.823 for two-group classification, respectively.

CONCLUSION

This pilot study demonstrates that it is possible to automatically predict the CD of infants around the age of one year based on their GMs recorded early in life.

SIGNIFICANCE

This study not only helps clinicians better understand infant CD mechanisms, but also provides an economical, portable and non-invasive way to screen infants at high-risk early to facilitate their recovery.

Using the center of pressure movement analysis in evaluating spontaneous movements in infants: a comparative study with general movements assessment

BACKGROUND

Researchers have attempted to automate the spontaneous movement assessment and have sought quantitative and objective methods over the past decade. The purpose of the study was to present a quantitative assessment method of spontaneous movement using center-of-pressure (COP) movement analysis.

METHODS

A total of 101 infants were included in the study. The infants were placed in the supine position on the force plate with the cranial-caudal orientation. In this position, the recording of video and COP movement data were made simultaneously for 3 min. Video recordings were used to observe global and detailed general movement assessment (GMA), and COP time series data were used to obtain quantitative movement parameters.

RESULTS

According to the global GMA, 13 infants displayed absent fidgety movements (FMs) and 88 infants displayed normal FMs. The binary logistic regression model indicated significant association between global GMA and COP movement parameters (chi-square = 20.817, p < 0.001). The sensitivity, specificity, and overall accuracy of this model were 85% (95% CI: 55-98), 83% (95% CI: 73-90), and 83% (95% CI: 74-90), respectively. The multiple linear regression model showed a significant association between detailed GMA (motor optimality score-revised/MOS-R) and COP movement parameters (F = 10.349, p < 0.001). The MOS-R total score was predicted with a standard error of approximately 1.8 points (6%).

CONCLUSIONS

The present study demonstrated the possible avenues for using COP movement analysis to objectively detect the absent FMs and MOS-R total score in clinical settings. Although the method presented in this study requires further validation, it may complement observational GMA and be clinically useful for infant screening purposes, particularly in clinical settings where access to expertise in observational GMA is not available.

Automating General Movements Assessment with quantitative deep learning to facilitate early screening of cerebral palsy

The Prechtl General Movements Assessment (GMA) is increasingly recognized for its role in evaluating the integrity of the developing nervous system and predicting motor dysfunctions, particularly in conditions such as cerebral palsy (CP). However, the necessity for highly trained professionals has hindered the adoption of GMA as an early screening tool in some countries. In this study, we propose a deep learning-based motor assessment model (MAM) that combines infant videos and basic characteristics, with the aim of automating GMA at the fidgety movements (FMs) stage. MAM demonstrates strong performance, achieving an Area Under the Curve (AUC) of 0.967 during external validation. Importantly, it adheres closely to the principles of GMA and exhibits robust interpretability, as it can accurately identify FMs within videos, showing substantial agreement with expert assessments. Leveraging the predicted FMs frequency, a quantitative GMA method is introduced, which achieves an AUC of 0.956 and enhances the diagnostic accuracy of GMA beginners by 11.0%. The development of MAM holds the potential to significantly streamline early CP screening and revolutionize the field of video-based quantitative medical diagnostics.

Infant movement classification through pressure distribution analysis

BACKGROUND

Aiming at objective early detection of neuromotor disorders such as cerebral palsy, we propose an innovative non-intrusive approach using a pressure sensing device to classify infant general movements. Here we differentiate typical general movement patterns of the "fidgety period" (fidgety movements) vs. the "pre-fidgety period" (writhing movements).

METHODS

Participants (N = 45) were sampled from a typically-developing infant cohort. Multi-modal sensor data, including pressure data from a pressure sensing mat with 1024 sensors, were prospectively recorded for each infant in seven succeeding laboratory sessions in biweekly intervals from 4 to 16 weeks of post-term age. 1776 pressure data snippets, each 5 s long, from the two targeted age periods were taken for movement classification. Each snippet was pre-annotated based on corresponding synchronised video data by human assessors as either fidgety present or absent. Multiple neural network architectures were tested to distinguish the fidgety present vs. fidgety absent classes, including support vector machines, feed-forward networks, convolutional neural networks, and long short-term memory networks.

