Process and system for design of orthosis

Abstract

The invention relates to a process and a system for design of an orthosis. A process operable using a computerized system for providing output data indicative of a geometry of a spinal region of a subject's body for spinal alignment correction, the process comprising the steps of: (i) detecting a body marker of the subject from a three-dimensional point cloud model of a body surface of the spinal region of the subject, the body marker is a marker indicative of a spinal anatomical marker of the subject; the method may include (i) determining a spinal correction of a spine of the subject, where the spinal correction provides a spinal alignment correction of the subject, and (iii) generating a corrected three-dimensional point cloud model of the spine region of the subject.

Description

TECHNICAL FIELD

[0001] The present invention relates to the field of orthotic devices, and more particularly to a process and system for the design of spinal orthotic devices. BACKGROUND

[0002] Within the field of orthopaedic intervention, there are several aspects, some of the main aspects being:

[0003] (i) internal joint replacement or repair devices, commonly referred to as "orthopaedic implants" or "prostheses", such as hip, knee and shoulder prostheses,

[0004] (ii) orthotic devices, such as spinal braces, for the intervention of deformities such as scoliosis, and such devices are typically provided externally to the body and attached to the body, such as spinal braces.

[0005] Within the field of orthopaedic and musculoskeletal correction practice, orthotic devices are also included, which are surgical devices or appliances that typically exert an external force on a part of the body to support a joint and also to correct deformities of a subject.

[0006] An example of such orthotic devices is an external correction device, for example a spinal brace. Such braces are used to apply force to the spine of a patient, for example a patient with scoliosis.

[0007] In particular, children with AIS (adolescent idiopathic scoliosis), which is a condition that typically affects children between the ages of 10 and adolescence, which is represented by the presence of an abnormal curvature of the spine to the right or left in an "S" or "C" shape. Adolescents with scoliosis are generally healthy and are typically treated with braces that are externally fixed to their spine to gradually force the spine into a more normal state by the brace.

[0008] In the prior art of the design and manufacture of orthotic devices such as spinal braces, typical steps include:

[0009] (i) manually forming a negative cast model from the body of a subject;

[0010] (ii) producing a positive cast using a milling machine, typically with a polymeric material;

[0011] (iii) manually correcting the positive cast; and

[0012] (iv) manually moulding a polymeric material on the positive cast to form the orthotic device.

[0013] Object of the present invention

[0014] It is an object of the present invention to provide a process and system for orthotic device design that overcomes or at least partially ameliorates at least some of the deficiencies associated with the prior art. SUMMARY

[0015] In a first aspect, the present invention provides a process operable using a computerized system for providing output data indicative of a geometry of a spinal region of a body of a subject for spinal alignment correction, the process comprising the steps of: (i) detecting a body landmark of the subject from a three-dimensional point cloud model of a body surface of a spinal region of the subject, wherein the body landmark is a landmark indicative of a spinal anatomical landmark of the subject; (ii) determining a spinal correction of the subject, wherein the spinal correction provides a spinal alignment correction for the subject, and (iii) generating a corrected three-dimensional point cloud model of the spinal region of the subject, wherein the corrected three-dimensional point cloud model is generated based on the spinal correction of the subject and the three-dimensional point cloud model of the surface of the spinal region of the subject, wherein the corrected three-dimensional model comprises output data indicative of a geometry of a surface of the body of the subject comprising the body landmark of the subject for the spinal alignment correction of the subject, and wherein the body landmark from the three-dimensional point cloud model of the body surface of the spinal region of the subject and the anatomical landmark of the subject are moved during the generation of the corrected three-dimensional point cloud model of the spinal region of the subject.

[0016] The three-dimensional point cloud model of the spinal region of the subject can be generated from one or more data input sets, wherein each data input set of the one or more data input sets is indicative of an optical image of the subject, and wherein the optical image is a three-dimensional optical image indicative of a geometry of the spinal region of the subject. The optical image can be a red, green, blue and depth (RGBD) image.

[0017] The three-dimensional point cloud model can be generated using one data set from one corresponding three-dimensional optical image of the spinal region of the subject. The one three-dimensional optical image can be a posteroanterior (PA) three-dimensional optical image of the spinal region of the subject.

[0018] The three-dimensional point cloud model can be generated using three data sets from three corresponding three-dimensional optical images of the spinal region of the subject. The three-dimensional optical images of the spinal region of the subject are preferably posteroanterior (PA), left (Lt) and right (Rt) three-dimensional optical images of the spinal region of the subject.

[0019] The spinal correction of the subject can be determined from the three-dimensional point cloud model of the spinal region of the subject.

[0020] The subject's spinal correction can be determined from anatomical landmarks of the subject's spine from one or more medical images of the subject's spine region. The one or more medical images can be one or more X-ray images of the subject's spine region.

[0021] The one or more medical images can be anteroposterior (AP) X-ray images of the subject's spine region to provide two-dimensional (2D) spinal alignment correction of the subject's spine. The one or more medical images are anteroposterior (AP) X-ray images and lateral (LAT) X-ray images of the subject's spine region to provide three-dimensional (3D) spinal alignment correction of the subject's spine.

[0022] The subject's body landmarks detected from the three-dimensional point cloud model of the surface of the subject's spine region can be detected by a pre-trained artificial intelligence (AI) component. The body landmark positions detected by the pre-trained artificial intelligence (AI) component can be further reviewed by one or more human operators and fine-tuned if needed.

[0023] The spinal correction for the subject's spinal alignment correction is determined by assigning one or more of a twist, a back balance, and a spinal curve correction by the one or more human operators.

[0024] The corrected three-dimensional point cloud model of the surface of the subject's spine region can be provided by a pre-trained artificial intelligence (AI) unit from the three-dimensional point cloud model of the surface of the subject's spine region and the body landmark positions, and can optionally further include fine-tuning by the one or more human operators by assigning one or more of a twist, a back balance, and a spinal curve correction.

[0025] The output data indicative of the geometric configuration of the spinal region of the surface of the subject's body for the spinal alignment correction is indicative of the geometric configuration of an orthosis for providing the spinal alignment correction to the subject.

[0026] In a second aspect, the present application provides a computerized system for providing output data indicative of a geometry of a spinal region of a subject's body for spinal alignment correction. The system includes a geometry optimization component for detecting a geometry of a body landmark of the subject from a three-dimensional point cloud model of a body surface of the spinal region of the subject, wherein the body landmark is a landmark indicative of a spinal anatomical landmark; the geometry optimization is for generating a corrected three-dimensional point cloud model of the spinal region of the subject, wherein the corrected three-dimensional point cloud model is generated based on a spinal correction of the subject and based on the three-dimensional point cloud model of the surface of the spinal region of the subject, wherein the spinal correction provides a spinal alignment correction of the subject, wherein the corrected three-dimensional model includes output data indicative of a geometry of the spinal region of the surface of the subject's body including the body landmark for the spinal alignment correction of the subject, and wherein the body landmark from the three-dimensional point cloud model of the body surface of the spinal region of the subject and the anatomical landmark of the subject's spine are moved during the generation of the corrected three-dimensional point cloud model of the spinal region of the subject.

[0027] The system can include a point cloud generation component for generating the three-dimensional point cloud model of the spinal region of the subject from one or more data input sets, wherein each data input set of the one or more data input sets is indicative of an optical image of the subject, and wherein the optical image is a three-dimensional optical image indicative of a geometry of the spinal region of the subject. The optical image can be a red, green, blue, and depth (RGBD) image.

[0028] The three-dimensional point cloud model can be generated using one data set from one corresponding three-dimensional optical image of the spinal region of the subject. The one three-dimensional optical image can be a posteroanterior (PA) three-dimensional optical image of the spinal region of the subject.

[0029] The three-dimensional point cloud model can be generated using three data sets from three corresponding three-dimensional optical images of the spinal region of the subject. The three-dimensional optical images of the spinal region of the subject can be posteroanterior (PA), left (Lt), and right (Rt) three-dimensional optical images of the spinal region of the subject.

[0030] The spinal correction of the subject is determined from the three-dimensional point cloud model of the spinal region of the subject.

[0031] The spinal correction of the subject can be determined from one or more medical images of the spinal region of the subject. The one or more medical images can be one or more X-ray images of the spinal region of the subject.

[0032] The one or more medical images can be anteroposterior (AP) X-ray images of the spinal region of the subject to provide a two-dimensional (2D) spinal alignment correction of the subject's spine.

[0033] The one or more medical images can be anteroposterior (AP) and lateral (LAT) X-ray images of a spinal region of the subject to provide a three-dimensional (3D) spinal alignment correction of the subject's spine.

[0034] The body landmarks of the subject detected from the three-dimensional point cloud model of the surface of the spinal region of the subject can be detected by a pre-trained artificial intelligence (AI) component.

[0035] The system can further include a user interface such that the corrected anatomical landmark positions detected by the pre-trained artificial intelligence (AI) component are further reviewed by one or more human operators for fine tuning if needed. The spinal correction for the spinal alignment correction of the subject can be determined by assigning one or more of a twist, a back balance, and a spinal curve correction by the one or more human operators.

[0036] The system can further include a pre-trained artificial intelligence (AI) unit, wherein the corrected three-dimensional point cloud model of the surface of the spinal region of the subject is provided by the pre-trained artificial intelligence (AI) unit from the three-dimensional point cloud model of the surface of the spinal region of the subject and the body landmark positions.

[0037] The system can further include another user interface for fine tuning by one or more human operators by assigning one or more of a twist, a back balance, and a spinal curve correction.

[0038] The system can further include an output interface for outputting the data indicative of the geometry of the spinal region of the surface of the body of the subject for the spinal alignment correction, the data being indicative of the geometry of an orthosis for providing the spinal alignment correction to the subject.

[0039] In a third aspect, the present application also provides a process operable using a computerized system that determines the mechanical properties of an orthosis for correction of spinal alignment of a subject. The process comprises the following steps: (i) receiving a three-dimensional model of a body surface of a spinal region of a subject and receiving a corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the corrected three-dimensional model is generated from the three-dimensional model and comprises output data indicative of the geometric configuration of the body surface of the spinal region of the subject for correction of spinal alignment; (ii) generating a numerical mechanical analysis model of the three-dimensional model of the orthosis and the corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the three-dimensional model of the orthosis is generated from the corrected three-dimensional model of the body surface of the spinal region of the subject, and wherein the mechanical properties of the orthosis comprise relative density; (iii) determining displacements of points of the corrected three-dimensional model from the three-dimensional model of the body surface of the spinal region of the subject; (iv) determining a strain energy of the orthosis from the displacements of step (iii) and varying a relative density distribution of the orthosis until a predetermined threshold of the strain energy is met and until a predetermined threshold of the relative density is met; (v) generating a topology of the orthosis based on the relative density distribution; and outputting an optimized model of the orthosis upon meeting the predetermined threshold of the relative density.

[0040] The relative density distribution of the orthosis is preferably a porosity distribution of the orthosis. The porosity distribution can be a non-uniform porosity distribution based on the topology optimization results of the subject.

[0041] The three-dimensional model of the body surface of the spinal region of the subject can be a three-dimensional point cloud model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional point cloud model.

[0042] Alternatively, the three-dimensional model of the body surface of the spinal region of the subject can be a three-dimensional mesh model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional mesh model.

[0043] Alternatively, the three-dimensional model of the body surface of the spinal region of the subject can be a three-dimensional volume model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional volume model.

[0044] The mechanical properties of the orthosis can be determined by the process of the present aspect, and wherein the geometric configuration of the orthosis is based on the corrected three-dimensional model of the body surface of the spinal region of the subject.

[0045] At least a portion of the orthosis can be formed by an additive manufacturing technique. At least a portion of the orthosis can be monolithic.

[0046] At least a portion of the orthosis can be formed from a polymeric material. At least a portion of the orthosis can be formed from polyurethane (PE).

[0047] In a fourth aspect, the present application provides a computerized system for determining mechanical properties of an orthosis for correction of spinal alignment of a subject, the system comprising an input interface for receiving a three-dimensional model of a body surface of a spinal region of a subject and for receiving a corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the corrected three-dimensional model is generated from the three-dimensional model and comprises output data indicative of a geometric configuration of the body surface of the spinal region of the subject for spinal alignment correction; and a processor unit for generating a numerical mechanical analysis model of a three-dimensional model of an orthosis and the corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the three-dimensional model of the orthosis is generated from the corrected three-dimensional model of the body surface of the spinal region of the subject, and wherein the mechanical properties of the orthosis comprise relative density; determining displacement of points of the corrected three-dimensional model from the three-dimensional model; and determining strain energy of the orthosis from the displacement, for varying a relative density distribution of the orthosis until a predetermined threshold of strain energy is met and until a predetermined threshold of relative density is met; and for generating a topology of the orthosis based on the relative density distribution, and outputting an optimized model of the orthosis when the predetermined threshold of relative density is met.

[0048] The relative density distribution of the orthosis is preferably a porosity distribution of the orthosis. The porosity distribution can be a non-uniform porosity distribution based on the topology optimization results of the subject.

[0049] The three-dimensional model of the body surface of the spinal region of the subject can be a three-dimensional point cloud model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional point cloud model.

[0050] Alternatively, the three-dimensional model of the body surface of the spinal region of the subject can be a three-dimensional mesh model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional mesh model.

