02-02-2017 дата публикации
Номер: US20170032535A1
Принадлежит:
Lung segmentation and bone suppression techniques are helpful pre-processing steps prior to radiographic analyses of the human thorax, as may occur during cancer screenings and other medical examinations. Autonomous lung segmentation may remove spurious boundary pixels from a radiographic image, as well as identify and refine lung boundaries. Thereafter, autonomous bone suppression may identify clavicle, posterior rib, and anterior rib bones using various image processing techniques, including warping and edge detection. The identified clavicle, posterior rib, and anterior rib bones may then be suppressed from the radiographic image to yield a segmented, bone suppressed radiographic image. 1. A method for performing lung segmentation , the method comprising:receiving, by a processor, a radiographic image;identifying, by the processor, region of interest (ROI) boundaries within the radiographic image;identifying, by the processor, lung boundaries in accordance with the ROI boundaries; andmerging, by the processor, the lung boundaries to generate a segmented lung structure.2. The method of claim 1 , wherein the ROI boundaries include a left ROI boundary claim 1 , a right ROI boundary claim 1 , an upper ROI boundary claim 1 , one or more lower ROI boundaries claim 1 , and a center ROI boundary.3. The method of claim 1 , wherein identifying the ROI boundaries within the radiographic image comprises:identifying a body region representing a torso of a patient depicted by the radiographic image; andidentifying the ROI boundaries in accordance with pixel intensity values inside the body region, wherein the ROI boundaries include a left ROI boundary, a right ROI boundary, an upper ROI boundary, one or more lower ROI boundaries, and a center ROI boundary.4. The method of claim 3 , wherein identifying the ROI boundaries in accordance with the pixel intensity values inside the body region comprises:computing a first horizontal intensity projection vector by summing pixel ...
Подробнее