Arch Development Corporation

University of Chicago

Kabushiki Kaisha Toshiba

Kunio Doi

Shigehiko Katsuragawa

Maryellen L Giger

Robert M Nishikawa

Hiroyuki Yoshida

Xin-Wei Xu

Qiang Li

Takayuki Ishida

Takehiro Ema

Junji Morishita

Wei Zhang

Kenji Suzuki

Heber MacMahon

Kenneth R Hoffmann

Charles E Metz

Naoki Asada

Masahito Aoyama

Heang-Ping Chan

Hidetaka Arimura

Akiko Kano

Michitaka Honda

Chin-Tu Chen

Kenichi Komatsu

Zhimin Huo

Samuel Armato

Ping Lu

Tsuneo Matsumoto

Feng Li

Katsumi Nakamura

Shigeru Sanada

Junji Shiraishi

Yali Amit

Kyongtae Ty Bae

Yulei Jiang

Laura E Fencil

Shigehiko Katsuagawa

Kazuto Ashizawa

Yuichiro Kume

Roger Engelmann

Shigehiki Katsuragwa

Yoshikazu Uchiyama

Kwok L Lam

Nobuyuki Nakamori

Fang-Fang Yin

Hitoshi Yoshimura

Xuan Chen

A method, system, and computer program product for modifying an appearance of an anatomical structure in a medical image, e.g., rib suppression in a chest radiograph. The method includes: acquiring, using a first imaging modality, a first medical image that includes the anatomical structure; applying the first medical image to a trained image processing device to obtain a second medical image, corresponding to the first medical image, in which the appearance of the anatomical structure is modified; and outputting the second medical image. Further, the image processing device is trained using plural teacher images obtained from a second imaging modality that is different from the first imaging modality. In one embodiment, the method also includes processing the first medical image to obtain plural processed images, wherein each of the plural processed images has a corresponding image resolution; applying the plural processed images to respective multi-training artificial neural networks (MTANNs) to obtain plural output images, wherein each MTANN is trained to detect the anatomical structure at one of the corresponding image resolutions; and combining the plural output images to obtain a second medical image in which the appearance of the anatomical structure is enhanced.

Image modification and detection using massive training artificial neural networks (MTANN)

A method, system, and computer program product for detecting at least one nodule in a medical image of a subject, including identifying, in the medical image, an anatomical region corresponding to at least a portion of an organ of interest; filtering the medical image to obtain a difference image; detecting, in the difference image, a first plurality of nodule candidates within the anatomical region; calculating respective nodule feature values of the first plurality of nodule candidates based on pixel values of at least one of the medical image and the difference image; removing false positive nodule candidates from the first plurality of nodule candidates based on the respective nodule feature values to obtain a second plurality of nodule candidates; and determining the at least one nodule by classifying each of the second plurality of nodule candidates as a nodule or a non-nodule based on at least one of the pixel values and the respective nodule feature values. True-positive nodules are identified using linear discriminant analysis and/or a Multi-MTANN.

Automated method and system for the detection of lung nodules in low-dose CT images for lung-cancer screening

A method for determining whether a first medical image and a second medical image are medical images of the same patient, comprising selecting a first region in the first medical image; selecting a second region in the second medical image; determining a common region based on a boundary of the first region and a boundary of the second region; calculating a correlation coefficient based on image data from the first medical image in the common region and image data from the second medical image in the common region; and determining whether the first medical image and the second medical image are medical images of the same patient based on the correlation coefficient. Biological fingerprints from parts of chest radiographs such as thoracic fields, cardiac shadows, lung apices, superior mediastinum, and the right lower lung that includes the costophrenic angle, are used for the purpose of patient recognition and identification.

Automated method of patient recognition using chest radiographs

An automated computerized scheme for detection and characterization of diffuse lung diseases on high-resolution computed tomography (HRCT) images including obtaining image data including pixels of an organ; segmenting the image data into organ image data and non-organ image data; extracting predetermined features from the organ image data to produce a set of image features; comparing the set of image features against a reference set of organ image features containing image data known to correspond to normal and abnormal conditions; and producing a comparison result.

