Novel Body Shape Descriptors for Abdominal Adiposity Prediction Using Magnetic Resonance Images and Stereovision Body Images

Sun, Jingjing; Xu, Bugao; Lee, Jane; Freeland‐Graves, Jeanne H.

doi:10.1002/oby.21957

Cited by 16 publications

(20 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…body surface area and segmental volume) to be collected directly 4 . This technique generates individual 3D human models that can be used in a range of applications, including anthropometric surveys 5,6 , virtual fitting of clothing 7 , sports performance prediction 8 , biomechanical analyses [9][10][11][12] and medical diagnosis [13][14][15] .…”

Section: Introductionmentioning

confidence: 99%

Comparison of depth cameras for three-dimensional reconstruction in medicine

Chiu

Thelwell

Senior

et al. 2019

Proc Inst Mech Eng H

View full text Add to dashboard Cite

KinectFusion is a typical three-dimensional reconstruction technique which enables generation of individual three-dimensional human models from consumer depth cameras for understanding body shapes. The aim of this study was to compare three-dimensional reconstruction results obtained using KinectFusion from data collected with two different types of depth camera (time-of-flight and stereoscopic cameras) and compare these results with those of a commercial three-dimensional scanning system to determine which type of depth camera gives improved reconstruction. Torso mannequins and machined aluminium cylinders were used as the test objects for this study. Two depth cameras, Microsoft Kinect V2 and Intel Realsense D435, were selected as the representatives of time-of-flight and stereoscopic cameras, respectively, to capture scan data for the reconstruction of three-dimensional point clouds by KinectFusion techniques. The results showed that both time-of-flight and stereoscopic cameras, using the developed rotating camera rig, provided repeatable body scanning data with minimal operator-induced error. However, the time-of-flight camera generated more accurate three-dimensional point clouds than the stereoscopic sensor. Thus, this suggests that applications requiring the generation of accurate three-dimensional human models by KinectFusion techniques should consider using a time-of-flight camera, such as the Microsoft Kinect V2, as the image capturing sensor.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison of depth cameras for three-dimensional reconstruction in medicine

Chiu

Thelwell

Senior

et al. 2019

Proc Inst Mech Eng H

View full text Add to dashboard Cite

show abstract

“…[24]. Compared with related clinical studies in body composition assessment [20] [19] [21] [1] [23] [25], our sample size is relatively large. The data collection and following studies involving human subjects were approved by the Institutional Review Board at the George Washington University (IRB# 041533).…”

Section: Data Preprocessingmentioning

confidence: 99%

3D Shape-Based Body Composition Inference Model Using a Bayesian Network

Hahn

Zhang

2020

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Body composition can be assessed in many different ways. High-end medical equipment, such as Dualenergy X-ray Absorptiometry (DXA), Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), offers high-fidelity pixel/voxel-level assessment but is prohibitive in cost. In the case of DXA and CT, the approach exposes users to ionizing radiation. Whole-body air displacement plethysmography (BOD POD) can accurately estimate body density, but the assessment is limited to the whole-body fat percentage. Optical 3D scan and reconstruction techniques, such as using depth cameras, have brought new opportunities for improving body composition assessment by intelligently analyzing body shape features. We present a novel supervised inference model to predict pixel-level body composition and percentage of body fat using 3D geometry features and body density. First, we use body density to model a fat distribution base prediction. Then, we use a Bayesian network to infer the probability of the base prediction bias with 3D geometry features. Finally, we correct the bias using non-parametric regression. We use DXA assessment as the ground truth in model training and validation. We compare our method, in terms of pixel-level body composition assessment, with the current stateof-the-art prediction models. Our method outperforms those prediction models by 52.69% on average. We also compare our method, in terms of whole-body fat percentage assessment, with the medical level equipment-BOD POD. Our method outperforms the BOD POD by 23.28%.

show abstract

“…Las técnicas de imagen, específicamente la resonancia magnética, han contribuido de manera importante a la comprensión de los fenómenos anatómicos, fisiopatológicos y neurodinámicos relacionados con la obesidad si bien no existe una única postura respecto a la validación de elementos del examen físico que ayuden a sospechar un nivel riesgoso de adiposidad que se beneficie categóricamente de un estudio imagenológico. Datos recientes han señalado que hasta trece descriptores corporales objetivables clínicamente tendrían una correlación significativa con las cuantificaciones basadas en imagen, exhibiendo perfiles distintos para el tipo de grasa estudiada y características del paciente, como su sexo (70) .…”

Section: Desafíos Futurosunclassified

Imágenes en obesidad: contribuyendo a un entendimiento más profundo de la enfermedad

et al. 2020

View full text Add to dashboard Cite

IntroducciónLa obesidad ha sido históricamente considerada un importante factor de riesgo para diversas patologías de la esfera metabólica y cardiovascular que constituyen las principales causas de muerte para la mayoría de los países desarrollados y en vías de desarrollo en la actualidad. Sin embargo, en la actualidad es abordada cada vez más como una enfermedad y no sólo como un factor de riesgo cardiovascular debido a su complejidad fisiopatológica (1) y a la profunda re-

show abstract

Novel Body Shape Descriptors for Abdominal Adiposity Prediction Using Magnetic Resonance Images and Stereovision Body Images

Abstract: Novel body shape descriptors defined on 3D body images can effectively predict abdominal adiposity quantified by MRI.

Cited by 16 publications

References 35 publications

Comparison of depth cameras for three-dimensional reconstruction in medicine

Comparison of depth cameras for three-dimensional reconstruction in medicine

3D Shape-Based Body Composition Inference Model Using a Bayesian Network

Imágenes en obesidad: contribuyendo a un entendimiento más profundo de la enfermedad

Contact Info

Product

Resources

About