Three Palm Software

Carestream Health, Inc.

Patrick Bernard Heffernan

Heidi Daoxian Zhang

Daoxian Heidi Zhang

Xiaohui Wang

Zhimin Huo

Michael D Heath

Mary E Couwenhoven

Marco Bucci

Yue Shen

László K Tabár

This invention provides a simple user interface and sequencing viewing method for a mammography interpretation workstation. In particular, the invention includes the method and apparatus that moves the source images and the associated data using two-level of pre-fetching and caching mechanism, sequences the reading workflow (including worklist, hanging protocol, viewing sequencing), draws markup using electronic grease pan, and automatically generates the recall forms and screening reports. The user interface operates on single button and mouse wheel style to maximize the radiologists' efficiency.

User interface and viewing workflow for mammography workstation

A method and apparatus are disclosed for an image preprocessing device that automatically detects chestwall laterality; removes border artifacts; and segments breast tissue and pectoral muscle from digital mammograms. The algorithms in the preprocessing device utilize the computer cache, a vertical Sobel filter and a probabilistic Hough transform to detect curved edges. The preprocessing result, along with a pseudo-modality normalized image, can be used as input to a CAD (computer-aided detection) server or to a mammography image review workstation. In the case of workstation input, the preprocessing results improve the protocol for chestwall-to-chestwall image hanging, and support optimal image contrast display of each segmented region.

Fast preprocessing algorithms for digital mammography CAD and workstation

A method of reviewing medical images and clinical data to generate a diagnosis or treatment decision is provided. The method includes receiving, at a computer-aided detection (CAD) system, the medical images and clinical data, processing the medical images and clinical data; to generate initial finding candidates and clustering the initial finding candidates into a plurality of groups. The method further includes classifying the initial finding candidates using machine learning algorithms integrated into the CAD system into one or more categories one or more categories of the initial finding candidates using type 2 fuzz logic, and determining detection and assessment statistics based on at least the assessed categories and classified findings using Bayesian probability analysis. The method also includes modifying the classified findings and assessed categories based on additional interactive input, and generating the diagnosis or treatment decision based on the determined detection, assessment statistics, and the additional interactive input.

Combination machine learning algorithms for computer-aided detection, review and diagnosis

The present invention provides an algorithm to detect and trace the spicules of a mass density in digital mammograms using an adaptive threshold edge algorithm and a flood-fill segmentation algorithm. Elongation criteria are used to remove false edges that do not radiate from a central mass margin. The algorithm works on a central mass border and spicules feature map that contains a subset of the pixels from the source image, so processing time is fast enough for use in a mammography CAD server and for real-time computation within a digital mammography workstation.

Mass spicules detection and tracing from digital mammograms

The present invention provides a method and system using computer-aided detection (CAD) algorithms to aid diagnosis and visualization of tomosynthesis mammography data. The proposed CAD algorithms process two-dimensional and three-dimensional tomosynthesis mammography images and identify regions of interest in breasts. The CAD algorithms include the steps of preprocessing; candidate detection of potential regions of interest; and classification of each region of interest to aid reading by radiologists. The detection of potential regions of interest utilizes two dimensional projection images for generating candidates. The resultant candidates in two dimensional images are back-projected into the three dimensional volume images. The feature extraction for classification operates in the three dimensional image in the neighborhood of the back-projected candidate location. The forward-projection and back-projection algorithms are used for visualization of the tomosynthesis mammography data in a fashion of synchronized MPR and VR.

Computer-aided diagnosis and visualization of tomosynthesis mammography data

The present invention provides a method for selecting mass density candidates from digital image, for example mammograms, for computer-aided lesion detection, review and diagnosis. A method of selecting mass density candidates from a digital image for computer-aided cancer detection, review and diagnosis includes down-sampling the digital image to a low resolution; smoothing an edge along a skinline; applying a Gaussian difference filter to enhance intensity to form a filtered image; masking the filtered image using a breast mask; using a Canny detector to find potential mass density contours; and generating a mass density candidate list from Canny contours produced in the Canny detector.

Algorithms for selecting mass density candidates from digital mammograms

A method for transforming radiological image data from a digital receiver obtains digital image data values from the digital receiver and compensates for exposure response differences between a screen film system and the digital receiver. Modulation transfer function differences between the screen film system and the digital receiver are compensated and noise content at frequencies approaching the Nyquist frequency for the digital receiver is suppressed.

Tone scale transformation for radiological images

A method for supporting diagnostic workflow from a medical imaging apparatus. A set of at least two images are obtained from a patient and displayed according to a user-specified image display layout selected from a plurality of image display layouts. One or more markers are associated with a region of interest in the displayed images. A list of regions of interest is generated, each having an entry for each associated marker. A classification is assigned to each entry in the list of regions of interest according to health risk.

Method for supporting diagnostic workflow from a medical imaging apparatus

A method for computer-aided detection of microcalcification clusters using a digital computer obtains digital mammography data for a single view image and normalizes and filters the image data to reduce noise. A first mask is generated and applied to the image data for defining the breast structure, forming a first cropped image. A second mask is generated and applied to the image data for defining muscle structure, forming a second cropped image. An artifact mask corresponding to vascular calcifications and known imaging artifacts is generated and applied to the first and second cropped images, defining first and second artifact-masked cropped images. In a repeated sequence, portions of each artifact-masked cropped image are processed using an enhancement algorithm and reducing edge effects to obtain a set of microcalcification cluster candidates and suspected microcalcification clusters. Image processing algorithms remove false positives from the listing of microcalcification clusters and classify candidate microcalcification clusters to identify true positives.

Growing community of inventors

Los Gatos, CA, United States of America

Patrick Bernard Heffernan