# US 11,432,931 B2 · Artificial neural network for fitting or aligning orthopedic implants

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,432,931 B2
- Document ID: US11432931B2
- Status: Granted
- Kind: B2
- Application number: 17/575,810
- Filed: 2022-01-14
- Published: 2022-05-05
- Granted: 2022-09-06
- Earliest claimed: 2018-02-06
- Applicants: Philipp K. Lang
- Inventors: Philipp K. Lang
- Web page: https://patentgrep.com/patent/US11432931B2

## CPC

- A61F 2/30942: {for designing or making customized prostheses, e.g. using templates, CT or NMR scans, finite-element analysis or CAD-CAM techniques}
- A61B 34/10: Computer-aided planning, simulation or modelling of surgical operations
- A61F 2/32: for the hip
- A61F 2/38: for elbows or knees
- A61F 2/40: for shoulders
- A61F 2/4202: {for ankles}
- G16H 20/40: relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
- G16H 30/40: for processing medical images, e.g. editing
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/50: for simulation or modelling of medical disorders
- A61B 34/20: Surgical navigation systems; Devices for tracking or guiding surgical instruments, e.g. for frameless stereotaxis
- A61B 2034/105: {Modelling of the patient, e.g. for ligaments or bones}
- A61B 2034/108: {Computer aided selection or customisation of medical implants or cutting guides}
- A61F 2002/3093: {for promoting ingrowth of bone tissue}
- A61F 2002/30943: {using mathematical models}
- A61F 2002/30948: {using computerized tomography, i.e. CT scans}
- A61F 2002/30952: {using CAD-CAM techniques or NC-techniques}
- A61F: FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS (dental prosthetics A61C)
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Devices, systems, techniques and methods for determining the fit of an implant and for determining one or more prognosticators, indicators or risk factors of postoperative performance are provided.

## Claims

### Claim 1

A system for fitting, aligning, or fitting and aligning a virtual implant component for a joint replacement in a patient comprising:
at least one computer system comprising at least one processor,
wherein the at least one processor is configured to receive imaging data of the joint of the patient,
wherein the imaging data comprises at least one image of at least a portion of a surface of the joint, wherein the imaging data comprises a CT scan, an MRI scan, an ultrasound scan, data generated based on one, two or more x-rays or combinations thereof of the joint,
wherein the at least one processor is configured to generate a three-dimensional (3D) model of the at least a portion of the surface of the joint based on the imaging data,
wherein the at least one processor is configured to access electronic data of a virtual implant component, the virtual implant component comprising a shape associated with a physical implant component,
wherein the at least one processor is configured to use an artificial neural network to fit, align, or fit and align the virtual implant component in relationship to the 3D model of the at least a portion of the surface of the joint, and
wherein the at least one processor is configured to use the artificial neural network to fit, align, or fit and align the virtual implant component in relationship to the at least a portion of the surface the joint, an anatomic structure, an anatomic axis, a biomechanical axis, a mechanical axis, a rotation axis, a predetermined angle, a version, a slope, a joint line, or a combination thereof.

### Claim 2 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to use the artificial neural network to select the virtual implant component from a library of virtual implant components, wherein the library of virtual implant components comprises at least two virtual implant components, wherein the at least two virtual implant components have different shapes.

### Claim 3 (depends on 2)

The system of claim 2, wherein the at least one processor is configured to use the artificial neural network to select the virtual implant component based on the fit, the alignment, or the fit and the alignment of the virtual implant component.

### Claim 4 (depends on 2)

The system of claim 2, wherein the virtual implant components are stored in STL file format in the library of virtual implant components.

### Claim 5 (depends on 1)

The system of claim 1, wherein the at least a portion of the surface of the joint comprises a cartilage surface, a subchondral bone surface, a cortical bone surface, or a combination thereof.

### Claim 6 (depends on 1)

The system of claim 1, wherein the at least a portion of the surface of the joint comprises an uncut bone surface, or wherein the at least a portion of the surface of the joint comprises a cut bone surface.

### Claim 7 (depends on 6)

The system of claim 6, wherein the cut bone surface comprises at least a portion of a margin, an edge, a perimeter or a combination thereof of the cut bone surface.

### Claim 8 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to use the artificial neural network to fit, align, or fit and align the virtual implant component in relationship to at least one margin of a cut bone surface, edge of a cut bone surface, perimeter of a cut bone surface, inclination, predetermined resection plane, or a combination thereof.

### Claim 9 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to use the artificial neural network to fit, align, or fit and align the virtual implant component using a range of motion measurement, a curvature analysis, a kinematic measurement, a kinematic simulation or a combination thereof.

### Claim 10 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to use the artificial neural network to fit, align, or fit and align the virtual implant component using a soft-tissue impingement analysis.

