University of Pittsburgh

Eastman-kodak Company

Walter F Good

David Gur

Glenn S Maitz

Richard Weil

Bruce R Whiting

James F Owen

Bin Zheng

David L Modney

Yuan-Hsiang Chang

John M Herron

Xiao Hui Wang

Abnormal regions in living tissue are detected by obtaining images from different views of the living tissue; performing single-image CAD of each image to determine suspected abnormal regions depicted in the image; and combining measurements of the suspected abnormal regions in each image to determine whether a suspected abnormal region is an abnormal region. The living tissue may be a human breast and the abnormal region may be a mass in the breast. Ipsilateral mammographic views of the breast, a craniocaudal view, and a mediolateral oblique view may be used. Features which are relatively invariant or behave predictably with respect to breast compression are extracted using the single-image CAD and then combined.

Multi-view computer-assisted diagnosis

A method and system for remote diagnosis of a radiograph includes remote locations connectable to diagnosis locations. At a remote location a radiographic image containing a part depicting tissue and a background part is obtained and digitized. The image can be considered to comprise a plurality of blocks. A block of the digitized radiographic image is segmented to obtain a part of the block which depicts mainly tissue. The part of the block is compressed and transmitted to a diagnosis location. This segmenting, compressing and transmitting of blocks is repeated until the entire part of the image which depicts tissue has been transmitted to the diagnosis location. For an image, the digitization, segmentation, compression and transmission can be performed in a pipelined fashion. optionally computer assisted diagnosis (CAD) can be performed on the digitized image. The diagnosis location receives the compressed segmented image and any CAD results; uncompressing the received image; combining the CAD results with the uncompressed image; and displays the uncompressed image and the CAD results.

Image facsimile with real time image segmentation

A computed radiography patient identification system which matches a patient with an X-ray image of the patient stored in a stimulable storage phosphor. The system includes a patient identifying bar code uniquely identifying a patient; a stimulable storage phosphor identifying bar code uniquely identifying a stimulable storage phosphor and a portable bar code scanner. The bar code scanner is used to scan the patient bar code and the storage phosphor bar code when a patient is exposed to an X-ray which is stored on the stimulable storage phosphor. Preferably, a mobile X-ray source has an associated set of bar codes identifying X-ray examination types (chest, head, limb, etc.) and/or X-ray exposure conditions. The bar code scanner scans the examination type bar code at the time the X-ray of the patient is taken. The system includes a storage phosphor reader for converting an X-ray image stored in a storage phosphor into an X-ray image signal. The bar code identification of such stimulable phosphor is also read out. The storage phosphor reader receives from the portable bar code reader, information relating to patient identification, storage phosphor identification and examination type and matches the patient identification and examination type with the X-ray image signal.

Computed radiography patient identification system

A method of automatically archiving image information utilizing available xt information is provided. The method includes automatic extraction of textual information from a text frame and converting this information into a text file. This text file is used to construct a text header which is then stored in conjunction with the images to which it relates. Images are stored on a page-by-page basis and the text header is used as a directory address for retrieving the information as well as serving as a message embedded in the image page. A second header may also be created in accordance with another aspect of the invention to identify each image page.

Method of identifying and archiving medical images

Growing community of inventors

Pittsburgh, PA, United States of America

Walter F Good