Automatic localization of anatomical landmarks on the back surface and construction of a body-fixed coordinate system

1987 ◽  
Vol 20 (10) ◽  
pp. 961-970 ◽  
Author(s):  
B. Drerup ◽  
E. Hierholzer
Keyword(s):  
Coordinate System ◽  
Back Surface ◽  
Anatomical Landmarks ◽  
Body Fixed Coordinate System ◽  
Automatic Localization

scholarly journals Zur exakten Behandlung von kollektiven Rotationen Teil A: Theorie / On the Exact Treatment of Collective Rotations Part A: Theory

1973 ◽  
Vol 28 (2) ◽  
pp. 206-215
Author(s):  
Hanns Ruder
Keyword(s):  
Coordinate System ◽  
Perturbation Expansion ◽  
Rotational Energy ◽  
The Body ◽  
System A ◽  
N Body Problem ◽  
Definition Of ◽  
Fixed System ◽  
Body Fixed Coordinate System ◽  
Groundstate Energy

Basic in the treatment of collective rotations is the definition of a body-fixed coordinate system. A kinematical method is derived to obtain the Hamiltonian of a n-body problem for a given definition of the body-fixed system. From this exact Hamiltonian, a consequent perturbation expansion in terms of the total angular momentum leads to two exact expressions: one for the collective rotational energy which has to be added to the groundstate energy in this order of perturbation and a second one for the effective inertia tensor in the groundstate. The discussion of these results leads to two criteria how to define the best body-fixed coordinate system, namely a differential equation and a variational principle. The equivalence of both is shown.

scholarly journals Real-Time Back Surface Landmark Determination Using a Time-of-Flight Camera

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6425
Author(s):  
Daniel Ledwoń ◽  
Marta Danch-Wierzchowska ◽  
Marcin Bugdol ◽  
Karol Bibrowicz ◽  
Tomasz Szurmik ◽  
...  
Keyword(s):  
Real Time ◽  
Average Distance ◽  
Time Of Flight ◽  
Point Clouds ◽  
Diagnostic Methods ◽  
Detection Methods ◽  
Back Surface ◽  
Anatomical Landmarks ◽  
Real Time Analysis ◽  
Similar Accuracy

Postural disorders, their prevention, and therapies are still growing modern problems. The currently used diagnostic methods are questionable due to the exposure to side effects (radiological methods) as well as being time-consuming and subjective (manual methods). Although the computer-aided diagnosis of posture disorders is well developed, there is still the need to improve existing solutions, search for new measurement methods, and create new algorithms for data processing. Based on point clouds from a Time-of-Flight camera, the presented method allows a non-contact, real-time detection of anatomical landmarks on the subject’s back and, thus, an objective determination of trunk surface metrics. Based on a comparison of the obtained results with the evaluation of three independent experts, the accuracy of the obtained results was confirmed. The average distance between the expert indications and method results for all landmarks was 27.73 mm. A direct comparison showed that the compared differences were statically significantly different; however, the effect was negligible. Compared with other automatic anatomical landmark detection methods, ours has a similar accuracy with the possibility of real-time analysis. The advantages of the presented method are non-invasiveness, non-contact, and the possibility of continuous observation, also during exercise. The proposed solution is another step in the general trend of objectivization in physiotherapeutic diagnostics.

scholarly journals Automatic Landmark Detection of Human Back Surface from Depth Images via Deep Learning

2021 ◽  
Author(s):  
Masumeh Delgarmi ◽  
Hamed Heravi ◽  
Ali Rahimpour Jounghani ◽  
Abdullah Shahrezie ◽  
Afshin Ebrahimi ◽  
...  
Keyword(s):  
Network Architecture ◽  
The Body ◽  
Microsoft Kinect ◽  
Training Data ◽  
Back Surface ◽  
Anatomical Landmarks ◽  
X Rays ◽  
Depth Images ◽  
Physical Dysfunction ◽  
The Status

AbstractStudying human postural structure is one of the challenging issues among scholars and physicians. The spine is known as the central axis of the body, and due to various genetic and environmental reasons, it could suffer from deformities that cause physical dysfunction and correspondingly reduce people’s quality of life. Radiography is the most common method for detecting these deformities and requires monitoring and follow-up until full treatment; however, it frequently exposes the patient to X-rays and ionization and as a result, cancer risk is increased in the patient and could be highly dangerous for children or pregnant women. To prevent this, several solutions have been proposed using topographic data analysis of the human back surface. The purpose of this research is to provide an entirely safe and non-invasive method to examine the spiral structure and its deformities. Hence, it is attempted to find the exact location of anatomical landmarks on the human back surface, which provides useful and practical information about the status of the human postural structure to the physician.In this study, using Microsoft Kinect sensor, the depth images from the human back surface of 105 people were recorded and, our proposed approach - Deep convolution neural network-was used as a model to estimate the location of anatomical landmarks. In network architecture, two learning processes, including landmark position and affinity between the two associated landmarks, are successively performed in two separate branches. This is a bottom-up approach; thus, the runtime complexity is considerably reduced, and then the resulting anatomical points are evaluated concerning manual landmarks marked by the operator as the benchmark. Our results showed that 86.9% of PDJ and 80% of PCK. According to the results, this study was more effective than other methods with more than thousands of training data.

