Apparatus and method for locating a position of an electrode on an organ model
Inventors
Aravamudan, Murali • Barve, Rakesh • Vaidya, Suthirth • Upadhyay, Uddeshya • Chunduru, Abhijith • PURANIK, Arjun • Chennamsetty, Sai Saketh
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12213774-B1
Publication Date
2025-02-04
Expiration Date
Abstract
An apparatus and method for locating a position of an electrode on an organ model. The apparatus includes a memory communicatively connected to at least a processor, wherein the memory contains instructions configuring the at least a processor to receive an organ model configured to digitally represent an organ, receive a set of sensor data from at least a sensor including an ultrasound sensor, determine an electrode position within the organ model as a function of the set of sensor data using a position machine-learning module, wherein determining the electrode position includes determining a model position within the organ model as a function of the set of sensor data and determining the electrode position within the model position of the organ model as a function of the set of sensor data and add a visual marker onto the electrode position in the model position of the organ model.
Core Innovation
The invention relates to an apparatus and a method for locating a position of an electrode on an organ model, wherein the organ model digitally represents an organ. The apparatus receives an organ model and a set of sensor data from at least a sensor comprising an ultrasound sensor, and determines an electrode position within the organ model as a function of the set of sensor data using a position machine-learning module.
The determining of the electrode position comprises determining a model position within the organ model as a function of the set of sensor data. The model position determination includes generating first position training data with correlations between exemplary sensor data and exemplary model positions, training a first position machine-learning model, and determining the model position using the trained first position machine-learning model.
The electrode position determination further includes generating second position training data with correlations between exemplary sensor data and exemplary electrode positions, and training a second position machine-learning model. The second position training data is iteratively updated on a feedback loop as a function of an output of the first position machine-learning model of the position machine-learning module, after which the electrode position is determined using the trained second position machine-learning model.
The located electrode position in the model position is used to add a visual marker onto the organ model, and the visual marker may be transmitted for display on a remote device. The disclosure further describes that organ models may be constructed or refined using electrocardiogram data and/or sensor-derived data, including representations such as a 3D voxel occupancy representation and refinement using a statistical shape model aligned and deformed to the imaging-derived 3D representation.
Claims Coverage
The independent claim set covers two inventive concepts: an apparatus and a corresponding method for locating an electrode position on a digitally represented organ model using ultrasound sensor data and a position machine-learning module with a two-stage training flow. The inventive features comprise a first and second machine-learning model, a feedback loop that iteratively updates the second position training data based on an output of the first position machine-learning model, and adding a visual marker to the electrode position on the organ model.
Two-stage electrode localization on a digitally represented organ model using ultrasound sensor data
Receiving an organ model configured to digitally represent an organ; receiving a set of sensor data from at least a sensor comprising an ultrasound sensor; determining an electrode position within the organ model as a function of the set of sensor data using a position machine-learning module; determining the electrode position by first determining a model position within the organ model as a function of the set of sensor data, then determining the electrode position within the model position.
Model position determination using first position training data
Generating first position training data comprising correlations between exemplary sensor data and exemplary model positions; training a first position machine-learning model of the position machine-learning module using the first position training data; determining the model position within the organ model using the trained first position machine-learning model.
Iteratively updated second position training data on a feedback loop
Generating second position training data comprising correlations between exemplary sensor data and exemplary electrode positions; training a second position machine-learning model of the position machine-learning module using the second position training data; iteratively updating the second position training data on a feedback loop as a function of an output of the first position machine-learning model of the position machine-learning module; determining the electrode position within the organ model using the trained second position machine-learning model.
Visual marker added to the electrode position in the model position of the organ model
Adding a visual marker onto the electrode position in the model position of the organ model.
The independent claims jointly require ultrasound-sensor-driven electrode localization within a digitally represented organ model using a position machine-learning module. They further require a two-stage training and inference structure with a first position machine-learning model for model position and a second position machine-learning model for electrode position, where the second position training data is iteratively updated on a feedback loop based on the output of the first position machine-learning model, and they require adding a visual marker onto the located electrode position in the organ model.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?