RESULTS

Here we show that the convolution neural network achieved the highest average classification accuracy (81.4%). By comparing the pros and cons of other methods aiming at automated general movement assessment to the pressure sensing approach, we infer that the proposed approach has a high potential for clinical applications.

CONCLUSIONS

We conclude that the pressure sensing approach has great potential for efficient large-scale motion data acquisition and sharing. This will in return enable improvement of the approach that may prove scalable for daily clinical application for evaluating infant neuromotor functions.

Mobile Device-Based Video Screening for Infant Head Lag: An Exploratory Study

INTRODUCTION

Video-based automatic motion analysis has been employed to identify infant motor development delays. To overcome the limitations of lab-recorded images and training datasets, this study aimed to develop an artificial intelligence (AI) model using videos taken by mobile phone to assess infants' motor skills.

METHODS

A total of 270 videos of 41 high-risk infants were taken by parents using a mobile device. Based on the Pull to Sit (PTS) levels from the Hammersmith Motor Evaluation, we set motor skills assessments. The videos included 84 level 0, 106 level 1, and 80 level 3 recordings. We used whole-body pose estimation and three-dimensional transformation with a fuzzy-based approach to develop an AI model. The model was trained with two types of vectors: whole-body skeleton and key points with domain knowledge.

RESULTS

The average accuracies of the whole-body skeleton and key point models for level 0 were 77.667% and 88.062%, respectively. The Area Under the ROC curve (AUC) of the whole-body skeleton and key point models for level 3 were 96.049% and 94.333% respectively.

CONCLUSIONS

An AI model with minimal environmental restrictions can provide a family-centered developmental delay screen and enable the remote monitoring of infants requiring intervention.

Continuous sensing and quantification of body motion in infants: A systematic review

Abnormal body motion in infants may be associated with neurodevelopmental delay or critical illness. In contrast to continuous patient monitoring of the basic vitals, the body motion of infants is only determined by discrete periodic clinical observations of caregivers, leaving the infants unattended for observation for a longer time. One step to fill this gap is to introduce and compare different sensing technologies that are suitable for continuous infant body motion quantification. Therefore, we conducted this systematic review for infant body motion quantification based on the PRISMA method (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). In this systematic review, we introduce and compare several sensing technologies with motion quantification in different clinical applications. We discuss the pros and cons of each sensing technology for motion quantification. Additionally, we highlight the clinical value and prospects of infant motion monitoring. Finally, we provide suggestions with specific needs in clinical practice, which can be referred by clinical users for their implementation. Our findings suggest that motion quantification can improve the performance of vital sign monitoring, and can provide clinical value to the diagnosis of complications in infants.

NeoCam: An Edge-Cloud Platform for Non-Invasive Real-Time Monitoring in Neonatal Intensive Care Units

In this work we introduce NeoCam, an open source hardware-software platform for video-based monitoring of preterms infants in Neonatal Intensive Care Units (NICUs). NeoCam includes an edge computing device that performs video acquisition and processing in real-time. Compared to other proposed solutions, it has the advantage of handling data more efficiently by performing most of the processing on the device, including proper anonymisation for better compliance with privacy regulations. In addition, it allows to perform various video analysis tasks of clinical interest in parallel at speeds of between 20 and 30 frames-per-second. We introduce algorithms to measure without contact the breathing rate, motor activity, body pose and emotional status of the infants. For breathing rate, our system shows good agreement with existing methods provided there is sufficient light and proper imaging conditions. Models for motor activity and stress detection are new to the best of our knowledge. NeoCam has been tested on preterms in the NICU of the University Hospital Puerta del Mar (Cádiz, Spain), and we report the lessons learned from this trial.

