Siemens Healthcare Gmbh

Siemens Healthineers Ag

Siqi Liu

Sasa Grbic

Dorin Comaniciu

Bogdan Georgescu

Zhoubing Xu

Arnaud Arindra Adiyoso

Guillaume Chabin

Shaohua Kevin Zhou

Daguang Xu

Eli Gibson

Olivier Pauly

Youngjin Yoo

Thomas Re

Brian Teixeira

Florin-Cristian Ghesu

Sebastien Piat

Awais Mansoor

Shikha Chaganti

Thomas Flohr

Boris Mailhe

Thomas Mertelmeier

Lucian Mihai Itu

Gerardo Hermosillo Valadez

Steffen Kappler

Anna Jerebko

Razvan Ionasec

Dominik Neumann

Ludwig Ritschl

Sebastian Vogt

Ruhan Sa

Julia Wicklein

Philipp Seegerer

Anamaria Vizitiu

Alexandru Turcea

Laszlo Lazar

Puyang Wang

Marvin Teichmann

Yiyuan Zhao

Yuemeng Li

Anna Boehm

Jie Yang

Iulian Ionut Stroia

Ziming Qiu

Zhengyang Shen

Valentin Ziebandt

Anna Böhm

A computer-implemented method is for providing quantitative airway information. In an embodiment, the method includes receiving and/or determining first medical image data of an airway segment; applying a first trained function to the first medical image data, to generate output data; determining the at least one quantitative airway information of the airway segment based on the output data; and providing the at least one quantitative airway information.

Method for providing airway information

A computer-implemented method is for classifying a region of interest in a medical image data set depicting a body part of a patient. The region of interest contains an object of potential pathological relevance. In an embodiment, the method includes a plurality of steps. One step is directed to generate a plurality of different representations of the region of interest. Another step is directed to determine, for each of the representations, a classification to generate a corresponding plurality of classifications. Thereby, each classification indicates a pathological relevance of the object in the respective representation. Yet, a further step is directed to calculate an ensemble classification for the region of interest based on the plurality of classifications.

Method and system for computer aided detection of abnormalities in image data

Systems and methods for generating a synthetic image are provided. An input medical image in a first modality is received. A synthetic image in a second modality is generated from the input medical image. The synthetic image is upsampled to increase a resolution of the synthetic image. An output image is generated to simulate image processing of the upsampled synthetic image. The output image is output.

Generating synthetic x-ray images and object annotations from CT scans for augmenting x-ray abnormality assessment systems

Systems and methods for generating a synthesized medical image are provided. An input medical image is received. A synthesized segmentation mask is generated. The input medical image is masked based on the synthesized segmentation mask. The masked input medical image has an unmasked portion and a masked portion. An initial synthesized medical image is generated using a trained machine learning based generator network. The initial synthesized medical image includes a synthesized version of the unmasked portion of the masked input medical image and synthesized patterns in the masked portion of the masked input medical image. The synthesized patterns is fused with the input medical image to generate a final synthesized medical image.

Medical image synthesis of abnormality patterns associated with COVID-19

A computer-implemented method is for classifying a lesion. In an embodiment, the method includes receiving a first medical image of an examination volume, the first medical image corresponding to a first examination time; receiving a second medical image of the examination volume, the second medical image corresponding to a second examination time, different from the first examination time; determining a first lesion area corresponding to a lesion within the first medical image; determining a registration function based on a comparison of the first medical image and the second medical image; determining a second lesion area within the second medical image based on the registration function and the first lesion area; and classifying the lesion within the first medical image based on the second lesion area. A computer-implemented method for providing a trained classification function, a classification system, and computer program products and computer-readable media are also disclosed.

Classifying a lesion based on longitudinal studies

Systems and methods for assessing a disease are provided. An input medical image in a first modality is received. Lungs are segmented from the input medical image using a trained lung segmentation network and abnormality patterns associated with the disease are segmented from the input medical image using a trained abnormality pattern segmentation network. The trained lung segmentation network and the trained abnormality pattern segmentation network are trained based on 1) synthesized images in the first modality generated from training images in a second modality and 2) target segmentation masks for the synthesized images generated from training segmentation masks for the training images. An assessment of the disease is determined based on the segmented lungs and the segmented abnormality patterns.

