205 results about "Lesion detection" patented technology

Methods are provided for close-range intraoperative, endoscopic and intravascular deflection and treatment of lesions, including tumors and non-malignant lesions. The methods use antibody fragments or subfragments labeled with isotopic and non-isotopic agents. Also provided are methods for detection and treatment of lesions with photodynamic agents and methods of treating lesions with a protein conjugated to an agent capable of being activated to emit Auger electron or other ionizing radiation. Compositions and kits useful in the above methods are also provided.

Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are commonly used to assess patients with known or suspected pathologies of the lungs and liver. In particular, identification and quantification of possibly malignant regions identified in these high-resolution images is essential for accurate and timely diagnosis. However, careful quantitative assessment of lung and liver lesions is tedious and time consuming. This disclosure describes an automated end-to-end pipeline for accurate lesion detection and segmentation.

A system, and computer implemented method are provided for interactively displaying three-dimensional structures. Three-dimensional volume data (34) is formed from a series of two-dimensional images (33) representing at least one physical property associated with the three-dimensional structure, such as a body organ having a lumen. A wire frame model of a selected region of interest is generated (38b). The wireframe model is then deformed or reshaped to more accurately represent the region of interest (40b). Vertices of the wire frame model may be grouped into regions having a characteristic indicating abnormal structure, such as a lesion. Finally, the deformed wire frame model may be rendered in an interactive three-dimensional display.

A system, and computer implemented method are provided for interactively displaying three-dimensional structures. Three-dimensional volume data (34) is formed from a series of two-dimensional images (33) representing at least one physical property associated with the three-dimensional structure, such as a body organ having a lumen. A wire frame model of a selected region of interest is generated (38b). The wireframe model is then deformed or reshaped to more accurately represent the region of interest (40b). Vertices of the wire frame model may be grouped into regions having a characteristic indicating abnormal structure, such as a lesion. Finally, the deformed wire frame model may be rendered in an interactive three-dimensional display.

Method and system for lesion detection is disclosed. A lesion is detected from each data set in the spatial domain based on an organ intensity subtracted (OIST) image. In the temporal domain, the lesion is detected based on a maximum frequency-magnitude difference (MFMD) map across a plurality of data sets. The detection result from the spatial domain and the detection result from the temporal domain are integrated to produce an integrated lesion detection result.

The present invention is an automated image analysis framework for cervical cancerous lesion detection. The present invention uses domain-specific diagnostic features in a probabilistic manner using conditional random fields. In addition, the present invention discloses a novel window-based performance assessment scheme for two-dimensional image analysis, which addresses the intrinsic problem of image misalignment. As a domain-specific anatomical feature, image regions corresponding to different tissue types are extracted from cervical images taken before and after the application of acetic acid during a clinical exam. The unique optical properties of each tissue type and the diagnostic relationships between neighboring regions are incorporated in the conditional random field model. The output provides information about both the tissue severity and the location of cancerous tissue in an 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.

The invention provides a medical image detection method and device, equipment and a storage medium. The method comprises the steps of obtaining a medical image; inputting the medical image into a segmentation model to obtain a target segmented image; wherein the target segmented image comprises a region of interest; inputting the target segmentation image and the medical image into a detection model to obtain a lesion detection image; wherein the lesion detection image comprises candidate positions of a lesion area, and the lesion area is located in the region of interest; wherein the segmentation model and the detection model are both deep learning models. The robustness of the segmentation model and the detection model provided by the method is high, the accuracy of the segmentation result of the medical image is improved, and the accuracy of the lesion detection result is improved.

A method and system for automatically detecting lesions in a 3D medical image, such as a CT image or an MR image, is disclosed. Body parts are detected in the 3D medical image. Anatomical landmarks, organs, and bone structures are detected in the 3D medical image based on the detected body parts. Search regions are defined in the 3D medical image based on the detected anatomical landmarks, organs, and bone structures. Lesions are detected in each search region using a trained region-specific lesion detector.

