Abstract: Methods, systems, and computer program products for generating speech data using artificial intelligence techniques are provided herein. A computer-implemented method includes implementing one or more artificial intelligence techniques in connection with one or more speech synthesis tasks; generating, in multiple sequential portions, at least one sequence of data, comprising one or more of phonetic data and prosodic data, by processing at least one previously generated sequence of data using the one or more artificial intelligence techniques; and generating speech data corresponding to at least a portion of the sequence of data by processing the at least a portion of the sequence of data using at least one artificial intelligence-based speech synthesis model.

Abstract: Embodiments of the present invention include generating a 3D model of a body cavity, and receiving, from a position transducer associated with a medical probe configured to be inserted into the cavity and having at least one elongated electrode disposed along a distal end of the probe, signals indicating orientation and location coordinates of the distal end within the body cavity. Based on the model and the signals, while parts of the given electrode other than the identified segment are not in contact with the inner surface of the cavity, a segment along a length of a given electrode that is in contact with tissue at a site on an inner surface of the cavity is identified. A graphical representation of the model with a visual marker at a location on the model corresponding to the site contacted by the segment of the given electrode is rendered to a display.

Abstract: A method includes receiving position signals that are indicative of positions of multiple electrodes disposed on an expandable balloon that is fitted at a distal end of a shaft for engaging a lumen of an organ to occlude the lumen. Based on the received position signals, a change is calculated in one or more dimensions of the balloon between (i) a first configuration in which the balloon is inflated but not engaged in the lumen, and (ii) a second configuration in which the balloon is inflated and engaged in the lumen. Using the calculated change, a degree is estimated to which the balloon occludes the lumen. The estimated degree of occlusion is presented to a user.

Abstract: Embodiments of the present invention include generating a 3D model of a body cavity, and receiving, from a position transducer associated with a medical probe configured to be inserted into the cavity and having at least one elongated electrode disposed along a distal end of the probe, signals indicating orientation and location coordinates of the distal end within the body cavity. Based on the model and the signals, while parts of the given electrode other than the identified segment are not in contact with the inner surface of the cavity, a segment along a length of a given electrode that is in contact with tissue at a site on an inner surface of the cavity is identified. A graphical representation of the model with a visual marker at a location on the model corresponding to the site contacted by the segment of the given electrode is rendered to a display.

Abstract: A system includes a processor and a display. The processor is configured to: receive a first plurality of ultrasound (US) images acquired at a site of an organ from a first plurality of positions and orientations, before performing a medical procedure at the site; receive a second plurality of US images acquired at the site, from a second plurality of positions and orientations, after performing the medical procedure at the site; and identify among the first and second plurality of US images, one or more pairs of first and second US images, respectively, which are acquired from matched orientations, and select a given pair among the pairs, in which a difference between the first and second US images is largest among the identified pairs. The display is configured to display the given pair of the first and second US images to a user.

Abstract: A method includes, using anatomical data, calculating multiple cross-sectional shapes of a lumen of an organ in a body of a patient at multiple respective positions on a medial axis of the lumen. One or more of the positions on the medial axis are identified, at which a given expandable frame of a catheter would fit the cross-sectional shapes. The one or more identified positions are presented to a user.

Abstract: A method includes receiving position signals that are indicative of positions of multiple electrodes disposed on an expandable balloon that is fitted at a distal end of a shaft for engaging a lumen of an organ to occlude the lumen. Based on the received position signals, a change is calculated in one or more dimensions of the balloon between (i) a first configuration in which the balloon is inflated but not engaged in the lumen, and (ii) a second configuration in which the balloon is inflated and engaged in the lumen. Using the calculated change, a degree is estimated to which the balloon occludes the lumen. The estimated degree of occlusion is presented to a user.

Abstract: Apparatus, including a probe having a distal end insertable into a nasal sinus of a human patient, and a location sensor positioned within the distal end. A sinuplasty balloon is positioned on the distal end at a selected opening of the nasal sinus. A processor receives first signals from the location sensor while the distal end is inserted into the nasal sinus and prior to positioning of the balloon at the selected opening, and generates a first map of the sinus. The processor inflates the balloon when it is at the selected opening, so as to enlarge the selected opening, and subsequently deflates the balloon. The processor then receives second signals from the location sensor and generates therefrom a second map of the sinus. The processor registers the first map with the second map and generates from the registered maps a numerical increase in size of the selected opening.

Abstract: A method includes receiving position signals that are indicative of positions of multiple electrodes disposed on an expandable balloon that is fitted at a distal end of a shaft for engaging a lumen of an organ to occlude the lumen. Based on the received position signals, a change is calculated in one or more dimensions of the balloon between (i) a first configuration in which the balloon is inflated but not engaged in the lumen, and (ii) a second configuration in which the balloon is inflated and engaged in the lumen. Using the calculated change, a degree is estimated to which the balloon occludes the lumen. The estimated degree of occlusion is presented to a user.

Abstract: A system and method for achieving linear alignment between elements in a procedure are disclosed. The system and method include determining the axis of a first element, such as the ostium, of a plurality of elements utilized in the procedure, determining the axis of a second element, such as a catheter, of the plurality of elements utilized in the procedure, and aligning the determined axis of the first element and the determined axis of the second element. The method may include further determining the axis of a third element, such as a sheath of the catheter, of the plurality of elements utilized in the procedure and aligning the determined axis of the third element with the aligned axis of the first element and the aligned axis of the second element.

