Acetabular cup positioning in total hip arthroplasty

Abstract

Methods, systems, and apparatus, including medium-encoded computer program products include: obtaining one or more preoperative medical images of a pelvic region, the images including a hip joint of a patient; determining, from the preoperative medical images, one or more biomechanical features associated with respective muscles of the hip joint of the patient; obtaining corresponding reference biomechanical features associated with respective muscles of a reference hip joint; and determining, using the extracted one or more biomechanical features and the corresponding reference biomechanical features, position data and orientation data for the acetabular cup for the total hip arthroplasty.

Description

[0001] DESCRIPTION

[0002] ACETABULAR CUP POSITIONING IN TOTAL HIP ARTHROPLASTY

[0003] TECHNICAL FIELD

[0004] This application relates to computer-assisted orthopedic surgical planning. More specifically, it relates to computer-implemented techniques for acetabular cup positioning in total hip arthroplasty (TH A).

[0005] BACKGROUND

[0006] Improper acetabular component — also frequently referred to as acetabular cup — placement in THA can result in mechanical instability, accelerated wear, impingement, and increased risk of dislocation. Traditional techniques often result in significant variation in implant positioning, leading to suboptimal surgical outcomes.

[0007] Conventional surgical protocols dictate the positioning of the acetabular component within predefined safe zones, such as the Lewinnek safe zone. The Lewinnek safe zone establishes standard anteversion and inclination parameters to reduce the likelihood of postoperative dislocation. However, clinical evidence demonstrates that dislocations may still occur even when the acetabular cup is placed within these ranges. This may be due to patient-specific anatomical factors, including changes in pelvic tilt across different functional positions (standing, sitting, and supine) that dynamically alter the effective anteversion and inclination angles of the implant.

[0008] Traditionally, cup orientation has been determined based on anatomical planes of the pelvis, such as the sagittal, coronal, and transverse planes. However, variability in pelvic positioning, both preoperatively and intraoperatively, introduces inconsistencies in defining these reference planes, leading to potential inaccuracies in cup placement. Furthermore, existing methods frequently rely on the bony acetabular rim as an alignment reference, despite evidence indicating that the rim may not necessarily correspond to the functional acetabular inlet due to anatomical variations or disease-related deformities.Some approaches have made use of imaging to gain insight for acetabular cup positioning.

[0009] US12198812B2 acquires images of a patient’s pelvic region in multiple anatomical positions to calculate pelvic tilt angles corresponding to each of the anatomical positions and a target range for the inclination and anteversion angles for an acetabular cup component of a hip implant.

[0010] WO2Q23029896A1 adjusts the position of an acetabular cup for THA using deep reinforcement learning (DRL) and patient medical image data.

[0011] B. Danaei and J. McPhee, “Model-Based Acetabular Cup Orientation Optimization Based on Minimizing the Risk of Edge-Loading and Implant Impingement Following Total Hip Arthroplasty”, ASME. J Biomech Eng., 144(11): 111008 (2022) describes a model-based method for determining patient-specific acetabular cup alignment in THA. Motion capture data from patient-specific daily activities are used to calculate hip contact forces and femur-pelvis orientation via a musculoskeletal model.

[0012] Conventional approaches often neglect the influence of soft tissue, such as tendons or muscle origin and insertion points, in the biomechanics of the hip joint for acetabular cup positioning for hip surgery.

[0013] SUMMARY

[0014] This application relates to systems and techniques for acetabular cup positioning in Total Hip Arthroplasty (THA) using patient-specific biomechanical analysis.

[0015] Biomechanical analysis including muscular analysis of medical images can provide insight into the working of the hip joint. This can be particularly helpful in patients with a medical condition that impacts the functioning of the hip joint, such as arthritis. Biomechanical analysis can be used to extract the effect of tendons and / or muscles of the pelvic area acting on the hip joint, which can be used to derive e.g., the present range of motion of patients with medical conditions that impact the functioning of their hip joints.

[0016] Biomechanical analysis can also be used to infer how the hip joints of such patients would work if the medical conditions were corrected. Further, this information can be used to find positionings and sizing for acetabular cups that are most suited to the patients, considering the specifics of the patients’ tendons and / or muscles’ anatomy in the pelvic area and how they affect hip joints. Forexample, aiming for a positioning of the acetabular cup for the patient with a corrected medical condition but preserving the present or a less-than-ideal range of motion of the patient -rather than an idealized range of motion- can have certain advantages. For example, adaptation to the implant can be hastened and the rehabilitation period can be shorter. In particular, patients who have become accustomed to limited ranges of motion over years will adapt to less-than-ideal ranges of motion more quickly than to idealized ranges of motion.

[0017] The systems and techniques described herein use automated computational workflows to perform biomechanical analysis, including muscular analysis, of medical images of the pelvic area of a patient for acetabular cup positioning.

[0018] In general, one or more aspects of the subject matter described in this specification can be embodied in one or more methods and also one or more non-transitory computer-readable mediums tangibly encoding a computer program operable to cause one or more processors to perform operations) including: obtaining one or more preoperative medical images of a pelvic region, the images including a hip joint of a patient; determining, from the preoperative medical images, one or more biomechanical features associated with respective muscles of the hip joint of the patient; obtaining corresponding reference biomechanical features associated with respective muscles of a reference hip joint; and determining, using the extracted one or more biomechanical features and the corresponding reference biomechanical features, position data and orientation data for the acetabular cup for the total hip arthroplasty.

