Abstract: A method of characterizing a tissue type of a tissue region includes providing a tissue classifier comprising multiple detector arrays for each of multiple tissue types. Each detector array comprises multiple detectors and each detector comprises multiple tissue type-assigned intravascular ultrasound (IVUS) spectra. A plurality of the tissue type-assigned IVUS spectra of each detector correspond to a tissue type of the detector and a plurality of the tissue type-assigned IVUS spectra correspond to other tissue types. For each of the detector arrays, an input IVUS spectrum of the tissue region is compared to the tissue type-assigned IVUS spectra of each of the detectors in the detector array. For each of the detectors, it is determined whether the input spectrum corresponds to the tissue type of the detector based on the comparisons of the input spectrum to the tissue type-assigned spectra for that detector.

Abstract: The invention is directed to systems and methods for detecting and presenting textural information from medical images. In one embodiment, a medical imaging system includes an imaging transducer assembly configured to emit one or more energy pulses and receive one or more echo signals, and a console, coupled to the imaging transducer assembly, configured to receive the one or more echo signals, generate an uncompressed image based on the one or more echo signals, generate a log compressed image based on the uncompressed image, generate a color overlay based on the uncompressed image, and apply the color overlay to the log compressed image.

Abstract: Systems and methods are described for displaying classifier output and confidence measure in an image. The confidence measure advantageously provides additional information to the user indicating the accuracy of the classification result. Based on the classification accuracy, the user may accept or reject the classification result. In an exemplary embodiment, the classifier output is displayed on the image by color coding regions in the image based on their classifications. The confidence measure is displayed by adjusting the transparencies of the color coded regions according to their confidence measures. In one embodiment, only the classifications having confidence measures above a threshold are displayed. In other embodiments, the classifier output and confidence measure may be displayed separately, contour lines may be drawn through image regions having similar confidence measures, and the confidence measure may be displayed for a region under a pointer that the user can move within the image.

Abstract: The improved system and method detects edges in an image defined by a data set. In one aspect, a plurality of arrays of pattern recognition classifiers are populated throughout an image. Each array may yield a value which indicates whether or not the array is on or near an edge to be detected. The edge may be interpolated between the arrays that are on or near an edge to be detected or extrapolated after an array on or near the edge. This edge detection method may result in more accurate edge detection.

Abstract: The systems and methods can apply a plurality of different classifiers to a given input image instead of a single classifier. The plurality of classifiers produce a plurality of classified images based on the input image, which are sequentially displayed to a human observer. The sequential display of the classified images produces a dynamic classified image, in which the classification of the input image varies with time depending on which one of the classified image is displayed at a given instant. The dynamic classified image provides dynamic stimuli that encourages the human visual system to excuse occasional classification errors from a minority of the classified images and to retain generally correct classifications from a majority of the classified images.

Abstract: An improved method of tracking a catheter's position within a human body does not rely on x-rays, but instead calculates the position of the catheter's imaging head by analyzing image data. Such an analysis is able to determine the position of the imaging head in 3 dimensional space, relative to an arbitrarily selected reference image. An image is compared with the reference image, correlation data between corresponding points on the two images are gathered, and a correlation loss rate in a particular direction is determined. This correlation loss rate is modeled to an exponential function, which is evaluated to estimate an angle of separation between the image and the reference image. One or more angles of separation are used to determine a position in three dimensional space of the image, relative to the reference image. By repeating this process for a series of images being gathered by a catheter, the position of the catheter can be determined.

Abstract: An improved method of tracking a catheter's position within a human body does not rely on x-rays, but instead calculates the position of the catheter's imaging head by analyzing image data. Such an analysis is able to determine the position of the imaging head in 3 dimensional space, relative to an arbitrarily selected reference image. An image is compared with the reference image, correlation data between corresponding points on the two images are gathered, and a correlation loss rate in a particular direction is determined. This correlation loss rate is modeled to an exponential function, which is evaluated to estimate an angle of separation between the image and the reference image. One or more angles of separation are used to determine a position in three dimensional space of the image, relative to the reference image. By repeating this process for a series of images being gathered by a catheter, the position of the catheter can be determined.

Abstract: The field of the invention relates to medical imaging systems, and more particularly to systems and methods for restoring a medical image affected by nonuniform rotational distortion. In one embodiment, an imaging system includes an imaging catheter having proximal and distal sections, an imaging device coupled to the distal section of the imaging catheter, said imaging device configured to rotate at a uniform angular velocity, and a processor electrically coupled to imaging device, said processor configured to generate a plurality of vectors as the imaging device rotates to form a medical image, estimate an instantaneous angular velocity of the imaging device as the imaging device rotates, and remap the plurality of vectors in the event that the estimated instantaneous angular velocity differs from the uniform angular velocity.

Abstract: The systems and methods of the invention described herein improve classification accuracy by producing classifiers with individuality, in which each classifier exhibits its own distinctive behavior. A method according to one exemplary embodiment produces each classifier with individuality by randomly selecting subsets of a feature vector and using the randomly selected subsets of the feature vector in the design of the classifier. Because different subsets of the feature vector are used for each classifier, each classifier exhibits its own distinctive behavior or individuality. The classifiers with individuality improve classification accuracy, for example, when used as classifiers in a classifier array. This is because the individuality among the classifiers in the array ensures that a misclassification committed by one of the classifiers will not be repeated by other classifiers in the array, thereby improving the overall accuracy of the classifier array.