[0051] Alternatively, the three-dimensional model of the body surface of the spinal region of the subject can be a three-dimensional volume model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional volume model.

[0052] The optimized model of the orthosis can be outputted when the predetermined threshold of relative density is met, and wherein the geometric configuration of the orthosis is based on the corrected three-dimensional model of the body surface spinal region of the subject.

[0053] In a fifth aspect, the present application provides a computerized system for determining the mechanical properties of an orthosis for correction of spinal alignment of a subject, the system comprising an input interface for receiving a three-dimensional model of a body surface of a spinal region of a subject and for receiving a corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the corrected three-dimensional model is generated from the three-dimensional model and comprises output data indicative of the geometry of the body surface of the spinal region of the subject for spinal alignment correction; a displacement calculation unit for calculating the displacement of each point in the three-dimensional model of the spinal region of the subject and in the corrected three-dimensional model of the spinal region of the subject; a meshing unit for generating a three-dimensional model of an orthosis from the corrected three-dimensional model of the spinal region of the subject; a numerical analysis unit for a mechanical simulation of the orthosis, wherein the numerical analysis unit performs the mechanical simulation based on the three-dimensional model of the orthosis, the displacement of each point in the three-dimensional model and the mechanical properties of the orthosis comprising relative density; a topology optimization unit for demonstrating a topology optimization of the model of the orthosis based on the results from the numerical analysis unit and for providing an optimized relative density of the orthosis when a predetermined threshold of strain energy is met and a predetermined threshold of relative density is met.

[0054] The relative density distribution of the orthosis is preferably a porosity distribution of the orthosis. The porosity distribution can be a non-uniform porosity distribution based on the topology optimization results of the subject.

[0055] The three-dimensional model of the body surface of the spinal region of the subject can be a three-dimensional point cloud model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional point cloud model.

[0056] Alternatively, the three-dimensional model of the body surface of the spinal region of the subject can be a three-dimensional mesh model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional mesh model.

[0057] Alternatively, the three-dimensional model of the body surface of the spinal region of the subject is a three-dimensional volume model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional volume model.

[0058] The system can further comprise a fine-tuning unit for mesh smoothing and gap repair of the mesh.

[0059] In a sixth aspect, the present application provides an orthosis for correction of spinal alignment of a subject, wherein the orthosis has a relative density determined by a process comprising the steps of: (i) receiving a three-dimensional model of a spinal region of a subject and receiving a corrected three-dimensional model of the spinal region of the subject, wherein the corrected three-dimensional model is generated from the three-dimensional model and comprises output data indicative of a geometric configuration of the spinal region of the subject's body for spinal alignment correction; (ii) generating a numerical mechanics analysis model of the three-dimensional model of the orthosis and the corrected three-dimensional model of the spinal region of the subject, wherein the three-dimensional model of the orthosis is generated from the corrected three-dimensional model of the spinal region of the subject, and wherein the mechanical properties of the orthosis comprise a relative density; (iii) determining displacements of points of the corrected three-dimensional model from the three-dimensional model; (iv) determining a strain energy of the orthosis from the displacements at step (iii) and varying a relative density distribution of the orthosis until a predetermined threshold of the strain energy is met and until a predetermined threshold of the relative density is met; wherein a topology of the orthosis is based on the relative density distribution, and wherein a geometric configuration of the orthosis is based on the corrected three-dimensional model of the body surface of the spinal region of the subject.

[0060] The relative density distribution of the orthosis is preferably a porosity distribution of the orthosis. The porosity distribution can be a non-uniform porosity distribution based on the topology optimization results of the subject.

[0061] At least a portion of the orthosis can be formed by an additive manufacturing technique. At least a portion of the orthosis can be monolithic.

[0062] At least a portion of the orthosis can be formed from a polymeric material. At least a portion of the orthosis can be formed from polyurethane (PE).

[0063] The three-dimensional model of the body surface of the spinal region of the subject can be a three-dimensional point cloud model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional point cloud model.

[0064] Alternatively, the three-dimensional model of the body surface of the spinal region of the subject can be a three-dimensional mesh model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional mesh model.

[0065] Alternatively, the three-dimensional model of the body surface of the spinal region of the subject is a three-dimensional volume model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional volume model.

[0066] In a seventh aspect, the present application provides a process operable using a computerized system for providing output data indicative of a geometry of a spinal region of a body of a subject for a spinal alignment correction and determining mechanical properties of an orthosis for a correction of a spinal alignment of the subject, the process comprising the steps of: (i) detecting a body landmark of the subject from a three-dimensional point cloud model of a body surface of a spinal region of the subject, wherein the body landmark is a landmark indicative of an anatomical landmark of a spine of the subject; (ii) determining a spinal correction of the subject, wherein the spinal correction provides a spinal alignment correction of the subject; (iii) generating a corrected three-dimensional point cloud model of the spinal region of the subject, wherein the corrected three-dimensional point cloud model is generated based on the spinal correction of the subject and the three-dimensional point cloud model of the surface of the spinal region of the subject, wherein the corrected three-dimensional model comprises output data indicative of a geometry of the surface of the body of the subject comprising the body landmark of the subject for the spinal alignment correction of the subject, and wherein the body landmark from the three-dimensional point cloud model of the body surface of the spinal region of the subject and the anatomical landmark of the spine of the subject are moved during the generation of the corrected three-dimensional point cloud model of the spinal region of the subject; (iv) receiving a three-dimensional model of the body surface of the spinal region of the subject and receiving a corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the corrected three-dimensional model is generated from the three-dimensional model and comprises output data indicative of a geometry of the body surface of the spinal region of the body of the subject for a spinal alignment correction; (v) generating a numerical mechanics analysis model of a three-dimensional model of an orthosis and the corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the three-dimensional model of the orthosis is generated from the corrected three-dimensional model of the body surface of the spinal region of the subject, and wherein the mechanical properties of the orthosis comprise a relative density; (vi) determining a displacement of a point of the corrected three-dimensional model from the three-dimensional model of the body surface of the spinal region of the subject; (vii) determining a strain energy of the orthosis from the displacement at step (vi) and varying a relative density distribution of the orthosis until a predetermined threshold of the strain energy is met and until a predetermined threshold of the relative density is met; and (vii) generating a topology of the orthosis based on the relative density distribution; and outputting an optimized model of the orthosis upon meeting the predetermined threshold of the relative density.

[0067] In an eighth aspect, the present application provides an orthosis for a correction of a spinal alignment of a subject, wherein a geometry of a spinal region of a body of the subject for a spinal alignment correction and mechanical properties of the orthosis for the correction of the spinal alignment of the subject are determined by a process according to the seventh aspect.

[0068] The relative density distribution of the orthosis is preferably a porosity distribution of the orthosis. The porosity distribution can be a non-uniform porosity distribution based on the topology optimization results for the subject.

[0069] At least a portion of the orthosis can be formed by an additive manufacturing technique. At least a portion of the orthosis can be monolithic.

[0070] At least a portion of the orthosis can be formed from a polymeric material. At least a portion of the orthosis can be formed from polyurethane (PE). BRIEF DESCRIPTION OF DRAWINGS

[0071] In order that a more precise understanding of the above-described application can be obtained, a more particular description of the application will be rendered by reference to specific embodiments thereof, which are illustrated in the appended drawings.

[0072] The drawings presented herein can not be drawn to scale, and any reference to dimensions in the drawings or the following description are specific to the disclosed embodiments.

[0073] Figure 1a A schematic view showing an exemplary embodiment of the overall system according to the application is shown;

[0074] Figure 1b A schematic view showing another exemplary embodiment of the overall system according to the application is shown;

[0075] Figure 1c A schematic view showing yet another exemplary embodiment of the overall system according to the application is shown;

[0076] Figure 2a(i) shows a general flow chart of the process of generating a three-dimensional optimization of an orthosis according to the application;

[0077] Figure 2a(ii) shows a general system for generating a three-dimensional optimization of an orthosis according to the application;

[0078] Figure 2b(i) shows a schematic view of an embodiment of an initial 3D model generation component according to the application.

[0079] Figure 2b(ii) shows a schematic view of an embodiment of a geometry configuration optimization component according to the application;

[0080] Figure 2c(i) shows a top view of a twist correction according to an embodiment of the application;

[0081] Figure 2c(ii) shows a side view of a twist correction according to an embodiment of the application;

[0082] Figure 2c(iii) shows a back view of a back balance according to an embodiment of the application;

[0083] Figure 2c(iv) shows a back view of the back balancing, according to an embodiment of the application;

[0084] Figure 2c(v) shows a back view of the back balancing, according to an embodiment of the application;

[0085] Figure 2d(i) shows a back view of the spine curve correction, according to an embodiment of the application;

[0086] Figure 2d(ii) shows a side view of the spine curve correction, according to an embodiment of the application;

[0087] Figure 2d(iii) shows a top view of the spine curve correction, according to an embodiment of the application;

[0088] Figure 3a(i) shows a general flowchart of the process of determining the mechanical properties of the orthosis for the correction of the spinal alignment of a subject, according to the present application;

[0089] Figure 3a(ii) shows a general system for determining the mechanical properties of the orthosis for the correction of the spinal alignment of a subject, according to the present application;

[0090] Figure 3b(i) shows a flowchart of an embodiment of the process of biomechanical optimization component, according to the present application;

[0091] Figure 3b(ii) shows a schematic of the embodiment of Figure 3b(i);

[0092] Figure 3b(iii) shows a representative volume element (RVE) in homogenization simulation;

[0093] Figure 4 is a flowchart representation of an embodiment of the steps of the present application for optimizing a body brace;

[0094] Figure 5 is a flowchart of the steps for optimizing a body brace of an embodiment of the present application;

[0095] Figure 6 shows an example of processing a point cloud of a back surface reconstruction of an embodiment of Figure 5

[0096] Figure 7 shows a first step of the process of a point cloud of a back surface reconstruction to an automatic mesh of an embodiment of Figure 5

[0097] Figure 8 shows a representation of a second step of the results of a point cloud of a back surface reconstruction to an automatic mesh of an embodiment of Figure 5

[0098] Figure 9 shows the refitting of a sub-zone mesh to​​​Figure 5 third step of the process of back surface reconstruction of the entire surface of the embodiment of

[0099] Figure 10 shows Figure 5 fourth step of the process of fitting control points to the surface of the back surface reconstruction of the embodiment of

[0100] Figure 11a and Figure 11b shows the process of calibrating all point clouds in the embodiment of the invention;

[0101] Figure 11c shows a perspective view of the reference plane with respect to Figure 11a and 11b

[0102] Figure 12 is a graphical representation of the result after 20000 iterations of the final fitting plane of the embodiment of Figures 11a-11c

[0103] Figure 13a shows a perspective view of the results of obtaining 2684 human back surface reconstructions and spine curves in the example of the invention;

[0104] Figure 13b shows a lateral view of the results of obtaining 2684 human back surface reconstructions and spine curves of the embodiment of Figure 13a

[0105] Figure 13c shows a top view of the results of obtaining 2684 human back surface reconstructions and spine curves of the embodiment of Figure 13a and 13b;

[0106] Figure 14 shows an example of correcting the point cloud of the example;

[0107] Figure 15a is a graphical representation of the spine curve (Naen) fitted to the spine curve (Sentin) obtained from the extreme points of the profile of the point cloud of the example;

[0108] Figure 15b is a graphical representation of the target spine curve of the example;

[0109] Figure 16 is a graphical representation of the corrected target point cloud of the example;

[0110] Figure 17a shows the mesh created by ABAQUS for the analysis of the example for static analysis and optimization;

[0111] Figure 17b ​​​shows a mesh created by Hypermesh for use in static analysis and optimization;

[0112] Figure 18a Shown is a manually adjusted mesh with control regions and points for static analysis and optimization;

[0113] Figure 18b A manually adjusted mesh with a mesh size of 10 with quadrilateral elements for static analysis and optimization is shown;

[0114] Figure 19a shows the calculation of nodal reaction forces according to the modified spinal curve;

[0115] Figure 19b An optimization model with node loads is shown;

[0116] Figure 20a The boundary conditions at the top, left and right, and bottom are shown respectively;

[0117] Figure 20b Results for nodal reactions extracted as nodal loads are shown;

[0118] Figure 21a shows the results of deformation during static analysis;

[0119] Figure 21b shows the results of stress during static analysis;

[0120] Figure 22a shows the results of deformation during the optimization process;

[0121] Figure 22b shows the results of stress during the optimization process;

[0122] Figures 23a-23d shows the results of the penalty method according to the present invention with different iterations for a solid isotropic material;

[0123] Figure 24a Boundary conditions with fixed top boundary and static analysis are shown;

[0124] Figure 24b Shown is a reference Figure 24a Boundary conditions with a fixed reference rotation point;

[0125] Figure 25a Shown in three dimensions Figure 24a and 24b The stress results during the static analysis;

[0126] Figure 25b Shown in three dimensions Figure 24a and 24bthe results of the deformation in the static analysis process;

[0127] Figure 26a the total strain energy is shown for different minimum densities;

[0128] Figure 26b the table representation of Figure 26a ;

[0129] Figure 27a the volume ratio is shown for different minimum densities;

[0130] Figure 27b the table representation of Figure 27a ;

[0131] Figures 28a-28d the material density distribution is shown for different minimum densities;

[0132] Figures 29a-29d the stress distribution is shown for different minimum densities;

[0133] Figures 30a-30d the deformation distribution is shown for different minimum densities;

[0134] Figure 31 a flow chart showing the optimization of the python script in the example of the embodiment of the invention is shown;

[0135] Figure 32a boundary conditions for the fitting of the element material properties (E and nu) in this example are shown;

[0136] Figure 32b the undeformed and deformed results of the fitting of the element material properties in this example and with respect to Figure 32a are shown;

[0137] Figure 32c the case generation for the fitting of the element material properties in this example and with respect to Figure 32a and 32b are shown;

[0138] Figure 33a the results of the curve fitting in this example are shown;

[0139] Figure 33b the results of the curve fitting updated with the optimization method are shown. In this embodiment and with reference to Figure 33a ;

[0140] Figure 34a preliminary results for the relative density of a cantilever beam in 2D are shown;

[0141] Figure 34b preliminary results for the stress of a cantilever beam are shown;

[0142] Figure 34c Preliminary results of the deformation of the cantilever beam are shown;

[0143] Figure 35a Preliminary results of the relative density of the cylindrical element embodiment according to the present application are shown;

[0144] Figure 35b Preliminary results of the stress of the cylindrical element example according to the present application and with reference to Figure 35a ;

[0145] Figure 35c Preliminary results of the deformation of the cylindrical element example according to the present application and with reference to Figure 35a and 35b ;

[0146] Figure 36a Flowchart of the python script for the automatic reconstruction of the model in an embodiment of the present application is shown;

[0147] Figure 36b Example of pre-processing of the ODB file is shown.