[0019] One or more aspects of the subject matter described in this specification can also be embodied in one or more systems including one or more processors; and a computer-readable medium storing instructions that cause the one or more processors to perform operations including: obtaining one or more preoperative medical images of a pelvic region, the images including a hip joint of a patient; determining, from the preoperative medical images, one or more biomechanical features associated with respective muscles of the hip joint of the patient; obtaining corresponding reference biomechanical features associated with respective muscles of a reference hip joint; and determining, using the extracted one or more biomechanical features and the corresponding reference biomechanical features, position data and orientation data for the acetabular cup for the total hip arthroplasty.These and other aspects can each, optionally, include one or more of the following features. Extracting, from the preoperative medical images, biomechanical features, can include extracting, from the preoperative medical images using one or more machine-learning algorithm, anatomical landmarks comprising muscle origin landmarks and muscle insertion landmarks; and extracting, using the anatomical landmarks, the biomechanical features. Extracting the anatomical landmarks including muscle origin landmarks and muscle insertion landmarks can include generating, using the preoperative medical images, a three-dimensional mesh of the hip pelvic region including a representation of one or more bones of the hip joint; and extracting the anatomical landmarks from the three-dimensional mesh. Generating the three-dimensional mesh can include generating a representation of an acetabulum and a femur bone of the patient.

[0020] Obtaining the corresponding reference biomechanical features associated with the respective muscles of the reference hip joint can include obtaining the reference biomechanical features based on mirroring of an opposite unaffected or clinically suitable hip joint of the patient or on a population-based statistical musculoskeletal model. The corresponding reference biomechanical features can include one or more reference biomechanical vectors. The one or more biomechanical features can include one or more biomechanical vectors. Each biomechanical vector of the one or more biomechanical vectors can have a direction and magnitude determined by the muscle and origin insertion landmarks. Determining the position data and the orientation data for the acetabular cup can include iteratively modifying the position data and orientation data for the acetabular cup to minimize a discrepancy function between the one or more biomechanical vectors and the corresponding reference biomechanical vectors. The preoperative medical images can include medical images of the pelvis region of the patient in one or more functional positions. The functional positions include any one of standing, seating, or supine. The preoperative medical images of the pelvic region can include at least one three-dimensional medical image. The preoperative medical images can include a CT or MRI scan. The method and / or the operations can include determining, for the determined position data and orientation data, a size of the acetabular cup that maintains impingement below a predetermined impingement threshold and meets anatomical constraints of the patient. The anatomical constraints can include one or more of an acetabulum size, acetabulum shape, or hip range of motion of the patient.One or more aspects of the subject matter described in this specification can be embodied in one or more methods and also one or more non-transitory computer-readable mediums tangibly encoding a computer program operable to cause one or more processors to perform operations) for planning placement of an acetabular cup in total hip arthroplasty, including: obtaining one or more preoperative medical images of a pelvic region of a patient in each of at least two anatomical positions; extracting, from the preoperative medical images, one or more pelvic muscles vectorial or tensorial features characterizing an effect of the pelvic muscles on one or more elements of a hip joint; and determining, using the extracted pelvic muscle vectorial or tensorial features, position data for the acetabular cup of the hip implant for the total hip arthroplasty.

[0021] One or more aspects of the subject matter described in this specification can also be embodied in one or more systems including one or more processors; and a computer-readable medium storing instructions that cause the one or more processors to perform operations including: obtaining one or more preoperative medical images of a pelvic region of a patient in each of at least two anatomical positions; extracting, from the preoperative medical images, one or more pelvic muscles vectorial or tensorial features characterizing an effect of the pelvic muscles on one or more elements of a hip joint; and determining, using the extracted pelvic muscle vectorial or tensorial features, position data for the acetabular cup of the hip implant for the total hip arthroplasty

[0022] These and other aspects can each, optionally, include one or more of the following features. Determining, using the extracted features, position data for the acetabular cup of the hip implant for a total hip arthroplasty can include using first one or more trained machine learning algorithms to determine position data for the acetabular cup of the hip implant for a total hip arthroplasty based on a range of motion of the patient in each of the at least two anatomical images derived from the extracted one or more pelvic muscles vectorial or tensorial features. The pelvic muscle vectorial or tensorial features can include pelvic muscle forces. For example, pelvic muscle forces directed from an acetabulum towards a femur bone and / or pelvic muscle forces directed from the femur bone towards the acetabulum. Determining, using the determined vectorial or tensorial pelvic muscle features, position data for the acetabular cup of the hip implant can include determining position data for the acetabular cup based on force distribution and / or force balance for each of the two or more functional positions. Determining the positiondata for the acetabular cup can include determining the position data that minimizes force imbalances in each of the two or more functional positions. The preoperative medical images can include medical images of the pelvis area of the patient in two or more functional positions. The functional positions can include any one of standing, seating, or supine. The method and the operations can further include extracting, from the preoperative medical images, features of one or more hip joint elements. The features can include features of an acetabulum and / or features of a femur bone of the patient. Extracting the one or more pelvic muscles vectorial or tensorial features can include extracting the one or more pelvic muscles features using a second one or more trained machine learning algorithms.

[0023] In general, one or more aspects of the subject matter described in this specification can be embodied in one or more methods (and also one or more non-transitory computer-readable mediums tangibly encoding a computer program operable to cause one or more processors to perform operations) for determining acetabular cup placement for an upcoming total hip arthroplasty, including: receiving preoperative medical images of the pelvic region of a patient who is in at least two different anatomical positions; estimating, from the preoperative medical images, forces applied in the pelvic region; and determining, based on the estimated forces, a placement of an acetabular cup for an upcoming total hip arthroplasty procedure.

[0024] One or more aspects of the subject matter described in this specification can also be embodied in one or more systems including one or more processors; and a computer-readable medium storing instructions that cause the one or more processors to perform operations including: receiving preoperative medical images of the pelvic region of a patient who is in at least two different anatomical positions; estimating, from the preoperative medical images, forces applied in the pelvic region; and determining, based on the estimated forces, a placement of an acetabular cup for an upcoming total hip arthroplasty procedure.

