312 results about "Computer-aided diagnosis" patented technology

The invention provides systems and methods for detection, grading, scoring and tele-screening of cancerous lesions. A complete scheme for automated quantitative analysis and assessment of human and animal tissue images of several types of cancers is presented. Various aspects of the invention are directed to the detection, grading, prediction and staging of prostate cancer on serial sections/slides of prostate core images, or biopsy images. Accordingly, the invention includes a variety of sub-systems, which could be used separately or in conjunction to automatically grade cancerous regions. Each system utilizes a different approach with a different feature set. For instance, in the quantitative analysis, textural-based and morphology-based features may be extracted at image- and (or) object-levels from regions of interest. Additionally, the invention provides sub-systems and methods for accurate detection and mapping of disease in whole slide digitized images by extracting new features through integration of one or more of the above-mentioned classification systems. The invention also addresses the modeling, qualitative analysis and assessment of 3-D histopathology images which assist pathologists in visualization, evaluation and diagnosis of diseased tissue. Moreover, the invention includes systems and methods for the development of a tele-screening system in which the proposed computer-aided diagnosis (CAD) systems. In some embodiments, novel methods for image analysis (including edge detection, color mapping characterization and others) are provided for use prior to feature extraction in the proposed CAD systems.

Described are systems, media, and methods for applying deep convolutional neural networks to medical images to generate a real-time or near real-time diagnosis.

A multispectral X-ray imaging system uses a wideband source and filtration assembly to select for M sets of spectral data. Spectral characteristics may be dynamically adjusted in synchrony with scan excursions where an X-ray source, detector array, or body may be moved relative to one another in acquiring T sets of measurement data. The system may be used in projection imaging and/or CT imaging. Processed image data, such as a CT reconstructed image, may be decomposed onto basis functions for analytical processing of multispectral image data to facilitate computer assisted diagnostics. The system may perform this diagnostic function in medical applications and/or security applications.

A method for using computer-aided diagnosis (CAD) for digital tomosynthesis mammograms (DTM) including retrieving a DTM image file having a plurality of DTM image slices; applying a three-dimensional gradient field analysis to the DTM image file to detect lesion candidates; identifying a volume of interest and locating its center at a location of high gradient convergence; segmenting the volume of interest by a three dimensional region growing method; extracting one or more three dimensional object characteristics from the object corresponding to the volume of interest, the three dimensional object characteristics being one of a morphological feature, a gray level feature, or a texture feature; and invoking a classifier to determine if the object corresponding to the volume of interest is a breast cancer lesion or normal breast tissue.

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. 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. The models take into account the most relevant image acquisition parameters that influence pixel value differences between images, e.g., tissue compression, incident radiation intensity, exposure time, film and digitizer characteristic curves for analog image, and digital detector response for digital image. The method facilitates temporal comparisons of medical images such as mammograms and/or comparisons of analog with digital images.

A statistical (a) Computer Aided Diagnostic (CAD) technique is described for symptomatic versus asymptomatic plaque automated classification of carotid ultrasound images and (b) presents a cardiovascular risk score computation. We demonstrate this for longitudinal Ultrasound, CT, MR modalities and extendable to 3D carotid Ultrasound. The on-line system consists of Atherosclerotic Wall Region estimation using AtheroEdge™ for longitudinal Ultrasound or Athero-CTView™ for CT or Athero-MRView from MR. This greyscale Wall Region is then fed to a feature extraction processor which uses the combination: (a) Higher Order Spectra; (b) Discrete Wavelet Transform (DWT); (c) Texture and (d) Wall Variability. Another combination uses: (a) Local Binary Pattern; (b) Law's Mask Energy and (c) Wall Variability. Another combination uses: (a) Trace Transform; (b) Fuzzy Grayscale Level Co-occurrence Matrix and (c) Wall Variability. The output of the Feature Processor is fed to the Classifier which is trained off-line.