System and method for computer-aided detection and characterization of diffuse lung disease

A method, system and computer readable medium for computerized processing of chest images including obtaining a digital first image of a chest (S); producing a second image which is a mirror image (S) of the first image; performing image warping on one of the first and second images to produce a warped image (S) which is registered to the other of the first and second images; and subtracting the warped image from the other image to generate a subtraction image (S). Another embodiment includes obtaining a digital first image of the chest of a subject; detecting ribcage edges on both sides of the lungs in the first chest image; determining average horizontal locations of the left and right ribcage edges at plural vertical locations; fitting the determined average horizontal locations to a straight line to derive a midline; rotating the chest image so that the midline is vertical; and shifting the rotated image to produce a lateral inclination corrected (S) second image with the midline centered in the lateral inclination corrected image.

System for computerized processing of chest radiographic images

A method, system, and computer program product for evaluating an image including an object, including filtering image data derived from the image with a first geometric enhancement filter having magnitude and likelihood filter components so as to produce first filtered image data in which a first geometric pattern is enhanced. Thereafter the filtered image data can be subjected to processing to derive a measure indicative of the presence of the object in the image, including determining a region of interest in the image, extracting at least one feature from the first filtered image data from within the region of interest, and applying the at least one extracted feature to a classifier configured to output the measure indicative of the presence of the object in the image. The image data can also be subjected to filtering with second and/or third geometric filters which enhance different geometric patterns, and which produce respective filtered data which are also processed to derive the measure indicative of the presence of the object.

Method, system, and computer program product for computer-aided detection of nodules with three dimensional shape enhancement filters

An automated computerized scheme for determination of the likelihood of malignancy in pulmonary nodules. The present invention includes steps of obtaining at least one computed tomography medical image of a pulmonary nodule in determining if the pulmonary nodule is malignant based on the examination of seven patient or image features. The method can be implemented when instructions are loaded into a computer to program the computer. The significance of employing seven patient or image features is that statistically, seven features are the most practical based on the unique implementation of statistical analysis. Out of the seven features that are now analyzed to determine if a pulmonary nodule is malignant, these features are selected to optimize the accuracy of the diagnosis of a pulmonary nodule. Through a unique sampling scheme, different embodiments of the present invention utilize different combinations of features to optimize the accuracy of the method of the present invention.

Computerized method for determination of the likelihood of malignancy for pulmonary nodules on low-dose CT

A method, system and computer readable medium for a computer-automated method for identifying given image data, including obtaining template image data corresponding to said given image data; calculating correlation values between the given image data and said template image data; and identifying said image data based on the correlation values calculated in the calculating step.

Method, system and computer readable medium for identifying chest radiographs using image mapping and template matching techniques

A method of training an artificial neural network (ANN) involves receiving a likelihood distribution map as a teacher image, receiving a training image, moving a local window across sub-regions of the training image to obtain respective sub-region pixel sets, inputting the sub-region pixel sets to the ANN so that it provides output pixel values that are compared to output pixel values of corresponding teacher image pixel values to determine an error, and training the ANN to reduce the error. A method of detecting a target structure in an image involves scanning a local window across sub-regions of the image by moving the local window for each sub-region so as to obtain respective sub-region pixel sets, inputting the sub-region pixel sets to an ANN so that it provides respective output pixel values that represent likelihoods that respective image pixels are part of a target structure, the output pixel values collectively constituting a likelihood distribution map. Another method for detecting a target structure involves training N parallel ANNs on either (A) a same target structure and N mutually different non-target structures, or (B) a same non-target structure and N mutually different target structures, the ANNs outputting N respective indications of whether the image includes a target structure or a non-target structure, and combining the N indications to form a combined indication of whether the image includes a target structure or a non-target structure. The invention provides related apparatus and computer program products storing executable instructions to perform the methods.

Massive training artificial neural network (MTANN) for detecting abnormalities in medical images

A method, system, and computer program product of selecting a set of training images for a massive training artificial neural network (MTANN). The method comprises selecting the set of training images from a set of domain images; training the MTANN with the set of training images; applying a plurality of images from the set of domain images to the trained MTANN to obtain a corresponding plurality of scores; and determining the set of training images based on the plurality of images, the corresponding plurality of scores, and the set of training images. The method is useful for the reduction of false positives in computerized detection of abnormalities in medical images. In particular, the MTAAN can be used for the detection of lung nodules in low-dose CT (LDCT). The MTANN consists of a modified multilayer artificial neural network capable of operating on image data directly.

