Canon Medical Systems Corporation

Toshiba Medical Systems Corporation

Masakazu Matsuura

Zhou Yu

Jian Zhou

Liang Cai

Katsuhito Morino

Hiroki Taguchi

Takahiro Yoda

Tomoyasu Komori

Tzu-Cheng Lee

Yasunobu Yamada

Hisashi Yasuda

Takuya Nemoto

Go Mukumoto

Yujie Lu

Katsuhiko Ishida

Atsushi Fukano

Ting Xia

A medical data processing method according to an embodiment includes inputting first medical data relating to a subject imaged with a medical image capture apparatus to a learned model to configured to generate second medical data having lower noise than that of the first medical data and having a super resolution compared with the first medical data based on the first medical data to output the second medical data.

Medical data processing method, model generation method, medical data processing apparatus, and computer-readable non-transitory storage medium storing medical data processing program

A medical image processing method includes obtaining a first set of projection data by performing, with a first CT apparatus including a first detector with a first pixel size, a first CT scan of an object in a first imaging region of the first detector; obtaining a first CT image with a first resolution by reconstructing the first set of projection data; obtaining a processed CT image with a resolution higher than the first resolution by applying a machine-learning model for resolution enhancement to the first CT image; and displaying the processed CT image or outputting the processed CT image for analysis. The machine-learning model is obtained by training using a second CT image based on a second set of projection data acquired by a second CT scan of the object in a second imaging region with a second CT apparatus including a second detector with a second pixel size.

Medical image processing method, medical image processing apparatus, and computer readable non-volatile storage medium storing medical image processing program

An information processing method of an embodiment is a processing method of information acquired by imaging performed by a medical image diagnostic apparatus, the information processing method includes the steps of: acquiring noise data by imaging a phantom using a medical imaging apparatus; based on first subject projection data acquired by the imaging performed by a medical image diagnostic modality of a same kind as the medical image diagnostic apparatus and the noise data, acquiring synthesized subject data in which noise based on the noise data is added to the first subject projection data; and acquiring a noise reduction processing model by machine learning using the synthesized subject data and second subject projection data acquired by the imaging performed by the medical image diagnostic modality.

Information processing method, medical image diagnostic apparatus, and information processing system

An information processing method of an embodiment is a processing method of information acquired by imaging performed by a medical image diagnostic apparatus, the information processing method includes the steps of: on the basis of first subject data acquired by the imaging performed by the medical image diagnostic apparatus, acquiring noise data in the first subject data; on the basis of second subject data acquired by the imaging performed by a medical image diagnostic modality same kind as the medical image diagnostic apparatus and the noise data, acquiring synthesized subject data in which noises based on the noise data are added to the second subject data; and acquiring a noise reduction processing model by machine learning using the synthesized subject data and third subject data acquired by the imaging performed by the medical image diagnostic modality.

A method and apparatus is provided to perform medical imaging in which feature-aware reconstruction is performed using a neural network. The neural network is trained to perform feature-aware reconstruction by using a training dataset in which the target data has a spatially-dependent degree of denoising and artifact reduction based on the features represented in the image. For example, a target image can be generated by reconstructing multiple images, each using a respective regularization parameter that is optimized for a different anatomy/organ (e.g., abdomen, lung, bone, etc.). And a target image can be generated using artifact reduction method (e.g. metal artifact reduction, aliasing artifact reduction, etc.). Then respective regions/features (e.g., abdomen, lung, and bone, artifact free, regions/features) can be extracted from the corresponding images and combined into a single combined image, which is used as the target data to train the neural network.

Apparatus and method for image reconstruction using feature-aware deep learning

Techniques are provided that enable displaying of medical images that depict cyclic motions in the subject. An X-ray CT system scans, with X-rays, the subject whose targeted region is experiencing a cyclic motion and acquires detection data. This X-ray CT system comprises a reconstruction processor, a moving image creator, and a display controller. The reconstruction processor generates a plurality of sets of volumetric data based on a plurality of sets of detection data that have been acquired during one cycle of the cyclic motion. The moving-image creator creates a moving image that shows the cyclic motion, on the basis of at least a part of the plural sets of volumetric data. The display controller superposes the moving image over an image based on the volumetric data and displays these images on the display unit.

X-ray CT system, image display device, and image display method

According to one embodiment, an X-ray computed tomography apparatus includes an X-ray tube, an X-ray detector, a projection data generation circuitry, a setting circuitry, and a scan start timing determination circuitry. The setting circuitry configured to set a region of interest on a slice image generated by a first scan for the object. The scan start timing determination circuitry configured to determine, based on a plurality of projection data values of interest corresponding to the region of interest out of the projection data values generated by a second scan at a dose lower than that in the first scan, a timing of terminating the second scan and starting a third scan at a dose higher than that in the second scan.

X ray computed tomography apparatus and scan start timing determination method

According to one embodiment, a medical imaging diagnosis apparatus includes a top-plate, a bed, a first gantry, a second gantry and a moving assembly. The top-plate places a subject thereon. The bed supports the top-plate. The first gantry includes an X-ray generator and an X-ray detector which revolve around the top-plate. The second gantry includes a gamma ray detector which detects gamma rays emitted from the subject. The moving assembly moves, based on a first position indicative of a center position of an effective view field in the first gantry and a second position indicative of a center position of an effective view field in the second gantry, the top-plate relative to the second position.

Medical imaging diagnosis apparatus, nuclear medicine diagnosis apparatus, X-ray CT apparatus, and bed apparatus

A medical imaging apparatus includes a reconstruction unit, a ROI setting unit, and a controller. The reconstruction unit receives projection data that is based on radiation detected by a detector, divides the projection data into a plurality of subsets, and apply a reconstruction process to the subsets by successive approximation to successively generate images. The ROI setting unit sets a ROI in the images. The controller obtains a variation value indicating a change in image quality from the images, and, when the variation value reaches a predetermined value, instructs the reconstruction unit on a new subset count less than the number of the subsets to sequentially reconstruct subsets as many as the new subset count into an image. The reconstruction unit assigns a weight to the projection data based on the ROI, and divides the projection data into the subsets based on the weight.

Growing community of inventors

Nasushiobara, Japan

Masakazu Matsuura