[0025] These and other aspects can each, optionally, include one or more of the following features. Estimating the forces applied in the pelvic region can include inputting the preoperative medical images into a machine learning model trained to estimate the dynamic forces applied in the pelvic region from such preoperative medical images. At least some of the preoperative medical images can be images of soft tissue. Estimating the forces applied in the pelvic region can include extracting parameters characteristic of muscular contraction and relaxation from the preoperativemedical images of soft tissue. Estimating the forces applied in the pelvic region can include estimating the forces applied in the pelvic region while the patient is in the anatomical positions. Determining the placement of the acetabular cup can include determining an orientation of the acetabular cup that withstands forces applied to the acetabular cup while the patient is in the anatomical positions. The anatomical positions can include any one of sitting, standing, or supine. The medical images of the pelvic region can include at least one three-dimensional medical image, for example, the medical images include a CT scan. The method and the operations can include estimating a pressure applied from a patient’s femur bone towards the patient’s acetabulum. Estimating, from the preoperative medical images, the forces applied in the pelvic region can include estimating the forces applied from muscles that are responsible for lateral or external rotation, muscles that are responsible for medial or internal rotation, muscles that are responsible for extension or retroversion, muscles that are responsible for flexion or anteversion, muscles that are responsible for abduction, or muscles that are responsible for adduction.

[0026] In general, one or more aspects of the subject matter described in this specification can be embodied in one or more methods (and also one or more non-transitory computer-readable mediums tangibly encoding a computer program operable to cause one or more processors to perform operations) for training a machine learning model for determining acetabular cup placement for an upcoming total hip arthroplasty, including: receiving medical images of the pelvic regions of healthy patients who are each in at least two different anatomical positions and training the machine learning model with the medical images of the pelvic regions of the healthy patients. At least some of the medical images of each healthy patient can represent soft tissue. At least some of the medical images of the pelvic regions of healthy patients are example inputs and acetabular cup positions shown in the medical images of the pelvic regions of healthy patients are desired outputs.

[0027] One or more aspects of the subject matter described in this specification can also be embodied in one or more systems including one or more processors; and a computer-readable medium storing instructions that cause the one or more processors to perform operations including: receiving medical images of the pelvic regions of healthy patients who are each in at least two different anatomical positions and training the machine learning model with the medical images of the pelvic regions of the healthy patients. At least some of the medical images of each healthypatient can represent soft tissue. At least some of the medical images of the pelvic regions of healthy patients are example inputs and acetabular cup positions shown in the medical images of the pelvic regions of healthy patients are desired outputs.

[0028] These and other aspects can each, optionally, include one or more of the following features. The method and the operations can include extracting parameters that characterize the soft tissue represented in the medical images, and training the machine learning model using the extracted parameters as example inputs. The method and the operations can further include receiving medical images of the pelvic regions of individuals with medical conditions affecting the hip who are each in at least two different anatomical positions. The method and the operations can further include training the machine learning model with the medical images of the pelvic regions of the individuals with medical conditions affecting the hip. At least some of the medical images of the pelvic regions of the individuals with medical conditions affecting the hip can be example inputs and acetabular cup positions shown in the medical images of the pelvic regions of individuals with medical conditions affecting the hip are desired outputs.

[0029] Particular embodiments of the subject matter described in this specification can be implemented to realize one or more of the following advantages. The described systems and techniques can integrate the results of patient-specific biomechanical analysis, including tendon and / or muscular analysis, derived from medical images into patient-specific preoperative planning of THA to improve the consistency and precision of acetabular cup placement. The described techniques can improve surgical results, improve implant longevity, reduce complications during total hip arthroplasty, and enhance patient outcomes.

[0030] The details of one or more implementations of the subject matter described in this specification are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages will become apparent from the description, the drawings, and the claims.

[0031] BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a flowchart of an example of a computer-implemented method for acetabular cup positioning.Like reference numbers and designations in the various drawings indicate like elements.

[0032] DETAILED DESCRIPTION FIG. 1 is a flowchart of an example of a computer-implemented method 100 for acetabular cup positioning for an upcoming total hip arthroplasty.

[0033] At 105, one or more preoperative medical images of a patient are obtained. The preoperative medical images can be images of the pelvic region, including a hip joint, of the patient. The images of the pelvic region can include at least one three-dimensional medical image. For example, the medical images can include a Computed Tomography (CT) scan, a Magnetic Resonance Imaging (MRI) scan, three-dimensional anatomical models generated from two-dimensional images (for example, as described inUS2023281842Al orUS2024005504Al), or any other three-dimensional imaging modality capable of reconstructing pelvic and femoral anatomy. In some examples, the medical images can include one or more radiographic images. In some examples, a combination of medical images can be used. For example, a combination of an MRI scan and one or more radiographic images can be used.

[0034] The preoperative medical images can include medical images of the pelvis region of the patient in one or more functional positions. For example, the medical images can be taken with the patient in any one or more of standing, seating, supine, or daily activity positions. The images can include a representation of one or more bones of the hip joint. The images can include a representation of the acetabulum and a femur bone of the patient.

[0035] At 110, one or more biomechanical features associated with respective muscles of the hip joint can be determined from the preoperative medical images. The biomechanical features can include biomechanical vectors that represent the state of respective muscles in the functional position in which the medical images are obtained and their effect on bones of the hip joint. The biomechanical features are patient-specific and represent the diseased musculoskeletal configuration of the hip joint of the patient.

[0036] For example, the muscles for which biomechanical features are determined can include one or more of gluteus medius, gluteus minimus, gluteus maximus, lateral rotators including piriformisand obturator muscles, tensor fascia lata (TFL), and iliopsoas, all of which influence acetabular cup positioning.

[0037] The muscles for which biomechanical features are determined include but are not limited to muscles that are responsible for lateral or external rotation, muscles that are responsible for medial or internal rotation, muscles that are responsible for extension or retroversion, muscles that are responsible for flexion or anteversion, muscles that are responsible for abduction, or muscles that are responsible for adduction.

[0038] The muscles that are responsible for lateral or external rotation include one or more of gluteus maximus; quadratus femoris; obturator internus; dorsal fibers of gluteus medius and minimus; iliopsoas (including psoas major from the vertebral column); obturator externus; adductor magnus, longus, brevis, and minimus; piriformis; or sartorius.

[0039] The muscles that are responsible for medial or internal rotation include one or more of anterior fibers of gluteus medius and minimus; tensor fasciae latae; the part of adductor magnus inserted into the adductor tubercle; or, with the leg abducted, the pectineus.