Mobile Solutions for Clinical Surveillance and Evaluation in Infancy-General Movement Apps

The Prechtl General Movements Assessment (GMA) has become a clinician and researcher toolbox for evaluating neurodevelopment in early infancy. Given that it involves the observation of infant movements from video recordings, utilising smartphone applications to obtain these recordings seems like the natural progression for the field. In this review, we look back on the development of apps for acquiring general movement videos, describe the application and research studies of available apps, and discuss future directions of mobile solutions and their usability in research and clinical practice. We emphasise the importance of understanding the background that has led to these developments while introducing new technologies, including the barriers and facilitators along the pathway. The GMApp and Baby Moves apps were the first ones developed to increase accessibility of the GMA, with two further apps, NeuroMotion and InMotion, designed since. The Baby Moves app has been applied most frequently. For the mobile future of GMA, we advocate collaboration to boost the field's progression and to reduce research waste. We propose future collaborative solutions, including standardisation of cross-site data collection, adaptation to local context and privacy laws, employment of user feedback, and sustainable IT structures enabling continuous software updating.

Automated postural asymmetry assessment in infants neurodevelopmental evaluation using novel video-based features

BACKGROUND AND OBJECTIVE

Neurodevelopmental assessment enables the identification of infant developmental disorders in the first months of life. Thus, the appropriate therapy can be initiated promptly, increasing the chances for correct motor function. Posture asymmetry is one of the crucial aspects evaluated during the diagnosis. Available diagnostic methods are mainly based on qualitative assessment and subjective expert opinion. Current trends in computer-aided diagnosis focus mostly on analyzing infants' spontaneous movement videos using artificial intelligence methods, based primarily on limbs movement. This study aims to develop an automatic method for determining the infant's positional asymmetry in a video recording using computer image processing methods.

METHODS

We made the first attempt to determine positional preferences in a recording automatically. We proposed six quantitative features describing trunk and head position based on pose estimation. As a result of our algorithm, we estimate the percentage of each trunk position in a recording using known machine learning methods. The training and test sets were created from 51 recordings collected during our research and 12 recordings from the benchmark dataset evaluated by five of our experts. The method was assessed using the leave-one-subject-out cross-validation method for ground truth video fragments and different classifiers. Log loss for multiclass classification and ROC AUC were determined to evaluate the results for both our and benchmark datasets.

RESULTS

In a classification of the shortened side, the QDA classifier yields the most accurate results, gaining the lowest log loss of 0.552 and AUC of 0.913. The high accuracy (92.03) and sensitivity (93.26) confirm the method's potential in screening for asymmetry.

CONCLUSIONS

The method allows obtaining quantitative information about positional preference, a valuable extension of basic diagnostics without additional tools and procedures. In combination with an analysis of limbs movement, it may constitute one of the elements of a novelty computer-aided infants' diagnosis system in the future.

TwinEDA: a sustainable deep-learning approach for limb-position estimation in preterm infants' depth images

Early diagnosis of neurodevelopmental impairments in preterm infants is currently based on the visual analysis of newborns' motion patterns by trained operators. To help automatize this time-consuming and qualitative procedure, we propose a sustainable deep-learning algorithm for accurate limb-pose estimation from depth images. The algorithm consists of a convolutional neural network (TwinEDA) relying on architectural blocks that require limited computation while ensuring high performance in prediction. To ascertain its low computational costs and assess its application in on-the-edge computing, TwinEDA was additionally deployed on a cost-effective single-board computer. The network was validated on a dataset of 27,000 depth video frames collected during the actual clinical practice from 27 preterm infants. When compared to the main state-of-the-art competitor, TwinEDA is twice as fast to predict a single depth frame and four times as light in terms of memory, while performing similarly in terms of Dice similarity coefficient (0.88). This result suggests that the pursuit of efficiency does not imply the detriment of performance. This work is among the first to propose an automatic and sustainable limb-position estimation approach for preterm infants. This represents a significant step towards the development of broadly accessible clinical monitoring applications.

