Hamamatsu-photonics K.k.

Social Welfare Corporation Seirei Social Welfare Community

Fumio Hashimoto

Kibo Ote

Hidenao Yamada

Osamu Yasuhiko

Akira Obana

Takashi Isobe

Masanori Ito

An image processing apparatus includes a feature extraction unit, a reconstruction unit, an evaluation unit, and a control unit. The feature extraction unit inputs an input image to a feature extraction NN, and outputs an intermediate image from the feature extraction NN. The reconstruction unit inputs the intermediate image to an m-th reconstruction NN, and outputs an m-th output image from the m-th reconstruction NN. The evaluation unit obtains an evaluation value based on a sum of differences between the m-th tomographic image and the m-th output image. The control unit repeatedly performs processes of the feature extraction unit and the reconstruction unit, calculation of the evaluation value by the evaluation unit, and training of the feature extraction NN and the m-th reconstruction NN based on the evaluation value.

Image processing device and image processing method

A radiation tomography system includes a radiation tomography apparatus and an image processing apparatus. The image processing apparatus includes an image reconstruction unit, an attenuation distribution image creation unit, and an attenuation correction unit. The attenuation distribution image creation unit includes a first processing unit and a second processing unit. The first processing unit creates and outputs an intermediate image based on an emission scan image using a trained neural network. The second processing unit creates and outputs an attenuation distribution image based on the intermediate image.

Attenuation distribution image creating device, image processing device, radiation computed tomography system, attenuation distribution image creating method, and image processing method

An ocular fundus image processing device acquires a first image generated by irradiating an ocular fundus of a subject with excitation light of a blue wavelength and a second image generated by irradiating the ocular fundus with excitation light of a green wavelength, generates three trained models for predicting a correction factor for calculating a quantity of macular pigment of the subject from input images including the first image and the second image through training using three different initial values, predicts three correction factors by inputting the input images including the first image and the second image to the three trained models, calculates a statistical value of the three correction factors and derives the statistical value as the correction factor of the subject, and calculates a quantity of macular pigment of the subject on the basis of the first image and the correction factor of the subject.

Ocular fundus image processing method, ocular fundus image processing device, ocular fundus image processing program, and recording medium having said program recorded thereon

The method includes an acquisition step for model generation of acquiring a hologram for model generation in which an image of a cell is captured and which is used to generate a learning model, a generation step for model generation of generating a new hologram for model generation having a different focal position from the acquired hologram for model generation and increasing the number of holograms for model generation, and a learning model generation step of generating a learning model by performing machine learning using the increased holograms for model generation.

Learning model generation method, identification method, learning model generation system, identification system, and non-transitory computer-readable storage medium

An image processing apparatus includes a first image creation unit, a second image creation unit, and a CNN processing unit. The first image creation unit creates a first tomographic image of an m-th frame using a data group in list data included in the m-th frame. The second image creation unit creates a second tomographic image using a data group in the list data having a data amount larger than that of the data group used in creating the first tomographic image. The CNN processing unit inputs the second tomographic image to a CNN, outputs an output tomographic image from the CNN, trains the CNN based on a comparison between the output tomographic image and the first tomographic image, and repeats the training operation to generate the output tomographic image in each training.

Growing community of inventors

Hamamatsu, Japan

Fumio Hashimoto