Carestream Health, Inc.

Riverain Medical Group, LLC

Hui Zhao

Zhimin Huo

Jing Jing Zhang

Jyh-Shyan Lin

Xin-Wei Xu

Ruiping Li

Edward A Martello

Tong Wei

Zhiqiang Lao

Fleming Y-m Lure

Fleming Lure

Ravi K Nareppa

Rujirutana Sriikanchana

Rujirutana Srikanchana

A system and method for generating a rib suppressed radiographic image using deep learning computation. The method includes using a convolutional neural network module trained with pairs of a chest x-ray image and its counterpart bone suppressed image. The bone suppressed image is obtained using a bone suppression algorithm applied to the chest x-ray image. The convolutional neural network module is then applied to a chest x-ray image or the bone suppressed image to generate an enhanced bone suppressed image.

Bone suppression for chest radiographs using deep learning

A method acquires a reconstructed tomographic volume image of anatomy of a patient and constructs a primary axis for a bone of interest in the imaged anatomy. The method forms a sectioned image of the bone in the volume image according to a first plane that is defined to extend along the bone and to extend through two or more articular surfaces. A primary axis for the bone is estimated, wherein the primary axis is midway between outer edges of the bone image that intersect the first sectioning plane. The bone is sectioned in the volume image by a second plane that is orthogonal to the first plane and that extends through the estimated primary axis. The method recalculates the position of the constructed primary axis according to the sectioning of the bone by the second plane. The recalculated constructed primary axis for the bone of interest is displayed.

Bone segmentation and display for 3D extremity imaging

A method for clavicle suppression in a chest x-ray image. The method identifies the lung fields in the x-ray image and detects at least one portion of a clavicle ridge that lies outside the lung fields. Edges of a clavicle on each side of the detected clavicle ridge are detected, edge detection extended for the clavicle edges into the lung fields, and the clavicle defined within the x-ray image according to the edge detection. The clavicle is suppressed within the x-ray image to generate a clavicle-suppressed x-ray image and the clavicle-suppressed x-ray image is displayed, stored, or transmitted.

Clavicle suppression in radiographic images

A method for providing tomosynthesis 3-D volume image data, executed at least in part on a computer, acquires a number of radiographic projection images of a subject over a range of angles. Reconstructed volume image data is generated from the acquired projection images. A number of regions of interest are defined within the reconstructed volume image data, wherein each region of interest has a number of image voxels. Image voxel data values are conditioned within at least one of the regions of interest to enhance contrast within the at least one region of interest. The conditioned image voxel data values are adjusted within the at least one of the regions of interest according to interpolation with two or more neighboring regions of interest. An image slice having at least a plurality of the adjusted image voxel data values is displayed.

Method for enhancing reconstructed 3-D tomosynthesis volume image

Computer-aided diagnosis techniques may be combined with techniques to obtain derived images from radiographic images to provide enhanced computer-aided diagnosis of, for example, lung nodules.

Computer aided diagnosis using derived images

Computer-aided diagnosis techniques may be combined with dual-energy radiography techniques to provide enhanced computer-aided diagnosis of, for example, lung nodules.

Growing community of inventors

Pittsford, NY, United States of America

Hui Zhao