### Claim 11 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to use the artificial neural network to fit, align, or fit and align the virtual implant component based on one or more CT images, MR images, x-ray images, ultrasound images, PET images, SPECT images, nuclear scintigraphy images, thermography images, wearable device data, IMU data, patient history, clinical assessments, patient reported outcome measurements, range of motion measurements, clinical scores, function scores, objective outcome measurements, subjective outcome measurements or a combination thereof.

### Claim 12 (depends on 1)

The system of claim 1, wherein the computer processor is configured to determine at least one measure of fit, alignment, or fit and alignment, wherein the at least one measure comprises one or more numeric distance value, surface area value, volume value, angle measurement value or a combination thereof.

### Claim 13 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to fit and/or align and/or select the virtual implant component so as to minimize an overhang, oversizing or overhang and oversizing in relationship to the at least a portion of the surface of the joint, the at least one anatomic structure, a cut bone surface, a margin of a cut bone surface, an edge of a cut bone surface, a perimeter of a cut bone surface, or a combination thereof.

### Claim 14 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to fit and/or align and/or select the virtual implant component so as to minimize an undersizing in relationship to the at least a portion of the surface of the joint, the at least one anatomic structure, a cut bone surface, a margin of a cut bone surface, an edge of a cut bone surface, a perimeter of a cut bone surface, or a combination thereof.

### Claim 15 (depends on 1)

The system of claim 1, wherein the joint is a knee joint and wherein the at least one processor is configured to use the artificial neural network to fit, align, or fit and align the virtual implant component in relationship to at least a peripheral margin, a bone edge, a dimension, a plane, a shape, a radius, a convexity, a concavity, or a surface of at least one of a medial wall of the femoral notch, a lateral wall of the femoral notch, a roof of the femoral notch, a residual ACL origin, a residual ACL insertion, a medial wall of the medial condyle, a lateral wall of the lateral condyle, a medial epicondylar eminence, a lateral epicondylar eminence, a medial femoral condyle, a lateral femoral condyle, a posterior portion of medial femoral condyle, a posterior portion of lateral femoral condyle, a central portion of medial femoral condyle, a central portion of lateral femoral condyle, an anterior portion of medial femoral condyle, an anterior portion of lateral femoral condyle, an intercondylar notch, an intercondylar notch surface, an intercondylar notch ceiling, an intercondylar notch medial wall, an intercondylar notch lateral wall, a posterior portion of medial tibial plateau, a posterior portion of lateral tibial plateau, a central portion of a medial tibial plateau, a central portion of a lateral tibial plateau, an anterior portion of medial tibial plateau, an anterior portion of lateral tibial plateau, a medial tibial spine, a lateral tibial spine, an anteromedial tibial rim, an anterolateral tibial rim, a medial tibial rim, a lateral tibial rim, a lowest point of the medial plateau, a lowest point of the lateral plateau, a highest point of the medial plateau, a highest point of the lateral plateau, an uncut medial tibial plateau surface, an uncut lateral tibial plateau surface, a cut medial tibial plateau surface, a cut lateral tibial plateau surface, an uncut femoral condyle surface, a cut femoral condyle surface, an uncut anterior femur surface, a cut anterior femur surface, a transepicondylar axis, a Whiteside's line, an anterior cortex, a tibial slope, a medial joint line, a lateral joint line or a combination thereof.

### Claim 16 (depends on 1)

The system of claim 1, wherein the joint is a hip joint and wherein the at least one processor is configured to use the artificial neural network to fit, the align, or fit and align the virtual implant component in relationship to at least a peripheral margin, a bone edge, a dimension, a plane, a shape, a radius, a convexity, a concavity or a surface of at least one of a portion of or an entire acetabulum, a portion of or an entire edge of an acetabulum, multiple portions of an edge of an acetabulum, a portion of an iliac wall, a portion of a pubic bone, a portion of an ischial bone, an anterior superior iliac spine, an anterior inferior iliac spine, a symphysis pubis, a portion of or an entire greater trochanter, a portion of or an entire lesser trochanter, a portion of or an entire femoral shaft, a portion of or an entire femoral neck, a portion of or an entire femoral head, a fovea capitis, a transverse acetabular ligament, a pulvinar, a ligamentum teres, a labrum, one or more osteophytes, a femoral neck angle, a femoral shaft angle, an acetabular angle, an inclination, an acetabular anteversion, a femoral anteversion, a femoral shaft angle, a pelvic tilt, a pelvic plane, a femoral offset, a Shenton's line, a Hilgenreiner line, a Perkin line, an acetabular index, a femoral resection plane, an acetabular resection plane, an uncut femoral surface, a cut femoral bone surface, or a combination thereof.

