Panasonic Corporation

Panasonic Intellectual Property Management Co., Ltd.

Panasonic Intellectual Property Corporation of America

Panasonic Holdings Corporation

Kazuki Kozuka

Kazutoyo Takata

Kenji Kondo

Hirohiko Kimura

Toyohiko Sakai

Ryota Fujimura

Tetsuji Fuchikami

Yoshikuni Sato

Masahiko Saito

Yasunori Ishii

Sotaro Tsukizawa

Koji Morikawa

Hideto Motomura

Shinobu Adachi

Luca Rigazio

Toru Tanigawa

Toru Nakada

Min Young Kim

Masaki Takahashi

Yumiko Kato

Taichi Sato

Yoshihide Sawada

Takashi Tsuzuki

Denis A Gudovskiy

Shun Ishizaka

First optimization processing for optimizing parameters of a DNN and second optimization processing for optimizing hyperpararneters for each sample used in data augmentation processing are alternately performed. The first optimization processing includes causing the DNN to predict a first augmentation label from a first augmented sample, calculating a first error function between the first augmentation label and a first correct label for a first sample, and updating the parameters in accordance with the first error function. The second optimization processing includes acquiring a second sample, causing the DNN after the updating of the parameters to predict a second label from the second sample, calculating a second error function between the second label and a second correct label for the second sample, and updating the hyperparameter in accordance with a gradient obtained by differentiation of the second error function with respect to the hyperparameter.

Data augmentation method, learning device, and recording medium

A risk prediction method is executed by a computer of a risk predictor using a convolutional neural network. The method includes making the convolutional neural network acquire an input image taken by an in-vehicle camera installed on a vehicle. The method also includes making the convolutional neural network estimate a risk area and a feature of the risk area, the risk area being in the acquired input image. The risk area has a possibility that a moving object may appear from the risk area into a travelling path of the vehicle, and the moving object may collide with the vehicle in a case where the vehicle simply continues running. The method further includes making the convolutional neural network output the estimated risk area and the estimated feature of the risk area as a risk predicted for the input image.

Risk prediction method

A method for controlling an information terminal causes a computer of the information terminal to receive, from a case retrieval system, a plurality of similar medical images having a feature quantity of a region of interest and a certain degree of similarity in accordance with the region of interest included in a target medical image, displays a display screen displaying the plurality of received similar medical images on a touch panel display, the display screen including a display region in which at least some of the plurality of received similar medical images are displayed, displays, if selection of a first similar medical image from among the at least some of the plurality of received similar medical images displayed in the display region is detected, the first similar medical image across the display region, and displays, if a swipe operation performed on the first similar medical image is detected, a second similar medical image, which has second highest similarity next to the first similar medical image among the plurality of similar medical images, in the display region such that a corresponding region of interest included in the second similar medical image is located at a certain position in the display region.

Control method and recording medium

A display screen including a first display area displaying plural similar medical images received from a case search system and a second display area displaying disease names is displayed on a display of an information terminal. Each similar medical image is a medical image contained in an electronic medical book, and has additional information which includes the number of a page containing the similar medical image. If the user's selection of a similar medical image is detected for the first time after the display of the display screen, a page of an electronic medical book containing the selected similar medical image is displayed on the display screen. If the user's selection of a disease name is detected for the first time after the display of the display screen, a page of an electronic medical book containing differential items corresponding to the selected disease name is displayed on the display screen.

Method for controlling information terminal, and recording medium

A user input obtainer receives an image movement instruction including identification information specifying a position shift or an image capture time shift to be performed and also including a displacement amount. When the identification information specifies the position shift, a slice position selector determines a tomographic image at a destination of the position shift based on the displacement amount from a set of tomographic images captured at the same time. On the other hand, when the identification information specifies the image capture time shift, the image capture time selector determines a tomographic image at a destination of the shift based on the displacement amount from sets of tomographic images that are identical to each other in terms of a patient, an examination portion, and a modality. A displaying image obtainer reads out the determined tomographic image from an image storage device and gives it to a display information generator.

