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

Deep learning-based classification of hemiplegia and diplegia in cerebral palsy using postural control analysis

Cerebral palsy (CP) is a neurological condition that affects mobility and motor control, presenting significant challenges for accurate diagnosis, particularly in cases of hemiplegia and diplegia. This study proposes a method of classification utilizing Recurrent Neural Networks (RNNs) to analyze time series force data obtained via an AMTI platform. The proposed research focuses on optimizing these models through advanced techniques such as automatic parameter optimization and data augmentation, improving the accuracy and reliability in classifying these conditions. The results demonstrate the effectiveness of the proposed models in capturing complex temporal dynamics, with the Bidirectional Gated Recurrent Unit (BiGRU) and Long Short-Term Memory (LSTM) model achieving the highest performance, reaching an accuracy of 76.43%. These results outperform traditional approaches and offer a valuable tool for implementation in clinical settings. Moreover, significant differences in postural stability were observed among patients under different visual conditions, underscoring the importance of tailoring therapeutic interventions to each patient's specific needs.

A systematic review of portable technologies for the early assessment of motor development in infants

Early screening and evaluation of infant motor development are crucial for detecting motor deficits and enabling timely interventions. Traditional clinical assessments are often subjective, without fully capturing infants' "real-world" behavior. This has sparked interest in portable, low-cost technologies to objectively and precisely measure infant motion at home, with a goal of enhancing ecological validity. In this systematic review, we explored the current landscape of portable, technology-based solutions to assess early motor development (within the first year), outlining the prevailing challenges and future directions. We reviewed 66 publications, which utilized video, sensors, or a combination of technologies. There were three key applications of these technologies: (1) automating clinical assessments, (2) illuminating new measures of motor development, and (3) predicting developmental outcomes. There was a promising trend toward earlier and more accurate detection using portable technologies. Additional research and demographic diversity are needed to develop fully automated, robust, and user-friendly tools. Registration & Protocol OSF Registries https://doi.org/10.17605/OSF.IO/R6JAE .

Deep learning empowered sensor fusion boosts infant movement classification

BACKGROUND

To assess the integrity of the developing nervous system, the Prechtl general movement assessment (GMA) is recognized for its clinical value in diagnosing neurological impairments in early infancy. GMA has been increasingly augmented through machine learning approaches intending to scale-up its application, circumvent costs in the training of human assessors and further standardize classification of spontaneous motor patterns. Available deep learning tools, all of which are based on single sensor modalities, are however still considerably inferior to that of well-trained human assessors. These approaches are hardly comparable as all models are designed, trained and evaluated on proprietary/silo-data sets.

METHODS

With this study we propose a sensor fusion approach for assessing fidgety movements (FMs). FMs were recorded from 51 typically developing participants. We compared three different sensor modalities (pressure, inertial, and visual sensors). Various combinations and two sensor fusion approaches (late and early fusion) for infant movement classification were tested to evaluate whether a multi-sensor system outperforms single modality assessments. Convolutional neural network (CNN) architectures were used to classify movement patterns.

RESULTS

The performance of the three-sensor fusion (classification accuracy of 94.5%) is significantly higher than that of any single modality evaluated.

CONCLUSIONS

We show that the sensor fusion approach is a promising avenue for automated classification of infant motor patterns. The development of a robust sensor fusion system may significantly enhance AI-based early recognition of neurofunctions, ultimately facilitating automated early detection of neurodevelopmental conditions.

Fine-Grained Fidgety Movement Classification Using Active Learning

Typically developing infants, between the corrected age of 9-20 weeks, produce fidgety movements. These movements can be identified with the General Movement Assessment, but their identification requires trained professionals to conduct the assessment from video recordings. Since trained professionals are expensive and their demand may be higher than their availability, computer vision-based solutions have been developed to assist practitioners. However, most solutions to date treat the problem as a direct mapping from video to infant status, without modeling fidgety movements throughout the video. To address that, we propose to directly model infants' short movements and classify them as fidgety or non-fidgety. In this way, we model the explanatory factor behind the infant's status and improve model interpretability. The issue with our proposal is that labels for an infant's short movements are not available, which precludes us to train such a model. We overcome this issue with active learning. Active learning is a framework that minimizes the amount of labeled data required to train a model, by only labeling examples that are considered "informative" to the model. The assumption is that a model trained on informative examples reaches a higher performance level than a model trained with randomly selected examples. We validate our framework by modeling the movements of infants' hips on two representative cohorts: typically developing and at-risk infants. Our results show that active learning is suitable to our problem and that it works adequately even when the models are trained with labels provided by a novice annotator.

