Abstract: The invention relates to an apparatus for determining a temporal breast cancer risk (27). This risk is indicative of detecting cancer in a breast within a predetermined time interval after a negative breast cancer detection result that has been obtained by carrying out a breast cancer detection procedure defined by a breast cancer detection parameter. The temporal breast cancer risk (27) is determined based on a) a probability parameter (25) being indicative of a probability of having breast cancer and b) a density parameter (26) being indicative of a density-related property of breast tissue of a breast, wherein the probability parameter (25) and the density parameter (26) have been determined based on a breast image data set (24) of the woman by using an artificial intelligence. The determined risk can be used, for instance, for deciding whether a supplemental examination should be performed immediately or for defining a screening interval.

Abstract: The invention relates to a displaying system for displaying digital breast tomosynthesis (DBT) data. First and second DBT volume images of the left breast of a woman and first and second DBT volume images of the right breast of the woman are provided by an image providing unit. Moreover, for each DBT volume image a two-dimensional navigation image is provided by a navigation image providing unit, wherein a user is allowed to indicate a location in the navigation image by using a user interface, whereafter a CAD marker associated with the location is determined in a DBT volume image of a breast and a corresponding CAD marker, if present, is determined in another DBT volume image of the breast. Slices of these DBT volume images, which are associated with the CAD markers, are presented on a display.

Abstract: The invention relates to a displaying system for displaying digital breast tomosynthesis (DBT) data. First and second DBT volume images of the left breast of a woman and first and second DBT volume images of the right breast of the woman are provided by an image providing unit. Moreover, for each DBT volume image a two-dimensional navigation image is provided by a navigation image providing unit, wherein a user is allowed to indicate a location in the navigation image by using a user interface, whereafter a CAD marker associated with the location is determined in a DBT volume image of a breast and a corresponding CAD marker, if present, is determined in another DBT volume image of the breast. Slices of these DBT volume images, which are associated with the CAD markers, are presented on a display.

Abstract: An adjunctive ultrasound mammography system and associated methods use an adjunctive ultrasound display configured for quick, intuitive, interactive viewing of volumetric ultrasound scans, displayed near a conventional x-ray mammogram display. Preferred navigations among a thick-slice image array, a selected enlarged thick-slice image, and planar ultrasound views are described, including a mode in which the planar ultrasound views are updated in real time as a cursor is moved across an active thick-slice image. In one example the thick-slice images are inverted prior to display, with non-breast areas of the image preferably segmented out and reset to dark. The inverted thick-slice images are of more familiar significance to radiologists as they are more like conventional x-ray mammograms and allow benign features to be more easily dismissed as compared to non-inverted thick-slice images.

Abstract: A method and system for processing and displaying breast ultrasound information is described. A 2D feature weighted volumetric coronal image as a “guide” or “road map” is generated from the 3D ultrasound data volume to represent the 3D dataset with the goal of emphasizing abnormalities within the breast while excluding non-breast structures, particularly those external to the breast such as ribs and chest wall.

Abstract: The present invention relates to a method of reconstruction of an object from projections, more particularly to a quantitative reconstruction of an object from projection views of the object. For example, quantitative reconstruction of an image of a human breast from projection views generated by digital breast tomosynthesis (DBT), computed tomography (CT), or standard mammography, and use of the reconstruction to identify densest regions.

Abstract: Methods and related systems provide an interactive user interface in which CAD results are displayed in such a way that they may be used for both interpretation of detected abnormalities and for avoiding perceptual oversights. The output of a (multi-view) computer aided detection system is presented to the reader of a screening case in two phases: (1) an interactive phase, and (2) a prompting phase. In the first phase the reader can probe image locations for CAD information. In the second phase regions identified as relevant by the CAD system and not yet probed by the reader are prompted or displayed to the user, as these may have been overlooked by the reader. The CAD results can be calibrated to a probability of malignancy.

