Siemens Healthcare Gmbh

Siemens Healthcare Diagnostics Gmbh

Other

Nec Corporation

Siemens Mobility Gmbh

Siemens Healthineers Ag

Kai Ma

Terrence Chen

Vivek Kumar Singh

Yao-Jen Chang

Birgi Tamersoy

Stefan Kluckner

Andreas Wimmer

Andreas Krauss

Benjamin S Pollack

Shanhui Sun

Michael Wels

Jiangping Wang

Ziyan Wu

Grzegorz Soza

Ralf Nanke

Brian Teixeira

Dorin Comaniciu

Bogdan Georgescu

Shaohua Kevin Zhou

Hui Joyce Zhang

Guofei Jiang

Ali Kamen

Daphne Yu

Junghwan Rhee

Thomas J O'Donnell

Nipun Arora

Jan Ernst

Mingqing Chen

Klaus J Kirchberg

Ruhan Sa

Susanne Dornberger

John Paulus, Jr

Susanne Oepping

Oliver Lehmann

Subhabrata Bhattacharya

Yifan Wu

Jianping Wang

Andreas Krauß

Lequan Yu

Venkatesh N Murthy

Tobias Betz

Liheng Zhang

Zhuokai Zhao

A method of characterizing a serum or plasma portion of a specimen in a specimen container provides a fine-grained HILN index (hemolysis, icterus, lipemia, normal) of the serum or plasma portion of the specimen, wherein the H, I, and L classes may each have five to seven sub-classes. The HILN index may also have one un-centrifuged class. Pixel data of an input image of the specimen container may be processed by a deep semantic segmentation network having, in some embodiments, more than 100 layers. A small front-end container segmentation network may be used to determine a container type and boundary, which may additionally be input to the deep semantic segmentation network. A discriminative network may be used to train the deep semantic segmentation network to generate a homogeneously structured output. Quality check modules and testing apparatus configured to carry out the method are also described, as are other aspects.

Methods and apparatus for fine-grained HIL index determination with advanced semantic segmentation and adversarial training

A method of characterizing a serum or plasma portion of a specimen in a specimen container includes capturing a plurality of images of the specimen container from multiple viewpoints, stacking the multiple viewpoint images along a channel dimension into a single stacked input, and processing the stacked input with a single deep convolutional neural network (SDNN). The SDNN includes a segmentation convolutional neural network that receives the stacked input and outputs multiple label maps simultaneously. The SDNN also includes a classification convolutional neural network that processes the multiple label maps and outputs an HILN determination (Hemolysis, Icterus, and/or Lipemia, or Normal) of the serum or plasma portion of the specimen. Quality check modules and testing apparatus configured to carry out the method are also described, as are other aspects.

Specimen container characterization using a single deep neural network in an end-to-end training fashion

A neural network-based method for quantifying a volume of a specimen. The method includes providing a specimen, capturing images of the specimen, and directly classifying to one of a plurality of volume classes or volumes using a trained neural network. Quality check modules and specimen testing apparatus adapted to carry out the volume quantification method are described, as are other aspects.

Deep learning volume quantifying methods and apparatus

For training for and performance of patient modeling from surface data in a medical system, a progressive multi-task model is used. Different tasks for scanning are provided, such as landmark estimation and patient pose estimation. One or more features learned for one task are used as fixed or constant features in the other task. This progressive approach based on shared features increases efficiency while avoiding reductions in accuracy for any given task.

Multi-task progressive networks for patient modeling for medical scans

A method for controlling a scanner comprises: sensing an outer surface of a body of a subject to collect body surface data, using machine learning to predict a surface of an internal organ of the subject based on the body surface data, and controlling the scanner based on the predicted surface of the internal organ.

Method for controlling scanner by estimating patient internal anatomical structures from surface data using body-surface and organ-surface latent variables

A method of training a neural network (Convolutional Neural Network-CNN) including reduced graphical annotation input is provided. The training method can be used to train a Testing CNN that can be used for determining Hemolysis (H), Icterus (I), and/or Lipemia (L), or Normal (N) of a serum or plasma portion of a test specimen. The training method includes capturing training images of multiple specimen containers including training specimens, generating region proposals of the serum or plasma portions of the training specimens; and selecting the best matches for the location, size and shape of the region proposals for the multiple training specimens. The obtained features (network and weights) from the training CNN can be used in a testing CNN. Quality check modules and testing apparatus adapted to carry out the training method, and characterization methods using abounding box regressor are described, as are other aspects.

