Comparison of depth cameras for three-dimensional reconstruction in medicine

Simple benchmarking method for determining the accuracy of depth cameras in body landmark location estimation: Static upright posture as a measurement example

To evaluate the postures in ergonomics applications, studies have proposed the use of low-cost, marker-less, and portable depth camera-based motion tracking systems (DCMTSs) as a potential alternative to conventional marker-based motion tracking systems (MMTSs). However, a simple but systematic method for examining the estimation errors of various DCMTSs is lacking. This paper proposes a benchmarking method for assessing the estimation accuracy of depth cameras for full-body landmark location estimation. A novel alignment board was fabricated to align the coordinate systems of the DCMTSs and MMTSs. The data from an MMTS were used as a reference to quantify the error of using a DCMTS to identify target locations in a 3-D space. To demonstrate the proposed method, the full-body landmark location tracking errors were evaluated for a static upright posture using two different DCMTSs. For each landmark, we compared each DCMTS (Kinect system and RealSense system) with an MMTS by calculating the Euclidean distances between symmetrical landmarks. The evaluation trials were performed twice. The agreement between the tracking errors of the two evaluation trials was assessed using intraclass correlation coefficient (ICC). The results indicate that the proposed method can effectively assess the tracking performance of DCMTSs. The average errors (standard deviation) for the Kinect system and RealSense system were 2.80 (1.03) cm and 5.14 (1.49) cm, respectively. The highest average error values were observed in the depth orientation for both DCMTSs. The proposed method achieved high reliability with ICCs of 0.97 and 0.92 for the Kinect system and RealSense system, respectively.

Estimating somatotype from a single-camera 3D body scanning system

Somatotype is an approach to quantify body physique (shape and body composition). Somatotyping by manual measurement (the anthropometric method) or visual rating (the photoscopic method) needs technical expertize to minimize intra- and inter-observer errors. This study aims to develop machine learning models which enable automatic estimation of Heath-Carter somatotypes using a single-camera 3D scanning system. Single-camera 3D scanning was used to obtain 3D imaging data and computer vision techniques to extract features of body shape. Machine learning models were developed to predict participants' somatotypes from the extracted shape features. These predicted somatotypes were compared against manual measurement procedures. Data were collected from 46 participants and used as the training/validation set for model developing, whilst data collected from 17 participants were used as the test set for model evaluation. Evaluation tests showed that the 3D scanning methods enable accurate (mean error < 0.5; intraclass correlation coefficients >0.8) and precise (test-retest root mean square error < 0.5; intraclass correlation coefficients >0.8) somatotype predictions. This study shows that the 3D scanning methods could be used as an alternative to traditional somatotyping approaches after the current models improve with the large datasets.

Sensor Architectures and Technologies for Upper Limb 3D Surface Reconstruction: A Review

3D digital models of the upper limb anatomy represent the starting point for the design process of bespoke devices, such as orthoses and prostheses, which can be modeled on the actual patient's anatomy by using CAD (Computer Aided Design) tools. The ongoing research on optical scanning methodologies has allowed the development of technologies that allow the surface reconstruction of the upper limb anatomy through procedures characterized by minimum discomfort for the patient. However, the 3D optical scanning of upper limbs is a complex task that requires solving problematic aspects, such as the difficulty of keeping the hand in a stable position and the presence of artefacts due to involuntary movements. Scientific literature, indeed, investigated different approaches in this regard by either integrating commercial devices, to create customized sensor architectures, or by developing innovative 3D acquisition techniques. The present work is aimed at presenting an overview of the state of the art of optical technologies and sensor architectures for the surface acquisition of upper limb anatomies. The review analyzes the working principles at the basis of existing devices and proposes a categorization of the approaches based on handling, pre/post-processing effort, and potentialities in real-time scanning. An in-depth analysis of strengths and weaknesses of the approaches proposed by the research community is also provided to give valuable support in selecting the most appropriate solution for the specific application to be addressed.

Surface imaging for real-time patient respiratory function assessment in intensive care

PURPOSE

Monitoring of physiological parameters is a major concern in Intensive Care Units (ICU) given their role in the assessment of vital organ function. Within this context, one issue is the lack of efficient noncontact techniques for respiratory monitoring. In this paper, we present a novel noncontact solution for real-time respiratory monitoring and function assessment of ICU patients.

METHODS

The proposed system uses a Time-of-Flight depth sensor to analyze the patient's chest wall morphological changes in order to estimate multiple respiratory function parameters. The automatic detection of the patient's torso is also proposed using a deep neural network model trained on the COCO dataset. The evaluation of the proposed system was performed on a mannequin and on 16 mechanically ventilated patients (a total of 216 recordings) admitted in the ICU of the Brest University Hospital.

RESULTS

The estimation of respiratory parameters (respiratory rate and tidal volume) showed high correlation with the reference method (r = 0.99; P < 0.001 and r = 0.99; P < 0.001) in the mannequin recordings and (r = 0.95, P < 0.001 and r = 0.90, P < 0.001) for patients.

CONCLUSION

This study describes and evaluates a novel noncontact monitoring system suitable for continuous monitoring of key respiratory parameters for disease assessment of critically ill patients.