Abstract: An automated process classifies MRI or other medical imaging data as belonging to neurological structures. A training part of the process uses a baseline data set with accompanying classification map, as well as an arbitrary number of training data sets, also with accompanying classification maps. Each training data set is registered to the baseline data set using a warp-based automated registration algorithm. The resulting probability map, mean values and covariance matrices are used to classify structures in an image data set using a maximum likelihood criterion.

Abstract: A system and method for automatic quantitative assessment of myocardial image quality includes a liver-heart artifact quantification unit for providing a sequence of images, detecting the heart position in each image, segmenting non-heart activity relative to the detected heart positions, measuring the liver-heart effect in each image based on the segmentations, fusing the measurements obtained in each image, and determining a quality number for the plurality of images responsive to the fused measurements; and also includes a heart detection unit for receiving the image sequence, generating a region of interest comprising the heart by 1-D pseudo-motion analysis of the image sequence, localizing the heart center by a training-based algorithm, fitting a curve to the localized heart centers of each image in the sequence, refining the heart center positions of localized heart centers falling outside of a tolerance distance from the fitted curve, and determining a bounding circle comprising the heart in accordance

Abstract: Software, methods and user interfaces for viewing and generating a lung report. In exemplary methods, a first baseline image is analyzed to localize lung nodules. The lung nodule information can be stored and used to relocate the previously localized lung nodules in a second, follow-up imaging scan. The follow-up scan can be analyzed—either manually or automatically—to generate statistics for the lung nodules localized in the follow-up scan. Information derived from the baseline scan can be used to ease the localization of the lung nodules in the follow-up scan. In some exemplary methods, both the baseline scan and follow-up scan are displayed and the nodules are selected for comparison. Typically, the graphical user interface can display a third, composite image that displays the change of size of the nodules.

Abstract: A non-invasive longitudinal method that is sensitive and objective for quantifying progressive loss of neurons in normal aging brains and brains that suffer from a neurodegenerative disease is provided. The method also provides clinicians, patients and drug companies with a method for evaluating the efficacy of various treatments and interventions by assessing a change in brain integrity. The method determines and localizes a change in brain integrity in a compartment of a brain from at least structural images and metabolite brain images, which are acquired for at least two time instances. The time period between two time instances is dependent on the disease pathology and disease progression and could, for instance, be at least 3 months between time instances as well as at least 6 or 12 months between time instances.

Abstract: There is disclosed a method for analysing the behaviour of a subject comprising the steps of: making one or more measurements or observations of the subject; coding the measurements or observations into a plurality of channels; and analysing the channels using artificial intelligence, in order to output information relating to the psychology of the subject.

Abstract: A control device and measurement system for a living body applies lights of at least one wavelength in a visible-infrared region to a plurality of incident positions on a surface of the living body, and a light detector detects lights transmitted through the living body at a plurality of detection positions on the surface of the living body. An operation unit determines a type of output signal, based on an intensity of the transmitted light and pre-stored reference data, and outputs a signal indicative thereof as the type of output signal. An external equipment executes a functional operation according to the type of output signal from the operation unit. The incident positions and the detection positions are alternately disposed in square lattice form and middle points between the incident positions and detection positions adjacent to one another are defined as measurement positions.

Abstract: To prevent erroneous detection of a ribcage boundary from a chest image, an outer search limit point is decided with precision. A profile of smoothed pixel-value integrated averages in each of right and left lung field of the image is obtained, a threshold for each of the right and left lung fields with the profile taken as a reference is decided, and each of the right and left lung fields is searched from a central part of each lung field outwardly on the image so that a position exceeding the threshold is determined. The position is set as the outer search limit point for a series of a upper lung ribcage boundary candidate points. In the search, in cases the position exceeding the threshold is not found, a first derivative of the profile is used to decide the outer search limit point.

Abstract: The present invention relates to a method and apparatus for the construction and/or use of multidimensional fields that can be used for high-resolution detection and characterization of features within objects. The multidimensional field is constructed from data that is collected by an array of radiation detectors that substantially surround the object under study. The detected radiation is produced by an array of radiation sources and is subsequently scattered, reflected, transmitted, or diffracted by the object under study and any features within the object under study. In particular embodiments of the invention, the radiation that is used is ultrasonic radiation and the object under study is human or animal tissue or an organ. In this case, the invention permits the detection and identification of cancer by an intelligently trained evaluation system.