Abstract: The systems and methods described herein provide for automatic time-gain compensation of an ultrasound image with an image processing algorithm. A method of automatic time-gain compensation is provided where ultrasound image data is obtained comprising a plurality of echogenic data sets, a plurality of time-gain compensation functions are determined for the plurality of echogenic data sets, wherein each time-gain compensation function is determined from a separate echogenic data set and the time-gain compensation functions are applied to the plurality of echogenic data sets automatically without user intervention. Also provided is an ultrasound imaging system having an ultrasound imaging device configured to collect ultrasound image data and an image processing system configured to automatically time-gain compensate the collected image data.

Abstract: In an image gathering and display system, data is interpolated by gathering non-interpolated input data and formatting that data such that a user of the data can interpolate the data without requiring the image gathering and display system to perform the interpolation. A series of weighted randomly selected non-interpolated input data values are displayed to the user as a stream of non-interpolated output values, such that the user interpolates the series of non-interpolated output values.

Abstract: Methods and systems for medical imaging are described. One implementation of the system includes an image acquisition subsystem configured to acquire medical images, an image analysis subsystem configured to analyze each acquired medical image and associate one or more descriptors with each acquired medical image based on the analysis, a database configured to store the acquired medical images and associated descriptors, and a query tool configured to search the database using descriptors.

Abstract: The invention is directed to systems and methods for detecting and presenting textural information from medical images. In one example embodiment, a medical imaging system includes an imaging transducer assembly configured to emit one or more energy pulses and receive one or more echo signals, and a console, coupled to the imaging transducer assembly, configured to receive the one or more echo signals, detect one or more signals that correspond with an abnormality, and invoke an alert in response to the detection of the one or more signals that correspond with an abnormality.

Abstract: The field of the invention relates to medical imaging systems, and more particularly to systems and methods for estimating the size and position of a stent or other medical device within a patient. In one embodiment, a medical imaging system includes an elongated tubular member having distal and proximal ends, configured to be inserted into a vessel of a patient, an imaging device coupled to the distal end of the elongated tubular member and configured to emit one or more energy pulses and receive one or more echo signals, and a console electrically coupled to the imaging device, wherein the console includes a computer-usable medium, electrically coupled to the imaging device, having a sequence of instructions which, when executed by a processor, causes said processor to execute a process including generating an image of the vessel, and providing a graphical representation of a stent to be overlaid onto the image.

Abstract: The systems and methods described herein provide for fast and accurate image segmentation through the application of a multi-stage classifier to an image data set. An image processing system is provided having a processor configured to apply a multi-stage classifier to the image data set to identify a distinctive region. The multi-stage classifier can include two or more component classifiers. The first component classifier can have a sensitivity level configured to identify one or more target regions in the image data set and the second component classifier can have a specificity level configured to confirm the presence of the distinctive region in any identified target regions. Also provided is a classification array having multiple multi-stage classifiers for identification and confirmation of more than one distinctive region or for the application of different classification configurations to the image data set to identify a specific distinctive region.

Abstract: The invention is generally directed to imaging systems, and more particularly to systems and methods for pattern recognition. In one embodiment, a medical imaging system includes an imaging device and a computer-usable medium, electrically coupled to the imaging device, having a sequence of instructions which, when executed by a processor, causes said processor to execute a process including generating an image from signals received by the imaging device, deconvolving the image, and then extracting a desired pattern from the deconvolved image.

Abstract: A new image processing method reduces Nonuniform Rotational Distortion (NURD) in a medical image acquired using a rotating transducer. The image comprises a plurality of image vectors having texture. In a preferred embodiment, the image processing technique computes an average frequency of the texture for each image vector and estimates an angle for each image vector based on the average frequency for the respective image vector. The image processing technique then corrects for NURD by remapping each image vector to the estimated angle for the respective image vector.

Abstract: The systems and methods described herein allow measurement of the velocity of a pulse wave propagating within a body lumen using an intravascular elongate medical device. The elongate medical device can include a data collection device configured to collect pulse wave data at a location within the lumen. The data collection device is communicatively coupled with a velocity measurement system and configured to output the collected data to the velocity measurement system. The velocity measurement system is configured to calculate the velocity of the pulse wave based on the collected data. The velocity of a pulse wave over a region of the lumen can be used for tissue characterization, diagnosis and the like.

Abstract: The systems and methods described herein provide for automatic time-gain compensation of an ultrasound image with an image processing algorithm. A method of automatic time-gain compensation is provided where ultrasound image data is obtained comprising a plurality of echogenic data sets, a plurality of time-gain compensation functions are determined for the plurality of echogenic data sets, wherein each time-gain compensation function is determined from a separate echogenic data set and the time-gain compensation functions are applied to the plurality of echogenic data sets automatically without user intervention. Also provided is an ultrasound imaging system having an ultrasound imaging device configured to collect ultrasound image data and an image processing system configured to automatically time-gain compensate the collected image data.

Abstract: The systems and methods can apply a plurality of different classifiers to a given input image instead of a single classifier. The plurality of classifiers produce a plurality of classified images based on the input image, which are sequentially displayed to a human observer. The sequential display of the classified images produces a dynamic classified image, in which the classification of the input image varies with time depending on which one of the classified image is displayed at a given instant. The dynamic classified image provides dynamic stimuli that encourages the human visual system to excuse occasional classification errors from a minority of the classified images and to retain generally correct classifications from a majority of the classified images.