[0148] Figure 36c Example of.stl file is shown.

[0149] Figure 37a Model and BC (Boundary Conditions) of the cylindrical rigid body are shown;

[0150] Figure 37b Mesh of the cylindrical rigid body of Figure 37a is shown;

[0151] Figure 38a Displacement distribution of the cylindrical rigid body of Figure 37a and 37b is shown;

[0152] Figure 38b Stress distribution of the cylindrical rigid body of Figure 37a , 37b and 38a to Figure 38c is shown; and

[0153] Figure 38c Relative density distribution of the cylindrical rigid body of Figure 37a , 37b and 38a and 38b is shown. DETAILED DESCRIPTION

[0154] The inventors have recognized the drawbacks of the orthoses of the prior art and, in recognition of the problems of the prior art, have provided a process and system for designing a spinal orthosis device that overcomes the problems of the prior art.

[0155] 1. Background explanation of the invention

[0156] The present inventors have noted the limitations of orthoses such as the prior art spinal braces and have sought to provide a process and system for designing orthoses which addresses the shortcomings exhibited by prior art orthoses.

[0157] It must be understood that although the exemplary embodiments depicted and described are in relation to embodiments of orthoses, in particular spinal braces, the present invention is not limited to such embodiments of such devices and is applicable to other and alternative orthoses.

[0158] 2. Correction device

[0159] Orthotic devices can be used to align and manipulate the body of a subject, however, for the purposes of illustration, the most commonly used orthosis in the context of the present invention is a spinal brace.

[0160] Such braces are attached to the subject for a portion of the day, as known in the art, for gradual manipulation and realignment and positioning of the body, in particular the spine of the subject.

[0161] 2.1. Idiopathic scoliosis

[0162] Idiopathic scoliosis is the most common type of spinal deformity occurring in children at the onset of puberty and it has a prevalence of up to 5.2%, known as adolescent idiopathic scoliosis (AIS).

[0163] Consequences of idiopathic scoliosis include severe developmental problems, severe cardiorespiratory complications, etc.

[0164] 2.2. Current methods for AIS management

[0165] For the treatment of idiopathic scoliosis, decisions are currently made mainly by assessing the severity of the spinal deformity assessed by the Cobb angle.

[0166] Treatment of AIS is generally done according to the severity defined by the Cobb angle: follow-up (mild AIS, Cobb angle 10°-25°); non-surgical management (moderate AIS, Cobb angle 25°-45°); surgery (severe AIS, Cobb angle >45°).

[0167] Spinal orthotic management is the most common and effective non-surgical modality for preventing curve progression by providing an external corrective force to the patient's torso.

[0168] 2.3. Conventional manual manufacturing methods are

[0169] Conventional manual manufacturing methods are:

[0170] (i) manually forming a negative cast model from the subject's body;

[0171] (ii) producing a positive cast using a milling machine with a polymer material such as polyurethane material (PE);

[0172] (iii) manually correcting the positive cast; and

[0173] (iv) manually molding the polymer material over the positive cast to form the orthosis

[0174] 2.4. Disadvantages of conventional manual manufacturing methods

[0175] Disadvantages of conventional manual manufacturing methods include lack of specific customization accuracy to the subject's complaint, laborious, time consuming and costly to produce, and often not specifically adapted to the subject's specific requirements.

[0176] Furthermore, such orthosis devices such as spinal braces can not necessarily provide the necessary load at the necessary areas on the subject for the orthotic manipulation of the spine, and excessive load in one position can cause damage to the skin tissue of the subject and inadequate manipulation for the necessary clinical outcome.

[0177] Similarly, insufficient load to the necessary areas will result in inadequate, incorrect or substandard manipulation and clinical outcome. SUMMARY

[0178] In a broad aspect, the present invention relates to a process and system for designing and optimizing orthosis-type devices.

[0179] The process includes utilizing the novel aspects of the present invention which form at least a portion of the device which has been formed and provided so as to have the necessary mechanical structural properties in order to provide the necessary biomechanical load to the subject.

[0180] The main structural element is preferably monolithic, and the monolithic structural element is preferably formed by an additive process, and preferably from a polymer material such as polyurethane (PE).

[0181] The monolithic structural element can be considered or alternatively referred to as a "non-periodic material design (AMD)" with a solid isotropic material.

[0182] The present invention provides orthosis-type devices with the necessary mechanical properties to meet the biomechanical requirements, whereby the orthosis-type devices include such monolithic structural elements for which the design is optimized such that the orthosis-type devices have the necessary mechanical properties to provide the necessary biomechanical goals.

[0183] Thus, the overall structural material element of such devices is optimized by an analytical approach and is accordingly formed to meet the biomechanical objectives and is provided in the form of an anisotropic graded density lattice material.

[0184] At any portion of the element, the mechanical properties of the monolithic structural element are determined by the relationship between the material mechanical properties (stiffness modulus and failure component) of the monolithic structural element and the anisotropic lattice cell architecture (relative density and anisotropy) and are also a function of the geometric properties of the monolithic structural element.

[0185] It should be noted that the monolithic structural element for such orthotic type devices can be custom designed based on specific patient requirements typically for patient type design, as well as having non-patient specific but size dependent or size independent general configurations and designs.

[0186] Thus, with respect to the embodiments of the inventive aspects of the present application, no assumptions or inclusions regarding limitations on applications or embodiments should be made or introduced, the embodiments of the inventive aspects of the present application are to provide monolithic structural elements having an anisotropic graded density lattice material required to meet the necessary biomedical objectives.

[0187] In the case of such orthotic devices, for example, a spinal brace, the optimization of the mechanical properties of the monolithic material structural element can be to provide the necessary loads to the subject's spine for repair and therapeutic purposes, such as in the case of a patient with a scoliosis.

[0188] 4. The invention - summary

[0189] The present application provides a process and system for designing and optimizing orthotic type devices.

[0190] Reference is made to Figure 1a , providing an exemplary embodiment of the entire system 1000 according to the present application as shown.

[0191] The system 1000 comprises:

[0192] (i) an initial point cloud component 100,

[0193] (ii) a geometric configuration optimization component 200, and

[0194] (iii) a biomechanical optimization component 300.

[0195] The initial point cloud component 100 receives red, green, blue and depth (RGBD) data indicative of images from different views of the subject, for example images that have been acquired by a depth camera such as by an RGBD camera, for example posterior-anterior, left and right views (PA, Lt, Rt) indicative of a spinal region of the subject. Such data can be acquired by an image acquisition device such as a depth camera.

[0196] The initial point cloud component 100 generates an initial three-dimensional (3D) point cloud of the subject’s body from the RGBD data.

[0197] The geometric configuration optimization component 200 then determines the necessary geometric configuration of the orthosis for the corrective alignment of the subject’s spine for the treatment purpose of the spinal alignment correction. This can be done for example by artificial intelligence (AI) or manually.

[0198] The biomechanics optimization component 300 then optimizes the design of the orthosis so as to achieve the necessary biomechanical parameters to cause the subject’s body to make the necessary spinal alignment.

[0199] The final optimized orthosis model provided by the biomechanics optimization component 300 can be manufactured for example by 3D printing.

[0200] As will be appreciated and understood by the skilled person, when providing a corrective measure for the intervention corrective alignment of the subject’s spine by a spinal orthosis, this is inevitably done typically over a number of months in a number of alignment steps.

[0201] Accordingly, the geometric configuration optimization component 200 will typically provide a first required geometric configuration of the focus of manipulation and alignment of the subject’s spine for a first step in a series of progressive alignment steps.

[0202] It will be appreciated that for the first step of spinal alignment, the degree or amount of alignment provided will depend on the subject as well as the clinical parameters relevant to that particular subject, and such decisions are typically made by a spinal specialist surgeon or clinician.

[0203] When satisfactory progress is made in the alignment of the subject’s spine, after the necessary time, the process can be repeated and updated RGBD images of the subject’s spine are acquired and an updated design of the optimized biomechanics orthosis is determined for the next stage of alignment.

[0204] The system can then repeat the process and clinical assessment until satisfactory clinical results are achieved.

[0205] The skilled person will also appreciate that the present invention can select an orthosis of predetermined biomechanical properties from such a library of orthoses appropriately, or can provide for the manufacture of a custom orthosis for a particular subject.

[0206] Reference is now made to Figure 1b , which is substantially identical to the system 1050 of Figure 1a , however, in addition to receiving RGBD data of the subject's spinal region, the initial point cloud component 100 also receives data indicative of one or more corresponding X-ray images of the subject.

[0207] As will be appreciated, the one or more corresponding X-ray images should be sufficient to provide the necessary clinical data for determining the geometry of the orthosis to meet the necessary alignment parameters.

[0208] It should thus be noted that this step or aspect of utilizing X-ray data of the subject is optional and in embodiments of the present application, the process and system can:

[0209] (i) not use X-rays, for example, with reference to Figure 1a ,

[0210] (ii) use only one X-ray image, for example, an anteroposterior (AP) X-ray,

[0211] (iii) use more than one X-ray image for anteroposterior (AP) and lateral (LAT) X-rays.

[0212] In the present embodiment, the optimized geometry is determined by both the subject's RGBD data as well as the X-ray data. In other embodiments, ways in which this can be provided are discussed in further detail below.

[0213] Reference is now made to Figure 1c , which shows another embodiment of the system 1100 of the present application, wherein the system 1100 comprises the following:

[0214] - a first input interface 001 to receive RGBD (red, green, blue and depth) images from an image acquisition device;

[0215] - a second input interface I / O 002 to receive X-ray images;

[0216] - an output interface I / O 003 for transmitting the optimized orthosis model, for example, by a three-dimensional (3D) printer for subsequent manufacturing;

[0217] - a first user interface UI 004 for receiving manual fine-tuning and confirmation for landmarking and spinal alignment detection from a spine specialist clinician;

[0218] - a second user interface UI 005 for receiving manual fine-tuning and confirmation for geometry optimization from a corrector;

[0219] - initial point cloud (PC) 3D model generation component 100;

[0220] - geometry configuration optimization component 200;

[0221] - biomechanics optimization component 300; and

[0222] - artificial intelligence (AI) component 400.

[0223] As an example, in embodiments of the present invention, the method of the present invention used in the above described system comprises the following steps:

[0224] (i) a first input interface 001 receives red, green, blue and depth (RGBD) images from different views of the subject, for example posterior, left and right views (PA, Lt, Rt) from image acquisition devices, which are indicative of the subject's spinal region;

[0225] (ii) a second input interface 002 receives corresponding X-ray images of the subject. It should be noted that such a step is optional and in embodiments of the present invention, the process and system can (i) not use X-rays, (ii) use only anteroposterior (AP) X-rays, (3) use both anteroposterior (AP) and lateral (LAT) X-rays, and all such embodiments are considered to fall within the scope of the present invention;

[0226] (iii) an initial point cloud (PC) 3D model generation component 100 receives data S1 indicative of the (RGBD) images from different views of the subject, and receives data S2 indicative of the X-ray data of the subject; and

[0227] (iv) an initial 3D point cloud of the subject's body is generated by the initial point cloud (PC) 3D model generation component 100, and data S9 indicative of said initial 3D point cloud of the subject's body is received by the geometry configuration optimization component 200.

[0228] (v) the geometry configuration optimization component 200 then determines the necessary geometry of an orthosis for the corrective alignment of the subject's spine for the treatment purpose of spinal alignment correction.

[0229] (vi) the biomechanics optimization component 300 then optimizes the design of the orthosis so as to achieve the necessary biomechanical parameters to cause the subject's body to make the necessary spinal alignment.