An Algorithm for the Detection of General Movements of Preterm Infants Based on the Instantaneous Heart Rate

Video recording and editing of general movements (GMs) takes time. We devised an algorithm to automatically extract the period of GMs emergence to assist in the assessment of GMs. The algorithm consisted of δHR: subtracting the moving average heart rate (HR) for the past 60 s from the average instantaneous HR; and %δHR: the percentage of the instantaneous HR to the moving average HR. Ten-second sections in which δHR was positive for three consecutive sections and contained at least one section with %δHR > 105% were extracted. Extracted periods are called automated extraction sections (AESs). We evaluated the concordance rate between AESs and GMs in three periods (gestational age 24−32, 33−34, and 35−36 weeks). The records of 84 very low birth weight infants were evaluated. Approximately 90% of AESs were accompanied by GMs at any period in both the supine and prone positions. The proportion of full-course (beginning to end) GMs among GMs in the AES was 80−85% in the supine position and 90% in the prone position in all periods. We could extract a sufficient number of assessable GMs with this algorithm, which is expected to be widely used for assisting in the assessment of GMs.

Intelligent wearable allows out-of-the-lab tracking of developing motor abilities in infants

Background

Early neurodevelopmental care needs better, effective and objective solutions for assessing infants’ motor abilities. Novel wearable technology opens possibilities for characterizing spontaneous movement behavior. This work seeks to construct and validate a generalizable, scalable, and effective method to measure infants’ spontaneous motor abilities across all motor milestones from lying supine to fluent walking.

Methods

A multi-sensor infant wearable was constructed, and 59 infants (age 5–19 months) were recorded during their spontaneous play. A novel gross motor description scheme was used for human visual classification of postures and movements at a second-level time resolution. A deep learning -based classifier was then trained to mimic human annotations, and aggregated recording-level outputs were used to provide posture- and movement-specific developmental trajectories, which enabled more holistic assessments of motor maturity.

Results

Recordings were technically successful in all infants, and the algorithmic analysis showed human-equivalent-level accuracy in quantifying the observed postures and movements. The aggregated recordings were used to train an algorithm for predicting a novel neurodevelopmental measure, Baba Infant Motor Score (BIMS). This index estimates maturity of infants’ motor abilities, and it correlates very strongly (Pearson’s r = 0.89, p < 1e-20) to the chronological age of the infant.

Conclusions

The results show that out-of-hospital assessment of infants’ motor ability is possible using a multi-sensor wearable. The algorithmic analysis provides metrics of motility that are transparent, objective, intuitively interpretable, and they link strongly to infants’ age. Such a solution could be automated and scaled to a global extent, holding promise for functional benchmarking in individualized patient care or early intervention trials.

Assessment of an infant’s motor abilities is a key part of regular health checks of infant development. However, there is shortage of methods that would allow objective and user-friendly tracking of infant motor abilities. We describe a system that measures infant’s posture and movement with sensors that are attached to the clothing. Movement signals are analyzed with a deep learning algorithm to predict maturity of motor abilities. The accuracy of analysis is comparable to human assessments. This system could enable early diagnosis of developmental delays, and it can be used to assess motor development in clinical trials.

Airaksinen et al. describe an infant wearable system that accurately quantifies key aspects of infant motor ability and uses deep learning algorithms to analyze movement signals. Motor ability age and maturation can be predicted, with the predictions correlating with other clinical and parental assessments.

Generating depth images of preterm infants in given poses using GANs

BACKGROUND AND OBJECTIVES

The use of deep learning for preterm infant's movement monitoring has the potential to support clinicians in early recognizing motor and behavioural disorders. The development of deep learning algorithms is, however, hampered by the lack of publicly available annotated datasets.