Artificial intelligence and machine learning approaches in cerebral palsy diagnosis, prognosis, and management: a comprehensive review

Cerebral palsy (CP) is a group of disorders that alters patients' muscle coordination, posture, and movement, resulting in a wide range of deformities. Cerebral palsy can be caused by various factors, both prenatal and postnatal, such as infections or injuries that damage different parts of the brain. As brain plasticity is more prevalent during childhood, early detection can help take the necessary course of management and treatments that would significantly benefit patients by improving their quality of life. Currently, cerebral palsy patients receive regular physiotherapies, occupational therapies, speech therapies, and medications to deal with secondary abnormalities arising due to CP. Advancements in artificial intelligence (AI) and machine learning (ML) over the years have demonstrated the potential to improve the diagnosis, prognosis, and management of CP. This review article synthesizes existing research on AI and ML techniques applied to CP. It provides a comprehensive overview of the role of AI-ML in cerebral palsy, focusing on its applications, benefits, challenges, and future prospects. Through an extensive examination of existing literature, we explore various AI-ML approaches, including but not limited to assessment, diagnosis, treatment planning, and outcome prediction for cerebral palsy. Additionally, we address the ethical considerations, technical limitations, and barriers to the widespread adoption of AI-ML for CP patient care. By synthesizing current knowledge and identifying gaps in research, this review aims to guide future endeavors in harnessing AI-ML for optimizing outcomes and transforming care delivery in cerebral palsy rehabilitation.

Enhanced Infant Movement Analysis Using Transformer-Based Fusion of Diverse Video Features for Neurodevelopmental Monitoring

Neurodevelopment is a highly intricate process, and early detection of abnormalities is critical for optimizing outcomes through timely intervention. Accurate and cost-effective diagnostic methods for neurological disorders, particularly in infants, remain a significant challenge due to the heterogeneity of data and the variability in neurodevelopmental conditions. This study recruited twelve parent-infant pairs, with infants aged 3 to 12 months. Approximately 25 min of 2D video footage was captured, documenting natural play interactions between the infants and toys. We developed a novel, open-source method to classify and analyse infant movement patterns using deep learning techniques, specifically employing a transformer-based fusion model that integrates multiple video features within a unified deep neural network. This approach significantly outperforms traditional methods reliant on individual video features, achieving an accuracy of over 90%. Furthermore, a sensitivity analysis revealed that the pose estimation contributed far less to the model's output than the pre-trained transformer and convolutional neural network (CNN) components, providing key insights into the relative importance of different feature sets. By providing a more robust, accurate and low-cost analysis of movement patterns, our work aims to enhance the early detection and potential prediction of neurodevelopmental delays, whilst providing insight into the functioning of the transformer-based fusion models of diverse video features.

A self-supervised spatio-temporal attention network for video-based 3D infant pose estimation

General movement and pose assessment of infants is crucial for the early detection of cerebral palsy (CP). Nevertheless, most human pose estimation methods, in 2D or 3D, focus on adults due to the lack of large datasets and pose annotations on infants. To solve these problems, here we present a model known as YOLO-infantPose, which has been fine-tuned, for infant pose estimation in 2D. We further propose a self-supervised model called STAPose3D for 3D infant pose estimation based on videos. We employ multi-view video data during the training process as a strategy to address the challenge posed by the absence of 3D pose annotations. STAPose3D combines temporal convolution, temporal attention, and graph attention to jointly learn spatio-temporal features of infant pose. Our methods are summarized into two stages: applying YOLO-infantPose on input videos, followed by lifting these 2D poses along with respective confidences for every joint to 3D. The employment of the best-performing 2D detector in the first stage significantly improves the precision of 3D pose estimation. We reveal that fine-tuned YOLO-infantPose outperforms other models tested on our clinical dataset as well as two public datasets MINI-RGBD and YouTube-Infant dataset. Results from our infant movement video dataset demonstrate that STAPose3D effectively comprehends the spatio-temporal features among different views and significantly improves the performance of 3D infant pose estimation in videos. Finally, we explore the clinical application of our method for general movement assessment (GMA) in a clinical dataset annotated as normal writhing movements or abnormal monotonic movements according to the GMA standards. We show that the 3D pose estimation results produced by our STAPose3D model significantly boost the GMA prediction performance than 2D pose estimation. Our code is available at github.com/wwYinYin/STAPose3D.