[0230] (vii) a final optimized orthosis model (for example in STL or CAD format) is provided by the biomechanics optimization component 300, which can be directly 3D printed.

[0231] In an embodiment of the present invention, the spine expert clinician provides manual fine-tuning and confirmation for landmark and spinal alignment detection s4 via the first user interface 004 , and the corrector provides manual fine-tuning and confirmation for geometry optimization s5 via the second user interface 005 .

[0232] An artificial intelligence (AI) component 400 may optionally be used for AI landmark and spinal alignment detection results s6, and for manually fine-tuning and confirming landmark and spinal alignment detection results for further AI model optimization s8.

[0233] An artificial intelligence (AI) component 400 may optionally be used for the AI ​​geometry optimization results s7 and a geometry-optimized 3D model of the orthosis s10. Alternatively, this may be done manually or semi-manually, for example with a pre-existing database to be accessed.

[0234] 5. Geometry optimization

[0235] 2a(i), there is shown a generalized flow chart of a process 200a for generating a three-dimensional optimization of an orthosis according to the present invention.

[0236] The process 200a can be operated using a computerized system for providing output data indicative of the geometry of a spinal region of a subject's body for spinal alignment correction.

[0237] Process 200a includes the following steps:

[0238] Step (i) 210a

[0239] detecting a body landmark of the subject from a three-dimensional point cloud model of a body surface of a spinal column region of the subject, wherein the body landmark is a landmark indicating an anatomical landmark of the spinal column of the subject;

[0240] Step (ii) 220a

[0241] determining a spinal correction of the subject's spine, wherein the spinal correction provides a spinal alignment correction of the subject, and

[0242] Step (iii) 230a

[0243] generating a rectified three-dimensional point cloud model of the subject's spinal region,

[0244] generating a corrected three-dimensional point cloud model based on the correction of the subject's spine and the three-dimensional point cloud model of the surface of the subject's spinal region,

[0245] The corrected three-dimensional point cloud model comprises output data indicative of a geometry of a spinal region of a surface of a body of the subject including the body landmark for spinal alignment correction of the subject, and

[0246] The body landmark of the three-dimensional point cloud model from a body surface of a spinal region of the subject and the anatomical landmark of the spine of the subject move during generation of the corrected three-dimensional point cloud model of the spinal region of the subject.

[0247] Referring to Figure 2a(ii), there is shown a general computerized system 200b for generating a three-dimensional optimization of an orthosis according to the present application.

[0248] The computerized system 200b provides output data indicative of a geometry of a spinal region of a body of the subject for spinal alignment correction.

[0249] The system 200b comprises a geometry optimization component 210b for detecting a body landmark of the subject from a three-dimensional point cloud model of a body surface of a spinal region of the subject, wherein the body landmark is a landmark indicative of a spinal anatomical landmark;

[0250] The geometry optimization component 210b is for generating a corrected three-dimensional point cloud model of a spinal region of the subject,

[0251] The corrected three-dimensional point cloud model is generated based on a spinal correction of the subject and based on a three-dimensional point cloud model of a surface of a spinal region of the subject, wherein the spinal correction provides a spinal alignment correction of the subject,

[0252] The corrected three-dimensional point cloud model comprises output data indicative of a geometry of a spinal region of a surface of a body of the subject including the body landmark for spinal alignment correction of the subject, and

[0253] The body landmark of the three-dimensional point cloud model from a body surface of a spinal region of the subject and the anatomical landmark of the spine of the subject move during generation of the corrected three-dimensional point cloud model of the spinal region of the subject.

[0254] The three-dimensional point cloud model of a spinal region of a subject can be generated from one or more data input sets, wherein each data input set of the one or more data input sets is indicative of an optical image of the subject, and wherein the optical image is a three-dimensional optical image indicative of a geometry of a spinal region of the subject.

[0255] A spinal correction of the subject can be determined from the three-dimensional point cloud model of a spinal region of the subject.

[0256] Alternatively, the subject's spinal correction can be determined from anatomical landmarks of the subject's spine from one or more medical images of the subject's spine region.

[0257] Determining the subject's spinal correction of the subject's spine can be done according to a rule-based criteria, which is preferably a clinical assessment criteria. The clinical assessment criteria can be a Cobb angle assessment.

[0258] Determining the subject's spinal correction of the subject's spine can be performed by a pre-trained artificial intelligence (AI) engine. The training of the artificial intelligence (AI) engine can be done with the assessment of a clinician (e.g. one or more clinicians), all done through a rule-based interval assessment and learning system, whereby anatomical landmarks are detected by the artificial intelligence (AI) engine and the recognition of rule-based bony protrusions or body landmarks are applied.

[0259] A. Initial 3D model generation - details

[0260] Referring to Figure 2b(i), there is shown an embodiment of a schematic diagram of an embodiment of an initial 3D model generation component 100 according to the present application.

[0261] The initial 3D model generation component 100 can generate an initial 3D point cloud model of a human body S9.

[0262] (1) RGBD images (R: Red, G: Green, B: Blue, D: Depth) from posteroanterior (PA), left (Lt) and right (Rt) views (S1) are acquired from suitable image acquisition devices.

[0263] (2) A RGBD-PC generator 103 can create a 3D point cloud S101 for each acquired RGBD image.

[0264] (3) The 3D point clouds from the 3 different views are registered by a point cloud (PC) registration unit 104 to generate a 3D point cloud of the human body S102.

[0265] (4) The RGBD images from the posteroanterior (PA) view are inputted to a point cloud (PC) landmark detector 102, which can detect anatomical landmarks from the RGBD images, typically by using 6 anatomical landmarks, which indicate the C7 vertebra, the left lower scapula angle, the right lower scapula angle, the left posterior iliac spine, the right posterior iliac spine and the coccyx tip by determining the coordinates of the anatomical landmarks in the RGBD images, and further map the landmarks to the 3D body point cloud (S6-2) based on the coordinates and depth information of each landmark.

[0266] (5) The anatomical landmarks detected by the artificial intelligence (AI) S6-2 are further fine-tuned and / or confirmed by the human expert S4-2, and the confirmed landmarks in the 3D point cloud (S8-2) are sent to the alignment registration unit S105 for further processing, and S8 represents the AI landmark and spinal alignment detection results that are fine-tuned and confirmed by hand.

[0267] (6) The X-ray image / multiple X-ray images S2 are input to the spinal alignment detector 101, which is capable of detecting the center of each vertebra from the X-ray image by determining the coordinates of the center of the vertebra in the X-ray image. The spinal alignment is generally composed of all the vertebra centers, which are the center of the vertebrae from C7 to L5 and the midpoint of the upper endplate of S1.

[0268] It must be noted that it is understood that the present invention can be utilized with or without input of X-ray images, and thus, its input is a preferred embodiment.

[0269] As such, the system and process in relation to the present embodiment can be considered to be capable of operating as three (3) different X-ray image inputs S2 as follows:

[0270] (i) No X-ray image input: no spinal alignment detected; spinal alignment detector 101 is inoperable or even not needed to be part of the system;

[0271] (ii) Only anterior-posterior (AP) X-ray image input: two-dimensional (2D); spinal alignment is detected by the spinal alignment detector 101; or

[0272] (iii) Both AP and lateral (LAT) X-ray image input: three-dimensional (3D) spinal alignment is detected by the spinal alignment detector 101.

[0273] (7) The spinal alignment that can be detected by the artificial intelligence (AI) S6-1 is further fine-tuned and / or confirmed by the human expert S4-1, and the confirmed spinal alignment S8-1 is sent to the alignment registration unit 105 for further processing. The present inventor has developed a deep learning model for spinal alignment detection.

[0274] (8) If X-ray images are input to the system, the spinal alignment (S8-1) is registered to the 3D point cloud of the human body (S102) according to the landmarks (S8-2) by the alignment registration unit (105). Both the spinal alignment (S8-1) and the landmarks (S8-2) contain the center positions of C7 and L5 for registration. The final output is the 3D point cloud of the human body with spinal alignment (S9).

[0275] If the X-ray images are not inputted to the system, no spinal alignment is detected, and the alignment registration unit (105) is not active, the final output is a 3D point cloud of the human body without spinal alignment (S9).

[0276] (9) The artificial intelligence (AI) component 400 contains two AI frameworks:

[0277] (i) for point cloud landmark detection S6-2, and

[0278] (ii) for spinal alignment detection S6-1.

[0279] Landmarks (S8-2) and spinal alignment (S8-1) that are fine-tuned and / or confirmed manually are used to further optimize the AI frameworks.

[0280] B. Geometry optimization using only 3D points (PC - Point Cloud data)

[0281] In embodiments of the present invention, the obstacles for geometric construction optimization are addressed with only RGBD data, without X-ray data, see Fig. 2b (i):

[0282] (i) The RGBD-PC generator 103 will create a 3D point cloud S101 for each view of the RGBD images S1;

[0283] (ii) The point cloud (PC) registration unit (104) will register the 3D point clouds from different views to generate a 3D point cloud of the body of the subject S102;

[0284] (iii) The point cloud (PC) landmark detector 102 will detect anatomical landmarks from the RGBD images S1, and the artificial intelligence (AI) component 400 can optionally be used for anatomical landmark detection. Alternatively, a human operator (e.g. a medical practitioner) can manually determine the position of the landmarks;

[0285] (iv) The alignment registration unit 105 will register the 3D point clouds of the subject S102 and the anatomical landmarks S8-2.

[0286] In case the point cloud data is obtained from other methods or processes, steps (i) and (ii) can be omitted, and the process starts from step (iii).

[0287] C. Geometry optimization using both 3D points (PC - Point Cloud data) and X-ray data

[0288] For point clouds obtained from e.g. RGBD image acquisition devices:

[0289] (i) The RGBD-PC generator 103 will create a 3D point cloud S101 for each view of the RGBD images S1;

[0290] (ii) The PC registration unit 104 will register 3D point clouds from different acquisition views to generate a 3D point cloud of the subject S102;

[0291] (iii) The PC landmark detector 102 will detect landmarks from RGBD images S1 and the AI component 400 is used for landmark detection;

[0292] (iv) The spinal alignment detector 101 can detect spinal alignment from X-rays and the AI component 400 is used for alignment detection; and

[0293] (v) The alignment registration unit 105 will register 3D point clouds of the subject S102, anatomical landmarks S8-2 and spinal alignment S8-1.

[0294] In the case where point cloud data is obtained from other methods or processes, steps (i) and (ii) can be omitted and the process starts from step (iii).

[0295] Artificial intelligence (AI) driven landmark and spinal alignment detection

[0296] Current techniques are typically manual landmark and spinal alignment detection by a spine surgeon, spine specialist or clinician.

[0297] 5.1. Point cloud (PC) landmark detector 102

[0298] According to embodiments of the present invention:

[0299] a. The present inventors have developed and provided a top-to-bottom AI framework for automatic detection of anatomical landmarks.

[0300] b. U-Net++ has been trained to segment the human body region from RGBD images.

[0301] c. HRNet has been further trained to identify the location of anatomical landmarks from the human body region based on RGBD images.

[0302] The key advantage provided by this embodiment of the present invention is to provide faster and more consistent detection results.

[0303] 5.2. Spinal alignment detector 101

[0304] In embodiments of the present invention, in relation to the spinal alignment detector 101:

[0305] a. The present inventors have developed a top-to-bottom AI framework to automatically detect vertebral centers.

[0306] b. U-Net is trained to segment the vertebral region from X-ray images.

[0307] c. The HRNet is further trained to identify the location of the 4 corners of each vertebra based on the X-ray image.

[0308] d. The center of the vertebra can be determined by calculating the center position of the 4 vertebra corners.

[0309] The key advantage provided by this embodiment of the invention is to provide faster and more consistent detection results.

[0310] 6. Geometry optimization

[0311] Referring to Figure 2b (ii), there is shown a schematic diagram of an embodiment of a geometry optimisation component 200 according to the present invention.

[0312] The geometry optimisation component 200 provides:

[0313] (A) manual geometry optimisation (i.e. geometry optimisation without AI), or

[0314] (B) artificial intelligence (AI) assisted geometry optimisation,

[0315] As described in exemplary embodiments of the present invention, a 3D model S10 of the geometry optimisation of the orthosis is generated for the initial 3D point cloud S9 of the human body.

[0316] A. Geometry optimization without artificial intelligence (AI)

[0317] For geometry optimisation with only 3D point cloud, the input (S9) will be the 3D point cloud of the human and the landmarks.

[0318] For geometry optimisation with 3D point cloud data and X-ray data, the input S9 will be the 3D point cloud data of the subject, as well as the anatomical landmarks and spinal alignment data, and:

[0319] (i) the clinician assigns the degree of twist correction S5-1 to the twist correction unit 203, which will twist correct the 3D point data of the subject, and the landmarks (and spinal alignment) are changed accordingly to provide a correction reference;

[0320] (ii) the clinician assigns the degree of back balance S5-2 to the back balance unit 204, which will back balance the 3D point data of the subject, and the anatomical landmarks (and spinal alignment) are changed accordingly to provide a correction reference; and

[0321] (iii) the clinician assigns the degree of spinal curve correction S5-3 to the spinal curve correction unit 205, which will spinal curve correct the 3D point data of the subject, and the anatomical landmarks (and spinal alignment) are changed accordingly to provide a correction reference.