[0040] The muscles that are responsible for extension or retroversion include one or more of gluteus maximus; dorsal fibers of gluteus medius and minimus; adductor magnus; and piriformis.

[0041] The muscles that are responsible for flexion or anteversion include one or more of hip flexors: iliopsoas (with psoas major from vertebral column); tensor fasciae latae, pectineus, adductor longus, adductor brevis, gracilis, rectus femoris or sartorius.

[0042] The muscles that are responsible for abduction include one or more of gluteus medius; tensor fasciae latae; gluteus maximus with its attachment at the fascia lata; gluteus minimus; piriformis; or obturator internus.

[0043] The muscles that are responsible for adduction include one or more of adductor magnus with adductor minimus; adductor longus, adductor brevis, gluteus maximus with its attachment at the gluteal tuberosity; gracilis (extends to the tibia); pectineus, quadratus femoris; or obturator extemus.Referring again to FIG. 1, determining 110 the biomechanical features, including biomechanical vectors, can include extracting 120, from the preoperative medical images, anatomical landmarks associated to muscles and / or tendons. For example, the anatomical landmarks can include muscle attachments to bones through corresponding tendons. Muscle attachments include muscle origins and muscle insertions. If the attachment is on a bone that remains substantially immobile when the muscle contracts, the attachment is a muscle origin. If the attachment is on a bone that moves when the muscle contracts, the attachment is a muscle insertion. The anatomical landmarks can include muscle origin and muscle insertion for a muscle. For example, muscle insertion landmarks in the femur and muscle origin landmarks in the pelvis or vice versa can be extracted.

[0044] A biomechanical vector of a muscle connects a muscle origin landmark and a muscle insertion landmark. The magnitude of the biomechanical vector represents a muscle length. The direction of the biomechanical vector represents a muscle direction. The biomechanical (or “muscle” vector) can be a vector pointing from the muscle origin to the muscle insertion and with a magnitude defined by the distance between the two.

[0045] Automated anatomical analysis models can be used. For example, the anatomical landmarks can be extracted using one or more machine-learning algorithms. For example, extracting, from the preoperative medical images using one or more machine-learning algorithms, anatomical landmarks including muscle origin and muscle insertion landmarks can include generating, using the preoperative medical images, a three-dimensional mesh of the hip pelvic region including a representation of one or more bones of the hip joint, and extracting the anatomical landmarks from the three-dimensional mesh. The one or more machine-learning algorithms can be machinelearning models trained to extract landmarks for a three-dimensional mesh. Deep learning models can be used. Supervised learning, unsupervised learning, or hybrid learning approaches can be used to train the one or more machine-learning models. Once coordinates of the muscle origin and muscle insertion anatomical landmarks have been extracted, the muscle origin and muscle insertion anatomical landmarks coordinates can be used to determine 110 the biomechanical features. Biomechanical vectors can be determined from the coordinates of the extracted landmarks, for example, by subtracting their coordinates.At 125, corresponding reference biomechanical features associated with respective muscles of a reference hip joint are obtained. The corresponding biomechanical reference features can correspond to a target “healthy” musculoskeletal configuration.

[0046] The reference biomechanical features can be derived by contralateral anatomical mirroring 127 of the opposite hip of the patient when the opposite hip is unaffected or is clinically suitable. For example, medical images of the patient can be used to determine one or more biomechanical features for the opposite hip, as described above for the affected hip. For example, biomechanical vectors for the opposite hip can be determined using anatomical landmarks and trained machine learning models as described above. The extracted biomechanical vectors for the opposite hip can then be subject to contralateral anatomical mirroring to obtain reference biomechanical vectors.

[0047] Additionally or alternatively, the reference biomechanical features can be obtained 125 from statistical musculoskeletal models constructed from medical images of a population of healthy individuals. For example, a plurality of medical images (e.g., MRI, CT, or other three-dimensional images or a combination of medical images, such as a combination of an MRI scan and one or more radiographic images) of a pelvic region including a hip joint of healthy individuals can be obtained. Biomechanical features, including biomechanical vectors, can be determined for each one of the plurality of medical images using anatomical landmarks and trained machine learning models as described above. The resulting biomechanical vectors can be averaged to determine reference biomechanical vectors.

[0048] Based on the one or more biomechanical features and the reference biomechanical features, position and orientation data for the acetabular cup can be determined 130. For example, determining position and orientation data can include iteratively modifying position and orientation data for the acetabular cup to minimize a discrepancy function between the one or more biomechanical vectors and the corresponding reference biomechanical vectors.

[0049] The position data can include spatial position data corresponding to a center of rotation of the hip joint, which corresponds to the center of rotation of the acetabular cup relative to the pelvis bone and femur. The orientation data can include an inclination angle and a version angle for the acetabular cup. The version angle can be an anteversion angle or a retroversion angle. In someexamples, other reference angles can be used to characterize the placement of the artificial acetabular cup.

[0050] For each candidate configuration of position and orientation data for the acetabular cup, the biomechanical vectors corresponding to respective muscles of the hip joint are recalculated and compared with the reference biomechanical vectors. A discrepancy function representing the difference between the patient-specific biomechanical vectors and reference biomechanical vectors is evaluated across a plurality of muscles. The discrepancy function can correspond to a weighted difference between diseased biomechanical vectors and reference biomechanical vectors, where weighting coefficients correspond to biomechanical relevance of corresponding individual muscles or muscle groups. The optimal cup placement (position data and orientation data) can be determined by minimizing the multi-muscle discrepancy function.

[0051] If it is determined 135 that the discrepancy function is above a certain threshold, the iterative method continues and the discrepancy function is further minimized. If it is determined 135 that the discrepancy function has reached an acceptable value, the iterative method ends.

