Abstract:Objective: To automate identification of postural point-features from colour videos of children with neuromotor disability, during clinical assessment. The automatic identification of 13 points of interest (2, 6, 2, 3 points on the head, trunk, pelvis, arm respectively) is required to estimate the location and orientation of head, trunk, and arm segments, from videos of the clinical test "Segmental Assessment of Trunk Control" (SATCo) which is a test of seated postural control. Methods: Three expert operators … Show more
“…These approaches make use of large datasets to train deep learning models capable of achieving state-ofthe-art classification accuracy. Several studies have attempted to make use of the general improvements to accuracy provided by deep learning by applying deep learning frameworks to similar movement related diagnostic activities [8], [21], [35]. Whilst the results are promising, the holistic application of deep learning in the healthcare domain faces several challenges, most notably the large amount of data required for suitable results, and the problem of understandable AI.…”
The pursuit of early diagnosis of cerebral palsy has been an active research area with some very promising results using tools such as the General Movements Assessment (GMA). In our previous work, we explored the feasibility of extracting pose-based features from video sequences to automatically classify infant body movement into two categories, normal and abnormal. The classification was based upon the GMA, which was carried out on the video data by an independent expert reviewer. In this paper we extend our previous work by extracting the normalised pose-based feature sets, Histograms of Joint Orientation 2D (HOJO2D) and Histograms of Joint Displacement 2D (HOJD2D), for use in new deep learning architectures. We explore the viability of using these pose-based feature sets for automated classification within a deep learning framework by carrying out extensive experiments on five new deep learning architectures. Experimental results show that the proposed fully connected neural network FCNet performed robustly across different feature sets. Furthermore, the proposed convolutional neural network architectures demonstrated excellent performance in handling features in higher dimensionality. We make the code, extracted features and associated GMA labels publicly available.
“…These approaches make use of large datasets to train deep learning models capable of achieving state-ofthe-art classification accuracy. Several studies have attempted to make use of the general improvements to accuracy provided by deep learning by applying deep learning frameworks to similar movement related diagnostic activities [8], [21], [35]. Whilst the results are promising, the holistic application of deep learning in the healthcare domain faces several challenges, most notably the large amount of data required for suitable results, and the problem of understandable AI.…”
The pursuit of early diagnosis of cerebral palsy has been an active research area with some very promising results using tools such as the General Movements Assessment (GMA). In our previous work, we explored the feasibility of extracting pose-based features from video sequences to automatically classify infant body movement into two categories, normal and abnormal. The classification was based upon the GMA, which was carried out on the video data by an independent expert reviewer. In this paper we extend our previous work by extracting the normalised pose-based feature sets, Histograms of Joint Orientation 2D (HOJO2D) and Histograms of Joint Displacement 2D (HOJD2D), for use in new deep learning architectures. We explore the viability of using these pose-based feature sets for automated classification within a deep learning framework by carrying out extensive experiments on five new deep learning architectures. Experimental results show that the proposed fully connected neural network FCNet performed robustly across different feature sets. Furthermore, the proposed convolutional neural network architectures demonstrated excellent performance in handling features in higher dimensionality. We make the code, extracted features and associated GMA labels publicly available.
“…These assessments, although reliable, are subjective and most consider the head/trunk as a single unit, ignoring both its multisegmental composition and any use of the hands for support to maintain a balanced posture (Heyrman et al, 2011;Pountney et al, 1999;Reid, 1997;Russell et al, 2002;Verheyden et al, 2004). The Segmental Assessment of Trunk Control (SATCo) is unique in addressing these issues, evaluating control based on 1) the position of individual trunk segments in space relative to a defined aligned posture and 2) the use of external support (Butler et al, 2010) (Cunningham et al, 2018).…”
Section: Introductionmentioning
confidence: 99%
“…While this work (Cunningham et al, 2018) demonstrates, for the first time, a feasible technical solution to automate tracking of individual trunk segments in a given sitting posture, and of changes away from that posture, it leaves unsolved the automated identification of the aligned trunk posture to act as a reference.…”
Background: The Segmental Assessment of Trunk Control (SATCo) evaluates sitting control at seven separate trunk segments, making a judgement based on their position in space relative to a defined, aligned posture. SATCo is in regular clinical and research use and is a Recommended Instrument for Cerebral Palsy and Spinal Cord Injury-Paediatric by The National Institute of Neurological Disorders and Stroke (US). However, SATCo remains a subjective assessment.Research question: This study tests the feasibility of providing an objective, automated identification of frames containing the aligned, reference trunk posture using deep convolutional neural network (DCNN) analysis of raw high definition and depth (HD+D) images.Methods: A SATCo was conducted on sixteen healthy male adults and recorded using a Kinect V2. For each of seven segments tested, two different trials were collected (control and nocontrol) to simulate a range of alignment configurations. For all images, classification of alignment obtained from a trained and validated DCNN was compared to expert clinician's labelling.Results: Using leave-one-out testing, at the optimal operating threshold, the DCNN correctly classified individual images (alignment v misaligned) with average precision 92.7±16% (mean±SD).Significance: These results show for the first time, automation of a key component of the SATCo test, namely identification of aligned trunk posture directly from raw images (HD+D). This demonstrates the potential of machine learning to provide a fully automated, objective SATCo test to enhance assessment of trunk control in children and adults for research and treatment of various conditions including neurodisability and stroke.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.