Veran Medical Technologies, Inc.

Torsten M Lyon

Troy L Holsing

Jerome R Edwards

Evan Austill, Jr

Christopher B Lee

Mark W Hunter

Jayson Oldfather

A system and method are presented for applying convolutional neural networks (CNNs) to aid in rapid on-site evaluation cytopathology. Image data are acquired from a biopsy slide. Areas of interest are determined using a first CNN. The image data is segmented into image tiles, and tiles showing the areas of interest are analyzed using a second CNN to assign a histologic category to the slide. The second CNN also utilizes site specific data relating to the biopsy location. Layered image data from multiple focal planes can be acquired of the slide and used as input to the second CNN. Categorized tiles are sorted and presented to a remote computing system for cytopathology determinations, aided by the results of applying the second CNN. Semantic segmentation can also be developed, both as input to the second CNN and as data presented to the remote computer system.

Rapid on-site evaluation using artificial intelligence for lung cytopathology

A method includes receiving during a first time interval associated with a path of motion of a dynamic body, image data associated with a plurality of images of the dynamic body. The plurality of images include an indication of a position of a first marker coupled to a garment at a first location, and a position of a second marker coupled to the garment at a second location. The garment is coupled to the dynamic body. During a second time interval, an image from the plurality of images is automatically identified that includes a position of the first marker that is substantially the same as a position of a first localization element relative to the dynamic body and a position of the second marker that is substantially the same as a position of the second localization element relative to the dynamic body.

Apparatus and method for image guided accuracy verification

Apparatus and method for automatic image guided accuracy verification

A method includes receiving during a first time interval image data associated with an image of a dynamic body. The image data includes an indication of the positions of a first marker and a second marker on a garment coupled to the dynamic body. The first marker and second marker are each coupled to the garment at a first and second locations, respectively. A distance is determined between the position of the first marker and the second marker. During a second time interval after the first time interval, data associated with a position of a first and second localization element that are each coupled to the garment is received. A distance between the first and second localization elements is determined. A difference is calculated between the distance between the first marker and the second marker and the distance between the first localization element and the second localization element.

Generally, systems, methods, and apparatus related to the use of a dynamic imaging modality in an image guided intervention are disclosed herein. More specifically, the use of such modalities in sealing a bodily opening, such as those that may be formed during an invasive medical procedure are disclosed herein. In some embodiments, a method includes viewing a representation of an instrument within a body of a patient, adjusting a position of the instrument based on the viewing such that a portion of the instrument is at a location within the body of the patient, and delivering a sealant via the instrument to the location within the body of the patient. The sealant is configured to seal an opening in the body part.

Growing community of inventors

Golden, CO, United States of America

Torsten M Lyon