Siemens Healthcare Gmbh

Siemens Aktiengesellschaft

Siemens Medical Solutions Usa, Inc.

Yale University

Razvan Ionasec

Dorin Comaniciu

Sasa Grbic

Matthias John

Philipp Hoelzer

Bogdan Georgescu

Jan Boese

Tommaso Mansi

Ingmar Voigt

Helene C Houle

Peter Mountney

Michael Suehling

Puneet Sharma

Ali Kamen

Yefeng Zheng

Bjoern Heismann

Noha Youssry El-Zehiry

Dominik Neumann

Chris Schwemmer

Max Schoebinger

Siqi Liu

Julian Krebs

Charles Henri Florin

Dime Vitanovski

Alois Noettling

Jonathan Sperl

Guillaume Chabin

Max Schöbinger

Michael W Lynch

James S Duncan

Philipp Hölzer

Mihai Scutaru

Jingjing Kanik

Christian Gesell

Peng Hao

Rainer Kärgel

Andre Hartung

Anand Vinod Tatpati

Joel Mancina

Murrill Michael Szucs

A method is for adapting method steps for finding a result in a CT-based decision support method to the evaluation of LDCT image datasets. In an embodiment of the method, a plurality of reference image datasets are acquired from a plurality of patients. A reference image dataset features at least one CT image dataset from one of the plurality of patients and an LDCT dataset from the patient. Furthermore, method steps for establishing result data are applied to the different image datasets of the reference image datasets. The result data is compared with one another and the method steps for establishing result data are adapted based upon a result of the comparison to the establishing of result data with reference to an LDCT image dataset. An LDCT-based decision support method is also described. Moreover an adaptation device is described. A system for LDCT-based decision support is further described.

Flexible use of a clinical decision support system

A method is for determining a processing sequence for processing an image, the processing sequence including a plurality of algorithms, each respective algorithm of the plurality of algorithms being configured to perform an image processing process on the image to generate a respective output. In an embodiment, the method includes determining one or more required outputs from the processing sequence; and determining, using a data processing system, the processing sequence based on the one or more required outputs determined, the data processing system being configured based on sequences previously determined.

Determining a processing sequence for processing an image

A method for setting a medical imaging protocol includes providing an information data set assigned to a patient. The information data set includes an information about a provisional diagnostic finding regarding the patient. In an embodiment, the method further includes assigning a probability value for a positive finding of the provisional diagnostic finding to the information data set; and automatically setting the medical imaging protocol. The medical imaging protocol is adapted to the provisional diagnostic finding such that an analysis of a result of the medical imaging protocol changes the probability value.

Method for setting a medical imaging protocol, system for setting a medical instrument, computer program and computer-readable medium

Systems and method are described for determining a malignancy of a nodule. A medical image of a nodule of a patient is received. A patch surrounding the nodule is identified in the medical image. A malignancy of the nodule in the patch is predicted using a trained deep image-to-image network.

Determining malignancy of pulmonary nodules using deep learning

A method is for the automated evaluation of at least one image data record of a patient recorded with a medical image recording device for the preparation of diagnostic findings. In the method, at least one item of input data describing the patient and/or the recording process and/or the examination target is determined after completion of the recording of the image data record. A selection algorithm which evaluates the image data record and the input data is used for determining at least one automated evaluation process to be applied and applicable and at least one image quality measure with regard to the evaluation process is determined by evaluating the image data record. The selected automated evaluation process is only performed for an image quality measure meeting a threshold quality requirement.

Method and device for the automated evaluation of at least one image data record recorded with a medical image recording device, computer program and electronically readable data carrier

For processing a medical image, medical image data representing a medical image of at least a portion of a vertebral column is received. The medical image data is processed to determine a plurality of positions within the image. Each of the plurality of positions corresponds to a position relating to a vertebral bone within the vertebral column. Data representing the plurality of positions is processed to determine a degree of deformity of at least one vertebral bone within the vertebral column.

Determination of a degree of deformity of at least one vertebral bone

A method for controlling an evaluation system for medical images of a patient is proposed. Medical images of the patient acquired at different time points are stored in an image database. Upon reception of a user command associated with a time-dependent evaluation command including at least one evaluation parameter describing an evaluation to be performed and identification information describing the patient, medical images of the patient fulfilling a relevancy criterion depending on the evaluation parameter and acquired at different time points are retrieved from the image database. The retrieved images are registered to each other in at least one registration process. Finally, a composite evaluation image data set including a time series of evaluation images is derived from the registered retrieved images and output to the user.

