Abstract: 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.

Abstract: 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.

Abstract: Anatomy, such as papillary muscle, is automatically detected (34) and/or detected in real-time. For automatic detection (34) of small anatomy, machine-learnt classification with spatial (32) and temporal (e.g., Markov) (34) constraints is used. For real-time detection, sparse machine-learnt detection (34) interleaved with optical flow tracking (38) is used.

Abstract: A method is for automatically generating estimation data for potential injury states of at least one person following an incident involving physical force or violence. In an embodiment, the method includes providing personal data relating to the person; providing incident data relating to the incident involving physical force or violence; and determining the estimation data for likely injury states via a modeling process based on the personal data and the incident data. At least one embodiment of the invention further relates to a respective system and vehicle compatible therewith.

Abstract: Systems and methods for optimizing the decision to perform additional clinical testing are provided. A model of cutoff values, associated with the initial clinical test and representing a tradeoff between a plurality of factors, is generated. Each of the cutoff values define a boundary within a range of results of the initial clinical test delineating results that provide a medical evaluation and results that do not provide the medical evaluation. At least one optimized cutoff value associated with the initial clinical test is determined from the cutoff values by optimizing the model based on the tradeoff between the plurality of factors. It is determined whether to perform the additional clinical test based on a result of the initial clinical test performed on the patient and the at least one optimized cutoff value.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: Anatomy, such as papillary muscle, is automatically detected (34) and/or detected in real-time. For automatic detection (34) of small anatomy, machine-learnt classification with spatial (32) and temporal (e.g., Markov) (34) constraints is used. For real-time detection, sparse machine-learnt detection (34) interleaved with optical flow tracking (38) is used.

Abstract: A mechanical property of anatomy is estimated from a patient in vivo, such as estimating a patient-specific material property of a valve. A morphological model is used to determine anatomy dynamics. A biomechanical model, using the anatomy dynamics, predicts the dynamics, based, at least in part, on one or more material properties. Using an inverse solution based on comparison of dynamics predicted by the biomechanical model and the dynamics determined from the morphological model, values for the material properties are determined.

Abstract: 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.

Abstract: A method and system for physiological image registration and fusion is disclosed. A physiological model of a target anatomical structure in estimated each of a first image and a second image. The physiological model is estimated using database-guided discriminative machine learning-based estimation. A fused image is then generated by registering the first and second images based on correspondences between the physiological model estimated in each of the first and second images.

Abstract: 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.

Abstract: 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.

Abstract: Computed tomography is used during a minimally invasive intervention. A processor detects the inserted device (e.g., catheter) from a CT scan of the patient. The bed and/or gantry of the CT are moved based on the detected location of the inserted device. As the device is moved within the patient, the automatic detection is used to continue to adjust the CT field of view to scan the device. To further assist the intervention, combining scans with different fields of view relative to the patient may generate an extended field of view image.

Abstract: A method and system for generating a patient specific anatomical heart model is disclosed. Volumetric image data, such as computed tomography (CT) or echocardiography image data, of a patient's cardiac region is received. Individual models for multiple heart components, such as the left ventricle (LV) endocardium, LV epicardium, right ventricle (RV), left atrium (LA), right atrium (RA), mitral valve, aortic valve, aorta, and pulmonary trunk, are estimated in said volumetric cardiac image data. A patient specific anatomical heart model is generated by integrating the individual models for each of the heart components.

Abstract: A mechanical property of anatomy is estimated from a patient in vivo, such as estimating a patient-specific material property of a valve. A morphological model is used to determine anatomy dynamics. A biomechanical model, using the anatomy dynamics, predicts the dynamics, based, at least in part, on one or more material properties. Using an inverse solution based on comparison of dynamics predicted by the biomechanical model and the dynamics determined from the morphological model, values for the material properties are determined.

Abstract: A method and system for determining an angulation of a C-arm image acquisition system for a cardiac intervention is disclosed. A 3D ultrasound image including a cardiac region is received. The 3D ultrasound image is registered to a 3D coordinate system of the C-arm image acquisition system. A cardiac structure of interest is detected in the registered 3D ultrasound image. An angulation of the C-arm image acquisition system is determined based on the detected structure of interest in the registered 3D ultrasound image.

Abstract: A method and system for modeling the pulmonary trunk in 4D image data, such as 4D CT and MRI data, is disclosed. Bounding boxes are detected in frames of the 4D image data. Anatomic landmarks are detected in the frames of the 4D image data based on the bounding boxes. Ribs or centerlines of the pulmonary artery are detected in the frames of the 4D image data based on the anatomic landmarks, and a physiological pulmonary trunk model is fit the frames of the 4D image data based on the detected ribs and anatomic landmarks. The boundary of the pulmonary trunk is detected in order to refine the boundary of the pulmonary trunk model in the frames of the 4D image data, resulting in a dynamic model of the pulmonary trunk. The pulmonary trunk can be quantitatively evaluated using the dynamic model.