Noninvasive diagnostic system
Inventors
Mahfouz, Mohamed M. • Komistek, Rick • Wasielewski, Ray C.
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-8444564-B2
Publication Date
2013-05-21
Expiration Date
Abstract
A method for diagnosing a joint condition includes in one embodiment: creating a 3d model of the patient specific bone; registering the patient's bone with the bone model; tracking the motion of the patient specific bone through a range of motion; selecting a database including empirical mathematical descriptions of the motion of a plurality actual bones through ranges of motion; and comparing the motion of the patient specific bone to the database.
Core Innovation
A noninvasive joint diagnostic system tracks motion of an actual patient bone by acquiring A-mode pulse echo ultrasound signals and utilizing the ultrasound signals to capture a point cloud representative of the actual patient bone. The system fits a deformable 3-D bone model to the captured point cloud to generate a 3-D patient specific bone model and registers the actual patient bone with the 3-D patient specific bone model to enable patient-specific 3-D motion analysis.
The system generates at least one localized bone point from an output of one or more ultrasound transducers positioned proximate the actual patient bone. It tracks the at least one localized bone point by tracking the motion of the one or more ultrasound transducers using one or more inertial sensors, and then tracks motion of the actual patient bone through a range of motion using the at least one tracked localized bone point in combination with the 3-D patient specific bone model.
The system compares patient kinematics, and optionally vibration, to a database of empirical mathematical descriptions of joint motion to diagnose joint injury and severity. It includes intelligent diagnosis using feature extraction and a multilayer backpropagation neural network classifier, and it supports time-synchronized data acquisition/display options.
Claims Coverage
The provided partial content includes one independent claim. The independent claim covers 3-D patient-specific bone modeling from A-mode pulse-echo ultrasound, registration of the patient bone to the model, and tracking of bone motion through a range of motion using localized bone points tracked via inertial sensors.
Patient-specific deformable 3-D bone model from A-mode pulse-echo ultrasound
acquiring A-mode pulse echo ultrasound signals of the actual patient bone; utilizing the ultrasound signals to capture a point cloud representative of the actual patient bone; fitting a deformable 3-D bone model to the captured point cloud to generate a 3-D patient specific bone model
Registration of actual patient bone with patient-specific 3-D model
registering the actual patient bone with the 3-D patient specific bone model
Localized bone point generation and tracking via inertial sensors
generating at least one localized bone point from an output of one or more ultrasound transducers positioned proximate the actual patient bone; tracking the at least one localized bone point by tracking the motion of the one or more ultrasound transducers using one or more inertial sensors
Range-of-motion bone tracking using tracked localized points and the 3-D patient-specific model
tracking motion of the actual patient bone through a range of motion using the at least one tracked localized bone point in combination with the 3-D patient specific bone model
Overall, the claim coverage is centered on producing a 3-D patient specific deformable bone model from A-mode pulse-echo ultrasound, registering the actual patient bone to that model, and tracking bone motion over a range of motion by combining tracked localized bone points with transducer motion tracked by inertial sensors.
Stated Advantages
Supports noninvasive joint diagnostic motion tracking and diagnosis of joint injury and severity.
Enables patient-specific 3-D bone motion analysis using a 3-D patient specific bone model reconstructed from A-mode pulse-echo ultrasound.
Enables diagnosing whether a joint condition is present and determining its severity using neural network analysis of vibration data.
Documented Applications
Joint injury diagnosis and severity determination during motion through a range of motion.
Knee joint-related motion and diagnosis, including examples involving femur, tibia, patella, and ligaments.
Interested in licensing this patent?