Method for controlling an evaluation device for medical images of patient, evaluation device, computer program and electronically readable storage medium

A method is for evaluating medical examination results of a patient. The method includes providing a medical ontology including multiple medical concepts occurring in image data sets and examination reports of patients; analysing the at least one image data set using at least one first analysis algorithm, the at least one first analysis algorithm being an artificial intelligence algorithm, for detection of medical concepts of the medical ontology, and marking the medical concepts detected in a result data structure referring to the medical ontology; analysing the at least one examination report using at least one second analysis algorithm, the at least one second analysis algorithm being a natural language processing algorithm, for detection of other medical concepts of the medical ontology, and marking the other medical concepts detected in the result data structure; and providing the result data structure to at least one evaluation application processing medical concepts.

Method and system for evaluating medical examination results of a patient, computer program and electronically readable storage medium

A computer-based diagnostic system includes an image generation unit adapted to generate tomographic images of a patient's organ; a deep machine learning unit configured to process generated tomographic images of the patient's organ to classify organ regions of diseased functional tissue of the patient's organ as belonging to one of a set of abnormal image patterns using trained deep neural networks; and a clinical decision support unit adapted to process classification results of the deep machine learning unit to calculate a diagnostic result output via an interface of the clinical decision support unit.

Computer-based diagnostic system

In personalized object creation, for implants, medical imaging is used to derive a model personalized to a patient. The model may be of a dynamic structure, such as part of the cardiovascular system, and is used to print the implant itself. The model may be used to print a mold to create the implant, a scaffold on which to grow tissue, and/or tissue itself. In another or additional approach, the medical imaging information is used to determine tissue properties. Differences in a material property of the anatomy is mapped to different materials used by a multi-material 3D printer, resulting in a printed object reflecting the size, shape, and/or other material property of the anatomy of the patient.

Personalized creation from medical imaging

A method includes provisioning a set of training data sets, each of the training data sets respectively including an acquisition data set; generating a first medical image for each of the training data sets of at least one first subset of the set of training data sets using the image reconstruction algorithm based on a respective acquisition data set; determining an image processing result for each of the respective first medical images using an image processing algorithm based on the respective first medical image; determining image processing information for each of the respective first medical images relating to a quality of the respective image processing result based on the respective image processing result; and optimizing the image reconstruction algorithm based on a first machine learning algorithm, the at least one first subset of the set of training data sets and the image processing information for the respective first medical images.

Method and data processing unit for optimizing an image reconstruction algorithm

A medical imaging system includes a medical imaging device for generating image data. The medical imaging device includes a first programming interface for transferring the image data and a second programming interface for transferring the supplementary data. The medical imaging system further includes a processing device for retrieving the image data and the associated supplementary data from the medical imaging device and for carrying out a further processing based upon the image data and the supplementary data.

Medical imaging system

At least one first 3D image dataset of an examination region of interest of a patient and a second 3D image dataset of the examination region of interest are received via at least one first interface. A geometric model of the examination region of interest is determined based at least on the first 3D image dataset, and a first spatial distribution of a first material property of the examination region of interest is determined based at least on the second 3D image dataset. A digital manufacturing model of an object is generated based on the geometric model and on the first spatial distribution, the manufacturing model having a material composition of the object that is dependent on the first distribution. The manufacturing model therefore takes into account the geometry and the first material property of the examination region of interest.

Method and computing unit for generating a manufacturing model

Anatomy, such as papillary muscle, is automatically detected () and/or detected in real-time. For automatic detection () of small anatomy, machine-learnt classification with spatial () and temporal (e.g., Markov) () constraints is used. For real-time detection, sparse machine-learnt detection () interleaved with optical flow tracking () is used.

Landmark detection with spatial and temporal constraints in medical imaging

A method and system for transcatheter aortic valve implantation (TAVI) planning is disclosed. An anatomical surface model of the aortic valve is estimated from medical image data of a patient. Calcified lesions within the aortic valve are segmented in the medical image data. A combined volumetric model of the aortic valve and calcified lesions is generated. A 3D printed model of the heart valve and calcified lesions is created using a 3D printer. Different implant device types and sizes can be placed into the 3D printed model of the aortic valve and calcified lesions to select an implant device type and size for the patient for a TAVI procedure. The method can be similarly applied to other heart valves for any type of heart valve intervention planning.

Growing community of inventors

Nuremberg, Germany

Razvan Ionasec