Fujifilm Corporation

Masaaki Oosake

Shumpei Kamon

Hiroaki Yamamoto

Goro Miura

Shinji Hayashi

Satoshi Naito

Toshihiro Usuda

Makoto Ozeki

Takayuki Tsujimoto

Misaki Kawahara

Masato Yoshioka

There are provided a machine learning system, a learning method, and a program that can facilitate learning of a large number of combined medical images. A machine learning system () includes: an image database () that stores a plurality of medical images; a geometric-shape database () that stores geometric shapes to be superimposed on the medical images; a processor (); and a learning model (), in which the processor () is configured to perform a selection accepting process of accepting selection of a medical image from among the medical images stored in the image database () and selection of a geometric shape from among the geometric shapes stored in the geometric-shape database (), a geometric-shape combining process of combining the selected medical image and the selected geometric shape and generating a composite image, and a training process of making the learning model perform learning by using the composite image.

Machine learning system, recognizer, learning method, and program

A processor generates a trained model by updating a learning model that uses an input image for training obtained by performing deterioration processing on a source image as input to output a first output image for training and a second output image for training, which have the number of pixels larger than the input image for training. A second intermediate layer of the learning model outputs a feature map to be input to a first output layer that outputs the first output image for training based on the feature map from a folded layer and a first intermediate layer. A third intermediate layer outputs the feature map to be input to a second output layer that outputs a second output image for training based on the feature map from the folded layer.

Image processing apparatus, operation method of image processing apparatus, and endoscope system

An image acquisition unit sequentially acquires a medical image. A recognition processing unit applies a recognition process to the medical image. A recognition result display determination unit determines to display or not display the result of the recognition process on a display according to blur in the medical image. A display control unit controls the display of the recognition process according to the determination by the recognition result display determination unit.

Medical imaging apparatus and operating method for same

In an endoscope apparatus including a processor, the processor specifies the position of a specific region and sets a reference scale in a picked-up image that is obtained from the image pickup of a subject on which the specific region formed by auxiliary measurement light is formed. Then, the processor extracts a region of interest, determines a measurement portion, calculates a measured value obtained from the measurement of the measurement portion, on the basis of the reference scale, and generates a measured value marker using the measured value. Further, the processor creates a specific image in which the measured value marker is superimposed on the picked-up image.

Endoscope apparatus, method of operating the same, and non-transitory computer readable medium

A medical image processing apparatus includes a processor configured to perform: a first determination process of determining, based on an acquired medical image, whether any of a plurality of imaging target sites is included in the medical image; a second determination process of determining, if it is determined in the first determination process that any of the plurality of imaging target sites is included in the medical image, whether the medical image is an image satisfying a determination criterion of a site included in the medical image; and a display control process of displaying, if it is determined in the second determination process that the medical image is the image satisfying the determination criterion of the site included in the medical image, a notification indicator on a display unit, the notification indicator indicating that the image satisfying the determination criterion of the site included in the medical image is captured.

Medical image processing apparatus, medical image processing method, and program

There are provided a learning apparatus, a learning method, a program, a trained model, and an endoscope system that can perform efficient learning even when the learning is performed using pieces of data acquired under conditions different from each other. A learning apparatus includes a hierarchical network including a first input layer, a second input layer, a first intermediate layer, a first normalization layer, a second normalization layer, a second intermediate layer, and an output layer. A learning control unit of the learning apparatus causes first learning and second learning to be performed. In the first learning, a to-be-trained model is trained based on a first error between a first recognition result and a correct answer for first data. In the second learning, the to-be-trained model is trained based on a second error between a second recognition result and a correct answer for second data.

Learning apparatus, learning method, program, trained model, and endoscope system

Provided is a medical image processing apparatus, a medical image processing method, and a program that are capable of reducing a gap between recognition by a recognizer and recognition by a user. The medical image processing apparatus is a medical image processing apparatus including a processor (), a memory (), and a monitor (). The processor () is configured to sequentially acquire a plurality of medical images in a chronological manner; recognize, on the basis of the acquired medical images, a specific scene in the medical images; acquire a recognition frequency of the recognized specific scene; and cause the monitor to display, in accordance with the recognition frequency, a notification indication that changes in two or more stages and that indicates a degree of recognition.