The application discloses a lesion detection method and apparatus of an eye fundus image. The method comprises the following steps: carrying out pretreatment on a to-be-detected eye fundus image; carrying out optic disk positioning on the eye fundus image after pretreatment and determining an optic disk region; carrying out morphological processing on the eye fundus image after pretreatment to obtain a healthy background image; and according to the healthy background image and the optic disk region, determining an effusion region in the eye fundus image after pretreatment. Therefore, the detection speed of the eye fundus image can be increased and accuracy of positioning of a lesion region can be improved.

Images with an overall field of view (FOV) may be captured during an endoscopic procedure but only a portion of the overall FOV displayed to an endoscopist. The overall FOV may be analyzed to identify an area of interest of a patient's organ based on the presence of a possible lesion during the endoscopic procedure. The endoscopist may be notified of the identified area of interest. After an area of interest is identified, the location of the area of interest may be tracked. Image stabilization may be provided by changing the displayed portion of the overall FOV to maintain the area of interest within the displayed portion as the area of interest moves relative to the endoscope.

A lesion detection system for use with a patient, comprising an optoacoustic guide wire assembly configured to be insertable into a patient's tissue. The optical acoustic guide wire assembly can be comprised of an optical waveguide have a first end and a second end, a light source coupled to the second end of the optical waveguide, wherein said light source configured to emit energy to the patient's tissue, at least one transducer configured to detect an ultrasound signal emitted from the patient's tissue in response to energy emitted from the light source, and a computer system.

The present invention provides a method for selecting mass density candidates from mammograms for computer-aided lesion detection, review and diagnosis. The method has two steps: a Gaussian difference filter to enhance the intensity and a Canny detector to find potential mass density contours. For circumscribed masses, an additional Hough circle detector is used. This invention makes use of both intensity and morphology information and only processes each image at a single gray-level, so both sensitivity and processing time are improved. The selection algorithm can be also used to select mass candidates from ultrasound images, from 3D tomosynthesis mammography images and from breast MRI images.

An apparatus for detecting a lesion is provided. The apparatus includes an extracting unit configured to extract at least one tissue region from an image of tissue regions, a setting unit configured to set at least one of the at least one extracted tissue region as a lesion detection candidate region, and a detecting unit configured to detect a lesion from the lesion detection candidate region.

The invention discloses a liver CT image multi-lesion classification method based on sample generation and transfer learning. The method mainly solves the problem that an existing method is not high in liver multi-lesion detection performance. The implementation scheme is as follows: dividing a data set; respectively constructing a liver organ segmentation network and a liver lesion detection network; based on the deep convolution generative adversarial network, constructing a liver cyst sample generation network and a liver hemangioma sample generation network, and respectively generating newliver cyst and liver hemangioma samples; constructing a liver lesion classification network; subjecting a liver CT image to be detected firstly to organ segmentation by using a liver organ segmentation network, then subjecting a segmentation result to lesion detection by using a liver lesion detection network, and finally classifying detected lesions by using a liver lesion classification network. According to the invention, imbalance of different types of sample sizes is relieved, the lesion classification performance is improved, and the method can be used for positioning and qualifying various lesions such as liver cancer, liver cyst and hepatic hemangioma existing in the liver CT image.

The embodiment of the invention provides a pneumonia lesion segmentation method and device, and solves the problems of low accuracy and low efficiency of an existing pneumonia lesion segmentation mode. The pneumonia lesion segmentation method comprises the following steps: predicting a lesion area on medical image data of a positive level based on an image semantic segmentation model; counting thelesion area of each parallel layer, and calculating the lesion volume by combining the lesion area of each parallel layer, wherein the image semantic segmentation model is established through the following training steps: inputting all or part of marked sample data into a focus segmentation model to obtain a prediction result output by the focus segmentation model; based on a focus detection frame predicted by a focus detection model and a lung region predicted by a lung lobe lung segment segmentation model, screening out a low-level false positive region from a prediction result to obtain afalse label of sample data, and adding unmarked sample data; and rechecking the pseudo label, and marking the marked sample data to update the marked sample data.