Abstract: Methods and Systems for analyzing data of a user viewing a display of dynamic hypermedia pages through a browser including monitoring and storing location and time of the user's gaze as eyetracker data, processing the eyetracker data into fixation data, monitoring and storing content of the displayed pages into a memory, restoring the displayed pages from the memory, mapping the fixations data onto the restored pages to thereby identify elements-of-regard, and storing the identified elements-of-regard in an elements-of-regard database.

Abstract: An MRI system center is connected to a plurality of MRI systems for visualizing the interior of a subject to be examined using a magnetic resonance phenomenon, through an electronic communication line. The MRI system center receives data of a log file on which a use state of the MRI systems is recorded or use-state data extracted from the log file, from the MRI systems through a communication control unit. A database unit stores the data of the log file or the use-state data. An analysis unit analyzes the data of the log file or the use-state data received within a given period of time.

Abstract: A method for evaluating a structural strength of cancellous bone and a computer readable media incorporating a program for implementing the method therein. The method includes the steps of acquiring an x-ray image and defining a region of interest on the acquired x-ray image; extracting a bone trabecular pattern in the defined region of interest; and setting an index of the structural strength of the cancellous bone using an area density of the extracted bone trabecular pattern.

Abstract: A diagnostic imaging system, notably a magnetic resonance imaging system comprises a receiver antenna for picking-up magnetic resonance signals and an ultrasound probe for receiving ultrasound echoes. A reconstruction unit is arranged to reconstruct a diagnostic image from the magnetic resonance signals and the ultrasound echoes in particular, the magnetic resonance image and ultrasound images are registered in a common reference frame and geometric distortions in the ultrasound image are corrected on the basis of the magnetic resonance image. Different tissues types are distinguished in the magnetic resonance image and corrections are made for differences between ultrasound sound velocities in these tissue types. Further, information contained in the magnetic resonance signals can be displayed in combination in the ultrasound echoes.

Abstract: A remote maintenance and operating guidance system in which data relating to the operation of a medical system in a hospital is transmitted to an operator who operates an operating device of the medical system from a service center by way of a communication device such as a dedicated telephone line. The system is equipped to monitor operations performed by the operator on the medical system, and to transmit data relating to the monitored operation to the operating device.

Abstract: A method for rejecting the magnetic response of surrounding biological tissues, in measuring the magnetic susceptibility response of a region of interest in a patient, to detect the presence of ferromagnetic foreign bodies. The magnetic response of the surrounding tissues is rejected by defining a statistically determined normal range of magnetic susceptibility responses, or by rejecting magnetic field responses characteristic of materials with isotropic magnetization properties.

Abstract: To prevent erroneous detection of a ribcage boundary from a chest image, an outer search limit point is decided with precision. A profile of smoothed pixel-value integrated averages in each of right and left lung field of the image is obtained, a threshold for each of the right and left lung fields with the profile taken as a reference is decided, and each of the right and left lung fields is searched from a central part of each lung field outwardly on the image so that a position exceeding the threshold is determined. The position is set as the outer search limit point for a series of a upper lung ribcage boundary candidate points. In the search, in cases the position exceeding the threshold is not found, a first derivative of the profile is used to decide the outer search limit point.

Abstract: An apparatus for detection of precancerous and cancerous conditions in a breast is provided and includes a computer for digitizing at least one of a mammogram image data and a (scinti)mammogram image data of a breast, computer-based software operably associated with the computer based means for manipulating at least one of said digitized mammogram image data and said digitized (scinti)mammogram image data and generating at least one of a mammogram ROI image and a (scinti)mammogram ROI image data indicative of precancerous and cancerous condition, and monitor operably associated with the computer based means for concurrently visually displaying at least one of said digitized mammogram image data and said digitized (scinti)mammogram image data and said mammogram ROI image and said (scinti)mammogram ROI image data in a superimposed manner.

Abstract: Disclosed is a system and method for determining a severity of a stenosis in a blood vessel depicted in a magnetic resonance imaging (MRI) data set. The system comprises a neural network configured to calculate the severity of the stenosis in the blood vessel based upon a number of input parameters, and the input parameters including at least one characteristic of a signal void associated with the stenosis in the MRI data set. The input parameters may include, for example, a flow rate of blood through the blood vessel, a length of a longitudinal axis of the signal void, and an average image intensity along the longitudinal axis of the signal void as well as other input parameters.

Abstract: A method and an apparatus for measuring and classifying skin anomalies by taking at least one digital image of the anomaly and a digital color reference image of healthy skin in the vicinity of the anomaly, computing surface measurement data including three-dimensional coordinates and color values scaled to the reference image of the anomaly and classifying the anomaly in predetermined categories on the basis of the surface measurement data.