METHODS

To mitigate the issue, this paper presents a Generative Adversarial Network-based framework to generate images of preterm infants in a given pose. The framework consists of a bibranch encoder and a conditional Generative Adversarial Network, to generate a rough image and a refined version of it, respectively.

RESULTS

Evaluation was performed on the Moving INfants In RGB-D dataset which has 12.000 depth frames from 12 preterm infants. A low Fréchet inception distance (142.9) and an inception score (2.8) close to that of real-image distribution (2.6) are obtained. The results achieved show the potentiality of the framework in generating realistic depth images of preterm infants in a given pose.

CONCLUSIONS

Pursuing research on the generation of new data may enable researchers to propose increasingly advanced and effective deep learning-based monitoring systems.

Automated Movement Analysis to Predict Cerebral Palsy in Very Preterm Infants: An Ambispective Cohort Study

The General Movements Assessment requires extensive training. As an alternative, a novel automated movement analysis was developed and validated in preterm infants. Infants < 31 weeks’ gestational age or birthweight ≤ 1500 g evaluated at 3−5 months using the general movements assessment were included in this ambispective cohort study. The C-statistic, sensitivity, specificity, positive predictive value, and negative predictive value were calculated for a predictive model. A total of 252 participants were included. The median gestational age and birthweight were 274/7 weeks (range 256/7−292/7 weeks) and 960 g (range 769−1215 g), respectively. There were 29 cases of cerebral palsy (11.5%) at 18−24 months, the majority of which (n = 22) were from the retrospective cohort. Mean velocity in the vertical direction, median, standard deviation, and minimum quantity of motion constituted the multivariable model used to predict cerebral palsy. Sensitivity, specificity, positive, and negative predictive values were 55%, 80%, 26%, and 93%, respectively. C-statistic indicated good fit (C = 0.74). A cluster of four variables describing quantity of motion and variability of motion was able to predict cerebral palsy with high specificity and negative predictive value. This technology may be useful for screening purposes in very preterm infants; although, the technology likely requires further validation in preterm and high-risk term populations.

Video-Based Automatic Baby Motion Analysis for Early Neurological Disorder Diagnosis: State of the Art and Future Directions

Neurodevelopmental disorders (NDD) are impairments of the growth and development of the brain and/or central nervous system. In the light of clinical findings on early diagnosis of NDD and prompted by recent advances in hardware and software technologies, several researchers tried to introduce automatic systems to analyse the baby's movement, even in cribs. Traditional technologies for automatic baby motion analysis leverage contact sensors. Alternatively, remotely acquired video data (e.g., RGB or depth) can be used, with or without active/passive markers positioned on the body. Markerless approaches are easier to set up and maintain (without any human intervention) and they work well on non-collaborative users, making them the most suitable technologies for clinical applications involving children. On the other hand, they require complex computational strategies for extracting knowledge from data, and then, they strongly depend on advances in computer vision and machine learning, which are among the most expanding areas of research. As a consequence, also markerless video-based analysis of movements in children for NDD has been rapidly expanding but, to the best of our knowledge, there is not yet a survey paper providing a broad overview of how recent scientific developments impacted it. This paper tries to fill this gap and it lists specifically designed data acquisition tools and publicly available datasets as well. Besides, it gives a glimpse of the most promising techniques in computer vision, machine learning and pattern recognition which could be profitably exploited for children motion analysis in videos.

