Siemens Healthineers Ag

Siemens Healthcare Gmbh

Siemens Medical Solutions Usa, Inc.

The Johns Hopkins University

The Cleveland Clinic Foundation

City of Hope National Medical Center

Bin Lou

Ali Kamen

Dorin Comaniciu

David Jean Winkel

Xin Yu

Mamadou Diallo

Bibo Shi

Tongbai Meng

Tommaso Mansi

Berthold Kiefer

Robert Grimm

Heinrich Von Busch

Francisco Pereira

Julian Krebs

Ahmet Tuysuzoglu

Nicolas Von Roden

Jingya Liu

Mariappan S Nadar

Henry R Halperin

Boris Mailhe

Sasa Grbic

Andreas Greiser

Benjamin L Odry

Zhoubing Xu

Lance Anthony Ladic

Mohamed Abazeed

Fernando Vega

Venkata Veerendranadh Chebrolu

Angeliki Lazaridou

Hiroshi Ashikaga

Ammar Chaudhry

Afshin Ezzi

Nilesh Mistry

Katherine Chih-ching Wu

Kareem Abdelrahman

For prediction of response of radiation therapy, radiomics are used for unsupervised machine training of an encoder-decoder network to predict based on input of image data, such as computed tomography image data and from segmentation. The trained encoder is then used to generate latent representations to be used as input to different classifiers or regressors for prediction of therapy responses, such as one classifier to predict response for an organ at risk and another classifier to predict another type of response for the organ at risk or to predict a response for the tumor.

Representation learning for organs at risk and gross tumor volumes for treatment response prediction

Systems and methods for predicting clinical outcomes of a patient are provided. An input medical image of a tumor of a patient is received. The tumor is segmented from the input medical image. One or more assessments of the tumor are performed based on the segmentation. A clinical outcome of the patient is predicted based on results of the one or more assessments of the tumor. The clinical outcome of the patient is output.

Multimodal analysis of imaging and clinical data for personalized therapy

Systems and methods are provided for optimizing a deep learning model. A multi-site dataset associated with different clinical sites and a deployment dataset associated with a deployment clinical site are received. A deep learning model is trained based on the multi-site dataset. The trained deep learning model is optimized based on the deployment dataset. The optimized trained deep learning model is output.

Localization and classification of abnormalities in medical images

For uncertainty estimation for a machine-learned model prediction in medical imaging, a distribution in latent space is sampled to determine uncertainty in machine-learned model prediction. For example, a segmentation is output by a machine-learned model in response to input of multi-parametric data. A latent space generated by the machine-learned model is used to estimate the uncertainty of the segmentation, such as a segmentation of a prostate lesion. The model of Kohl, et al., may be used as the variational auto encoder generates a latent space representing the distribution of the training data, which latent space may be used to determine uncertainty.

Uncertainty estimation in medical imaging

For decision support in a medical therapy, machine learning provides a machine-learned generator for generating a prediction of outcome for therapy personalized to a patient. Deep learning may result in features more predictive of outcome than handcrafted features. More comprehensive learning may be provided by using multi-task learning where one of the tasks (e.g., segmentation, non-image data, and/or feature extraction) is unsupervised and/or draws on a greater number of training samples than available for outcome prediction alone.

Decision support system for medical therapy planning

Systems and methods for determining whether input medical images are out-of-distribution of training images on which a machine learning based medical imaging analysis network is trained are provided. One or more input medical images of a patient are received. One or more reconstructed images of the one or more input medical images are generated using a machine learning based reconstruction network. It is determined whether the one or more input medical images are out-of-distribution from training images on which a machine learning based medical imaging analysis network is trained based on the one or more input medical images and the one or more reconstructed images. The determination of whether the one or more input medical images are out-of-distribution from the training images is output.

Out-of-distribution detection for artificial intelligence systems for prostate cancer detection

In an method for training artificial intelligence entities (AIE) for abnormality detection, medical imaging data of the human organ is provided as training data having training samples, the medical imaging data including imaging results from different types of imaging techniques for each training sample of the training data, a pre-trained or randomly initialized AIE is provided, and the AIE is trained using the provided training samples. The training may include, for at least one training sample, a first loss function for a sub-structure of the AIE is calculated independently of a first spatial region of the human organ, and, for a training sample, a second loss function for a sub-structure of the AIE is calculated independently of a second spatial region of the human organ. The AIE may be trained using the calculated first loss function and the calculated second loss function.

Methods and systems for improved abnormality detection in medical imaging data

For autonomous MR scanning for a given medical test, a simplified MR scanner may be used without or will little input or control by a technologist (e.g., by a physician, radiologist, or person trained in MR scanner operation). The MR scanner autonomously positions, scans, checks quality, analyzes, and/or outputs an answer to a diagnostic question with or without an MR image. Scan analysis, based on artificial intelligence, allows for on-going or on-the-fly alteration of the scanning configuration to acquire the data desired to answer the diagnostic question. By using a simplified MR scanner, both position of the patient relative to the MR scanner and localization of the scan by the MR scanner are jointly solved. Sensors may sense a patient in a scan position where the reduced radio frequency requirements allow for a more open bore.

Autonomous magnetic resonance scanning for a given medical test

Similar pre-stored medical datasets are identified by comparison with a current case dataset. A current case dataset is provided and includes radiological data of a patient. A number of pre-stored medical datasets each including radiological data of other patients are provided. Each case dataset is evaluated according to a predefined AI-based method to obtain a number of definitive features for that case dataset. The definitive features of the current case dataset are compared with the definitive features of each pre-stored medical dataset to identify a number of pre-stored medical datasets most similar to the current case dataset. The identified number of most similar pre-stored medical datasets are output.

Method and arrangement for identifying similar pre-stored medical datasets

Risks of radiation-induced toxicity associated with a radiotherapy treatment of a target region of a patient are predicted. Data associated with a region of interest comprising the target region is received. The received data includes a predefined dose map of the radiotherapy treatment and pre-radiotherapy-treatment imaging data of the region of interest. A trained machine-learning algorithm is applied to the received data. The trained machine-learning algorithm generates at least one toxicity indicator based on the received data. The at least one toxicity indicator is indicative of the risks of the radiation-induced toxicity.

Radiation-induced toxicity and machine learning

Brain tumor or other tissue classification and/or segmentation is provided based on from multi-parametric MRI. MRI spectroscopy, such as in combination with structural and/or diffusion MRI measurements, are used to classify. A machine-learned model or classifier distinguishes between the types of tissue in response to input of the multi-parametric MRI. To deal with limited training data for tumors, a patch-based system may be used. To better assist physicians in interpreting results, a confidence map may be generated using the machine-learned classifier.

Tumor tissue characterization using multi-parametric magnetic resonance imaging

Systems and methods for predicting a patient specific risk of cardiac events for cardiac arrhythmia are provided. A medical image sequence of a heart of a patient is received. Cardiac function features are extracted from the medical image sequence. Additional features are extracted from patient data of the patient. A patient specific risk of a cardiac event is predicted based on the extracted cardiac function features and the extracted additional features.

Patient specific risk prediction of cardiac events from image-derived cardiac function features

Systems and methods are provided for classifying an abnormality in a medical image. An input medical image depicting a lesion is received. The lesion is localized in the input medical image using a trained localization network to generate a localization map. The lesion is classified based on the input medical image and the localization map using a trained classification network. The classification of the lesion is output. The trained localization network and the trained classification network are jointly trained.

Growing community of inventors

Princeton, NJ, United States of America

Bin Lou