Abstract: A method and system for the computerized automatic analysis of lesions in magnetic resonance (MR) images, a computer programmed to implement the method, and a data structure for storing required parameters is described. Specifically the system includes the computerized analysis of lesions in the breast using spatial, temporal and/or hybrid measures. Techniques include novel developments and implementations of two-dimensional and three-dimensional features to assess the characteristics of the lesions and in some cases give an estimate of the likelihood of malignancy or of prognosis. The system can also allow for the enhanced visualization of the breast and its pathological states. The system also includes an option to merge the extracted features with those from x-ray and/or ultrasound images in order to further characterize the lesion and/or make a diagnosis and/or a prognosis.

Abstract: Obtaining fast dipole size estimation with less influence of noise by using a regional dipole model. An artificial neural network section 30 executes regional dipole size estimation using a neural network having coupling coefficients representing coupling states among as plurality of units and thresholds thereof.

Abstract: A method for using acetic acid as a contrast agent during reflectance confocal imaging of normal and neoplastic tissue, particularly epithelium. In one aspect, the invention includes a method of using acetic acid as a contrast agent for confocal imaging of cells, including applying acetic acid to the diagnostic tissue sample in sufficient concentration to induce a small scale alteration of the index of refraction of nuclei in the cells; and imaging such cells using a reflectance confocal imaging system.

Abstract: The present method of processing spectral data calculates the first to fourth derivative spectra of an original spectrum with respect to the wavenumber and creates a two-dimensional representation by plotting coordinates consisting of the derivative values of some order as their abscissas and the original spectral values or derivative values of another order different from that order as their ordinates. In this two-dimensional plotting, maximal points, minimal points, maximal slope points (inflection points) and the like are clearly represented, so that a great amount of accurate feature information about the analyzed object can be easily obtained.

Abstract: An apparatus and methods for spectroscopic detection of tissue abnormality, particularly precancerous cervical tissue, using neural networks to analyze in vivo measurements of fluorescence spectra. The invention excites fluorescence intensity spectra in both normal and abnormal tissue. This fluorescence spectroscopy data is used to train a group (ensemble) of neural networks, preferably radial basis function (RBF) neural networks. Once trained, fluorescence spectroscopy data from unknown tissue samples is classified by the trained neural networks. This process is used to differentiate pre-cancers from normal tissues, and can also be used to differentiate high grade pre-cancers from low grade pre-cancers. One embodiment of the invention is able to distinguish pre-cancerous tissue from both normal squamous tissue (NS) and normal columnar (NC) tissue in a single-stage of analysis.

Abstract: A device to detect the location of a magnet coupled to an indwelling medical device within a patient uses three or more sets of magnetic sensors each having sensor elements arranged in a known fashion. Each sensor element senses the magnetic field strength generated by the magnet and provides data indicative of the direction of the magnet in a three-dimensional space. The device uses fundamental equations for electricity and magnetism that relate measured magnetic field strength and magnetic field gradient to the location and strength of a magnetic dipole. The device uses an iterative process to determine the actual location and orientation of the magnet. An initial estimate of the location and orientation of the magnet results in the generation of predicted magnetic field values. The predicted magnetic field values are compared with the actual measured values provided by the magnetic sensors.

Abstract: An automated method, and a computer storage medium storing instructions for executing the method, for analysis of image features in lung nodule detection in a chest radiographic image represented by digital data, including preprocessing the image to identify candidate nodules in the image; establishing a region of interest (ROI) including a candidate nodule identified in the preprocessing step; performing image enhancement of the candidate nodule within the ROI; obtaining a histogram of accumulated edge gradients as a function of radial angles withing the ROI after performing the image enhancement; and determining whether the candidate nodule is a false positive based on the obtained histogram. A 64.times.64-pixel region of interest (ROI) centered at the candidate location is used. The contrast of the ROI is improved by a two-dimensional background subtraction. A nodule shape matched filter is used for enhancement of the nodular pattern located in the central area of the ROI.

Abstract: A computer-aided method for detecting, classifying, and displaying candidate abnormalities, such as microcalcifications and interstitial lung disease in digitized medical images, such as mammograms and chest radiographs, a computer programmed to implement the method, and a data structure for storing required parameters, wherein in the classifying method candidate abnormalities in a digitized medical image are located, regions are generated around one or more of the located candidate abnormalities, features are extracted from at least one of the located candidate abnormalities within the region and from the region itself, the extracted features are applied to a classification technique, such as an artificial neural network (ANN) to produce a classification result (i.e., probability of malignancy in the form of a number and a bar graph), and the classification result is displayed along with the digitized medical image annotated with the region and the candidate abnormalities within the region.