A technique is disclosed for generating variance data and a variance map from measured projection data acquired from a tomography system. The method comprises accessing the measured projection data from the tomography system. The method further comprises generating the variance map from the measured projection data and displaying, analyzing or processing the variance map. The variance data is determined based upon a statistical model from measured image data, and may be used for image analysis, data acquisition, in computer aided diagnosis routines, and so forth.

The invention discloses a method for automatically identifying a breast tumor area based on an ultrasound image. The method comprises the following steps of acquiring the ultrasound image of the breast, and preprocessing the ultrasound image; segmenting the ultrasound image subjected to preprocessing through an image segmentation method to obtain a plurality of segmented subareas; extracting a grey level histogram, texture features, gradient features and morphological features of the ultrasound image, and combining the grey level histogram, the texture features, the gradient features and the morphological features of the ultrasound image with two-dimensional position information to obtain high-dimensionality feature vectors; selecting the most effective feature subset of the high-dimensionality feature vectors through feature ordering based on biclustering and a selection method; performing learning classification on the selected most effective feature subset through a classifier, and then automatically identifying the breast tumor area. By means of the method, the breast tumor area can be identified automatically from segment results of the breast tumor ultrasound image, therefore, automation performance of computer-aided diagnosis is improved, manual operation of clinical doctors is reduced, and subjective influence of clinical doctors is reduced.

A computer-aided diagnosis (CAD) apparatus and method. The CAD apparatus includes an area divider configured to divide a current image frame into a first area and a second area based on location of a region of interest (ROI) detected in a previous image frame. The CAD apparatus further includes a functional processor configured to perform different functions of the CAD apparatus for the first area and the second area.

An apparatus configured to display 3D volumetric data acquired from a patient by an imaging system comprises a 3D volumetric display system configured to generate a real-time 3D diagnostic display of the 3D volumetric data. The 3D volumetric display system includes a graphical user interface configured to permit a user to access, view, and manipulate the 3D volumetric data. The graphical user interface also includes a plurality of 3D computer-aided diagnosis (CAD) markers, each plurality of 3D CAD markers having a delineator configured to navigate through the 3D volumetric data to locate pathology and to permit a user to compile and to prepare a report containing diagnosis information in a virtual-reality environment.

The invention provides an image segmentation method based on an annotated image learn. The method comprises two processes of: 1, learning an annotated training sample, namely segmenting the training image, performing scene classification on the training image, and establishing connection between the annotated words and the segmentation region on a special scene; and 2, determining the annotated words of the region to be segmented according to a model parameter acquired by learning in the process 1, performing information fusion according to the annotated information of the region and finishing segmentation. According to the method, the image segmentation and the identification process are fused by learning the annotated image; the annotated words serve as connecting link of the image segmentation and object identification; connection is established between low-grade visual stimulation and the annotated words representing high-grade semantic information to guide the image segmentation process, so that the cognitive ability of the image segmentation result is improved. The method can be directly applied to the actual application fields such as automatic image annotation, computer-aided diagnosis of a medical image, segmentation and classification of remote sensing images, multimedia information retrieval and the like.

A method of characterizing a mass within a digital mammogram. A region of interest is identified that includes the mass and surrounding tissue. A border outline of the mass is identified. A rectangular image is formed wherein each column of the image is formed by repetition of steps. A vector is employed for each of a set of ray angles, wherein the vector extends from a central point of the mass and intersects the border outline at an intersection point. A starting pixel along the vector is identified, between the intersection point and the central point, at a first distance before the intersection point. An ending pixel along the vector is identified at a second distance beyond the intersection point. Pixels along the vector, from the starting pixel to the ending pixel, are remapped as the respective column in the rectangular image. Texture features are extracted from the formed rectangular image.