Abstract: A method includes, using anatomical data, calculating multiple cross-sectional shapes of a lumen of an organ in a body of a patient at multiple respective positions on a medial axis of the lumen. One or more of the positions on the medial axis are identified, at which a given expandable frame of a catheter would fit the cross-sectional shapes. The one or more identified positions are presented to a user.

Abstract: An apparatus includes a camera and a processor. The camera is configured to capture images of a display of a temperature measurement system that displays a tissue temperature. The processor is configured to analyze the captured images to extract a numerical value of the tissue temperature displayed by the temperature measurement system, and initiate an action responsively to the extracted numerical value.

Abstract: Physicians performing invasive procedures utilize instruments inserted into a human body to perform the procedures. Such procedures typically involve actions to be performed on specific targeted anatomical structures. During the procedure, nearby anatomical structures unrelated to the procedure should generally be avoided. A system and techniques are provided herein for monitoring the position of such unrelated nearby anatomical structures relative to one or more surgical instruments. The system emits a warning to a human operator such as a surgeon if one of the instruments is too close to a monitored anatomical structure.

Abstract: Physicians performing invasive procedures require accuracy and precision when working with surgical tools. Surgical procedures are increasingly becoming minimally invasive, with physicians operating using cameras to view the surgery site and directing their tools through oculars or video displays. Ideally, the physician should be able to perform the invasive procedure while simultaneously observing both the real-time image of the patient and additional data critical for his medical decisions about the manipulation of the surgical tool and the next surgical step. The augmented reality navigation system of the present disclosure provides tool location visibility for invasive procedures through the use of location sensors included on a camera and/or on the tools used during a procedure. A location tracking system determines and monitors the locations of the tools and camera based on the characteristics of signals detected by the sensors and displays informational overlays on images obtained with a camera.

Abstract: Embodiments of the present invention include generating a 3D model of a body cavity, and receiving, from a position transducer associated with a medical probe configured to be inserted into the cavity and having at least one elongated electrode disposed along a distal end of the probe, signals indicating orientation and location coordinates of the distal end within the body cavity. Based on the model and the signals, while parts of the given electrode other than the identified segment are not in contact with the inner surface of the cavity, a segment along a length of a given electrode that is in contact with tissue at a site on an inner surface of the cavity is identified. A graphical representation of the model with a visual marker at a location on the model corresponding to the site contacted by the segment of the given electrode is rendered to a display.

Abstract: A method includes receiving position signals that are indicative of positions of multiple electrodes disposed on an expandable balloon that is fitted at a distal end of a shaft for engaging a lumen of an organ to occlude the lumen. Based on the received position signals, a change is calculated in one or more dimensions of the balloon between (i) a first configuration in which the balloon is inflated but not engaged in the lumen, and (ii) a second configuration in which the balloon is inflated and engaged in the lumen. Using the calculated change, a degree is estimated to which the balloon occludes the lumen. The estimated degree of occlusion is presented to a user.

Abstract: Apparatus, including a probe having a distal end insertable into a nasal sinus of a human patient, and a location sensor positioned within the distal end. A sinuplasty balloon is positioned on the distal end at a selected opening of the nasal sinus. A processor receives first signals from the location sensor while the distal end is inserted into the nasal sinus and prior to positioning of the balloon at the selected opening, and generates a first map of the sinus. The processor inflates the balloon when it is at the selected opening, so as to enlarge the selected opening, and subsequently deflates the balloon. The processor then receives second signals from the location sensor and generates therefrom a second map of the sinus. The processor registers the first map with the second map and generates from the registered maps a numerical increase in size of the selected opening.

Abstract: A method includes, receiving a first sequence of first positions of a medical device that moves in a body of a patient. The first positions of the medical device are visualized to a user, by automatically moving a dummy device, external to the body, in a second sequence of second positions that mimics the first sequence.

Abstract: Apparatus, including a probe having a distal end insertable into a nasal sinus of a human patient, and a location sensor positioned within the distal end. A sinuplasty balloon is positioned on the distal end at a selected opening of the nasal sinus. A processor receives first signals from the location sensor while the distal end is inserted into the nasal sinus and prior to positioning of the balloon at the selected opening, and generates a first map of the sinus. The processor inflates the balloon when it is at the selected opening, so as to enlarge the selected opening, and subsequently deflates the balloon. The processor then receives second signals from the location sensor and generates therefrom a second map of the sinus. The processor registers the first map with the second map and generates from the registered maps a numerical increase in size of the selected opening.

Abstract: A method and system for automatic landmark registration and registration using trajectory information and shape sensing during an endoscopic procedure, such as bronchoscopy, are described herein. A segmentation centerline of airways of a lung may be generated based on a pre-operative computed tomography (CT) image of the lung. Landmarks may be automatically detected on the segmentation centerline corresponding to bifurcations in the airways of the lung. A location data point cloud of locations of a catheter through the airways of the lung during navigation may be generated. A bounding volume of the airways of the lung may be generated and a bounding volume centerline may be detected. Landmarks may be detected on the bounding volume centerline for the same bifurcations. Then, the two sets of landmarks may be mapped as part of registration. The trajectory information with shape sensing may be used to provide non-rigid or fine registration.