[0322] Thus, the final corrected 3D point cloud S10 is the corrected target and will be used for further orthotic brace design.

[0323] The rule-based evaluation criteria can be used as the clinical evaluation criteria. The clinical evaluation criteria can be the Cobb angle evaluation.

[0324] B. Geometry optimization with artificial intelligence (AI)

[0325] For geometry optimization with AI:

[0326] (i) The subject's initial 3D point cloud, anatomical landmarks (and spinal alignment) S9 is input to the AI geometry optimization unit 202, which will automatically generate an AI geometry optimized 3D model S201;

[0327] (ii) Steps (i), (ii) and (iii) of "A" above Geometry optimization without artificial intelligence (AI) Will also be performed to fine-tune the AI generated results.

[0328] The AI generation is able to use a 3D generative model to directly generate an optimized 3D model.

[0329] Alternatively, the AI model can select a specific master brace model from a library based on the patient's 3D point cloud data, anatomical landmarks (and spinal alignment).

[0330] The training of the AI model can be done with the evaluation of a clinician (e.g. one or more clinicians), by rule spaced evaluation and learning system, whereby the anatomical landmarks are detected by an artificial intelligence (AI) engine and the recognition of rule-based bony protrusions or body landmarks are applied.

[0331] The rule-based evaluation criteria is preferably a clinical evaluation criteria. For example, the clinical evaluation criteria can be the Cobb angle evaluation.

[0332] By way of operable example, and also with reference to the embodiment of Fig. 2b, the geometry optimization with and without AI is demonstrated:

[0333] (1) The geometry optimization mode is selected via a signal from the user S5-0

[0334] If the user selects manual mode :

[0335] (2) The optimization mode switch 201 will be toggled up and the initial 3D point cloud S is directly input to the torsion correction unit 203 and the AI geometry optimization unit 202 will not work as it has been bypassed.

[0336] (3) The present inventor has developed three (3) unique geometric configuration optimization units:

[0337] (a) torsion correction unit 203,

[0338] (b) back balance unit 204, and

[0339] (c) spinal curve correction unit (205)

[0340] The orthosis gradually performs three (3) different geometric transformations on the initial 3D point cloud S9 to assist in orthosis design.

[0341] The orthosis only needs to assign 1 parameter for each geometric configuration optimization unit S5-1, S5-2, S5-3 to control the degree of each geometric configuration transformation.

[0342] Each parameter S5-1, S5-2, S5-3 has a specific clinical significance.

[0343] If the user selects AI assisted mode :

[0344] The optimization mode switch 201 will be switched down, and the initial 3D point cloud S9 is input to the AI geometric configuration optimization unit 202, which will automatically generate the AI geometric configuration optimized 3D model of the orthosis S201.

[0345] (4) Via the three unique geometric configuration optimization units torsion correction unit 203, back balance unit 204, and spinal curve correction unit 205, the AI-optimized 3D model of the orthosis S201 is further fine-tuned and / or confirmed by the AN orthosis in order to generate the final geometric configuration optimization of the orthosis model S10.

[0346] The AI component (400) contains an AI framework for automatic geometric configuration optimization of the initial point cloud S9.

[0347] The manually fine-tuned and / or confirmed optimized result S10 is used to further optimize the AI framework.

[0348] Current orthosis design techniques utilize a three-point pressure system to maintain proper spinal positioning [1].

[0349] Spinal orthoses are classified according to their fixed spinal regions, such as cervical orthoses (CO), cervico-thoracic orthoses (CTO), and lumbosacral orthoses (LSO) [2, 3].

[0350] The design variables are 2D displacements of three pre-defined points in the system, which are discrete variables and do not guarantee effective spinal correction and correction efficacy from a 3D perspective.

[0351] Current technology aims to restore the normal configuration of the 2D longitudinal spine, which neglects the spinal correction from the top view of the human body [4].

[0352] 6.1 Twist correction unit, back balancing unit and spinal curvature correction unit

[0353] According to embodiments of the present application, there are provided:

[0354] a. Twist correction unit 203

[0355] The twist correction unit 203 provides:

[0356] (i) Calculate the degree of torso rotation of the subject based on the PIIS (Posterior Inferior Iliac Spine) baseline from the top view,

[0357] (ii) Calculate the degree of rotation of each point in the point cloud,

[0358] (iii) Find the midline as the axis of rotation (passing through the centroid),

[0359] (iv) Rotate each point according to the calculated degree S202 according to the axis of rotation,

[0360] (v) Manually input parameter (range from 0%~100%) S5-1 to control the degree of twist correction (see Fig. 2c(i) and 2c(ii)):

[0361] 0% means no correction,

[0362] 100% means the torso rotation is corrected to 0.

[0363] b. Back balance unit 204

[0364] The back balancing unit 204 provides:

[0365] (i) Freeze the front of the body.

[0366] (ii) Fit and adjust the back of the point cloud according to all points at each height, the goal is to average the left-right symmetric position of the point cloud S203.

[0367] (iii) Manually input parameter (range from 0%~100%) (S5-2) to control the degree of back balancing (see Fig. 2c(iii)-2c(iv))

[0368] a. 0% means no correction,

[0369] b. 100% means perfect left-right symmetry.

[0370] c. Spine curve correction unit 205

[0371] The spinal curve correction unit 205 provides

[0372] (i) Calculate the length of the spinal curve;

[0373] (ii) fixing the last point of the spinal curve and straightening the curve into a straight line of the same length;

[0374] (iii) moving the point to a corrected position S10 according to the corrected spinal curve; and

[0375] (iv) Manually input the parameter S5-3 (ranging from 0% to 200%) to control the degree of spinal curve correction (see Figures 2d(i)-2d(iii)).

[0376] a. % means no correction,

[0377] b. 100% means correcting the spinal curve to a straight line, and

[0378] c. 200% means correcting the spinal curve to a symmetrical curve.

[0379] Key advantages provided by this embodiment of the invention include:

[0380] (i) more accurately modeling spinal deformation from a 3D perspective,

[0381] (ii) more precise and continuous correction of the orthosis model based on the 3D correction of the patient's spine, and

[0382] (iii) Spine correction based on 3D parameters with specific clinical significance.

[0383] 6.2. Artificial Intelligence (AI) Geometric Optimization Unit

[0384] In an embodiment of the present invention, regarding the intelligent (AI) geometry optimization unit (202):

[0385] a. A deep learning network using the basic architecture of PointNet [5] is used to extract point cloud features (S9) from the entire initial point cloud of the human body.

[0386] b. Another deep learning network with PointNet architecture is trained to extract multi-scale point cloud features centered on each anatomical landmark and vertebral center.

[0387] c. Combine the features from step a and step b through feature cascading.

[0388] d. Develop a multi-layer perceptron (MLP) to generate the displacement of each point based on the merged features.

[0389] e. applying a displacement to the initial point cloud to generate a geometry-optimized point cloud for the orthosis S201.

[0390] f. employing a pipeline of generative adversarial networks (GANs) to train the AI model.

[0391] Key advantages provided by this embodiment of the invention include:

[0392] (i) novel first AI-driven geometry-optimized and design for orthoses,

[0393] (ii) fast automatic orthosis design, and

[0394] (iii) consistent optimized results, which are not influenced by subjective experience or errors of the corrector, etc.

[0395] 7. Biomechanics optimization

[0396] Referring to Figure 3a(i), there is shown a general flowchart of a process 300a of determining the mechanical properties of a corrective orthosis for spinal alignment of a subject, in accordance with the present invention.

[0397] The process 300a comprises the following steps:

[0398] Step (i) 310a

[0399] receiving a three-dimensional model of a body surface of a spinal region of a subject and receiving a corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the corrected three-dimensional model is generated from the three-dimensional model and comprises output data indicative of a geometry of the body surface of the spinal region of the subject’s body for spinal alignment correction.

[0400] Step (ii) 320a

[0401] generating a numerical mechanics analysis model of a three-dimensional model of an orthosis and the corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the three-dimensional model of the orthosis is generated from the corrected three-dimensional model of the body surface of the spinal region of the subject, and wherein the mechanical properties of the orthosis comprise relative density.

[0402] Step (iii) 330a

[0403] determining a displacement of points of the corrected three-dimensional model from the three-dimensional model of the body surface of the spinal region of the subject.

[0404] Step (iv) 340a

[0405] determine a strain energy of the orthosis from the displacements from the step (iii) and vary a relative density distribution of the orthosis until a predetermined threshold of the strain energy is met and until a predetermined threshold of the relative density is met.

[0406] Step (v) 350a

[0407] generate a topology of the orthosis based on the relative density distribution; and output an optimized model of the orthosis when the predetermined threshold of the relative density is met.

[0408] Fig. 3a(ii) illustrates a general computerized system 300b for determining mechanical properties of an orthosis for correction of spinal alignment of a subject, according to the present application.

[0409] The computerized system 300b comprises an input interface 310b for receiving a three-dimensional model of a body surface of a spinal region of a subject, and for receiving a corrected three-dimensional model of the body surface of the spinal region of the subject.

[0410] The corrected three-dimensional model is generated from the three-dimensional model and comprises output data indicative of a geometry of the body surface of the spinal region of the subject's body for spinal alignment correction.

[0411] The system 300b further comprises a processor unit 320b for generating a numerical mechanics analysis model of the three-dimensional model of the orthosis and the corrected three-dimensional model of the body surface of the spinal region of the subject.

[0412] The three-dimensional model of the orthosis is generated from the corrected three-dimensional model of the body surface of the spinal region of the subject, and wherein the mechanical properties of the orthosis comprise a relative density; for:

[0413] (i) determining displacements of points of the corrected three-dimensional model from the three-dimensional model; and

[0414] (ii) determining a strain energy of the orthosis from the displacements, for varying a relative density distribution of the orthosis until a predetermined threshold of the strain energy is met and until a predetermined threshold of the relative density is met; and for generating a topology of the orthosis based on the relative density distribution; and outputting an optimized model of the orthosis when the predetermined threshold of the relative density is met.

[0415] The three-dimensional model of the body surface of the spinal region of the subject can be a three-dimensional point cloud model, a three-dimensional mesh model or a three-dimensional volume model, and the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional point cloud model, a three-dimensional mesh model or a three-dimensional volume model.

[0416] Referring to Figure 3b(i), a flowchart of an embodiment of the process of biomechanics optimization component is shown, and Figure 3b(ii) shows a schematic diagram of the embodiment of Figure 3b(i) according to the present application.

[0417] The biomechanics optimization component 300 provides biomechanics optimization of the geometry optimization results of the orthosis S10, and generates the final optimized 3D model of the orthosis S3 for further 3D printing and manufacturing of the orthosis.

[0418] According to the present application:

[0419] (1) The displacement calculation unit 301 calculates the displacement of each point S301 in the point cloud based on the geometry-optimized point cloud S10 and the initial point cloud S9.

[0420] (2) The 3D mesh model of the geometry-optimized orthosis S302 is generated by the meshing unit 300 based on the geometry-optimized point cloud of the orthosis S10.

[0421] (3) The point displacement S301, the 3D mesh model of the orthosis S302, and the relative density S304-1 are input into the numerical analysis unit 302 for biomechanics simulation of the orthosis S303.

[0422] (4) Based on the simulation results S303, the topology optimization unit 304 performs topology optimization on the orthosis model, which generates the optimized relative density distribution of the orthosis model S304-1 and the corresponding porosity design of the orthosis model S304-2.

[0423] (5) The optimization terminator 304 compares the difference between the original and optimized relative density distributions.

[0424] If the relative density distribution is not significantly updated and a predetermined threshold is met, the optimization will be terminated, and the optimized porosity design of the orthosis model S304-2 will be output.

[0425] Otherwise, the optimization will continue, and the optimized relative density distribution S304-1 will be fed back to the numerical analysis unit 302 for the next iteration of simulation optimization until the predetermined threshold is met.

[0426] The predetermined threshold of the objective function (strain energy) is determined as the termination condition of the optimization problem, which iteratively optimizes the distribution of relative density until the objective function is less than the predetermined threshold.

[0427] (6) The optimized porosity design of the orthosis model S304-2 can be further processed by the fine-tuning unit 305 for mesh smoothing and gap repair, which will generate the final optimized 3D model of the orthosis S3 for 3D printing.

[0428] Current technology related to spinal orthosis design currently employs solid orthosis models that are limited by traditional manufacturing methods.

[0429] Some designs have employed porous structures with the aim of improving air permeability and comfort. However, the location of the pores is not mathematically determined or designed to provide the necessary optimized biomechanical outcomes compared to the present invention.

[0430] Therefore, such existing devices cannot provide the necessary predetermined biomechanical outcomes and can indeed cause local stress concentration, which is harmful to the human body during spinal correction. Furthermore, the porosity distribution is not personalized to cater to the different biomedical cases of the patient. The traditional three-point pressure system does not take into account the topological optimization of the orthosis structure. The current existing orthosis structure and shape distribution mainly depends on the doctor's expertise without a logical approach and without taking into account the necessary biomechanical outcomes.

[0431] 7.1. Numerical analysis unit

[0432] With respect to the numerical analysis unit 302 of the embodiments of the present invention, the embodiments utilize a multiscale numerical analysis framework based on the porous structure of the orthosis to ensure that both the mechanical constraints of spinal correction and excellent biomedical performance are satisfied.