Computer Vision for Gait Assessment in Cerebral Palsy: Metric Learning and Confidence Estimation

Assessing the motor impairments of individuals with neurological disorders holds significant importance in clinical practice. Currently, these clinical assessments are time-intensive and depend on qualitative scales administered by trained healthcare professionals at the clinic. These evaluations provide only coarse snapshots of a person's abilities, failing to track quantitatively the detail and minutiae of recovery over time. To overcome these limitations, we introduce a novel machine learning approach that can be administered anywhere including home. It leverages a spatial-temporal graph convolutional network (STGCN) to extract motion characteristics from pose data obtained from monocular video captured by portable devices like smartphones and tablets. We propose an end-to-end model, achieving an accuracy rate of approximately 76.6% in assessing children with Cerebral Palsy (CP) using the Gross Motor Function Classification System (GMFCS). This represents a 5% improvement in accuracy compared to the current state-of-the-art techniques and demonstrates strong agreement with professional assessments, as indicated by the weighted Cohen's Kappa ( κlw = 0.733 ). In addition, we introduce the use of metric learning through triplet loss and self-supervised training to better handle situations with a limited number of training samples and enable confidence estimation. Setting a confidence threshold at 0.95 , we attain an impressive estimation accuracy of 88% . Notably, our method can be efficiently implemented on a wide range of mobile devices, providing real-time or near real-time results.

Human Pose Estimation for Clinical Analysis of Gait Pathologies

Gait analysis serves as a critical diagnostic tool for identifying neurologic and musculoskeletal damage. Traditional manual analysis of motion data, however, is labor-intensive and heavily reliant on the expertise and judgment of the therapist. This study introduces a binary classification method for the quantitative assessment of gait impairments, specifically focusing on Duchenne muscular dystrophy (DMD), a prevalent and fatal neuromuscular genetic disorder. The research compares spatiotemporal and sagittal kinematic gait features derived from 2D and 3D human pose estimation trajectories against concurrently recorded 3D motion capture (MoCap) data from healthy children. The proposed model leverages a novel benchmark dataset, collected from YouTube and publicly available datasets of their typically developed peers, to extract time-distance variables (e.g. speed, step length, stride time, and cadence) and sagittal joint angles of the lower extremity (e.g. hip, knee, and knee flexion angles). Machine learning and deep learning techniques are employed to discern patterns that can identify children exhibiting DMD gait disturbances. While the current model is capable of distinguishing between healthy subjects and those with DMD, it does not specifically differentiate between DMD patients and patients with other gait impairments. Experimental results validate the efficacy of our cost-effective method, which relies on recorded RGB video, in detecting gait abnormalities, achieving a prediction accuracy of 96.2% for Support Vector Machine (SVM) and 97% for the deep network.

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.

Robust and Interpretable General Movement Assessment Using Fidgety Movement Detection

Fidgety movements occur in infants between the age of 9 to 20 weeks post-term, and their absence are a strong indicator that an infant has cerebral palsy. Prechtl's General Movement Assessment method evaluates whether an infant has fidgety movements, but requires a trained expert to conduct it. Timely evaluation facilitates early interventions, and thus computer-based methods have been developed to aid domain experts. However, current solutions rely on complex models or high-dimensional representations of the data, which hinder their interpretability and generalization ability. To address that we propose [Formula: see text], a method that detects fidgety movements and uses them towards an assessment of the quality of an infant's general movements. [Formula: see text] is true to the domain expert process, more accurate, and highly interpretable due to its fine-grained scoring system. The main idea behind [Formula: see text] is to specify signal properties of fidgety movements that are measurable and quantifiable. In particular, we measure the movement direction variability of joints of interest, for movements of small amplitude in short video segments. [Formula: see text] also comprises a strategy to reduce those measurements to a single score that quantifies the quality of an infant's general movements; the strategy is a direct translation of the qualitative procedure domain experts use to assess infants. This brings [Formula: see text] closer to the process a domain expert applies to decide whether an infant produced enough fidgety movements. We evaluated [Formula: see text] on the largest clinical dataset reported, where it showed to be interpretable and more accurate than many methods published to date.

