Ge Precision Healthcare LLC

Lehel Ferenczi

Gopal Biligeri Avinash

Tao Tan

Pál Tegzes

Gireesha Chinthamani Rao

László Ruskó

Levente Imre Török

Rakesh Mullick

Krishna Seetharam Shriram

Vikram Reddy Melapudi

Ravi Soni

Soumya Ghose

Bipul Das

Zoltan Kiss

Alec Joseph Baenen

Zita Herczeg

Khaled Salem Younis

Máté Fejes

Beth Ann Heckel

Hongxu Yang

Balazs Peter Cziria

Florian Wiesinger

Katelyn Rose Nye

Min Zhang

German Guillermo Vera Gonzalez

Buer Qi

Balázs Péter Cziria

Poonam Dalal

Richárd Zsámboki

Hongxiang Yi

Attila Márk Rádics

Fei Mian

Bernadett Kolozsvári

Vanda Czipczer

Pulak Goswami

Dennis Wei Zhou

Dejun Wang

Gireesha Chintharnani Rao

Methods and systems are provided for inferring thickness and volume of one or more object classes of interest in two-dimensional (2D) medical images, using deep neural networks. In an exemplary embodiment, a thickness of an object class of interest may be inferred by acquiring a 2D medical image, extracting features from the 2D medical image, mapping the features to a segmentation mask for an object class of interest using a first convolutional neural network (CNN), mapping the features to a thickness mask for the object class of interest using a second CNN, wherein the thickness mask indicates a thickness of the object class of interest at each pixel of a plurality of pixels of the 2D medical image; and determining a volume of the object class of interest based on the thickness mask and the segmentation mask.

System and methods for inferring thickness of object classes of interest in two-dimensional medical images using deep neural networks

An image processing system is provided. The image processing system includes a display, a processor, and a memory. The memory stores processor-executable code that when executed by the processor causes receiving images of a region of interest of a patient with an enteric tube or line disposed within the region of interest, detecting the medical tube or line within the image, generating a combined image by combining the received images, and superimposing graphical markers on the combined image that indicate placement or misplacement of the enteric tube or line, and displaying the combined image on a display. In further aspects, a classification of the enteric tube or line (e.g., correctly placed tube present, malpositioned tube present, and so forth) and a detected positional change in the placement of the enteric tube or line may be determined and communicated to one or more clinicians. Additionally, the outputs of the image processing system may also be provided to facilitate triage of patients, helping prioritize which tube placements require further attention and in what order.

System and method for visualizing placement of a medical tube or line

Methods and systems are provided for segmenting structures in medical images. In one embodiment, a method includes receiving an input dataset including a set of medical images, a structure list specifying a set of structures to be segmented, and a segmentation protocol, performing an input check on the input dataset, determining whether each medical image of the set of medical images has passed the input check and removing any medical images from the set of medical images that do not pass the input check to form a final set of medical images, segmenting each structure from the structure list using one or more segmentation models and the final set of medical images, receiving a set of segmentations output from the one or more segmentation models, processing the set of segmentations to generate a final set of segmentations, and displaying and/or saving in memory the final set of segmentations.

Systems and methods for segmenting objects in medical images

An image processing system is provided. The image processing system includes a display, a processor, and a memory. The memory stores processor-executable code that when executed by the processor causes receiving an image of a region of interest of a patient with an enteric tube or line disposed within the region of interest, detecting the medical tube or line within the image, generating a combined image by superimposing graphical markers on the image that indicate placement or misplacement of the enteric tube or line, and displaying the combined image on a display. In further aspects, a classification of the enteric tube or line (e.g., correctly placed tube present, malpositioned tube present, and so forth) may be determined and communicated to one or more clinicians. Additionally, the outputs of the image processing system may also be provided to facilitate triage of patients, helping prioritize which tube placements require further attention and in what order.

Techniques are described for optimizing deep learning model performance using image harmonization as a pre-processing step. According to an embodiment, a method comprises decomposing, by a system operatively coupled to a processor, an input image into sub-images. The method further comprises harmonizing the sub-images with corresponding reference sub-images of at least one reference image based on two or more different statistical values respectively calculated for the sub-images and the corresponding reference-sub images, resulting in transformation of the sub-images into modified sub-images images. In some implementations, the modified sub-images can be combined into a harmonized image having a more similar appearance to the at least one reference image relative to the input image. In other implementations, harmonized images and/or modified sub-images generated using these techniques can be used as ground-truth training samples for training one or more deep learning model to transform input images with appearance variations into harmonized images.

Image harmonization for deep learning model optimization

Systems/techniques that facilitate AI-based region-of-interest masks for improved data reconstructions are provided. In various embodiments, a system can access a set of two-dimensional medical scan projections. In various aspects, the system can generate a set of two-dimensional region-of-interest masks respectively corresponding to the set of two-dimensional medical scan projections. In various instances, the system can generate a region-of-interest visualization based on the set of two-dimensional region-of-interest masks and the set of two-dimensional medical scan projections. In various cases, the system can generate the set of two-dimensional region-of-interest masks by executing a machine learning segmentation model on the set of two-dimensional medical scan projections.

AI-based region-of-interest masks for improved data reconstruction

System and methods for inferring thickness of anatomical classes of interest in two-dimensional medical images using deep neural networks

Systems and techniques that facilitate freeze-out as a regularizer in training neural networks are presented. A system can include a memory and a processor that executes computer executable components. The computer executable components can include: an assessment component that identifies units of a neural network, a selection component that selects a subset of units of the neural network, and a freeze-out component that freezes the selected subset of units of the neural network so that weights of output connections from the frozen subset of units will not be updated for a training run.

Freeze-out as a regularizer in training neural networks

Growing community of inventors

Dunakeszi, Hungary

Lehel Ferenczi