[0052] The determination of cup position and orientation data can be implant-agnostic. This eliminates the need for an implant model or any implant-dependent measurements. After determining a candidate optimized cup position and orientation, a size for the acetabular cup can be determined 140 and a verification step including evaluating potential impingement 155 conditions can be performed. Data from digital templates of implants can be used. For example, the digital template can include size and shape data of an acetabular component and a femoral component of the implant. For example, collisions between femoral and acetabular components of a template across one or more ranges of hip motion of the patient can be analyzed. If an impingement condition is detected, the candidate implant template size can be iteratively adjusted, for instance by iteratively trying templates of different sizes, until an impingement-free configuration satisfying biomechanical constraints is obtained. For example, the biomechanical constraints can include the acetabulum size, acetabulum shape, including acetabulum curvature, and / or one or more ranges of hip motion of the patient.

[0053] The acetabular cup positioning, for example, the position data and orientation data of the acetabular cup as described by the center of rotation of the acetabular cup and an inclination angle and aversion angle can be provided 160 as part of patient-specific preoperative planning of THA. Implant size data, including acetabular component size data, and optionally corresponding femoral component size data, can also be provided as part of the patient-specific preoperative planning of THA.

[0054] The optimization process determines an acetabular cup placement that restores biomechanical balance between diseased biomechanical vectors and target reference biomechanical vectors. Patients who have become accustomed to less-than-ideal acetabular cup positions over long periods will generally adapt to less-than-ideal acetabular cup positions and ranges of motion more quickly than to idealized acetabular cup positions and idealized ranges of motion. Accordingly, modified target biomechanical reference vectors can be used rather than those corresponding to completely healthy individuals.

[0055] In other examples of systems and methods for determining pre-operative placement of an artificial acetabular cup in THA, determining the pre-operative placement of an artificial acetabular cup can include determining an orientation of the acetabular cup. For example, the pre-operative placement can be characterized by an inclination angle and a version angle for the acetabular cup. The version angle can be an anteversion angle or a retroversion angle. In some examples, other reference angles can be used to characterize the placement of the artificial acetabular cup. The described techniques can analyze medical images to estimate patient-specific pelvic muscle features. Images acquired with the patient in two or more anatomical positions can be analyzed to obtain pelvic muscle features at each position.

[0056] The pelvic muscle features can describe the state of the muscles at each position (e.g., pelvic muscles position, length, stretch, etc.). The pelvic muscle features can describe the effect of the pelvic muscles on one or more elements of the hip joint at each position. For example, the pelvic muscle features can include tensorial or vectorial quantities, such as forces, accelerations, pressure, stress, etc., generated by the pelvic muscles and affecting one or more hip joint elements and that would thus affect the artificial acetabular cup of a hip implant. For example, the pelvic muscle features can include forces generated from a patient’s acetabulum towards the femur bone of the patient and from the femur bone towards the acetabulum. In some examples, additional forces can be considered. The muscles for which pelvic muscle features can be obtained include but are not limited to muscles that are responsible for lateral or external rotation, muscles that are responsiblefor medial or internal rotation, muscles that are responsible for extension or retroversion, muscles that are responsible for flexion or anteversion, muscles that are responsible for abduction, or muscles that are responsible for adduction.

[0057] The obtained patient-specific pelvic muscle features in each of two or more anatomical positions can be analyzed and compared to each other to understand the different forces or other vectorial or tensorial quantities that describe how the pelvic muscles affect the hip joint at each of the different positions. In some cases, the range of motion of the patient at each of the different positions can be extracted. The impact of the pelvic muscle features on the range of motion can also be analyzed in order to understand how the hip joint of the patient would work once the medical condition is corrected.

[0058] Based on the forces or the other vectorial or tensorial quantities that describe how the pelvic muscle affect one or more elements of the hip joint, a position for the artificial acetabular cup can be determined.

[0059] The described techniques can integrate machine- learning based inference of the pelvic muscle features based on medical imaging analysis into a method for preoperative planning of THA.

[0060] In some examples, the determination can be implant-agnostic. This eliminates the need for an implant model or any implant-dependent measurements. The medical imaging analysis can include acquiring preoperative medical images of the patient’s pelvic region in two or more functional positions, including standing, seating, and supine. The medical images can include at least one three-dimensional medical image. For example, the medical images can include an MRI scan. For example, the medical images can include a MRI scan for at least one of the two or more functional positions or for the two or more functional positions. The medical images can include a CT scan for at least one of the two or more functional positions or for the two or more of the functional positions. In some examples, the medical images can include one or more radiographic images for at least one of the two or more functional positions or for the two or more of the functional positions. In some examples, a combination of medical images can be used. For example, a combination of an MRI scan and one or more radiographic images for each of the anatomical positions can be used.Patient-specific muscle features can be obtained using a trained machine learning algorithm. For example, deep learning algorithms can be used.

[0061] For example, the pre-operative medical image data can be processed with a trained machinelearning algorithm for analysis. The machine-learning algorithm can calculate pelvic muscle features affecting the hip joint or one or more hip joint elements, as described above. For example, forces or other vectorial or tensorial quantities characterizing how the pelvic muscles affect one or more hip joint elements and, in some cases, the range of motion of the patient extract, can be extracted from the medical images and used to train a machine learning algorithm to determine positions of acetabulum. For example, the machine learning algorithm can be trained to extract, from the medical images, forces generated from a patient’s acetabulum towards the femur bone, and the forces from the femur bone towards the acetabulum in each anatomical position.

[0062] The machine-learning algorithm can use the determined vectorial or tensorial quantities in two or more anatomical positions to determine an acetabular cup position. For example, the machine learning algorithm can be trained to determine a distribution and / or balance of forces exerted by the pelvic muscles on the hip joint at each of the anatomical positions. Other vectorial or tensorial quantities can be used additionally or alternatively. For example, accelerations, stress, pressure, strain, etc. can be used additionally or alternatively.

[0063] The machine-learning algorithm can calculate the pelvic muscle force distribution to determine an acetabular cup positioning and orientation that can withstand the forces of the pelvic muscles for the patient at each of the anatomical positions. For example, the machine-learning algorithm can determine the acetabular cup positioning adapted to the present range of motion, or to another less-than-ideal range of motion, of the patient in each of the anatomical positions.

