摘要:
A method and system for detecting and tracking multiple catheters in a fluoroscopic image sequence in an integrated central processing unit and graphics processing unit framework is disclosed. A catheter electrode model is initialized in a first frame of the fluoroscopic image sequence. The catheter landmark candidates are detected, by a graphics processing unit, in the first frame of the fluoroscopic image sequence. The catheter electrode model is tracked, by a central processing unit, and is detected by the graphics processing unit, in subsequent frames of the fluoroscopic image sequence by detecting catheter landmark candidates in the subsequent frames of the fluoroscopic image sequence using at least one trained catheter landmark detector, and outputting the catheter model tracking and landmark detection results of for each frame of the fluoroscopic image sequence.
摘要:
A method for visualizing the quality of an ablation process with a processing and display unit is provided. A 3D dataset of an anatomical object and a 3D image model of an ablation instrument are provided, wherein the 3D image model models at least the surface of the ablation instrument. A position and an alignment of the 3D image model of the ablation instrument within the anatomical object is specified, wherein the 3D image model of the ablation instrument is incorporated into the 3D dataset of the anatomical object. At least a part of the incorporated 3D image model of the ablation instrument and of the 3D dataset of the anatomical object is presented and at least one characteristic quality value is determined as a function of the location of the 3D image model of the ablation instrument in relation to the anatomical object.
摘要:
A method and system for motion estimation modeling for cardiac and respiratory motion compensation is disclosed. Specifically, a coronary sinus catheter is tracked in a plurality of frames of a fluoroscopic image sequence; and cardiac and respiratory motion of a left atrium is estimated in each of the plurality of frames based on tracking results of the coronary sinus catheter using a trained motion estimation model.
摘要:
A method for visualizing the quality of an ablation process with a processing and display unit is provided. A 3D dataset of an anatomical object and a 3D image model of an ablation instrument are provided, wherein the 3D image model models at least the surface of the ablation instrument. A position and an alignment of the 3D image model of the ablation instrument within the anatomical object is specified, wherein the 3D image model of the ablation instrument is incorporated into the 3D dataset of the anatomical object. At least a part of the incorporated 3D image model of the ablation instrument and of the 3D dataset of the anatomical object is presented and at least one characteristic quality value is determined as a function of the location of the 3D image model of the ablation instrument in relation to the anatomical object.
摘要:
A method and system for detecting and tracking multiple catheters in a fluoroscopic image sequence in an integrated central processing unit and graphics processing unit framework is disclosed. A catheter electrode model is initialized in a first frame of the fluoroscopic image sequence. The catheter landmark candidates are detected, by a graphics processing unit, in the first frame of the fluoroscopic image sequence. The catheter electrode model is tracked, by a central processing unit, and is detected by the graphics processing unit, in subsequent frames of the fluoroscopic image sequence by detecting catheter landmark candidates in the subsequent frames of the fluoroscopic image sequence using at least one trained catheter landmark detector, and outputting the catheter model tracking and landmark detection results of for each frame of the fluoroscopic image sequence.
摘要:
A method and system for tracking an ablation catheter and a circumferential mapping catheter in a fluoroscopic image sequence is disclosed. Catheter electrode models for the ablation catheter and the circumferential mapping catheter are initialized in a first frame of a fluoroscopic image sequence based on user inputs. The catheter electrode models for the ablation catheter and the circumferential mapping catheter are then tracked in each remaining frame of the fluoroscopic image sequence. In each remaining frame, candidates of catheter landmarks such as the catheter tip, electrodes and body points are detected for the ablation catheter and the circumferential mapping catheter, tracking hypotheses for the catheter electrode models are generated, and for each of the ablation catheter and the circumferential mapping catheter, the catheter electrode model having the highest probability score is selected from the generated tracking hypotheses.