An endoscope system comprises an image acquisition unit, a discrimination processing unit, and a discrimination processing control unit. The image acquisition unit acquires an endoscope image obtained by imaging an observation target using an endoscope. The discrimination processing unit discriminates a portion having a specific feature in the observation target by performing discrimination processing, using an endoscope image. The discrimination processing control unit controls a start or an end of the discrimination processing on the basis of a change in operation of an endoscope or the endoscope image.

Endoscope system, processor device, and method of operating endoscope system

A medical image processing apparatus includes the following. A processor is configured to: acquire a medical image obtained by capturing an image of an observation target; detect a region of interest from the medical image; and cause a display to display report information and the medical image, the report information reporting that the region of interest has been detected. A screen displayed on the display has a first region in which the medical image is displayed, and a second region provided outside the first region. The second region is divided into four regions by using line segments passing through a center of the first region, and a detected location of the region of interest is reported by displaying the report information in one of the four regions.

Medical image processing apparatus

An image processing apparatus acquires a color image including a plurality of primary color signals, performs color space conversion processing on the color image to generate a brightness signal image and a color difference signal image, performs super-resolution processing on the brightness signal image and the color difference signal image to generate a prediction brightness signal image, and uses the prediction brightness signal image to generate a super-resolution color image in which a resolution of the color image is increased.

Image processing apparatus, image processing method, non-transitory computer readable medium, and endoscope system

An object of the present invention is to provide a learning apparatus and a learning method capable of appropriately learning pieces of data that belong to the same category and are acquired under different conditions. In a learning apparatus according a first aspect of the present invention, first data and second data are respectively input to a first input layer and a second input layer that are independent of each other, and feature quantities are calculated. Thus, the feature quantity calculation in one of the first and second input layers is not affected by the feature quantity calculation in the other input layer. In addition to feature extraction performed in the input layers, each of a first intermediate feature quantity calculation process and a second intermediate feature quantity calculation process is performed at least once in an intermediate layer that is shared by the first and second input layers. Thus, the feature quantities calculated from the first data and the second data in the respective input layers can be reflected in the intermediate feature quantity calculation in the intermediate layer. Consequently, pieces of data that belong to the same category and are acquired under different conditions can be appropriately learned.

Learning apparatus and learning method

A medical image processing apparatus includes a recognition unit that detects a region of interest from a medical image and classifies the region of interest, a display control unit that causes emphasis display of the region of interest and a classification for the region of interest to be displayed in a screen for displaying the observation target, and a change determining unit that determines at least any of whether to change a display style of the emphasis display or whether to change a display style of the classification. The display control unit changes the display style of the emphasis display in the case where it is determined to change the display style of the emphasis display and changes the display style of the classification in the case where it is determined to change the display style of the classification.

Medical image processing apparatus, processor device, endoscope system, medical image processing method, and program

There are provided a learning apparatus and a learning method that can facilitate creation of teaching data and prevent overtraining. A learning apparatus () includes a first database that stores a first image set in which a first image for learning and coordinate information for identifying a region larger than a region of interest included in the first image are associated with each other, and a second database that stores a second image set in which a second image for learning and second mask data for identifying a region of interest included in the second image are associated with each other. In a case of using the first image set to update a parameter of a CNN () (in a case of performing learning), a mask data creation unit () creates first mask data on the basis of the coordinate information for identifying the region larger than the region of interest. The first image and the second image are used as input images for the CNN (), and the first mask data and the second mask data are used as teaching data to update the parameter of the CNN ().

Learning apparatus and learning method for training neural network

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

Provided are a medical image processing device, a medical image processing method, and an endoscope system that make it easy to compare a region of interest and its peripheral region with each other and make it unlikely to miss the region of interest if the region of interest in a time-series image is reported by using figures. A coordinates calculating unit () that calculates, on the basis of region-of-interest information indicating a region of interest in a time-series image, a plurality of sets of coordinates of interest on an outline of a polygon or circle having a symmetric shape that surrounds the region of interest. A reporting information display control unit (B) that superposes figures on the basis of the calculated plurality of sets of coordinates of interest when superposing the figures for reporting the region of interest on the time-series image. Herein, the figures have a size that does not change with respect to a size of the region of interest.

Growing community of inventors

Kanagawa, Japan

Masaaki Oosake