Canon Kabushiki Kaisha

Fujifilm Corporation

Satoshi Naito

Takahiro Kawamura

Haruyasu Nakatsugawa

Jun Enomoto

Takashi Tajima

Daiki Harada

Noriaki Ida

Hideki Yamagishi

Takeshi Koishi

Yukio Chiba

Hirofumi Sawada

Reiko Fujino

Makoto Kimura

Koji Okawa

Shumpei Kamon

Masaaki Oosake

Mamoru Sato

Toshihiko Fukasawa

Makoto Satoh

Yuji Omori

Susumu Igarashi

Goro Miura

Saku Hiwatashi

Misaki Kawahara

There are provided a medical image processing apparatus, a medical image processing method, a machine learning system, and a program that can reduce the volume of communication and can reduce the processing load of retraining or additional training that is performed by a machine learning apparatus. A medical image processing apparatus () includes: a trainer () that performs additional training for a first computer-aided diagnosis device on the basis of an input medical image; an evaluation unit that compares a second computer-aided diagnosis device obtained by the additional training with the first computer-aided diagnosis device and evaluates whether learning difference information about the additional training contributes to improvement of performance of the first computer-aided diagnosis device; a communication determination unit that determines, on the basis of a result of evaluation, whether the learning difference information is to be communicated; and a communication unit () that outputs the learning difference information in accordance with a result of determination by the communication determination unit.

Medical image processing apparatus, medical image processing method, machine learning system, and program

An apparatus includes a first holding unit configured to hold, in a reference image, first reference pixels in a search range including a block corresponding to a first block as a coding target in the input image, a first search unit configured to search for a motion vector of a prediction block included in the first block, using the first reference pixels, a second holding unit configured to hold, in the reference image, second reference pixels in a search range including a block corresponding to a second block as a coding target, a second search unit configured to search for a motion vector of a prediction block included in the second block, using the second reference pixels, and a transfer unit configured to read, from among the first reference pixels, a reference pixel to be used by the second search unit for the search.

Image coding apparatus, image coding method, and storage medium

A moving image coding apparatus includes a feature amount derivation unit configured to derive a feature amount of a block having a reference size smaller than the block unit, the block included in a subject frame being a processing subject of the frames included in the moving image, a decision unit configured to, in a case where the feature amount, derived by the feature amount derivation unit, of the block having the reference size is matched with a first condition, decide the reference size as a block size for inter-prediction and decide a size equal to or smaller than the block size for inter-prediction as a block size for intra-prediction, and a selection unit configured to perform a predetermined evaluation and select one of inter-prediction and intra-prediction as a prediction method for the block having the block size decided by the decision unit.

Moving image coding apparatus, moving image coding method and recording medium

An image coding apparatus which codes an image using intra prediction determines a size of a prediction block to be a unit of processing for performing intra prediction. The image coding apparatus derives a prediction error by performing intra prediction on the prediction block, derives a coding cost of a prediction mode when performing the intra prediction using a reference according to the determined size, and determines the coding cost of the prediction mode based on the coding cost of the prediction mode and the prediction error. The image coding apparatus determines a prediction mode of the prediction block from among a plurality of prediction modes based on the coding cost.

Image coding apparatus, image coding method, and program

An image obtaining section obtains a radiation image that includes a periodic pattern of a grid. A frequency analyzing section performs frequency analysis on the radiation image to obtain a frequency spectrum of the radiation image. A peak determining section determines a peak within the frequency spectrum to be a target of processing. A first judging section measures the width of the peak which is the target of processing, and judges the quality of the grid based on the measured width of the peak.

Method, apparatus, and program for judging grid quality

It is detected whether a grid stripe is present in a radiographic image. In a case in which the grid stripe is detected, a process of removing the grid stripe from the radiographic image is performed and the radiographic image is displayed. In a case in which the grid stripe is not detected, a process of removing a scattered component from the radiographic image is performed and a radiographic image subjected to the scattered radiation removal process and a radiographic image before the process are displayed.

Radiographic image processing device, method, and program

The distance between the radiation source and an object (SOD value) is acquired, distance dependent information which is obtained from a radiation image and changes with the distance between a radiation source and a radiation detector (SID value) is acquired, a temporary thickness of the object is determined by a first function representing the correspondence relationship of first information having at least one piece of the distance dependent information, the SID value, and the thickness of the object, and the temporary SID value is determined by adding the SOD value to the determined value. The thickness of the object is determined by a second function representing the correspondence relationship of second information having at least one piece of the distance dependent information, the SID value, and the thickness of the object, and the SID value is determined by adding the SOD value to the determined value.

Radiation image analysis device, method, and program

A subject image is acquired. A virtual model of the subject having a predetermined body thickness distribution is acquired. A composite image of an estimated primary X-ray image, which is obtained by estimating a primary X-ray image of the virtual model obtained by radiography from the virtual model, and an estimated scattered X-ray image, which is obtained by estimating a scattered X-ray image of the virtual model obtained by radiography from the virtual model, is generated as an estimated image which is obtained by estimating a radiographic image of the subject obtained by radiography. The body thickness distribution of the virtual model is corrected such that a difference between the estimated image and the subject image is reduced. The corrected body thickness distribution of the virtual model is determined as the body thickness distribution of the subject.

Radiographic image analysis device and method, and storage medium having stored therein program

A radiographic image captured by irradiating a subject with radiation is acquired. A scattered radiation removal unit removes a scattered component from the radiographic image using at least imaging conditions. A correction information acquisition unit acquires correction information for correcting the degree of removal of the scattered component and changes the imaging conditions on the basis of the correction information. The scattered radiation removal unit performs a process of removing the scattered component from the radiographic image on the basis of the changed imaging conditions.

A frequency resolution unit performs frequency resolution of a radiographic image to generate band images representing frequency components in a plurality of frequency bands. A reference image generation unit generates a reference image representing information associated with scattered radiation included in the radiographic image, and generates a plurality of band reference images corresponding to a plurality of frequency bands from the reference image. A band image conversion unit performs conversion between the corresponding pixels of the band reference images and the band images in the corresponding frequency bands to generate converted band images. A synthesis unit synthesizes the converted band images to generate a processed radiographic image with converted contrast.

Radiographic image processing device, method, and recording medium

A radiographic image processing device includes: an image acquisition section that acquires a subject image detected by a shielded detection portion and a non-shielded detection portion; an area information acquisition section that acquires area information which is information for specifying a non-shielded image area and a shielded image area; and a scattered ray suppression section that estimates spreading of scattered rays generated in a non-shielded subject portion, estimates that scattered rays that spread to the non-shielded image area from a shielded subject portion are not present, calculates a scattered ray component in each position in the non-shielded image area as the estimated scattered rays reach each position in the non-shielded image area, and suppresses the scattered ray component in each position in the non-shielded image area according to the calculated scattered ray component.

Radiographic image processing device, radiographic image processing method, and recording medium

To prevent deterioration in performance that is caused by the processing for copying a context parameter between memories, an image processing apparatus writes an updated context parameter into context memories corresponding to respective entropy coding units and into a shared context memory, until it completes encoding processing for M blocks positioned on the left side of a slice.

Image coding apparatus, image coding method, and recording medium thereof, image decoding apparatus, and image decoding method, and recording medium thereof

Growing community of inventors

Yokohama, Japan

Satoshi Naito