A medical image processing apparatus of the present invention includes: a three-dimensional model estimating section for estimating a three-dimensional model of an object based on a two-dimensional image of an image of the object which is inputted from a medical image pickup apparatus; an image dividing section for dividing the two-dimensional image into a plurality of regions each of which includes at least one or more pixels; a feature value calculation section for calculating a feature value according to a grayscale of each pixel in one region for each of the plurality of regions; and a lesion detection reference setting section for setting lesion detection reference for detecting a locally protruding lesion in the regions of the three-dimensional model which correspond to each of the plurality of regions, based on the feature value according to the grayscale.

An organ lesion detection method includes the following steps: acquiring image data of a first organ, wherein the image data includes a plurality of layers of image data; detecting the image data of the first organ through a trained multistage neuron network to get a first detection result; and determining whether there is lesion in the first organ based on the first detection result.

A method is provided for detecting lesions in ultrasound images. The method includes acquiring an ultrasound image, generating a Fisher-tippett (FT) distribution-based edge feature map from the acquired ultrasound image, generating gradient concentration (GC) scores for pixels of the acquired ultrasound image using the FT distribution-based edge feature map, and identifying a candidate lesion region within the acquired ultrasound image based on the GC scores.

The invention provides a Nd<3+> sensitized core-shell upconversion nanocrystal material, and a preparation method and application thereof in water detection. The developed Nd<3+> sensitized core-shell upconversion nanocrystal material can effectively detect the water content in organic solvent. The upconversion nanocrystal provided by the invention is prepared by taking oleic acid and octadecene as solvent and rare earth chloride as a reactant through a coprecipitation method, and is then subjected to surface treatment by means of HCl. The nanocrystal material has the advantages of high detection convenience, high accuracy, favorable chemical stability and the like. The obtained product is regular in shape, uniform in size and narrow in particle size distribution. The invention combines Nd<3+> sensitization and core-shell structure design to realize the multimode excitation of the upconversion nanocrystal. The Nd<3+> sensitization design favorably overcomes an overheating effect caused by exciting light in a water detection process. Hopefully, the nanocrystal material is widely used in the fields of chemical industry production and biological lesion detection.

The invention provides a method for partitioning breast lesion. The method comprises steps as follows: coarse chest partition is performed on a magnetic resonance image on the basis of an oval model before a contrast medium is injected, and a first image is acquired; silhouette is performed after registration of magnetic resonance images obtained before and after the contrast medium is injected, and a silhouette image of the breast part is extracted from the acquired silhouette images on the basis of the first image; the silhouette image of each layer of breast parts is subjected to lesion detection, and a second image is acquired; and a three-dimensional communication area is found sequentially from the second image, self-adaptive region growing is performed on the silhouette image by taking the gravity center of each communication area as a seed point, and the magnetic resonance images are acquired after suspicious lesions of the breast are partitioned. The provided method for partitioning breast lesions can simply, effectively and automatically partition the suspicious lesions and can be widely applied to magnetic resonance imaging data by injecting various contrast media.

The invention provides a deep learning based automatic coronary artery disease detection method, system and equipment. A deep learning based object detection technique is applied to coronary artery lesion detection through a training step and a testing step; a machine learning based text processing technique is applied to coronary artery lesion detection; by technical fusion of text processing andimage processing, information of multiple modes is fused and applied to coronary artery lesion detection; a coronary artery lesion detection process is automated completely without artificial participation. By adoption of the technical scheme, technical problems of low accuracy in pixel detection and failure in real-time detection of lesions in medical images are solved, and heart coronary arterylesions can be detected out in real time to provide references and assistance for doctors. Compared with other systems, the system has advantages that the lesion detection rate is increased remarkably, and a diagnosis and treatment process is shortened.