Computer Vision to the Rescue: Infant Postural Symmetry Estimation from Incongruent Annotations

• URL: http://arxiv.org/abs/2207.09352v1
• Date: Tue, 19 Jul 2022 15:59:40 GMT
• Title: Computer Vision to the Rescue: Infant Postural Symmetry Estimation from Incongruent Annotations
• Authors: Xiaofei Huang, Michael Wan, Lingfei Luan, Bethany Tunik, Sarah Ostadabbas
• Abstract summary: Bilateral postural symmetry plays a key role as a potential risk marker for autism spectrum disorder (ASD) We develop a computer vision based infant symmetry assessment system, leveraging 3D human pose estimation for infants.
• Score: 10.240757129801757
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Bilateral postural symmetry plays a key role as a potential risk marker for autism spectrum disorder (ASD) and as a symptom of congenital muscular torticollis (CMT) in infants, but current methods of assessing symmetry require laborious clinical expert assessments. In this paper, we develop a computer vision based infant symmetry assessment system, leveraging 3D human pose estimation for infants. Evaluation and calibration of our system against ground truth assessments is complicated by our findings from a survey of human ratings of angle and symmetry, that such ratings exhibit low inter-rater reliability. To rectify this, we develop a Bayesian estimator of the ground truth derived from a probabilistic graphical model of fallible human raters. We show that the 3D infant pose estimation model can achieve 68% area under the receiver operating characteristic curve performance in predicting the Bayesian aggregate labels, compared to only 61% from a 2D infant pose estimation model and 60% from a 3D adult pose estimation model, highlighting the importance of 3D poses and infant domain knowledge in assessing infant body symmetry. Our survey analysis also suggests that human ratings are susceptible to higher levels of bias and inconsistency, and hence our final 3D pose-based symmetry assessment system is calibrated but not directly supervised by Bayesian aggregate human ratings, yielding higher levels of consistency and lower levels of inter-limb assessment bias.

Related papers

• Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation [51.00725889172323]
  We propose a Pose-Oriented Transformer (POT) with uncertainty guided refinement for 3D human pose estimation. We first develop novel pose-oriented self-attention mechanism and distance-related position embedding for POT to explicitly exploit the human skeleton topology. We present an Uncertainty-Guided Refinement Network (UGRN) to refine pose predictions from POT, especially for the difficult joints.
  arXiv  Detail & Related papers  (2023-02-15T00:22:02Z)
• Anatomy-guided domain adaptation for 3D in-bed human pose estimation [62.3463429269385]
  3D human pose estimation is a key component of clinical monitoring systems. We present a novel domain adaptation method, adapting a model from a labeled source to a shifted unlabeled target domain. Our method consistently outperforms various state-of-the-art domain adaptation methods.
  arXiv  Detail & Related papers  (2022-11-22T11:34:51Z)
• Automatic Assessment of Infant Face and Upper-Body Symmetry as Early Signs of Torticollis [11.187291473332325]
  We apply computer vision pose estimation techniques developed expressly for the data-scarce infant domain to the study of torticollis. We use a combination of facial landmark and body joint estimation techniques designed for infants to estimate a range of geometric measures pertaining to face and upper body symmetry.
  arXiv  Detail & Related papers  (2022-10-26T20:39:14Z)
• Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Persons [75.86463396561744]
  In multi-person 2D pose estimation, the bottom-up methods simultaneously predict poses for all persons. Our method achieves 38.4% improvement on bounding box precision and 39.1% improvement on bounding box recall over the state of the art (SOTA) For the human pose AP evaluation, we achieve a new SOTA (71.0 AP) on the COCO test-dev set with the single-scale testing.
  arXiv  Detail & Related papers  (2022-08-25T10:09:10Z)
• Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation [70.32536356351706]
  We introduce MRP-Net that constitutes a common deep network backbone with two output heads subscribing to two diverse configurations. We derive suitable measures to quantify prediction uncertainty at both pose and joint level. We present a comprehensive evaluation of the proposed approach and demonstrate state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-29T07:14:58Z)
• Leveraging Clinically Relevant Biometric Constraints To Supervise A Deep Learning Model For The Accurate Caliper Placement To Obtain Sonographic Measurements Of The Fetal Brain [0.0]
  We propose a deep learning (DL) approach to compute 3 key fetal brain biometry from the 2D USG images of the transcerebellar plane (TC) We leveraged clinically relevant biometric constraints (relationship between caliper points) and domain-relevant data augmentation to improve the accuracy of a U-Net DL model. For all cases, the mean errors in the placement of the individual caliper points and the computed biometry were comparable to error rates among clinicians.
  arXiv  Detail & Related papers  (2022-03-28T04:00:22Z)
• Towards human-level performance on automatic pose estimation of infant spontaneous movements [2.7086496937827005]
  Four types of convolutional neural networks were trained and evaluated on a novel infant pose dataset. The best performing neural network had a similar localization error to the inter-rater spread of human expert annotations. Overall, the results of our study show that pose estimation of infant spontaneous movements has a great potential to support research initiatives on early detection of developmental disorders in children with perinatal brain injuries.
  arXiv  Detail & Related papers  (2020-10-12T18:17:47Z)
• Probabilistic 3D surface reconstruction from sparse MRI information [58.14653650521129]
  We present a novel probabilistic deep learning approach for concurrent 3D surface reconstruction from sparse 2D MR image data and aleatoric uncertainty prediction. Our method is capable of reconstructing large surface meshes from three quasi-orthogonal MR imaging slices from limited training sets.
  arXiv  Detail & Related papers  (2020-10-05T14:18:52Z)
• Neural Descent for Visual 3D Human Pose and Shape [67.01050349629053]
  We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image. We rely on a recently introduced, expressivefull body statistical 3d human model, GHUM, trained end-to-end. Central to our methodology, is a learning to learn and optimize approach, referred to as HUmanNeural Descent (HUND), which avoids both second-order differentiation.
  arXiv  Detail & Related papers  (2020-08-16T13:38:41Z)
• Preterm infants' pose estimation with spatio-temporal features [7.054093620465401]
  This paper introduces the use of preterm-temporal features for limb detection and tracking. It is the first study to use depth videos acquired in the actual clinical practice for limb-pose estimation.
  arXiv  Detail & Related papers  (2020-05-08T09:51:22Z)
• Exploring Partial Intrinsic and Extrinsic Symmetry in 3D Medical Imaging [39.5958976939981]
  We present a novel methodology to detect imperfect bilateral symmetry in CT of human anatomy. The structurally symmetric nature of the pelvic bone is explored and is used to provide interventional image augmentation for treatment of unilateral fractures in patients with traumatic injuries.
  arXiv  Detail & Related papers  (2020-03-04T19:08:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.