Method of training massive training artificial neural networks (MTANN) for the detection of abnormalities in medical images

A method, computer program product, and system ( ) for computerized analysis of the likelihood of malignancy in a pulmonary nodule using artificial neural networks (ANNs) (S ). The method, on which the computer program product and the system is based on, includes obtaining a digital outline of a nodule; generating objective measures corresponding to physical features of the outline of the nodule; applying the generated objective measures to an ANN; and determining a likelihood of malignancy of the nodule based on an output of the ANN. Techniques include novel developments and implementations of artificial neural networks and feature extraction for digital images. Output from the inventive method yields an estimate of the likelihood of malignancy (S ) for a pulmonary nodule.

System for detection of malignancy in pulmonary nodules

An automated method for analyzing a nodule and a computer storage medium storing computer instructions by which the method can be implemented when the instructions are loaded into a computer to program the computer. The method includes obtaining a digital image including the nodule; segmenting the nodule to obtain an outline of the nodule, including generating a difference image from chest image, identifying image intensity contour lines representative of respective image intensities in a region of interest including the nodule, and obtaining an outline of the nodule based on the image intensity contours; extracting features of the nodule based on the outline; applying features including the extracted features to at least one image classifier; and determining a likelihood of malignancy of the nodule based on the output of the at least one classifier. In one embodiment, extracted features are applied to a linear discriminant analyzer and/or an artificial neural network analyzer, the outputs of which are thresholded and the nodule determined to be non-malignant if each classifier output is below the threshold. In another embodiment, a common nodule appearing in an x-ray chest image and a CT image is segmented in each image, features extracted based on the outlines of each segmented nodule in the respective x-ray chest and CT images, and the extracted features from the x-ray chest image and CT images merged as inputs to a common classifier, with the output of the common classifier indicating the likelihood of malignancy.

Automated computerized scheme for distinction between benign and malignant solitary pulmonary nodules on chest images

A method to determine whether a candidate abnormality in a medical digital image is an actual abnormality, a system which implements the method, and a computer readable medium which stores program steps to implement the method, wherein the method includes obtaining a medical digital image including a candidate abnormality; obtaining plural first templates and plural second templates respectively corresponding to predetermined abnormalities and predetermined non-abnormalities; comparing the candidate abnormality with the obtained first and second templates to derive cross-correlation values between the candidate abnormality and each of the obtained first and second templates; determining the largest cross-correlation value derived in the comparing step and whether the largest cross-correlation value is produced by comparing the candidate abnormality with the first templates or with the second templates; and determining the candidate abnormality to be an actual abnormality when the largest cross-correlation value is produced by comparing the candidate abnormality with the first templates and determining the candidate abnormality to be a non-abnormality when the largest cross-correlation value is produced by comparing the candidate abnormality with the second templates. An actual abnormality is similarly classified as malignant or benign based on further cross-correlation values obtained by comparisons with additional templates corresponding to malignant and benign abnormalities.

Process, system and computer readable medium for pulmonary nodule detection using multiple-templates matching

A method, system, computer readable medium and apparatus for computerized detection of lung nodules in computer tomography images, by which mask images are created such that subtractions of the mask image from a targeted CT section image reveal or highlight small lung nodules in the target CT section. The mask image is created utilizing the targeted CT section image along with other CT section images generated from the same CT scan. Based on these other section CT images and the targeted CT section image, a mask image can be created that is very similar to the target CT section image, but without the presence of small lung nodules. When the mask image is subtracted from the targeted CT section image, the differences between the mask images and the CT section images reveal small lung nodules. The mask image may be created by linear interpolation or a morphological filtered image.

Subtraction technique for computerized detection of small lung nodules in computer tomography images

A method, system and computer readable medium of computerized processing of chest images including obtaining digital first and second images of a chest and detecting rib edges in at least one of the first and second images. The rib edges are detected by correlating points in the at least one of the first and second images to plural rib edge models using a Hough transform to identify approximate rib edges in one of the images, and delineating actual rib edges derived from the identified approximate rib edges using a snake model. The method system and computer readable medium further include deriving the shift values using the actual rib edges and warping one of the first and second images to produce a warped image which is registered to the other of the first and second images based at least in part on the shift values.

Method, system and computer readable medium for computerized processing of contralateral and temporal subtraction images using elastic matching

Growing community of inventors

Willowbrook, IL, United States of America

Kunio Doi