Abstract: 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.

Abstract: A discrimination device is a device that discriminates whether or not a discrimination target object is a blood cell based on an image of the discrimination target object, and includes a blood cell feature extraction unit that acquires an image of a blood cell and extracts a feature of the blood cell from the acquired image, a discrimination target object feature extraction unit that acquires the image of the discrimination target object and extracts a feature of the discrimination target object from the acquired image, and a discrimination unit that discriminates whether or not the discrimination target object is a blood cell through anomaly detection based on the extracted feature of the blood cell and the feature of the discrimination target object.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.