International Business Machines Corporation

Merative US L.p.

Other

Guerbet

Amin Katouzian

Arkadiusz Sitek

Benedikt Werner Graf

Yiting Xie

Anup Pillai

Tanveer Fathima Syeda-Mahmood

Ehsan Dehghan Marvast

Ashutosh Jadhav

Chaitanya Shivade

Vandana Mukherjee

Marina Bendersky

Marwan Sati

Giovanni John Jacques Palma

Mark D Bronkalla

Lilla Boroczky

Sun Young Park

Ahmed El Harouni

Paul Dufort

Omid Bonakdar Sakhi

Maria Victoria Sainz De Cea

Pedro Luis Esquinas Fernandez

Yusuke Takeuchi

Frederic Commandeur

David Richmond

Kourosh Jafari-Khouzani

Vicky Guo

Arun Krishnan

Wen Wei

Aly Mohamed

Mechanisms are provided for detecting lesions in diffusion weighted imaging (DWI) images. The mechanisms receive a first set of DWI images corresponding to a anatomical structure, from medical imaging computer system(s). The first set of DWI images comprises a plurality of DWI images having at least two different b-values. The mechanisms generate a second set of DWI images from the first set of DWI images based on at least one predetermined criterion. The second set of DWI images comprises different DWI images having different b-values. The mechanisms extract feature data from the second set of DWI images, input the feature data into at least one computer neural network, and generate an output from the neural network(s) comprising at least one of a lesion classification or a lesion mask based on results of processing, by the neural network(s), of the feature data extracted from the second set of DWI images.

Lesion detection and segmentation

Methods and systems of estimating b-values. One system including an electronic processor configured to receive a set of medical images associated with a patient, where the set of medical images are diffusion-weighted images. The electronic processor is also configured to extract a set of patches from each medical image included in the set of medical images. The electronic processor is also configured to determine, via an estimation model trained using machine learning, a set of estimated b-values, where each estimated b-value is associated with a patch included in the set of patches. The electronic processor is also configured to determine a b-value for each of the medical images included in the set of medical images, where the b-value is based on the set of estimated b-values.

Estimation of b-value in prostate magnetic resonance diffusion weighted images

A mechanism is provided in a data processing system for automatic determination of b-value difference from diffusion-weighted (DW) images. The mechanism receives a series of images wherein a first image has a first b-value and a second image has an unknown b-value. The mechanism applies a generative adversarial network (GAN) model to estimate a difference between b-values in the series of images. The mechanism determines a b-value for the second image based on the first b-value and the estimated difference between b-values.

Automatic determination of b-values from diffusion-weighted magnetic resonance images

Methods and systems for clinical report generation. One system includes an electronic processor configured to receive a query image and determine a similarity metric for a plurality of medical images, where the similarity metric represents a similarity between the query image and each of the plurality of medical images. The electronic processor is also configured to determine a predetermined number of medical images from the plurality of medical images based on the similarity metric for each of the plurality of medical images. The electronic processor is also configured to rank a plurality of reports, where each of the plurality of reports correspond to one of the predetermined number of medical images. The electronic processor is also configured to generate a clinical report including information extracted from at least one of the plurality of reports based on the ranking of the plurality of reports.

Automatic clinical report generation

A system, method, and computer program product for treatment planning are disclosed. The system includes at least one processing component, at least one memory component, a training module, a retrieval module, and a plan generator. The training module generates hash codes by hashing features from data sources with data source-specific hash functions, and generates superclass hash codes by hashing the generated hash codes with at least one superclass hash function. The retrieval module extracts features from case data, and locates features from the data sources that are similar to the extracted features. The plan generator calculates outcome probabilities for the case data based on known outcomes associated with the located features.

Treatment planning based on multimodal case similarity

Provided is a method, computer program product, and system for hashing electronic health records. A processor may collect a set of electronic health records (EHRs). The processor may perform an encounter analysis on the set of EHRs to determine a set of attributes associated to the set of EHRs. The processor may hash the set of attributes to generate one or more hashing indexes that correspond to the set of EHRs. The processor may store the one or more hashing indexes in a list used for document retrieval.

Hashing electronic records

A computer implemented method, a data processing system and a computer program product to determine a likelihood of pneumothorax of a patient, the method including assessing a digital image of a chest x-ray of the patient, applying a standard detection pipeline to the digital image, applying a confounding factor detector to the digital image, and applying a high-resolution detection pipeline to the digital image.

Pneumothorax detection

Mechanisms are provided to implement an automated medical image processing pipeline selection (MIPPS) system. The MIPPS system receives medical image data associated with a patient electronic medical record and analyzes the medical image data to extract evidence data comprising characteristics of one or more medical images in the medical image data indicative of a medical image processing pipeline to select for processing the one or more medical images. The evidence data is provided to a machine learning model of the MIPPS system which selects a medical image processing pipeline based on a machine learning based analysis of the evidence data. The selected medical image processing pipeline processes the medical image data to generate a results output.

Determining appropriate medical image processing pipeline based on machine learning

A method, system, and computer program product provide disease simulation in synthetic projection imagery. The method obtains first medical imaging data of a first imaging type as source imaging data. A second imaging type to be generated from the source imaging data is identified. The method identifies a parameter set for the second imaging type. Second medical imaging data is modeled from the first medical imaging data based on the parameter set. A set of synthetic images is generated from the first medical imaging data based on the modeled second medical imaging data.

Disease simulation in medical images

Techniques for fracture detection are provided. A first image is received to be processed to identify rib fractures. A first set of regions of interest (ROIs) is identified by processing the first image using a first machine learning model, where each ROI in the first set of ROIs corresponds to a first potential fracture. Further, a first ROI of the first set of ROIs is upsampled, and the system attempts to verify the first potential fracture in the first ROI by processing the upsampled first ROI using a second machine learning model.

Automated fracture detection using machine learning models

A computer-implemented method for classifying and presenting a contrast phase (CP) of a contrast enhanced computerized tomography (CECT) scan is provided. The method includes training an artificial intelligence (AI) algorithm utilizing a set of CPs labeled CECT data to associate a set of characteristics of the data with a probability associated with the CP. The method includes receiving a new set of unlabeled CECT data, and applying the AI algorithm to the new unlabeled CECT data to associate a first probability of a first CP and a second probability of a second CP. The method also includes providing a graphical representation including the first probability of the first CP and the second probability of the second CP.

Method of determining contrast phase of a computerized tomography image

Growing community of inventors

Lexington, MA, United States of America

Amin Katouzian