Abstract: Systems and techniques that facilitate hybrid unsupervised and supervised image segmentation are provided. In various embodiments, a system can access a computed tomography (CT) image depicting an anatomical structure. In various aspects, the system can generate, via an unsupervised modeling technique, at least one class probability mask of the anatomical structure based on the CT image. In various instances, the system can generate, via a deep-learning model, an image segmentation based on the CT image and based on the at least one class probability mask.

Abstract: Systems and techniques that facilitate hybrid unsupervised and supervised image segmentation are provided. In various embodiments, a system can access a computed tomography (CT) image depicting an anatomical structure. In various aspects, the system can generate, via an unsupervised modeling technique, at least one class probability mask of the anatomical structure based on the CT image. In various instances, the system can generate, via a deep-learning model, an image segmentation based on the CT image and based on the at least one class probability mask.

Abstract: There is set forth herein a method including performing with an X-ray detector array of a CT imaging system one or more calibration scans, wherein the one or more calibration scans include obtaining for each element of the first through Nth elements of the X-ray detector array one or more calibration measurements; and updating a spectral response model for each element of the first through Nth elements using the one or more calibration measurements. In another aspect, a CT imaging system can perform imaging, e.g. including material decomposition (MD) imaging, using updated spectral response models for elements of an X-ray detector array. The spectral response models can be updated using a calibration process so that different elements of an X-ray detector array have different spectral response models.

Abstract: There is set forth herein a method including performing with an X-ray detector array of a CT imaging system one or more calibration scans, wherein the one or more calibration scans include obtaining for each element of the first through Nth elements of the X-ray detector array one or more calibration measurements; and updating a spectral response model for each element of the first through Nth elements using the one or more calibration measurements. In another aspect, a CT imaging system can perform imaging, e.g. including material decomposition (MD) imaging, using updated spectral response models for elements of an X-ray detector array. The spectral response models can be updated using a calibration process so that different elements of an X-ray detector array have different spectral response models.

Abstract: A self-contained electrolocation apparatus of the present invention includes an electrically conducting needle cannula having a proximal end, a distal end and a hollow bore therethrough. The invention further includes a non-conductive tube having a proximal end and a distal end, the tube being mounted over the needle cannula so that the distal end of the non-conductive tube is proximal to the distal end of the needle cannula. The non-conductive tube has a conductive layer thereon, whereby the needle cannula and the conductive layer respectively define first and second conductors coaxially spaced from one another by the non-conductive tube. There is a grip fixedly attached to the needle cannula for manipulating the apparatus. The grip has an electrical stimulus generator circuit within it that is electrically connected to the first conductor and the second conductor.

Abstract: An electrolocation apparatus is provided for locating a nerve to which anesthesia may be delivered. The apparatus includes a needle assembly having an electrically conductive needle cannula non-conductive tube secured over the needle cannula, and a conductive plating on the tube. The conductors are connected to a stimulator that generates alternating high and low charge pulses with a constant low current level. The high charge pulses generate noticeable muscle twitches immediately after insertion of the needle into the patient. Muscle twitches responsive to the high charge pulses will peak in magnitude, and muscle twitches responsive to the low charge pulses will become observable as the needle approaches the targeted nerve, and will be indistinguishable from the muscle twitches responsive to the high charge pulses when the needle is in a position for administration of anesthetic.