[0433] Homogenization :

[0434] Homogenization is performed in the element basis via discretization of the orthosis model into shell elements.

[0435] The porosity distribution of the orthosis is controlled via the relative density of each element.

[0436] As shown in Figure 3b(iii), a square plate model can be used as a representative volume element (RVE) in the homogenization simulation.

[0437] From a macroscopic scale, the homogenized model with different relative densities is obtained via continuous excavation or creation of holes or pores of different radii at the center of the RVE.

[0438] Therefore, the constitutive relationship between the relative density of the element and other element mechanical properties is determined by the homogenization process using the following equation:

[0439]

[0440] Therefore, the result of the constitutive relationship is shown as follows:

[0441]

[0442]

[0443] Once the relative density of the elements is determined, other element mechanical properties can be calculated for use as input for further mechanical analysis.

[0444] From a macroscopic scale, a solid orthosis model is employed for mechanical simulation using the element relative density and other mechanical properties as input information.

[0445] Non-uniform porosity distribution :

[0446] The present invention provides an analytical deterministic design method or process for non-uniform porosity distribution based on the topology optimization results of different subjects in order to meet the necessary biomechanical requirements.

[0447] After discretizing the orthosis model into a plurality of rectangular elements, the porosity distribution of the orthosis is controlled via the relative density of each element, which is derived from the results of topology optimization.

[0448] In combination with additive manufacturing technology, non-uniform porosity distribution can be achieved in order to provide the necessary orthosis, such as a spinal orthosis.

[0449] The homogenization provided by the present invention has the following advantages:

[0450] Homogenization :

[0451] (i) This ensures high efficiency of orthosis modeling with complex geometrical configurations.

[0452] (ii) This greatly improves the computational efficiency in numerical simulation.

[0453] Non-uniform porosity distribution :

[0454] (i) This ensures logical and proper material distribution in the orthosis while avoiding local stress concentration in the human body, which can cause discomfort to the subject and in some cases can cause injury.

[0455] (ii) Customized design of orthosis with various logical and proper porosity distribution can be achieved to accommodate the patient's biomedical condition.

[0456] 7.2. Topology optimization unit

[0457] The topology optimization unit 304 of the present embodiment can utilize an automated topology optimization framework based on the method of solid isotropic material with penalization (SIMP) to achieve the best biomedical and structural performance with the least amount of material.

[0458] Objective function :

[0459] For the objective function, the total strain energy is where F, U and K represent global force, displacement and stiffness matrices, respectively.

[0460] In the element analysis, the strain energy can also be expressed as

[0461] For a total of N elements .

[0462] The optimization problem to obtain the optimal distribution of relative density is expressed as follows:

[0463]

[0464]

[0465] Optimization variables :

[0466] The relative density represents the volume ratio of the element after discretizing the orthotic model, which varies from zero to one.

[0467] The relative density is different from and , and must be greater than 0 to avoid the singularity of the matrix during the calculation.

[0468]

[0469] In order to avoid the chessboard pattern configuration and lead to the inability to obtain clear optimization boundaries, it is necessary to use the convolution method to filter and update the optimized design variables, which can provide self-smoothing results:

[0470]

[0471] The main purpose of using the filter function is to avoid too discrete results of the porosity distribution in the actual orthosis.

[0472] In the above equation, R represents the radius of the convolution filter, M represents the total number of elements in the domain, and dist(i,j) represents the distance between the two elements.

[0473] The filter weight mainly depends on the distance between the discrete elements.

[0474] A larger relative distance means that the influence of interaction is smaller, so the influence of adjacent elements is reduced.

[0475] On the contrary, if the adjacent elements are very close to each other, their interaction has a greater influence, and the weight needs to be increased.

[0476] Constraint conditions :

[0477] The volume ratio constraint is shown as follows:

[0478]

[0479] And V represents the volume of the target optimization orthosis, and V shows the volume of the current iteration step.

[0480] The constraint is the volume fraction between the reserved material of the target spinal orthosis and the initial model , which is defined as 50% in the current optimization process.

[0481] Optimization solver :

[0482] By solving the control equation KU=F using the finite element method (FEM) to obtain the node displacement and node force at each node of the structure, the element is connected through the node, so the node force is propagated through the node.

[0483] Optimization using the optimality criteria (OC) method requires calculating the partial derivatives of the objective function and constraints, and solving them by applying the Lagrange multiplier ( ).

[0484]

[0485]

[0486]

[0487] where U and K are global displacement and stiffness matrices, and , and are element stiffness, displacement and volume.

[0488] The purpose of the Lagrange multiplier method is to directly convert the constrained optimization problem into an unconstrained optimization problem by converting the constraints into variables.

[0489] The mathematical meaning behind the Lagrange multiplier is the coefficient of each vector in the linear combination of the gradients of the constraint equations. is a scalar and is a vector; while is a relaxation factor, and satisfies the Kuhn-Tucker conditions as follows:

[0490]

[0491] In order to simplify the calculation by considering :

[0492]

[0493] Therefore, the iterative formula for the application of the spinal orthosis update based on the optimality criteria method can be obtained as follows:

[0494]

[0495] wherein, is a damping coefficient that ensures stable convergence. The convergence criterion can be determined based on the difference between the maximum components of the design variables of two adjacent iteration steps:

[0496]

[0497] wherein, denotes the iteration convergence criterion (typically set to 0.01). The optimization process is completed when the difference between the maximum values of the design variables in adjacent analysis steps satisfies the above expression.

[0498] The advantages of the topology optimization provided by the present invention include:

[0499] (i) The topology optimization can be applied to a multi-stage spinal orthosis model, allowing a corresponding orthosis to be generated for each correction stage;

[0500] (ii) It ensures that the maximum biomedical and structural performance is achieved under specific volume constraints, resulting in high cost-effectiveness of the orthosis product;

[0501] (iii) The porosity distribution obtained by topology optimization of the spinal orthosis is more reasonable, rational and appropriate;

[0502] (iv) The optimized spinal orthosis avoids local stress concentration, which can prolong the service life of the orthosis product; and

[0503] (v) Automatic optimization greatly improves the design efficiency of the orthosis and helps to eliminate the experience dependence of doctors in orthosis design.

[0504] 8. Example - Orthosis of the Invention

[0505] Referring to Figure 4 , there is shown a flowchart representation 400 of an exemplary embodiment of the steps of the present invention for an orthosis, in this case an optimized body brace for the spine of a subject.

[0506] Step 1 - Point cloud data pre-processing (410)

[0507] The point data is pre-processed to create a surface model for analysis.

[0508] The twist angle and displacement of the spine are obtained from the AI model.

[0509] Step 2-Stationary state analysis to obtain node RF (420)

[0510] Import boundary conditions to solve the nodal RF using infinite elements.

[0511] Step 3 -Optimization based on the corrected E and nu (423)

[0512] This step includes importing the node RF as a boundary condition to optimize and update E and nu in each cycle and obtain the relative density of each element.

[0513] Step 4 - Generate automatic rebuild (440)

[0514] This step involves using computer-aided design software to automatically reconstruct the stent model and export the model.

[0515] refer to Figure 5 , a flow chart showing steps for optimizing a body support of an embodiment of the present invention.

[0516] exist Figure 6 The processing is shown in Figure 5 An example of a point cloud of the back surface reconstruction of an embodiment. Collect and pre-process the human back point cloud data. After reconstructing the point cloud of the back surface. Figure 6 As shown, the entire surface plane is being rotated, which is then used to refine the spine curve.

[0517] Now refer to Figure 7 , showing Figure 5 This example shows the first step in the process of automatically meshing a point cloud to a back surface. The resulting mesh is a poor quality mesh of triangular elements. Repairing the mesh is necessary because many elements overlap and have unclear boundaries.

[0518] Now refer to Figure 8 , showing Figure 5 The embodiment of the back surface is a representation of the second step of reconstructing the point cloud into an automatic mesh result.

[0519] Now refer to Figure 9 , showing the refitting of the subregion grid to Figure 5 The third step in the back surface reconstruction process of the embodiment is to reconstruct the entire surface. The entire mesh is divided into several regions. A mesh is created for each divided region. The sub-meshes in different regions are then joined together and refitted to the entire surface.

[0520] Now refer to Figure 10 , showing Figure 5The fourth step in the process of fitting control points to the back surface reconstruction is described in this embodiment. The boundary control points are extracted and divided into four sections. Each section of control points is fitted to a plane. Although the control points are also extracted and fitted to the surface, the differences between the entire surface and the four planes are compared using Boolean comparisons.

[0521] refer to Figures 11a-22b , an embodiment of the design optimization process of the correction device (i.e., spinal brace-type correction device) according to the present invention is shown and described.

[0522] refer to Figure 11a and Figure 11b , shows an example of a process of calibrating all point clouds in an embodiment of the present invention. Figure 11c Shows about Figure 11a and 11b Perspective view of the reference plane; since the reference plane of the initial point cloud is uncertain, the adjustment of the spine needs to be performed on the reference plane, and all point clouds need to be calibrated.

[0523] Figure 12 Shown in Figures 11a-11c Example of a graphical representation of the results of the final fitted plane after 20,000 iterations. The reference plane is found by using the random sampling consensus method of the point cloud of the calibration plate.

[0524] Now refer to Figures 13a-13c , Figure 13a A perspective view showing the results of 2684 human back surface reconstructions and spinal curves obtained in an example of the present invention.

[0525] Figure 13b shows the 2684 Figure 13a Lateral view of the human back surface reconstruction and the resulting spinal curves.

[0526] Figure 13c It shows that 2684 Figure 13a and 13b are top views of the results of human back surface reconstruction and spinal curve.

[0527] Figure 14 This shows an example of correcting the point cloud for this example. When correcting the point cloud, some points will be lost, so the point cloud will appear disconnected layer by layer. Since the correction of the ridges is not significant, it does not have much effect on this point cloud.

[0528] Now referring to Figures 15 and 15b, Figure 15a is a graphical representation of the spine curve (Naen) of this example fitted to the spine curve (Sentin) obtained from the extreme points of the point cloud contour.

[0529] Figure 15bA graphical representation of the target spine curve of the present example is shown.

[0530] Figure 16 A graphical representation of the revised target point cloud of the present example.

[0531] The updated spine curve (Naen) is fitted to the spine curve (Sentin) obtained from the extreme points of the point cloud profile. The code is then rewritten for point cloud transverse transformation. The code still needs further improvement in order to mitigate distortion of low precision point clouds and local points of high precision point clouds, as Figure 16

[0532] Figures 17a-18b relates to the preparation of a mesh for analyzing a stent according to the present application.

[0533] Figure 17a A mesh created by ABAQUS for analyzing the present example for static analysis and optimization is shown. Figure 17b A mesh created by Hypermesh for static analysis and optimization is shown.

[0534] The mesh created by ABAQUS and Hypermesh has poor quality. The mesh elements are not uniformly distributed.

[0535] Figure 18a A mesh manually adjusted with control zones and points for static analysis and optimization is shown.

[0536] Figure 18b A mesh with quadrilateral elements manually adjusted with a mesh size of 10 for static analysis and optimization is shown. The entire model is manually divided into 46 sub-zones to correct the mesh node by node and generate the corresponding.INP file, resulting in a uniform distribution of 4 node shell elements.

[0537] Figures 19a-20b relates to the calculation of node reactions, the optimized model of node patterns, and the boundary conditions of node loads according to the present example.

[0538] Figure 19a The calculation of wave node reactions according to the modified spine curve is shown. Figure 19b The optimized model with node loads is shown.

[0539] Figure 20a The boundary conditions of the top, left and right, and bottom are shown, respectively.

[0540] Figure 20b The results of the node reactions extracted as node loads are shown.

[0541] Figures 21a-22b ​The static analysis for determining static deformations and stresses according to the present example and the optimization showing the deformations and stresses. Figure 21a The results of the deformations during the static analysis are shown. Figure 21b The results of the stresses during the static analysis are shown. Figure 22a The results of the deformations during the optimization are shown. Figure 22b The results of the stresses during the optimization are shown.

[0542] The optimization process now converges in a second iteration step and the deformations are increased from the optimization result, but the deformation distribution is the same as the one shown in the static analysis as Figure 21a and 22a The maximum stress is reduced by 64%.

[0543] Referring to Figures 23a-23d , illustrative examples of the iterative implementation of the solid isotropic material according to the present invention are shown.

[0544] Figure 23a The first iteration is shown, Figure 23b the eighth iteration is shown, Figure 23c the 12th iteration is shown, and Figure 23d the 54th iteration is shown.

[0545] For illustrative purposes implemented in the practice of the process of the present invention, Figures 24a to 30d illustrative examples are provided.

[0546] Figures 24a to 25b The boundary conditions and the static analysis of the structural cylindrical element are shown.

[0547] Figure 24a The boundary conditions and the static analysis of the structural element with a fixed top boundary are shown. Referring to Figure 24a , Figure 24b The boundary conditions with a fixed reference rotation point are shown.

[0548] Figure 25a The stress results during the static analysis process of the element of Figure 24a and 24b are shown in three dimensions. Figure 25b The results of the deformations of the structural element of Figure 24a , 24b and 25a during the static analysis process are shown in three dimensions.

[0549] Figure 26a The objective function according to the present invention, i.e. the total strain energy at different minimum densities, is shown. Figure 26b is a tabular representation of Figure 26a .