Abstract: Disclosed is a method of analyzing tissue from an image comprising providing an electronic image of tissue (100, 400, 450, 600, 800, 1100), determining a reference value from the image (1070, 1170, 1270), establishing an hint representation (500,700) of the image, and using the hint representation in analysis of the tissue to quantify the breast and compute a calibration error. Also disclosed is a system which runs an inner breast edge detection algorithm (1310) on the electronic image to detect the inner breast edge on the image (1315), and refined the inner breast edge location (1340) if a calibration error is not acceptable (1324). Also disclosed is automatic estimation of breast composition and temporal analysis of images.

Abstract: A method and system for processing and displaying breast ultrasound information is described. A 2D feature weighted volumetric coronal image as a “guide” or “road map” is generated from the 3D ultrasound data volume to represent the 3D dataset with the goal of emphasizing abnormalities within the breast while excluding non-breast structures, particularly those external to the breast such as ribs and chest wall.

Abstract: Methods and related systems are described for providing an interactive user interface in which CAD results are displayed in such a way that they may be used for both interpretation of detected abnormalities and for avoiding perceptual oversights. Systems are described in which the output of a (multi-view) computer aided detection system is presented to the reader of a screening case in two phases: (1) an interactive phase, and (2) a prompting phase. In the first phase the reader can probe image locations for CAD information. In the second phase regions identified as relevant by the CAD system and not yet probed by the reader are prompted or displayed to the user, as these may have been overlooked by the reader. The CAD results can be calibrated to a probability of malignancy.

Abstract: A method, system, and related computer program products for processing and displaying dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) information are described. A plurality of instances of an MRI volume of the body part acquired at a respective plurality of sample times subsequent to an administration of a tracer is processed to determine a plurality of pharmacokinetic (PK) parameters characterizing a mathematical model-based relationship between a plasma tracer concentration and a total tracer concentration within the body part. For one preferred embodiment, computation of the PK parameters is performed according to a generalized signal model such that computation can be carried out in real time during an interactive viewer session, with required reference regions being selectable and optionally re-selectable by the viewer without requiring extensive waiting times for PK parameter computation. Associated user interfaces and computer-aided detection (CAD) algorithms are also provided.

Abstract: Disclosed is a method of analysing tissue from an image comprising providing an electronic image of tissue (100, 400, 450, 600, 800, 1100), determining a reference value from the image (1070, 1170, 1270), establishing an hint representation (500,700) of the image, and using the hint representation in analysis of the tissue to quantify the breast and compute a calibration error. Also disclosed is a system which runs an inner breast edge detection algorithm (1310) on the electronic image to detect the inner breast edge on the image (1315), and refined the inner breast edge location (1340) if a calibration error is not acceptable (1324). Also disclosed is automatic estimation of breast composition and temporal analysis of images.

Abstract: Methods and related systems are described for detection of breast cancer in 3D ultrasound imaging data. Volumetric ultrasound images are obtained by an automated breast ultrasound scanning (ABUS) device. In ABUS images breast cancers appear as dark lesions. When viewed in transversal and sagittal planes, lesions and normal tissue appear similar as in traditional 2D ultrasound. However, architectural distortion and spiculation are frequently seen in the coronal views, and these are strong indicators of the presence of cancer. The described computerized detection (CAD) system combines a dark lesion detector operating in 3D with a detector for spiculation and architectural distortion operating on 2D coronal slices. In this way a sensitive detection method is obtained. Techniques are also described for correlating regions of interest in ultrasound images from different scans such in different scans of the same breast, scans of a patient's right versus left breast, and scans taken at different times.

Abstract: The disclosure includes computer implemented methods and devices comprising processors for inputting images and medical history into an electronic medium and analyzing x-ray images of a subject's breasts to determine density. The disclosure further contemplates using these methods and devices to generate a numerical value. The disclosure further contemplates using the numerical value to determine whether the subject should have magnetic resonance imaging of the breasts.