[0064] The acetabular cup positioning, for example, the orientation of the artificial acetabular cup as described by an inclination angle and a version angle can be output by the trained machine learning algorithm and provided as part of patient-specific preoperative planning of THA.

[0065] The machine learning algorithms can be trained with a set of medical images of healthy individuals or with data extracted from such images. For example, for each individual of a set of healthy individuals, one or more medical images for two or more anatomical positions can be used for training the machine learning algorithms. The medical images of the pelvic regions of healthypatients can serve as example inputs and acetabular cup positions shown in those medical images can serve as the desired outputs. One or more three-dimensional images (e.g., a MRI, a CT scan, etc.) can be used. Additionally, one or more radiographic images for each healthy individual can be used. A similar set of medical images can be provided for each individual of a set of healthy individuals. Machine learning algorithms that are trained with medical images can then determine individualized acetabular cup positioning from corresponding images of different patients.

[0066] In some implementations, parameters extracted from such medical images (either by a machine learning algorithm or otherwise) can be used to train a machine learning algorithm. For example, the forces or other vectorial or tensorial quantities that characterize how the pelvic muscles affect one or more hip joint elements can be extracted from images gathered using imaging modalities that are capable of imaging soft tissue. For example, the dimensional changes associated with muscular contraction and relaxation can be determined from such images and used to train machine learning algorithms. The parameters extracted from medical images of the pelvic regions of healthy patients can serve as example inputs and acetabular cup positions shown in those medical images can serve as the desired outputs. Machine learning algorithms that are trained with the parameters extracted from such medical images can then determine individualized acetabular cup positioning from corresponding parameters extracted from medical images of different patients.

[0067] In some implementations, both medical images and data extracted from medical images can be used as example inputs when training a machine learning algorithm and then input into the trained algorithm to determine individualized acetabular cup positioning from corresponding extracted data and medical images of different patients.

[0068] In some implementations, medical images of individuals with medical conditions affecting the hip (e.g., arthrosis) and / or parameters extracted therefrom can also be used in training a machine learning algorithm, i.e., in conjunction with medical images of healthy individuals. The acetabular cup positions of the individuals with medical conditions affecting the hip can serve as the desired outputs during such training. By using medical images of both healthy individuals and individuals with medical conditions affecting the hip to train the model, the model can effectively be trained to output less-than-ideal acetabular cup positions. In other words, the acetabular cup positions output by the model will be intermediate between a healthy hip and a diseased hip. Patients who have become accustomed to less-than-ideal acetabular cup positions over long periods willgenerally adapt to less-than-ideal acetabular cup positions and ranges of motion more quickly than to acetabular cup positions and idealized ranges of motion. Supervised or unsupervised learning can be used to train the machine learning algorithm.

[0069] One or more aspects of the subject matter described in this specification can be embodied in one or more computer-implemented methods as described above. One or more aspects of the subject matter described in this specification can also be embodied in one or more non-transitory computer-readable mediums tangibly encoding a computer program operable to cause one or more processors to perform operations. One or more aspects of the subject matter described in this specification can also be embodied in one or more systems including one or more processors; and a computer-readable medium storing instructions that cause the one or more processors to perform operations including any of the methods described above.

[0070] Embodiments of the subject matter and the functional operations described in this specification can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Embodiments of the subject matter described in this specification can be implemented using one or more modules of computer program instructions encoded on a non-transitory computer-readable medium for execution by, or to control the operation of, data processing apparatus. The computer-readable medium can be a manufactured product, such as hard drive in a computer system or an optical disc sold through retail channels, or an embedded system. The computer-readable medium can be acquired separately and later encoded with the one or more modules of computer program instructions, e.g., after delivery of the one or more modules of computer program instructions over a wired or wireless network. The computer-readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, or a combination of one or more of them.

[0071] The term “data processing apparatus” encompasses all apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers. The apparatus can include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, a runtime environment, or a combination of one or more of them. In addition, theapparatus can employ various different computing model infrastructures, such as web services, distributed computing, and grid computing infrastructures.

[0072] A computer program (also known as a program, software, software application, script, or code) can be written in any suitable form of programming language, including compiled or interpreted languages, declarative or procedural languages, and it can be deployed in any suitable form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.

[0073] The processes and logic flows described in this specification can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit). Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read only memory or a random access memory or both. The essential elements of a computer are a processor for performing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magnetooptical disks, or optical disks. However, a computer need not have such devices.

[0074] Moreover, a computer can be embedded in another device, e.g., a mobile telephone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device (e.g., a universal serial bus (USB) flash drive), to name just a few. Devices suitable for storing computer program instructions and datainclude all forms of nonvolatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magnetooptical disks; and CDROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0075] To provide for interaction with a user, embodiments of the subject matter described in this specification can be implemented on a computer having a display device, e.g., an LCD (liquid crystal display) display device, an OLED (organic light emitting diode) display device, or another monitor, for displaying information to the user, and a keyboard and a pointing device, e.g., a mouse or a trackball, by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any suitable form of sensory feedback, e.g., visual feedback, auditory feedback, or tactile feedback; and input from the user can be received in any suitable form, including acoustic, speech, or tactile input.

[0076] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. Embodiments of the subject matter described in this specification can be implemented in a computing system that includes a back-end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front-end component, e.g., a client computer having a graphical user interface or a browser user interface through which a user can interact with an implementation of the subject matter described is this specification, or any combination of one or more such back-end, middleware, or front-end components. The components of the system can be interconnected by any suitable form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (“LAN”) and a wide area network (“WAN”), an inter-network (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks).While this specification contains many implementation details, these should not be construed as limitations on the scope of what is being or may be claimed, but rather as descriptions of features specific to particular embodiments of the disclosed subject matter. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.