[0550] Figure 27aVolume fractions for different minimum densities based on volume fraction constraint are shown. Figure 27b is Figure 27a represented in a table.

[0551] Figures 28a-28d Material density distributions for different minimum densities are shown.

[0552] Figure 28a Data for a minimum density of 0.1 is shown, Figure 28b Data for a minimum density of 0.3 is shown, Figure 28c Data for a minimum density of 0.5 is shown, and Figure 28d Data for a minimum density of 0.7 is shown.

[0553] Figures 29a-29d Stress distributions for different minimum densities are shown;

[0554] Figure 29a Data for a minimum density of 0.1 and a maximum stress of 6.283 MPa is shown, Figure 29b Data for a minimum density of 0.3 and a maximum stress of 124.6 MPa is shown, Figure 29c Data for a minimum density of 0.5 and a maximum stress of 139.0 MPa is shown, and Figure 29d Data for a minimum density of 0.7 and a maximum stress of 194.3 MPa is shown.

[0555] Figures 30a-30d Deformation distributions for different minimum densities are shown;

[0556] Figure 30a Data for a minimum density of 0.1 is shown, Figure 30b Data for a minimum density of 0.3 is shown, Figure 30c Data for a minimum density of 0.5 is shown, and Figure 30d Data for a minimum density of 0.7 is shown.

[0557] Figure 31 A flowchart showing the optimization of the python script in the example of the embodiment of the invention is shown. In step 3110, the model is first created, meshed, and boundary conditions in ABAQUS. Where the boundary conditions are obtained from the equal node reaction force load of the static displacement constraint analysis case. Element and node properties are calculated 3120 by the center point of each element and neighbor weight (Rmin) of each element to avoid the checkerboard.

[0558] The data is then imported into ABAQUS for static analysis 3130. No global stiffness matrix modification is needed directly against the boundary conditions. If the results converge, the element density will be appended to the.odb file. If the results do not converge, further steps 3160 will be performed. The FOP results are obtained by updating the element material properties to calculate the element sensitivity. These steps are repeated from the static analysis 3130 until the results converge.

[0559] Figure 32a The fitted boundary conditions of the element material properties (E and nu) in this example are shown. Figure 32b The fitted undeformed and deformed results of the element material properties in this example and with respect to Figure 32a are shown. Figure 32c The fitted case generation of the element material properties in this example and with respect to Figure 32a and 32b are shown.

[0560] Figure 33a The results of the curve fitting in this example are shown. Figure 33b The results of the curve fitting updated with the optimization method are shown. In this example and with respect to Figure 33a . Figure 34a The preliminary results of the relative density of the cantilever beam in this example for the 2D case are shown. Figure 34b The preliminary results of the stress of the cantilever beam in this example are shown. Figure 34c The preliminary results of the deformation of the cantilever beam in this example are shown.

[0561] Figure 35a The preliminary results of the relative density of the cylindrical element example of the stent according to the present invention are shown. Figure 35b The preliminary results of the stress of the cylindrical element example according to the present invention and with respect to Figure 35a are shown.

[0562] Figure 35c The preliminary results of the deformation of the cylindrical element example according to the present invention and with respect to Figure 35a and 35b are shown.

[0563] Figure 36a The flowchart of the python script for model automatic reconstruction in an embodiment of the present invention is shown. The node coordinates and element relative density are obtained in the pre-processing ODB file 3610. The center point of each element is calculated by Heron formula 3620. The voids are created according to the relative density, which is the relationship between E / nu and the void ratio. Separate solid and extract surfaces are created. The entire element surface and offset are joined together and the.stl file 3600c is exported for 3D printing.

[0564] Figure 36b An example of a pre-processed ODB file is shown. Figure 36c An example of a.stl file is shown.

[0565] Figure 37a A model and BC (boundary conditions) of a cylindrical rigid body are shown. Figure 37b A mesh of the cylindrical rigid body of Figure 37a is shown.

[0566] Figure 38a Displacement distribution of the cylindrical rigid body of Figure 37a and 37b is shown. Figure 38b Stress distribution of the cylindrical rigid body of Figure 37a , 37b and 38a is shown; and

[0567] Figure 38c Relative density distribution of the cylindrical rigid body of Figure 37a , 37b and 38a and 38b is shown.

[0568] The introduction and adoption of computer-aided design and computer-aided manufacturing (CAD / CAM) systems have helped to more accurate digital design and higher productivity, replacing negative mold casting and manual correction procedures.

[0569] Additive manufacturing (3D printing) can more accurately manufacture a brace to achieve a perfect fit and enable greater customization to the patient.

[0570] Non-periodic material design (AMD) with solid isotropic material and penalization (SIMP) can achieve the best material distribution and obtain a brace with higher strength under certain objective functions and constraints.

[0571] As provided by the present invention, there is an AI-facilitated system and device that uses depth sensing and SIMP to produce an effective orthosis for AIS patients with AMD. The benefits provided will include effective correction and comfort in wearing and using.

[0572] 9. References

[0573] [1] Wepner, Justin L., and Alan P. Alfano. “Principles and Components of Spinal Orthoses.” Atlas of Trainings Maps and Assistive Devices. Elsevier, 2019. 69-89.

[0574] [2] Lumsden, R.M.I.I., and Morris, J.M. "An in vivo study of axial rotation and immobilization at the lumbosacral joint." JBJS 50.8 (1968): 1591-1602.

[0575] [3] Newman, Meredith, Catherine Minns Lowe, and Karen Barker. "Spinal orthoses for vertebral osteoporosis and osteoporotic vertebral fracture: a systematic review." Archives of Physical Medicine and Rehabilitation 97.6 (2016): 1013-1025.

[0576] [4] Weinstein, Stuart L, et al. "Adolescent idiopathic scoliosis." The Lancet (London, England) 371 9623 (2008): 1527-37. doi:10.1016 / S0140-6736(08)60658-3.

[0577] [5] Qi, Charles R., et al. "Pointnet: Deep learning on point sets for 3d classification and segmentation." IEEE Conference on Computer Vision and Pattern Recognition. 2017.

Claims

1. A process operable using a computerized system for providing output data indicative of a geometry of a spinal region of a body of a subject for spinal alignment correction, the process comprising the steps of: (i) detecting a body landmark of the subject from a three-dimensional point cloud model of a body surface of the spinal region of the subject, wherein the body landmark is a landmark indicative of a spinal anatomical landmark of the subject; (ii) determining a spinal correction of the subject's spine, wherein the spinal correction provides a spinal alignment correction of the subject, and (iii) generating a corrected three-dimensional point cloud model of the spinal region of the subject, wherein the corrected three-dimensional point cloud model is generated based on the spinal correction of the subject and the three-dimensional point cloud model of the surface of the spinal region of the subject, wherein the corrected three-dimensional point cloud model comprises output data for the spinal alignment correction of the subject, the output data indicative of the geometry of the spinal region of the surface of the body of the subject, the geometry comprising the body landmark of the subject, and wherein the body landmark from the three-dimensional point cloud model of the body surface of the spinal region of the subject and the spinal anatomical landmark of the spine of the subject are moved during the generation of the corrected three-dimensional point cloud model of the spinal region of the subject.

2. The process of claim 1, wherein, the three-dimensional point cloud model of the spinal region of the subject is generated from one or more data input sets, wherein, each data input set of the one or more data input sets is indicative of an optical image of the subject, and, wherein the optical image is a three-dimensional optical image indicative of the geometry of the spinal region of the subject.

3. The process of claim 2, wherein, the optical image is a red, green, blue, and depth (RGBD) image.

4. The process of claim 3, wherein, the three-dimensional point cloud model is generated using one data set from one corresponding three-dimensional optical image of the spinal region of the subject.

5. The process of claim 4, wherein, the one three-dimensional optical image is a posterior-anterior (PA) three-dimensional optical image of the spinal region of the subject.

6. The process of claim 2 or claim 3, wherein, the three-dimensional point cloud model is generated using three data sets from three corresponding three-dimensional optical images of the spinal region of the subject.

7. The process of claim 6, wherein, the three-dimensional optical images of the spinal region of the subject are posterior-anterior (PA), left (Lt), and right (Rt) three-dimensional optical images of the spinal region of the subject.

8. The process of any one of the preceding claims, wherein, the spinal correction of the subject is determined from the three-dimensional point cloud model of the spinal region of the subject.

9. The process of any one of claims 1 to 7, wherein, from the one or more medical images of the spinal region of the subject, the spinal anatomy of the subject from the spinal anatomy of the subject's spine.

10. The process of claim 9, wherein, the one or more medical images are one or more X-ray images of the spinal region of the subject.

11. The process of claim 10, wherein, the one or more medical images are anteroposterior (AP) X-ray images of the spinal region of the subject to provide two-dimensional (2D) spinal alignment corrections of the subject's spine.

12. The process of claim 10, wherein, the one or more medical images are anteroposterior (AP) X-ray images and lateral (LAT) X-ray images of the spinal region of the subject to provide three-dimensional (3D) spinal alignment corrections of the subject's spine.

13. The process of any one of the preceding claims, wherein, the body landmarks of the subject detected from the three-dimensional point cloud model of the surface of the spinal region of the subject are detected by a pre-trained artificial intelligence (AI) component.

14. The process of claim 13, wherein, the body landmark positions detected by the pre-trained artificial intelligence (AI) component are further reviewed by one or more human operators and fine-tuned if needed.

15. The process of claim 14, wherein, the spinal corrections for spinal alignment corrections of the subject are determined by assigning one or more of twist, back balance, and spinal curve corrections by the one or more human operators.

16. The process of any one of claims 1 to 13, wherein, the corrected three-dimensional point cloud model of the surface of the spinal region of the subject is provided from the three-dimensional point cloud model of the surface of the spinal region of the subject and the body landmark positions by a pre-trained artificial intelligence (AI) unit.

17. The process of claim 16, further comprising: fine-tuning by one or more human operators by assigning one or more of twist, back balance, and spinal curve corrections.

18. The process of any one of the preceding claims, wherein, the output data indicative of the geometry of the spinal region of the surface of the body of the subject for spinal alignment corrections is indicative of a geometry of an orthosis for providing the spinal alignment corrections to the subject.

19. A computerized system for providing output data indicative of a geometry of a spinal region of a body of a subject for spinal alignment corrections, the system comprising: a geometry optimization component for detecting body landmarks of the subject from a three-dimensional point cloud model of a body surface of the spinal region of the subject, wherein the body landmarks are landmarks indicative of spinal anatomy; the geometry optimization component for generating a corrected three-dimensional point cloud model of the spinal region of the subject, wherein the corrected three-dimensional point cloud model is generated based on the spine correction of the subject and based on the three-dimensional point cloud model of the surface of the spinal region of the subject, wherein the spine correction provides a spinal alignment correction of the subject, wherein the corrected three-dimensional point cloud model comprises output data for the spinal alignment correction of the subject, the output data indicating the geometric configuration of the surface of the body of the subject including the body landmarks of the subject in the spinal region; wherein the body landmarks from the three-dimensional point cloud model of the body surface of the spinal region of the subject and the spinal anatomical landmarks of the spine of the subject are moved during the generation of the corrected three-dimensional point cloud model of the spinal region of the subject.

20. The computerized system of claim 19, further comprising: a point cloud generation component for generating the three-dimensional point cloud model of the spinal region of the subject from one or more data input sets, wherein, each data input set of the one or more data input sets indicates an optical image of the subject, and wherein, the optical image is a three-dimensional optical image indicating the geometric configuration of the spinal region of the subject.

21. The computerized system of claim 20, wherein, the optical image is a red, green, blue, and depth (RGBD) image.

22. The computerized system of claim 19 or claim 20, wherein, the three-dimensional point cloud model is generated using one data set from one corresponding three-dimensional optical image of the spinal region of the subject.

23. The computerized system of claim 22, wherein, the one three-dimensional optical image is a posterior-anterior (PA) three-dimensional optical image of the spinal region of the subject.

24. The computerized system of claim 20 or claim 21, wherein, the three-dimensional point cloud model is generated using three data sets from three corresponding three-dimensional optical images of the spinal region of the subject.

25. The computerized system of claim 24, wherein, the three-dimensional optical images of the spinal region of the subject are posterior-anterior (PA), left (Lt), and right (Rt) three-dimensional optical images of the spinal region of the subject.

26. The computerized system of any one of claims 19 to 25, wherein, the spine correction of the subject is determined from the three-dimensional point cloud model of the spinal region of the subject.

27. The computerized system of any one of claims 19 to 25, wherein, the spine correction of the subject is determined from one or more medical images of the spinal region of the subject.

28. The computerized system of claim 27, wherein, the one or more medical images are one or more X-ray images of the spinal region of the subject.

29. The computerized system of claim 28, wherein, The one or more medical images are anteroposterior (AP) X-ray images of the spinal region of the subject to provide two-dimensional (2D) spinal alignment correction of the spine of the subject.

30. The computerized system of claim 27, wherein, The one or more medical images are anteroposterior (AP) X-ray images and lateral (LAT) X-ray images of the spinal region of the subject to provide three-dimensional (3D) spinal alignment correction of the spine of the subject.