Abstract: Numerical image processing based on a model of medical image acquisition of two or more medical images to provide grayscale registration is described. The grayscale registered temporal images may then be displayed for visual comparison and/or further processed by a computer-aided diagnosis system for detection of medical abnormalities therein. A parametric method includes spatially registering two images and performing gray scale registration of the images. A parametric transform model, e.g., analog to analog, digital to digital, analog to digital, or digital to analog model, is selected based on the image acquisition method(s) of the images, i.e., digital or analog/film. Gray scale registration involves generating a joint pixel value histogram from the two images, statistically fitting parameters of the transform model to the joint histogram, generating a lookup table, and using the lookup table to transform and register pixel values of one image to the pixel values of the other image.

Abstract: Simultaneous grayscale and geometric registration of images, such as mammograms, facilitates temporal comparison and enhances the speed and reliability of computer aided diagnosis (CAD) detection of medical abnormalities. The method generally includes optimizing a merit function, e.g., sum of squared errors, containing parameters associated with a transformation function for simultaneous geometric and grayscale registering of the images, the optimizing of the merit function being performed by determining optimal values of the parameters using data in the images and registering one image to the other by applying the geometric and grayscale transformation function using the optimal values of the parameters. The optimizing may be performed iteratively from coarse to fine resolutions using a modified Levenberg-Marquardt method for optimizing nonlinear parameters with linear regression for optimizing linear parameters.

Abstract: A method, system, and related computer program products for processing and displaying dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) information are described. A plurality of instances of an MRI volume of the body part acquired at a respective plurality of sample times subsequent to an administration of a tracer is processed to determine a plurality of pharmacokinetic (PK) parameters characterizing a mathematical model-based relationship between a plasma tracer concentration and a total tracer concentration within the body part. For one preferred embodiment, computation of the PK parameters is performed according to a generalized signal model such that computation can be carried out in real time during an interactive viewer session, with required reference regions being selectable and optionally re-selectable by the viewer without requiring extensive waiting times for PK parameter computation. Associated user interfaces and computer-aided detection (CAD) algorithms are also provided.

Abstract: Simultaneous grayscale and geometric registration of images, such as mammograms, facilitates temporal comparison and enhances the speed and reliability of computer aided diagnosis (CAD) detection of medical abnormalities. The method generally includes optimizing a merit function, e.g., sum of squared errors, containing parameters associated with a transformation function for simultaneous geometric and grayscale registering of the images, the optimizing of the merit function being performed by determining optimal values of the parameters using data in the images and registering one image to the other by applying the geometric and grayscale transformation function using the optimal values of the parameters. The optimizing may be performed iteratively from coarse to fine resolutions using a modified Levenberg-Marquardt method for optimizing nonlinear parameters with linear regression for optimizing linear parameters.

Abstract: Numerical image processing of two or more medical images to provide grayscale registration thereof is described, the numerical image processing algorithms being based at least in part on a model of medical image acquisition. The grayscale registered temporal images may then be displayed for visual comparison by a clinician and/or further processed by a computer-aided diagnosis (CAD) system for detection of medical abnormalities therein. A parametric method includes spatially registering two images and performing gray scale registration of the images. A parametric transform model, e.g., analog to analog, digital to digital, analog to digital, or digital to analog model, is selected based on the image acquisition method(s) of the images, i.e., digital or analog/film.

Abstract: A method and apparatus for the automated detection of masses in a digital mammogram, the method for use in a computer aided diagnosis system for assisting a radiologist in identifying and recognizing suspicious portions of the digital mammogram. A gradient image is created from the digital mammogram, and information in the gradient image is processed for identifying masses. In a preferred embodiment, a portion of a spiculation detection algorithm is applied to the gradient image for identifying masses. The spiculation detection algorithm comprises a line detection portion and a post-line detection portion, and it is the post-line detection portion which is applied to the gradient image for identifying masses. Advantageously, computer programs which have already been written for spiculation detection may, with minor modifications, be ported into mass detection programs.