### Claim 17 (depends on 1)

The system of claim 1, wherein the joint is a shoulder joint and wherein the at least one processor is configured to use the artificial neural network to fit, the align, or fit and align the virtual implant component in relationship to a peripheral margin, a bone edge, a dimension, a plane, a shape, a radius, a convexity, a concavity, or a surface of at least one of a portion of or an entire glenoid, a portion of or an entire coracoid process, a portion of or an entire acromion, a portion of a clavicle, a portion of or an entire humeral head, a portion of or an entire humeral neck, a portion of a humeral shaft, one or more humeral osteophytes, one or more glenoid osteophytes, a portion of or an entire glenoid labrum, a portion of or an entire shoulder ligament, a portion of a shoulder capsule, a humeral neck angle, a humeral shaft angle, a glenoid angle, a glenoid inclination, a glenoid anteversion, a humeral anteversion, a humeral shaft angle, a humeral offset, a humeral resection plane, a glenoid resection plane, an uncut humeral surface, a cut humeral bone surface, or a combination thereof, or wherein the joint is an ankle joint and wherein the at least one processor is configured to use the artificial neural network to fit, the align, or fit and align the virtual implant component in relationship to at least a peripheral margin, a bone edge, a dimension, a plane, a shape, a radius, a convexity, a concavity or a surface of at least one of a portion of or an entire distal tibia, a portion of or an entire distal fibular, a portion of or an entire talus, one or more tibial or fibular osteophytes, one or more talar osteophytes, a portion of or an entire ankle ligament, a portion of an ankle joint capsule, a tibial angle, a fibular angle, a talar angle, a tibial resection plane, a talar resection plane, an uncut tibial surface, an uncut talar surface, a cut tibial bone surface, a cut talar bone surface, or a combination thereof.

### Claim 18 (depends on 1)

The system of claim 1, wherein the artificial neural network is a discriminative artificial neural network or a generative neural network.

### Claim 19 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to determine a score of virtual implant oversizing, implant overhang, implant undersizing, implant fit, implant alignment or a combination thereof in relationship to the at least a portion of the surface of the joint, the anatomic structure, the anatomic axis, the biomechanical axis, the mechanical axis, the rotation axis, the predetermined angle, the version, the slope, the joint line, a cut bone surface, a margin of a cut bone surface, an edge of a cut bone surface, a perimeter of a cut bone surface, or a combination thereof.

### Claim 20 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to compute a risk of developing postoperative pain based on the fit, alignment, or fit and alignment of the virtual implant component.

### Claim 21 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to determine a virtual implant component overhang, virtual implant component oversizing, virtual implant component undersizing, virtual component implant fit, virtual implant component alignment or combinations thereof in numeric values, and wherein the numeric values comprise at least one of mm, mm2, mm3, an angular measurement or a combination thereof.

### Claim 22 (depends on 1)

The system of claim 1, wherein the joint is a knee joint and wherein the at least one processor is configured to align the virtual implant component in relationship to the 3D model based at least in part on a transepicondylar axis, a Whiteside's line, a femoral bone surface, a femoral condyle surface, a femoral offset, a femoral component flexion, an anterior cortex, a tibial plateau surface, a tibial slope, a medial joint line, a lateral joint line, a cartilage surface, a bone surface, or a combination thereof.

### Claim 23 (depends on 1)

The system of claim 1, wherein the joint is a hip joint and wherein the at least one processor is configured to align the virtual implant component in relationship to the 3D model based at least in part on a femoral neck angle, a femoral shaft angle, an acetabular angle, an acetabular anteversion, a femoral anteversion, an inclination, a femoral shaft angle, a pelvic tilt, a pelvic plane, a Shenton's line, a Hilgenreiner line, a Perkin line, an impingement analysis, a cartilage surface, a bone surface or a combination thereof.

### Claim 24 (depends on 1)

The system of claim 1, wherein the joint is a shoulder joint and wherein the at least one processor is configured to align the virtual implant component in relationship to the 3D model based at least in part on a glenoid version, a humeral version, a cartilage surface, a bone surface or a combination thereof.

### Claim 25 (depends on 1)

The system of claim 1, wherein the joint is an ankle joint and wherein the at least one processor is configured to align the virtual implant component in relationship to the 3D model based at least in part on a tibial angle, a fibular angle, a talar angle, a tibial resection plane, a talar resection plane, an uncut tibial surface, an uncut talar surface, a cut tibial bone surface, a cut talar bone surface, a cartilage surface, a bone surface or a combination thereof.

### Claim 26 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to generate a treatment plan based on the fit, alignment or fit and alignment of the virtual implant component in relationship to the 3D model, wherein the treatment plan comprises coordinate information of a bone facing surface of the virtual implant component.

### Claim 27 (depends on 1)

The system of claim 1, wherein the at least one processor is configured to register at least a portion of the coordinate information of the bone facing surface of the virtual implant component with the patient.