The developing brain: Challenges and opportunities to promote school readiness in young children at risk of neurodevelopmental disorders in low- and middle-income countries

This paper discusses possibilities for early detection and early intervention in infants with or at increased risk of neurodevelopmental disorders in low- and middle-income countries (LMICs). The brain's high rate of developmental activity in the early years post-term challenges early detection. It also offers opportunities for early intervention and facilitation of school readiness. The paper proposes that in the first year post-term two early detection options are feasible for LMICs: (a) caregiver screening questionnaires that carry little costs but predict neurodevelopmental disorders only moderately well; (b) the Hammersmith Infant Neurological Examination and Standardized Infant NeuroDevelopmental Assessment (SINDA) which are easy tools that predict neurodisability well but require assessment by health professionals. The young brain's neuroplasticity offers great opportunities for early intervention. Ample evidence indicates that families play a critical role in early intervention of infants at increased risk of neurodevelopmental disorders. Other interventional key elements are responsive parenting and stimulation of infant development. The intervention's composition and delivery mode depend on the infant's risk profile. For instance, in infants with moderately increased risk (e.g., preterm infants) lay community health workers may provide major parts of intervention, whereas in children with neurodisability (e.g., cerebral palsy) health professionals play a larger role.

A Pose-based Feature Fusion and Classification Framework for the Early Prediction of Cerebral Palsy in Infants

The early diagnosis of cerebral palsy is an area which has recently seen significant multi-disciplinary research. Diagnostic tools such as the General Movements Assessment (GMA), have produced some very promising results. However, the prospect of automating these processes may improve accessibility of the assessment and also enhance the understanding of movement development of infants. Previous works have established the viability of using pose-based features extracted from RGB video sequences to undertake classification of infant body movements based upon the GMA. In this paper, we propose a series of new and improved features, and a feature fusion pipeline for this classification task. We also introduce the RVI-38 dataset, a series of videos captured as part of routine clinical care. By utilising this challenging dataset we establish the robustness of several motion features for classification, subsequently informing the design of our proposed feature fusion framework based upon the GMA. We evaluate our proposed framework's classification performance using both the RVI-38 dataset and the publicly available MINI-RGBD dataset. We also implement several other methods from the literature for direct comparison using these two independent datasets. Our experimental results and feature analysis show that our proposed pose-based method performs well across both datasets. The proposed features afford us the opportunity to include finer detail than previous methods, and further model GMA specific body movements. These new features also allow us to take advantage of additional body-part specific information as a means of improving the overall classification performance, whilst retaining GMA relevant, interpretable, and shareable features.

Improving Preterm Infants' Joint Detection in Depth Images Via Dense Convolutional Neural Networks

Preterm infants' spontaneous motility is a valuable diagnostic and prognostic index of motor and cognitive impairments. Despite being recognized as crucial, preterm infant's movement assessment is mostly based on clinicians' visual inspection. The aim of this work is to present a 2D dense convolutional neural network (denseCNN) to detect preterm infant's joints in depth images acquired in neonatal intensive care units. The denseCNN allows to improve the performance of our previous model in the detection of joints and joint connections, reaching a median recall value equal to 0.839. With a view to monitor preterm infants in a scenario where computational resources are scarce, we tested the architecture on a mid-range laptop. The prediction occurs in real-time (0.014 s per image), opening up the possibility of integrating such monitoring system in a domestic environment.

An Automated Approach for General Movement Assessment: A Pilot Study

Objective: The objective of the study was to develop an automatic quantitative approach to identify infants with abnormal movements of the limbs at term equivalent age (TEA) compared with general movement assessment (GMA). Methods: GMA was performed at TEA by a trained operator in neonates with neurological risk. GMs were classified as normal (N) or abnormal (Ab), which included poor repertoire and cramped synchronized movements. The signals from four micro-accelerometers placed on all limbs were recorded for 10 min simultaneously. A global index (KC_index), quantifying the characteristics of individual limb movements and the coordination among the limbs, was obtained by adding normalized kurtosis of the distribution of the first principal component of the acceleration signals to the cross-correlation of the jerk for the upper and lower limbs. Results: Sixty-eight infants were studied. A KC_index cut-off of 201.5 (95% CI: 199.9-205.0) provided specificity = 0.86 and sensitivity = 0.88 in identifying infants with Ab movements. Conclusions: KC_index provides an automatic and quantitative measure that may allow the identification of infants who require further neurological evaluation.