Mean 3D Dispersion for Automatic General Movement Assessment of Preterm Infants

The General Movement assessment (GMA) is a validated assessment of brain maturation primarily based on the qualitative analysis of the complexity and the variation of spontaneous motor activity. The GMA can identify preterm infants presenting an early abnormal developmental trajectory before term-equivalent age, which permits a personalized early developmental intervention. However, GMA is time-consuming and relies on a qualitative analysis; these limitations restrict the implementation of GMA in clinical practice. In this study based on a validated dataset of 183 videos from 92 premature infants (54 males, 38 females) born <33 weeks of gestational age (GA) and acquired between 32 and 40 weeks of GA, we introduce the mean 3D dispersion (M3D) for objective quantification and classification of normal and abnormal GMA. Moreover, we have created a new 3D representation of skeleton joints which allows an objective comparison of spontaneous movements of infants of different ages and sizes. Preterm infants with normal versus abnormal GMA had a distinct M3D distribution (p <0.001). The M3D has shown a good classification performance for GMA (AUC=0.7723) and presented an accuracy of 74.1%, a sensitivity of 75.8%, and a specificity of 70.1% when using an M3D of 0.29 as a classification threshold.Clinical relevance- Our study paves the way for the development of quantitative analysis of GMA within the Neonatal Unit.

The Classification of Movement in Infants for the Autonomous Monitoring of Neurological Development

Neurodevelopmental delay following extremely preterm birth or birth asphyxia is common but diagnosis is often delayed as early milder signs are not recognised by parents or clinicians. Early interventions have been shown to improve outcomes. Automation of diagnosis and monitoring of neurological disorders using non-invasive, cost effective methods within a patient's home could improve accessibility to testing. Furthermore, said testing could be conducted over a longer period, enabling greater confidence in diagnoses, due to increased data availability. This work proposes a new method to assess the movements in children. Twelve parent and infant participants were recruited (children aged between 3 and 12 months). Approximately 25 min 2D video recordings of the infants organically playing with toys were captured. A combination of deep learning and 2D pose estimation algorithms were used to classify the movements in relation to the children's dexterity and position when interacting with a toy. The results demonstrate the possibility of capturing and classifying children's complexity of movements when interacting with toys as well as their posture. Such classifications and the movement features could assist practitioners to accurately diagnose impaired or delayed movement development in a timely fashion as well as facilitating treatment monitoring.

Open video data sharing in developmental science and clinical practice

In behavioral research and clinical practice video data has rarely been shared or pooled across sites due to ethical concerns of confidentiality, although the need of shared large-scaled datasets remains increasing. This demand is even more imperative when data-heavy computer-based approaches are involved. To share data while abiding by privacy protection rules, a critical question arises whether efforts at data de-identification reduce data utility? We addressed this question by showcasing an established and video-based diagnostic tool for detecting neurological deficits. We demonstrated for the first time that, for analyzing infant neuromotor functions, pseudonymization by face-blurring video recordings is a viable approach. The redaction did not affect classification accuracy for either human assessors or artificial intelligence methods, suggesting an adequate and easy-to-apply solution for sharing behavioral video data. Our work shall encourage more innovative solutions to share and merge stand-alone video datasets into large data pools to advance science and public health.

A Two-stream Convolutional Network for Musculoskeletal and Neurological Disorders Prediction

Musculoskeletal and neurological disorders are the most common causes of walking problems among older people, and they often lead to diminished quality of life. Analyzing walking motion data manually requires trained professionals and the evaluations may not always be objective. To facilitate early diagnosis, recent deep learning-based methods have shown promising results for automated analysis, which can discover patterns that have not been found in traditional machine learning methods. We observe that existing work mostly applies deep learning on individual joint features such as the time series of joint positions. Due to the challenge of discovering inter-joint features such as the distance between feet (i.e. the stride width) from generally smaller-scale medical datasets, these methods usually perform sub-optimally. As a result, we propose a solution that explicitly takes both individual joint features and inter-joint features as input, relieving the system from the need of discovering more complicated features from small data. Due to the distinctive nature of the two types of features, we introduce a two-stream framework, with one stream learning from the time series of joint position and the other from the time series of relative joint displacement. We further develop a mid-layer fusion module to combine the discovered patterns in these two streams for diagnosis, which results in a complementary representation of the data for better prediction performance. We validate our system with a benchmark dataset of 3D skeleton motion that involves 45 patients with musculoskeletal and neurological disorders, and achieve a prediction accuracy of 95.56%, outperforming state-of-the-art methods.