[0077] Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0078] Thus, particular embodiments of the invention have been described. Other embodiments are within the scope of the following claims. In addition, actions recited in the claims can be performed in a different order and still achieve desirable results.EXAMPLES

[0079] Although the present application is defined in the attached claims, it should be understood that the present invention can also (additionally or alternatively) be defined in accordance with the following examples:

[0080] 1. A computer-implemented method for planning placement of an acetabular cup in total hip arthroplasty, comprising:

[0081] obtaining one or more preoperative medical images of a pelvic region of a patient in each of at least two anatomical positions;

[0082] extracting, from the preoperative medical images, one or more pelvic muscle vectorial or tensorial features characterizing an effect of the pelvic muscles on one or more elements of a hip joint; and

[0083] determining, using the extracted pelvic muscle vectorial or tensorial features, position data for the acetabular cup of the hip implant for the total hip arthroplasty.

[0084] 2. The method of example 1, wherein determining, using the extracted features, position data for the acetabular cup of the hip implant for a total hip arthroplasty comprises using first one or more trained machine learning algorithms to determine position data for the acetabular cup of the hip implant for a total hip arthroplasty based on a range of motion of the patient in each of the at least two anatomical images derived from the extracted one or more pelvic muscles vectorial or tensorial features.

[0085] 3. The method of any preceding example, wherein the pelvic muscle vectorial or tensorial features include pelvic muscle forces, for example, pelvic muscle forces directed from an acetabulum towards a femur bone and / or pelvic muscle forces directed from the femur bone towards the acetabulum.

[0086] 4. The method of example 3, wherein determining, using the determined vectorial or tensorial pelvic muscle features, position data for the acetabular cup of the hip implant comprises determining position data for the acetabular cup based on force distribution and / or force balance for each of the two or more functional positions, and optionally wherein determining the positiondata for the acetabular cup comprises determining the position data that minimizes force imbalances in each of the two or more functional positions.

[0087] 5. The method of any preceding example, wherein the preoperative medical images include medical images of the pelvis area of the patient in two or more functional positions, and optionally wherein the functional positions include any one of standing, seating, or supine.

[0088] 6. The method of any preceding example 1, further comprising extracting, from the preoperative medical images, features of one or more hip joint elements, and optionally wherein the features include either features of an acetabulum and / or features of a femur bone of the patient.

[0089] 7. The method of example 1, wherein extracting the one or more pelvic muscles vectorial or tensorial features comprises extracting the one or more pelvic muscles features using a second one or more trained machine learning algorithms.

[0090] 8. A data processing apparatus comprising a processor configured to perform operations comprising the method of any one of examples 1 to 7.

[0091] 9. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of any one of examples 1 to 7.

[0092] 10. A method for determining acetabular cup placement for an upcoming total hip arthroplasty, the method comprising:

[0093] receiving preoperative medical images of the pelvic region of a patient who is in at least two different anatomical positions;

[0094] estimating, from the preoperative medical images, forces applied in the pelvic region; and determining, based on the estimated forces, a placement of an acetabular cup for an upcoming total hip arthroplasty procedure.

[0095] 11. The method of example 0, wherein estimating the forces applied in the pelvic region comprises inputting the preoperative medical images into a machine learning model trained to estimate the dynamic forces applied in the pelvic region from such preoperative medical images.12. The method of example 0, wherein:

[0096] at least some of the preoperative medical images are images of soft tissue; and estimating the forces applied in the pelvic region comprises extracting parameters characteristic of muscular contraction and relaxation from the preoperative medical images of soft tissue.

[0097] 13. The method of example 0, wherein estimating the forces applied in the pelvic region comprises estimating the forces applied in the pelvic region while the patient is in the anatomical positions.

[0098] 14. The method of example 0, wherein determining the placement of the acetabular cup comprises determining an orientation of the acetabular cup that withstands forces applied to the acetabular cup while the patient is in the anatomical positions.

[0099] 15. The method of example 0, wherein the anatomical positions include any one of sitting, standing, or supine.

[0100] 16. The method of example 0, wherein the medical images of the pelvic region include at least one three-dimensional medical image, for example, the medical images include a CT scan.

[0101] 17. The method of example 0, comprising estimating a pressure applied from a patient’s femur bone towards the patient’s acetabulum.

[0102] 18. The method of example 0, wherein estimating, from the preoperative medical images, the forces applied in the pelvic region comprises estimating the forces applied from muscles that are responsible for lateral or external rotation, muscles that are responsible for medial or internal rotation, muscles that are responsible for extension or retroversion, muscles that are responsible for flexion or anteversion, muscles that are responsible for abduction, or muscles that are responsible for adduction.

[0103] 19. A data processing apparatus comprising a processor configured to perform operations comprising the method of any one of examples 0 to 0.20. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of any one of examples 0 to 0.

[0104] 21. A method for training a machine learning model for determining acetabular cup placement for an upcoming total hip arthroplasty, the method comprising:

[0105] receiving medical images of the pelvic regions of patients who are each in at least two different anatomical positions, wherein at least some of the medical images of each healthy patient represent soft tissue;

[0106] training the machine learning model with the medical images of the pelvic regions of the healthy patients, wherein at least some of the medical images of the pelvic regions of healthy patients are example inputs and acetabular cup positions shown in the medical images of the pelvic regions of healthy patients are desired outputs.

[0107] 22. The method of example 0, further comprising:

[0108] extracting parameters that characterize the soft tissue represented in the medical images; and

[0109] training the machine learning model using the extracted parameters as example inputs.

[0110] 23. The method of example 0, further comprising:

[0111] receiving medical images of the pelvic regions of individuals with medical conditions affecting the hip who are each in at least two different anatomical positions; and

[0112] training the machine learning model with the medical images of the pelvic regions of the individuals with medical conditions affecting the hip, wherein at least some of the medical images of the pelvic regions of the individuals with medical conditions affecting the hip are example inputs and acetabular cup positions shown in the medical images of the pelvic regions of individuals with medical conditions affecting the hip are desired outputs.

[0113] 24. A computer-implemented method for determining placement of an acetabular cup for a total hip arthroplasty, comprising:

[0114] obtaining one or more preoperative medical images of a pelvic region, the images including a hip joint of a patient;

[0115] determining, from the preoperative medical images, one or more biomechanical featuresassociated with respective muscles of the hip joint of the patient;

[0116] obtaining corresponding reference biomechanical features associated with respective muscles of a reference hip joint; and

[0117] determining, using the extracted one or more biomechanical features and the corresponding reference biomechanical features, position data and orientation data for the acetabular cup for the total hip arthroplasty.