Methods and apparatus for bio-fluid specimen characterization using neural network having reduced training

For topogram predication from surface data, a sensor captures the outside surface of a patient. A generative adversarial network (GAN) generates the topogram representing an interior organ based on the outside surface of the patient. To further adapt to specific patients, internal landmarks are used in the topogram prediction. The topogram generated by one generator of the GAN may be altered based on landmarks generated by another generator.

Topogram prediction from surface data in medical imaging

A correspondence between frames of a set of medical image data is determined where the set of medical image data includes at least one frame acquired without contrast medium and at least one frame acquired with contrast medium. First data representing a first image frame acquired without contrast medium is received. Second data representing a second image frame acquired with contrast medium is received. A position of a feature of a medical device in the second image frame is determined at least partly on the basis of a position of the feature determined from the first image frame.

Method of determining a correspondence between frames of medical image data with and without contrast medium through probability distribution maps relating to position of a feature

A method for identifying a feature in a first image comprises establishing an initial database of image triplets, and in a pose estimation processor, training a deep learning neural network using the initial database of image triplets, calculating a pose for the first image using the deep learning neural network, comparing the calculated pose to a validation database populated with images data to identify an error case in the deep learning neural network, creating a new set of training data including a plurality of error cases identified in a plurality of input images and retraining the deep learning neural network using the new set of training data. The deep learning neural network may be iteratively retrained with a series of new training data sets. Statistical analysis is performed on a plurality of error cases to select a subset of the error cases included in the new set of training data.

Method and system for efficiently mining dataset essentials with bootstrapping strategy in 6DOF pose estimate of 3D objects

A method of obtaining a medical image includes obtaining, via a camera, at least one surface image of a patient. A pose of the patient is determined from the at least one surface image of the patient using at least one spatial information module. The patient is positioned, via a moveable bed, to an imaging start position and a medical image of the patient is obtained using a medical imaging modality.

System and method for assisted patient positioning

A method for training a learning-based medical scanner including (a) obtaining training data from demonstrations of scanning sequences, and (b) learning the medical scanner's control policies using deep reinforcement learning framework based on the training data.

Method and system for learning to obtain medical scans of patients

Machine learning is used to train a network to predict the location of an internal body marker from surface data. A depth image or other image of the surface of the patient is used to determine the locations of anatomical landmarks. The training may use a loss function that includes a term to limit failure to predict a landmark and/or off-centering of the landmark. The landmarks may then be used to configure medical scanning and/or for diagnosis.

Internal body marker prediction from surface data in medical imaging

A system and method includes acquisition of a plurality of sets of body surface data, first data indicating locations of a first one or more body landmarks for each of the plurality of sets of body surface data, and second data indicating locations of a second one or more body landmarks for each of the plurality of sets of body surface data, training, using the plurality of sets of body surface data and data indicating locations of the first one or more body landmarks for each of the plurality of sets of body surface data, of a first reinforcement learning network to identify the first one or more body landmarks based on body surface data, and training, using the plurality of sets of body surface data and data indicating locations of the second one or more body landmarks for each of the plurality of sets of body surface data, of a second reinforcement learning network to identify the second one or more body landmarks based on body surface data.

Body landmark detection based on depth images

A system includes: a movable X-ray tube scanner; a range sensor movable with the X-ray tube scanner; an X-ray detector positioned to detect X-rays from the X-ray tube passing through a standing subject between the X-ray tube and the X-ray detector; and a processor configured for automatically controlling the X-ray tube scanner to transmit X-rays to a region of interest of the patient while the subject is standing between the X-ray tube and the X-ray detector.

X-ray system and method for standing subject

A method and system for classification of endoscopic images is disclosed. An initial trained deep network classifier is used to classify endoscopic images and determine confidence scores for the endoscopic images. The confidence score for each endoscopic image classified by the initial trained deep network classifier is compared to a learned confidence threshold. For endoscopic images with confidence scores higher than the learned threshold value, the classification result from the initial trained deep network classifier is output. Endoscopic images with confidence scores lower than the learned confidence threshold are classified using a first specialized network classifier built on a feature space of the initial trained deep network classifier.

Method and system for classification of endoscopic images using deep decision networks

Growing community of inventors

Princeton, NJ, United States of America

Kai Ma