According to an aspect of the invention, a method for training a classifier for classifying candidate regions in computer aided diagnosis of digital medical images includes providing a training set of annotated images, each image including one or more candidate regions that have been identified as suspicious, deriving a set of descriptive feature vectors, where each candidate region is associated with a feature vector. A subset of the features are conditionally dependent, and the remaining features are conditionally independent. The conditionally independent features are used to train a naïve Bayes classifier that classifies the candidate regions as lesion or non-lesion. A joint probability distribution that models the conditionally dependent features, and a prior-odds probability ratio of a candidate region being associated with a lesion are determined from the training images. A new classifier is formed from the naïve Bayes classifier, the joint probability distribution, and the prior-odds probability ratio.

A method for training a classifier for classifying candidate regions in computer aided diagnosis of digital medical images includes providing a training set of images, each image including one or more candidate regions that have been identified as suspicious by a computer aided diagnosis system. Each image has been manually annotated to identify malignant regions. Multiple instance learning is applied to train a classifier to classify suspicious regions in a new image as malignant or benign by identifying those candidate regions that overlap a same identified malignant region, grouping each candidate region that overlaps the same identified malignant region into a same bag, and maximizing a probability

wherein N is a number of bags, p_i is a probability of bag i containing a candidate region that overlaps with an identified malignant region, and y_i is a label where a value of 1 indicates malignancy and 0 otherwise.

The invention discloses an evaluating system of depressive disorder degree quantization. The system comprises an electrocardio and pulse wave integral detection device, a data transmission device and a data processing platform. The invention further discloses an evaluating method of depressive disorder degree quantization. The method comprises the following steps that firstly, human physiological information under different states is acquired through a multi-state comprehensive test platform; secondly; HRV characteristic parameters under the different states are obtained on the basis of the heart rate variability analysis principle; thirdly, the function balance states of sympathetic nerves and pneumogastric nerves in the automatic nervous system are evaluated; fourthly, a depressive disorder degree quantization evaluation model is built, and the depressive disorder degree level of a tested person is evaluated fast and objectively. The system and method belong to the technical field of computer-aided diagnosis, depressive disorder degree quantization evaluation is achieved, the blank of the technical field of depressive disorder inspection is filled up, and the system and method are easy and convenient to implement, save medical resources and have the good clinic practicality.

The invention relates to the technical field of medical image computer aided diagnosis, and discloses a medical image auxiliary diagnosis and semi-supervised sample generation system. The medical image aided diagnosis and semi-supervised sample generation system comprises a hospital image filing and communication module (a), a pulmonary nodule-based automatic detection module (b), a deep learning-based semantic annotation generation module (c) and a sample library module (d), wherein the hospital image filing and communication module is used for filing image data; the pulmonary nodule-based automatic detection module is used for automatically detecting pulmonary nodules to generate suspected pulmonary nodule positions; the deep learning-based semantic annotation generation module is used for receiving a small quantity of instructions of doctors and generating samples with accurate pulmonary nodule profiles and pulmonary nodule ingredient properties; and the sample library module is used for storing qualified samples so that online learning can be carried out by other self-learning systems. According to the system, the problem that computer aided software cannot feed closed loops back, cannot generate high-quality samples and cannot carry out self-learning is solved, and a feasible method is provided for a self-learning computer aided diagnosis system of CT images.

A computer-assisted diagnosis method for assisting diagnosis of anatomical structures in a digital volumetric medical image of at least one lung includes identifying an anatomical structure of interest in the volumetric digital medical image. The anatomical structure of interest is automatically segmented, in real-time, in a predefined volume of interest (VOI). Quantitative measurements of the anatomical structure of interest are automatically computed, real-time. A result of the segmenting step and a result of the computing step are displayed, in real-time. A likelihood that the anatomical structure of interest corresponds to a disease or an area warranting further investigation is estimating, in real-time, based on predefined criteria and the quantitative measurements. A warning is generated, in real-time, when the likelihood is above a predefined threshold.

Methods for fully automatic quantification and interpretation of three dimensional images of the brain or other organs. A system for Computer Aided Diagnosis (CAD) of diseases affecting cerebral cortex from SPECT images of the brain, where said images may represent cerebral blood flow (CBF). The methods include image processing, statistical shape models, a virtual brain atlas, reference databases and machine learning.