Case display apparatus, case displaying method, and storage medium background to seamlessly present diagnostic images captured at different times for comparative reading

A similar case retrieval apparatus includes: a lesion portion acquirer that acquires partial images including lesion portion images, an image feature extractor that extracts image features of each of the plurality of partial images; a location information acquirer that acquires location information of each of the partial images; a lateral position determiner that determines the right organ or the left organ in which each of the lesion portions exists based on the location information; a unilateral distribution identifier that determines whether or not a distribution of the lesion portions is a unilateral distribution; and a similar case retriever that retrieves case data from a case database including both case data for the unilateral distribution in the right organ and case data for the unilateral distribution in the left organ when the unilateral distribution identifier identifies that the distribution of the lesion portions is the unilateral distribution.

Similar case retrieval apparatus, similar case retrieval method, non-transitory computer-readable storage medium, similar case retrieval system, and case database

A method includes displaying, on a display of an information terminal, thumbnail images of similar cases received from a case search system and displaying, in a disease name list display area, a disease name list formed from a list of disease names of the similar cases and the number of cases. If a plurality of regions of interest are set by a user when a search is conducted, the disease name list enters a mode in which the name of a concomitant disease is displayable therein.

Method and recording medium

Similar medical images having a predetermined similarity to a region of interest in a medical image to be interpreted are received from a case search system. A display screen on which the received similar medical images are displayed is displayed on a display. The display screen includes display frames within which similar medical images are displayed. In response to an instruction for enlarging the similar medical images, corresponding regions of interest in the similar medical images are enlarged and displayed with the sizes of the display frames maintained unchanged on the display screen. In response to an instruction for causing a selected similar medical image among the enlarged and displayed similar medical images to move within a corresponding display frame, the other unselected similar medical image(s) is caused to move within a corresponding display frame synchronously with the movement of the selected similar medical image in the same movement direction.

Control method and non-transitory computer-readable recording medium for comparing medical images

A control method of an information terminal causes a display to display a display screen which includes a first display region and a second display region. The first display region displays an object medical image. The second display region displays M number of similar medical images and includes ND number of individual regions for displaying the M number of the similar medical images. When an instruction from one or more instruction buttons is detected, a display size of each corresponding region of interest that is included in the second number of the similar medical images is changed while maintaining a size of each of the individual regions in the second display region, and each of the similar medical images is magnified at a magnification ratio of a reference thumbnail.

Control method of information terminal and computer-readable recording medium

A control method of an information terminal includes sensing specification information indicating a region of interest in a medical image, receiving from a case retrieval system one or more similar medical images each having a prescribed degree of similarity with a feature quantity of the region of interest indicated by the specification information in accordance with the region of interest, and displaying the medical image that is managed by a medical information management system in a first display region that is displayed on the display and displaying thumbnail views of a plurality of similar medical images received from the case retrieval system in a second display region that differs from the first display region.

A display control unit vertically divides a case display area in accordance with the number of disease names selected by a user to create a number of sub-areas equal to the number of disease names. Each of the sub-areas is vertically elongated so that thumbnail images of similar cases of the corresponding disease name are displayed so as to be aligned in a column. The display control unit displays, in each sub-area, thumbnail images of similar cases of the corresponding disease name so that the thumbnail images are aligned in a column in order of decreasing similarity to a search query image displayed in a layout area.

Control method and non-transitory computer-readable recording medium

An apparatus includes a memory, and circuitry which, in operation, performs operations including, storing, in the memory, an object occurrence map defining an occurrence area where there is a possibility that an object appears, detecting the object included in a captured image of a scene seen in a running direction of a vehicle, switching a vehicle drive mode, based on a result of the detection of the object and the object occurrence map, from an automatic drive mode in which the vehicle is automatically driven to a manual drive mode in which the vehicle is driven manually by a driver, and controlling driving of the vehicle in the switched manual drive mode.

Method of switching vehicle drive mode from automatic drive mode to manual drive mode depending on accuracy of detecting object

A transfer learning apparatus includes a transfer target data evaluator and an output layer adjuster. The transfer target data evaluator inputs a plurality of labeled transfer target data items each assigned a label of a corresponding evaluation item from among one or more evaluation items to a neural network apparatus having been trained by using a plurality of labeled transfer source data items and including in an output layer output units, the number of which is larger than or equal to the number of evaluation items, and obtains evaluation values output from the respective output units. The output layer adjuster preferentially assigns, to each of the one or more evaluation items, an output unit from which the evaluation value having the smallest difference from the label of the evaluation item is obtained with a higher frequency, as an output unit that outputs the evaluation value of the evaluation item.

Growing community of inventors

Osaka, Japan

Kazuki Kozuka