Abstract: A computerized imaging system (such as CAT scan, MRI imaging, ultrasound imaging, infrared, X-ray, UV/visible light fluorescence, Raman spectroscopy or microwave imaging) is employed to sense the position of an endoscopic treatment system within the body of a patient. In a preferred embodiment, the system provides real-time computer control to maintain and adjust the position of the treatment system and/or the position of the patient relative to the treatment system; and also provides (if desired) real-time computer control of the operation of the treatment system itself. Other embodiments include scanning mechanisms for directing laser light or other radiation under controlled conditions at select locations within the body.

Abstract: Time-Of-Flight (TOF) MRI techniques are used to enhance blood flows into one of a pair of images for a given plane or slice of a patent's body. Arithmetic subtraction of such images produces a resultant image of substantially only blood flows since images of fat or other tissue are thus nulled out of the resultant image. All basic MRI sequences (e.g., FE, SE, etc.) can be used in conjunction with a pre-pulse on additional sub-sequences in a plane displaced from the objective plane to be imaged. Both arterial and venous blood flows can be imaged (separately or together in one resultant image). Color coding can be used in the resultant images to distinguish blood flow directions and/or velocities.

Abstract: A fetal data processing system and method, and a fetal monitor and method for monitoring the condition of a fetus are disclosed. A fetal heart rate time series is received and sampled. A non-linear time-frequency transformation is performed to generate a time-frequency representation of the fetal heart rate time series for heart rate time series data spanning a time period which is preferably less than ten seconds. Analysis of fetal heart rate and fetal heart rate variability and other available data is performed to evaluate fetal well-being. Because of the high time resolution of the transformation, short-term transient variations in the heart rate and heart rate variability are considered in the analysis.

Abstract: A system and method is provided for the treatment of hypreproliferative diseases, such as cancer, using real-time computer control to visualize, to position and to operate drug infusing and imaging devices within the body of the patient. The invention employs a computerized imaging system (such as CAT scan, MRI imaging, ultrasound imaging, infrared, X-ray, UV/visible light fluorescence, Raman spectroscopy, single photon emission computed tomography or microwave imaging) to sense the position of a drug infusing catheter within the body.

Abstract: An automated computer-aided diagnosis (CAD) method and system using artificial neural networks (ANNs) for the quantitative analysis of image data. Three separate ANNs were applied for detection of interstitial disease on digitized two-dimensional chest images. The first ANN was trained with horizontal profiles in regions of interest (ROIs) selected from normal and abnormal chest radiographs. The second ANN was trained using vertical output patterns obtained from the 1.sup.st ANN for each ROI. The output value of the 2.sup.nd ANN was used to distinguish between normal and abnormal ROIS with interstitial infiltrates. If the ratio of the number of abnormal ROIs to the total number of all ROIs in a chest image was greater than a certain threshold level, the chest image was considered abnormal. In addition, the third ANN was applied to distinguish between normal and abnormal chest images where the chest image was not clearly normal or abnormal.

Abstract: A live body internal condition predicting and expressing system is capable of predicting the internal condition of a live body on the basis of an electromagnetic field distribution at significantly reduced period.

Abstract: Non-invasive quantitative in-vivo electromagnetic evaluation of bone is performed by subjecting bone to an electrical excitation wave-form supplied to a pair of electrodes on opposite sides of a bony member, and involving a repetitive finite duration signal consisting of plural frequencies that are in the range 0 Hz-200 MHz. Signal-processing of a bone-current response signal and a bone-voltage response signal is operative to sequentially average the most recently received given number of successive bone-current and bone-voltage response signals to obtain an averaged per-pulse bone-current signal and an averaged per-pulse bone-voltage signal, and to produce their associated Fourier transforms. These Fourier transforms are further processed to obtain the frequency-dependent bone-admittance function.

Abstract: A method and apparatus for directly identifying and characterizing input data derived from regions of interest in ultrasound images of organs in the presence of attenuation from interposed contrast agent, for the purpose of diagnosing abnormalities. The input data is classified into one of a number of classes depending upon the characteristics of that data, in order to distinguish normal conditions from abnormal conditions. The invention is based on the recognition that significant information relating to the health of tissue exists in regions of interest in ultrasound images in the presence of attenuation from interposed contrast agent. This information is in the form of backscatter speckle patterns that have "texture" characteristics that are distinguishable in healthy versus diseased tissue. The invention classifies such patterns as probably normal or abnormal by means of an analysis system that may include a neural network system.