[0118] 25. The method of example 24, wherein extracting, from the preoperative medical images, biomechanical features, comprises

[0119] extracting, from the preoperative medical images using one or more machine-learning algorithm, anatomical landmarks comprising muscle origin landmarks and muscle insertion landmarks; and

[0120] extracting, using the anatomical landmarks, the biomechanical features.

[0121] 26. The method of example 25, wherein extracting the anatomical landmarks comprising muscle origin landmarks and muscle insertion landmarks comprises:

[0122] generating, using the preoperative medical images, a three-dimensional mesh of the hip pelvic region including a representation of one or more bones of the hip joint; and extracting the anatomical landmarks from the three-dimensional mesh.

[0123] 27. The method of example 26, wherein generating the three-dimensional mesh includes generating a representation of an acetabulum and a femur bone of the patient.

[0124] 28. The method of any one of examples 24 to 27, wherein obtaining the corresponding reference biomechanical features associated with the respective muscles of the reference hip joint comprises obtaining the reference biomechanical features based on mirroring of an opposite unaffected or clinically suitable hip joint of the patient or on a population-based statistical musculoskeletal model.

[0125] 29. The method of any one of examples 24 to 28, wherein:

[0126] the corresponding reference biomechanical features comprise one or more reference biomechanical vectors,

[0127] the one or more biomechanical features comprise one or more biomechanical vectors, andeach biomechanical vector of the one or more biomechanical vectors has a direction and magnitude determined by the muscle and origin insertion landmarks.

[0128] 30. The method of example 29, wherein determining the position data and the orientation data for the acetabular cup comprises iteratively modifying the position data and orientation data for the acetabular cup to minimize a discrepancy function between the one or more biomechanical vectors and the corresponding reference biomechanical vectors.

[0129] 31. The method of any one of examples 24 to 30, wherein the preoperative medical images include medical images of the pelvis region of the patient in one or more functional positions, and optionally wherein the functional positions include any one of standing, seating, or supine.

[0130] 32. The method of any one of examples 24 to 31, wherein the preoperative medical images of the pelvic region comprise at least one three-dimensional medical image, optionally wherein the preoperative medical images comprise a CT or MRI scan.

[0131] 33. The method of any one of examples 24 to 32, comprising determining, for the determined position data and orientation data, a size of the acetabular cup that maintains impingement below a predetermined impingement threshold and meets anatomical constraints of the patient.

[0132] 34. The method of any one of examples 24 to 33, wherein the anatomical constraints comprise one or more of an acetabulum size, acetabulum shape, or hip range of motion of the patient.

[0133] 35. A data processing apparatus comprising a processor configured to perform operations comprising the method of any one of examples 24 to 34.

[0134] 36. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of any one of examples 24 to 34.

Claims

CLAIMS1. A computer-implemented method for determining placement of an acetabular cup for a total hip arthroplasty, comprising:obtaining one or more preoperative medical images of a pelvic region, the images including a hip joint of a patient;determining, from the preoperative medical images, one or more biomechanical features associated with respective muscles of the hip joint of the patient;obtaining corresponding reference biomechanical features associated with respective muscles of a reference hip joint; anddetermining, using the extracted one or more biomechanical features and the corresponding reference biomechanical features, position data and orientation data for the acetabular cup for the total hip arthroplasty.

2. The method of claim 1, wherein extracting, from the preoperative medical images, biomechanical features, comprisesextracting, from the preoperative medical images using one or more machine-learning algorithm, anatomical landmarks comprising muscle origin landmarks and muscle insertion landmarks; andextracting, using the anatomical landmarks, the biomechanical features.

3. The method of claim 2, wherein extracting the anatomical landmarks comprising muscle origin landmarks and muscle insertion landmarks comprises:generating, using the preoperative medical images, a three-dimensional mesh of the hip pelvic region including a representation of one or more bones of the hip joint; andextracting the anatomical landmarks from the three-dimensional mesh.

4. The method of claim 3, wherein generating the three-dimensional mesh includes generating a representation of an acetabulum and a femur bone of the patient.

5. The method of any of the preceding claims, wherein obtaining the corresponding reference biomechanical features associated with the respective muscles of the reference hip joint comprises obtaining the reference biomechanical features based on mirroring of an oppositeunaffected or clinically suitable hip joint of the patient or on a population-based statistical musculoskeletal model.

6. The method of any preceding claim, wherein:the corresponding reference biomechanical features comprise one or more reference biomechanical vectors,the one or more biomechanical features comprise one or more biomechanical vectors, and each biomechanical vector of the one or more biomechanical vectors has a direction and magnitude determined by the muscle and origin insertion landmarks.

7. The method of claim 6, wherein determining the position data and the orientation data for the acetabular cup comprises iteratively modifying the position data and orientation data for the acetabular cup to minimize a discrepancy function between the one or more biomechanical vectors and the corresponding reference biomechanical vectors.

8. The method of any preceding claim, wherein the preoperative medical images include medical images of the pelvis region of the patient in one or more functional positions, and optionally wherein the functional positions include any one of standing, seating, or supine.

9. The method of any preceding claim, wherein the preoperative medical images of the pelvic region comprise at least one three-dimensional medical image, optionally wherein the preoperative medical images comprise a CT or MRI scan.

10. The method of any preceding claim, comprising determining, for the determined position data and orientation data, a size of the acetabular cup that maintains impingement below a predetermined impingement threshold and meets anatomical constraints of the patient.

11. The method of any preceding claim, wherein the anatomical constraints comprise one or more of an acetabulum size, acetabulum shape, or hip range of motion of the patient.

12. A data processing apparatus comprising a processor configured to perform operations comprising the method of any one of claims 1 to 11.

13. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of any one of claims 1 to 11.

Images