Assessment of abnormality patterns associated with COVID-19 from x-ray images

Systems and methods for generating synthesized medical images for training a machine learning based network. An input medical image in a first modality is received comprising a nodule region for each of one or more nodules, a remaining region and an annotation for each of the nodules. A synthesized medical image in a second modality is generated from the input medical image comprising the annotation for each of the nodules. A synthesized nodule image of each of the nodule regions and synthesized remaining image of the remaining region are generated in the second modality. It is determined whether a particular nodule is visible in the synthesized medical image based on the synthesized nodule image for the particular nodule and the synthesized remaining image. If at least one nodule is not visible in the synthesized medical image, the annotation for the not visible nodule is removed from the synthesized nodule image.

X-ray image synthesis from CT images for training nodule detection systems

Systems and methods for assessing a disease are provided. Medical imaging data of lungs of a patient is received. The lungs are segmented from the medical imaging data and abnormality regions associated with a disease are segmented from the medical imaging data. An assessment of the disease is determined based on the segmented lungs and the segmented abnormality regions. The disease may be COVID-19 (coronavirus disease 2019) or diseases, such as, e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), or other types of viral and non-viral pneumonia.

Assessment of abnormality regions associated with a disease from chest CT images

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

Systems and methods are provided for generating a synthesized medical image patch of a nodule. An initial medical image patch and a class label associated with a nodule to be synthesized are received. The initial medical image patch has a masked portion and an unmasked portion. A synthesized medical image patch is generated using a trained generative adversarial network. The synthesized medical image patch includes the unmasked portion of the initial medical image patch and a synthesized nodule replacing the masked portion of the initial medical image patch. The synthesized nodule is synthesized according to the class label. The synthesized medical image patch is output.

Class-aware adversarial pulmonary nodule synthesis

Systems and methods for generating synthesized images are provided. An input medical image patch, a segmentation mask, a vector of appearance related parameters, and manipulable properties are received. A synthesized medical image patch including a synthesized nodule is generated based on the input medical image patch, the segmentation mask, the vector of appearance related parameters, and the manipulable properties using a trained object synthesis network. The synthesized nodule is synthesized according to the manipulable properties. The synthesized medical image patch is output.

Manipulable object synthesis in 3D medical images with structured image decomposition

A method, apparatus and non-transitory computer readable medium are for segmenting different types of structures, including cancerous lesions and regular structures like vessels and skin, in a digital breast tomosynthesis (DBT) volume. In an embodiment, the method includes: pre-classification of the DBT volume in dense and fatty tissue and based on the result; localizing a set of structures in the DBT volume by using a multi-stream deep convolutional neural network; and segmenting the localized structures by calculating a probability for belonging to a specific type of structure for each voxel in the DBT volume by using a deep convolutional neural network for providing a three-dimensional probabilistic map.

Semantic segmentation for cancer detection in digital breast tomosynthesis

A computer-implemented method for identifying features in 3D image volumes includes dividing a 3D volume into a plurality of 2D slices and applying a pre-trained 2D multi-channel global convolutional network (MC-GCN) to the plurality of 2D slices until convergence. Following convergence of the 2D MC-GCN, a plurality of parameters are extracted from a first feature encoder network in the 2D MC-GCN. The plurality of parameters are transferred to a second feature encoder network in a 3D Anisotropic Hybrid Network (AH-Net). The 3D AH-Net is applied to the 3D volume to yield a probability map;. Then, using the probability map, one or more of (a) coordinates of the objects with non-maximum suppression or (b) a label map of objects of interest in the 3D volume are generated.

3D anisotropic hybrid network: transferring convolutional features from 2D images to 3D anisotropic volumes

Growing community of inventors

Princeton, NJ, United States of America

Siqi Liu