scholarly journals Numerical Analysis of Second-Order Mean Wave Forces by a Stabilized Higher Order Boundary Element Method

2018 ◽  
Author(s):  
Yan-Lin Shao
Keyword(s):  
Free Surface ◽  
Boundary Element Method ◽  
Coordinate System ◽  
Boundary Element ◽  
Matrix Equation ◽  
Wave Structure ◽  
Surface Conditions ◽  
Structure Interaction ◽  
Wave Structure Interaction ◽  
Body Fixed Coordinate System

A stabilized Higher-Order Boundary Element Method (HOBEM) based on cubic shape functions is presented to solve the linear wave-structure interaction with the presence of steady or slowly varying velocities. The m-terms which involves second derivatives of local steady flow are difficult to calculate accurately on structure surfaces with high curvatures. They are also not integrable at the sharp corners. A formulation of the Boundary Value Problem (BVP) in a body-fixed coordinate system is thus adopted, which avoids the calculation of the m-terms. The use of body-fixed coordinate system also avoid the inconsistency in the traditional perturbation method when 2nd order slowly-vary motions are larger than the linear motions. The stabilized numerical method presented in this paper is based on streamline integration and biased differencing scheme along the streamlines. The presence of convective terms in the kinematic and dynamic free surface conditions will lead to instable solution if the explicit method is used. Thus a fully implicit scheme is used in this paper for the time integration of kinematic and dynamic free surface conditions. In an implicit scheme, solution of an additional matrix equation is normally required due to the fact that the presence of convective terms are approximated using the variables at current time step rather than the previous time steps only. A method that avoids solving such matrix equation is presented in this paper, which will reduce the computational efforts in the implicit method. The methodology is applicable on unstructured meshes. It can also be used in general second order wave-structure interaction analysis with presence of steady or slowly-varying velocities.

Automatic Landmark Detection of Human Back Surface from Depth Images via Deep Learning

2021 ◽  
Author(s):  
Masumeh Delgarmi ◽  
Hamed Heravi ◽  
Ali Rahimpour Jounghani ◽  
Abdullah Shahrezie ◽  
Afshin Ebrahimi ◽  
...  
Keyword(s):  
Network Architecture ◽  
The Body ◽  
Microsoft Kinect ◽  
Training Data ◽  
Back Surface ◽  
Anatomical Landmarks ◽  
X Rays ◽  
Depth Images ◽  
Physical Dysfunction ◽  
The Status

AbstractStudying human postural structure is one of the challenging issues among scholars and physicians. The spine is known as the central axis of the body, and due to various genetic and environmental reasons, it could suffer from deformities that cause physical dysfunction and correspondingly reduce people’s quality of life. Radiography is the most common method for detecting these deformities and requires monitoring and follow-up until full treatment. This method frequently exposes the patient to X-rays and ionization. Therefore, cancer risk is increased in the patient and could be riskier for children or pregnant women. To prevent this, several solutions have been proposed using topographic data analysis of the human back surface. The purpose of this research is to provide an entirely safe and non-invasive method to examine the spiral structure and its deformities. Hence, it is attempted to find the exact location of anatomical landmarks on the human back surface, which provides useful and practical information about the status of the human postural structure to the physician.In this study, using Microsoft Kinect sensor, the depth images from the human back surface of 105 people were recorded and, our proposed approach - Deep convolution neural network-was used as a model to estimate the location of anatomical landmarks. In network architecture, two learning processes, including landmark position and affinity between the two associated landmarks, are successively performed in two separate branches. This is a bottom-up approach; thus, the runtime complexity is considerably reduced, and then the resulting anatomical points are evaluated concerning manual landmarks marked by the operator as the benchmark. Our results showed that 86.9% of PDJ and 80% of PCK. According to the results, this study was more effective than other methods with more than thousands of training data.

A three-dimensional active shape model for the detection of anatomical landmarks on the back surface

2005 ◽  
Vol 219 (2) ◽  
pp. 129-142 ◽  
Author(s):  
T Huysmans ◽  
R Van Audekercke ◽  
J Vander Sloten ◽  
H Bruyninckx ◽  
G Van der Perre
Keyword(s):  
Mode Shapes ◽  
Distribution Model ◽  
Back Surface ◽  
Active Shape Model ◽  
Anatomical Landmarks ◽  
Shape Model ◽  
Point Distribution ◽  
Pelvic Inclination ◽  
Active Shape ◽  
Point Distribution Model

In this study relations between anatomical landmarks on the dorsal surface of the human torso corresponding to underlying skeletal structures are established. By examining the statistics of the positions of the landmarks in a training set of subjects a point distribution model is derived. Rotations of the pelvis are simulated in order to show that the main mode shapes of variation are consistent with rotations of the pelvis relative to the trunk. The parameters of these mode shapes can therefore be used as independent measures of clinical parameters such as pelvic inclination, pelvic tilt, etc. The point distribution model is further applied to improve reliability and robustness for an automatic and objective detection of the anatomical landmarks on the back surface (active shape model). The results show that it is possible to replace radiographs by surface measurements in order to measure position and orientation of the pelvis, which is particularly valuable in the case of functional examinations that normally involve a large number of radiographs (e.g. to measure the position of the pelvis in a scoliosis).

Sign in / Sign up

Export Citation Format

Share Document