31. The computerized system of any one of claims 19 to 30, wherein, The body landmarks of the subject detected from the three-dimensional point cloud model of the surface of the spinal region of the subject are detected by a pre-trained artificial intelligence (AI) component.

32. The computerized system of claim 31, further comprising: a user interface such that the corrected anatomical landmark positions detected by the pre-trained artificial intelligence (AI) component are further reviewed by one or more human operators and fine-tuned if needed.

33. The computerized system of claim 32, wherein, The spinal correction for spinal alignment correction of the subject is determined by assigning one or more of twist, back balance, and spinal curve correction by the one or more human operators.

34. The computerized system of any one of claims 19 to 31, further comprising: a pre-trained artificial intelligence (AI) unit, wherein, The corrected three-dimensional point cloud model of the surface of the spinal region of the subject is provided by the pre-trained artificial intelligence (AI) unit from the three-dimensional point cloud model of the surface of the spinal region of the subject and the body anatomical landmark positions.

35. The computerized system of claim 34, further comprising: another user interface for fine-tuning by one or more human operators by assigning one or more of twist, back balance, and spinal curve correction.

36. The computerized system of any one of claims 19 to 35, further comprising: an output interface for outputting the data indicative of the geometry of the spinal region of the surface of the body of the subject for spinal alignment correction, the geometry being indicative of the geometry of an orthosis for providing the spinal alignment correction to the subject.

37. A process operable using a computerized system that determines the mechanical properties of an orthosis for correction of spinal alignment of a subject, the process comprising the steps of: (i) receiving a three-dimensional model of a body surface of a spinal region of the subject and receiving a corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the corrected three-dimensional model is generated from the three-dimensional model and comprises output data indicative of the geometry of the body surface of the spinal region of the body of the subject for spinal alignment correction; (ii) generating a numerical mechanics analysis model of a three-dimensional model of the orthosis and a corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the three-dimensional model of the orthosis is generated from the corrected three-dimensional model of the body surface of the spinal region of the subject, and wherein the mechanical properties of the orthosis include relative density; (iii) determining displacements of points of the corrected three-dimensional model from the three-dimensional model of the body surface of the spinal region of the subject; (iv) determining a strain energy of the orthosis from the displacements of step (iii) and varying a relative density distribution of the orthosis until a predetermined threshold of strain energy is met and until a predetermined threshold of relative density is met; and (v) generating a topology of the orthosis based on the relative density distribution; and outputting an optimized model of the orthosis when the predetermined threshold of relative density is met.

38. The process of claim 37, wherein, the relative density distribution of the orthosis is a porosity distribution of the orthosis.

39. The process of claim 38, wherein, the porosity distribution is a non-uniform porosity distribution based on topology optimization results of the subject.

40. The process of any one of claims 37 to 39, wherein, the three-dimensional model of the body surface of the spinal region of the subject is a three-dimensional point cloud model, and wherein, the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional point cloud model.

41. The process of any one of claims 37 to 39, wherein, the three-dimensional model of the body surface of the spinal region of the subject is a three-dimensional mesh model, and wherein, the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional mesh model.

42. The process of any one of claims 37 to 39, wherein, the three-dimensional model of the body surface of the spinal region of the subject is a three-dimensional volume model, and wherein, the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional volume model.

43. An orthosis for correcting spinal alignment of a subject, wherein, the mechanical properties of the orthosis are determined by the process of any one of claims 37 to 42, and wherein, the geometry of the orthosis is based on the corrected three-dimensional model of the body surface of the spinal region of the subject.

44. The orthosis of claim 43, wherein, at least a portion of the orthosis is formed by an additive manufacturing technique.

45. The orthosis of claim 43 or claim 44, wherein, at least a portion of the orthosis is monolithic.

46. The orthosis of any one of claims 43 to 45, wherein, at least a portion of the orthosis is formed from a polymeric material.

47. The orthosis of claim 46, wherein, The at least one portion of the orthosis is formed of polyurethane (PE).

48. A computerized system for determining mechanical properties of an orthosis for correction of spinal alignment of a subject, the system comprising: an input interface for receiving a three-dimensional model of a body surface of a spinal region of the subject, and for receiving a corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the corrected three-dimensional model is generated from the three-dimensional model and comprises output data indicative of the geometric configuration of the body surface of the spinal region of the subject for spinal alignment correction; and a processor unit for generating a numerical mechanics analysis model of the three- dimensional model of the orthosis and the corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the three-dimensional model of the orthosis is generated from the corrected three- dimensional model of the body surface of the spinal region of the subject, and wherein the mechanical properties of the orthosis comprise relative density; displacement of points of the corrected three-dimensional model determined from the three-dimensional model; and strain energy of the orthosis determined from the displacement, for varying a relative density distribution of the orthosis until a predetermined threshold of strain energy is met and until a predetermined threshold of relative density is met; and for generating a topology of the orthosis based on the relative density distribution, and outputting an optimized model of the orthosis upon meeting the predetermined threshold of relative density.

49. The computerized system of claim 48, wherein, the relative density distribution of the orthosis is a porosity distribution of the orthosis.

50. The computerized system of claim 49, wherein, the porosity distribution is a non-uniform porosity distribution based on topology optimization results of the subject.

51. The computerized system of any one of claims 48 to 50, wherein, the three-dimensional model of the body surface of the spinal region of the subject is a three- dimensional point cloud model, and wherein, the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional point cloud model.

52. The computerized system of any one of claims 48 to 50, wherein, the three-dimensional model of the body surface of the spinal region of the subject is a three- dimensional mesh model, and wherein, the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional mesh model.

53. The computerized system of any one of claims 48 to 50, wherein, the three-dimensional model of the body surface of the spinal region of the subject is a three- dimensional volume model, and wherein, the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional volume model.

54. The computerized system of any one of claims 48 to 53, outputting an optimized model of the orthosis when a predetermined threshold of relative density is met, and wherein the geometry of the orthosis is based on the corrected three-dimensional model of the spinal region of the subject's body surface.

55. A computerized system for determining mechanical properties of an orthosis for correction of spinal alignment of a subject, the system comprising: an input interface for receiving a three-dimensional model of a body surface of a spinal region of the subject and for receiving a corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the corrected three-dimensional model is generated from the three-dimensional model and comprises output data indicative of the geometry of the body surface of the spinal region of the subject's body for spinal alignment correction; a displacement calculation unit for calculating a displacement of each point in the three-dimensional model of the spinal region of the subject and in the corrected three-dimensional model of the spinal region of the subject; a meshing unit for generating a three-dimensional model of an orthosis from the corrected three-dimensional model of the spinal region of the subject; a numerical analysis unit for a mechanical simulation of the orthosis, wherein the numerical analysis unit performs the mechanical simulation based on the three-dimensional model of an orthosis, the displacement of each point in the three-dimensional model, and the mechanical properties of the orthosis comprising relative density; and a topology optimization unit for demonstrating a topology optimization of a model of the orthosis based on results from the numerical analysis unit, and for providing an optimized relative density of the orthosis when a predetermined threshold of strain energy is met and a predetermined threshold of relative density is met.

56. The computerized system of claim 55, wherein the relative density distribution of the orthosis is a porosity distribution of the orthosis.

57. The computerized system of claim 56, wherein the porosity distribution is a non-uniform porosity distribution based on the topology optimization results of the subject.

58. The computerized system of any one of claims 55 to 57, wherein the three-dimensional model of the body surface of the spinal region of the subject is a three-dimensional point cloud model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional point cloud model.

59. The computerized system of any one of claims 55 to 57, wherein the three-dimensional model of the body surface of the spinal region of the subject is a three-dimensional mesh model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional mesh model.

60. The computerized system of any one of claims 55 to 57, wherein the three-dimensional model of the body surface of the spinal region of the subject is a three-dimensional volume model, and wherein the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional volume model. The corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional volumetric model.

61. The computerized system according to any one of claims 55-60, further comprising: a fine-tuning unit for mesh smoothing and gap repair of the mesh.

62. An orthosis for correcting spinal alignment of a subject, wherein, The orthosis has a relative density determined by a process comprising: (i) receiving a three-dimensional model of the spinal region of the subject and receiving a corrected three-dimensional model of the spinal region of the subject, wherein the corrected three-dimensional model is generated from the three-dimensional model and comprises output data indicative of the geometric configuration of the spinal region of the body of the subject for spinal alignment correction; (ii) generating a numerical mechanics analysis model of the three-dimensional model of the orthosis and the corrected three-dimensional model of the spinal region of the subject, wherein the three-dimensional model of the orthosis is generated from the corrected three-dimensional model of the spinal region of the subject, and wherein the mechanical properties of the orthosis comprise relative density; (iii) determining displacements of points of the corrected three-dimensional model from the three-dimensional model; (iv) determining strain energy of the orthosis from the displacements of step (iii) and changing the relative density distribution of the orthosis until a predetermined threshold of strain energy is met and until a predetermined threshold of relative density is met; wherein the topology of the orthosis is based on the relative density distribution, and wherein the geometric configuration of the orthosis is based on the corrected three-dimensional model of the body surface of the spinal region of the subject.

63. The orthosis according to claim 62, wherein, the relative density distribution of the orthosis is a porosity distribution of the orthosis.

64. The orthosis according to claim 63, wherein, the porosity distribution is a non-uniform porosity distribution based on topology optimization results of the subject.

65. The orthosis according to any one of claims 62-64, wherein, at least a portion of the orthosis is formed by an additive manufacturing technique.

66. The orthosis according to any one of claims 62-65, wherein, at least a portion of the orthosis is monolithic.

67. The orthosis according to any one of claims 62-66, wherein, at least a portion of the orthosis is formed by a polymeric material.

68. The orthosis according to claim 67, wherein, at least a portion of the orthosis is formed by polyurethane (PE).

69. The orthosis according to any one of claims 62-68, wherein, the three-dimensional model of the body surface of the spinal region of the subject is a three-dimensional point cloud model, and wherein, the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional point cloud model.

70. The orthosis according to any one of claims 62-68, wherein, the three-dimensional model of the body surface of the spinal region of the subject is a three-dimensional mesh model, and wherein, the corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional mesh model. The corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional mesh model.

71. The orthosis of any one of claims 62 to 68, wherein, The three-dimensional model of the body surface of the spinal region of the subject is a three-dimensional volume model, and wherein, The corrected three-dimensional model of the body surface of the spinal region of the subject is a corrected three-dimensional volume model.

72. A process operable using a computerized system for providing output data indicative of a geometry of a spinal region of a body of a subject for spinal alignment correction and for determining mechanical properties of an orthosis for spinal alignment correction of a subject, the process comprising the steps of: (i) detecting a body landmark of the subject from a three-dimensional point cloud model of a body surface of the spinal region of the subject, wherein the body landmark is a landmark indicative of a spinal anatomical landmark of the subject; (ii) determining a spinal correction of the subject, wherein the spinal correction provides for spinal alignment correction of the subject, and (iii) generating a corrected three-dimensional point cloud model of the spinal region of the subject, wherein the corrected three-dimensional point cloud model is generated based on the spinal correction of the subject and the three-dimensional point cloud model of the surface of the spinal region of the subject, wherein the corrected three-dimensional point cloud model comprises output data for spinal alignment correction of the subject, the output data being indicative of the geometry of the surface of the body of the subject including the body landmark of the subject, and wherein the body landmark from the three-dimensional point cloud model of the body surface of the spinal region of the subject and the spinal anatomical landmark of the subject of the subject are moved during the generation of the corrected three-dimensional point cloud model of the spinal region of the subject, (iv) receiving a three-dimensional model of the body surface of the spinal region of the subject and receiving a corrected three-dimensional model of the body surface of the spinal region of the subject, wherein the corrected three-dimensional model is generated from the three-dimensional model and comprises output data indicative of the geometry of the body surface of the spinal region of the body of the subject for spinal alignment correction; (v) generating a numerical mechanical analysis model of the three-dimensional model of the orthosis and the corrected three-dimensional point cloud model of the body surface of the spinal region of the subject, wherein the three-dimensional model of the orthosis is generated from the corrected three-dimensional model of the body surface of the spinal region of the subject, and wherein the mechanical properties of the orthosis comprise relative density; (vi) determining displacement of points of the corrected three-dimensional point cloud model from the three-dimensional model of the body surface of the spinal region of the subject; (vii) determining a strain energy of the orthosis from the displacement at step (vi) and varying the relative density distribution of the orthosis until a predetermined threshold of strain energy is met and until a predetermined threshold of relative density is met; and (vii) generating a topology of the orthosis based on the relative density distribution; and outputting an optimized model of the orthosis when the predetermined threshold of relative density is met.

73. An orthosis for correcting spinal alignment of a subject, wherein, the geometry of a spinal region of a subject's body for spinal alignment correction and the mechanical properties of an orthosis for correcting spinal alignment of the subject are determined by the process of claim 72.

74. The orthosis of claim 72 or claim 73, wherein, at least a portion of the orthosis is formed by an additive manufacturing technique.

75. The orthosis of any one of claims 72 to 74, wherein, at least a portion of the orthosis is monolithic.

76. The orthosis of any one of claims 72 to 75, wherein, at least a portion of the orthosis is formed from a polymeric material.

77. The orthosis of claim 76, wherein, the at least a portion of the orthosis is formed from polyurethane (PE).

Images