CN-115297764-B - Information processing device, information processing method, and recording medium
Abstract
An information processing device, an information processing method, and a recording medium are provided that can suppress the case where lesions in medical images are ignored. An information processing device is provided with a data acquisition unit that acquires medical image data and additional data, the additional data including at least 1 of display-related data that defines a presentation mode of an image displayed on a display unit of a display and environment data that represents a surrounding environment of the display, and a data calculation unit that calculates, based on the medical image data and the additional data, omission-suppressing data that suppresses lesions from being omitted from the medical image data.
Inventors
- Dong Zhengshi
- KATO YUTAKA
Assignees
- EIZO株式会社
Dates
- Publication Date
- 20260505
- Application Date
- 20210318
- Priority Date
- 20200414
Claims (8)
- 1. An information processing apparatus includes a data acquisition unit and a data calculation unit, The data acquisition unit acquires medical image data and additional data, The supplemental data includes at least 1 of display related data and environmental data, The display related data is data defining a presentation style of an image displayed on a display section of the display, The environment data is data representing the surroundings of the display, The data operation unit calculates the probability based on a learning model that outputs the probability when the medical image data and the additional data are input, and generates neglect suppression data based on the probability, The omission factor suppressing data is data suppressing the omission of lesions in the medical image data, The probability is a value that indicates whether the lesion is easily ignored.
- 2. The information processing apparatus according to claim 1, wherein, The omission factor suppressing data includes image data indicating an area where lesions are easily omitted among areas within the medical image data.
- 3. The information processing apparatus according to claim 1 or 2, wherein, The ignore suppression data includes score data representing a likelihood that lesions in the medical image data are ignored.
- 4. The information processing apparatus according to claim 1 or 2, wherein, The ignore suppression data comprises location data, The position data is data that determines the position of an area where lesions are easily ignored, among areas within the medical image data.
- 5. The information processing apparatus according to claim 1 or 2, wherein, The display association data includes at least 1 of display settings, display specifications, viewer settings, and display measurement values, The display setting value is a setting value for defining a presentation mode of an image displayed on the display section, The display specification indicates a characteristic that the display has in advance, The viewer setting value is a setting value for defining a presentation style of the image displayed on the display unit, and is a setting value of an application program for displaying the image on the display unit, The display measurement value is a measurement value of luminance or chromaticity of the display section.
- 6. The information processing apparatus according to claim 1 or 2, wherein, The environmental data includes at least 1 of an illuminance value and a ranging value, The illuminance value is a value indicating illuminance around the display portion, The ranging value is a value representing a distance between the display and a human body.
- 7. An information processing method includes an acquisition step and an operation step, In the acquiring step, medical image data and additional data are acquired, The supplemental data includes at least 1 of display related data and environmental data, The display related data is a presentation style defining an image displayed on a display portion of the display, The environment data is data representing the surroundings of the display, In the operation step, the probability is calculated based on a learning model that outputs a probability when the medical image data and the additional data are input, and the neglect suppression data is generated based on the probability, The omission factor suppressing data is data suppressing the omission of lesions in the medical image data, The probability is a value that indicates whether the lesion is easily ignored.
- 8. A recording medium storing a computer program for causing a computer to execute an information processing method including an acquisition step and an operation step, In the acquiring step, medical image data and additional data are acquired, The supplemental data includes at least 1 of display related data and environmental data, The display related data is a presentation style defining an image displayed on a display portion of the display, The environment data is data representing the surroundings of the display, In the operation step, the probability is calculated based on a learning model that outputs a probability when the medical image data and the additional data are input, and the neglect suppression data is generated based on the probability, The omission factor suppressing data is data suppressing the omission of lesions in the medical image data, The probability is a value that indicates whether the lesion is easily ignored.
Description
Information processing device, information processing method, and recording medium Technical Field The present invention relates to an information processing apparatus, an information processing method, and a computer program. Background The radiologist uses medical images such as mammography images to determine whether or not a lesion is present. Here, the judgment of the presence or absence of a lesion or the like is carefully performed by the radiologist, but on the other hand, the radiologist may have to interpret a plurality of medical images, and there is a possibility that the lesion is ignored. For example, patent document 1 discloses a technique of calculating whether there is a risk of physical lesions or the like by computer image analysis on mammography images in which potential lesions cannot be observed with naked eyes. Prior art literature Patent literature Patent document 1 U.S. patent application publication No. 2017/0249739 specification Disclosure of Invention (Problem to be solved by the invention) For example, the manner in which the medical image is presented depends on factors such as the display used by the radiologist or the environment in which the radiologist interprets the image. And the risk of computation will also vary depending on such factors. However, the technique of patent document 1 does not consider these factors in calculating the above risk, and therefore the calculated risk deviates from the actual situation, which increases the possibility that lesions in medical images are ignored. The present invention has been made in view of such circumstances, and an object thereof is to provide an information processing apparatus, an information processing method, and a computer program capable of suppressing a situation in which lesions in medical images are ignored. (Means for solving the problems) According to the present invention, there is provided an information processing apparatus including a data acquisition unit that acquires medical image data and additional data including at least 1 of display-related data defining a presentation style of an image displayed on a display unit of a display and environment data representing an ambient environment of the display, and a data calculation unit that calculates, based on the medical image data and the additional data, omission-suppressing data that suppresses omission of lesions in the medical image data. According to the present invention, the data calculation unit can calculate data (neglect suppression data) for suppressing the lesion from being ignored in the medical image data. Since the neglect suppressing data is based on additional data including at least 1 of the display related data and the environment data, the neglect suppressing data takes the above factors into consideration, and as a result, it is possible to suppress a situation in which lesions in the medical image are ignored. Various embodiments of the present invention are illustrated below. The embodiments shown below may be combined with each other. Preferably, there is provided the information processing apparatus, wherein the omission suppressing data includes image data indicating an area where lesions are easily omitted among areas within the medical image data. Preferably, an information processing apparatus is provided, wherein the omission suppressing data includes score data of a possibility that lesions are omitted in the medical image data. Preferably, there is provided the information processing apparatus, wherein the omission suppressing data includes position data, which is data of positions of regions where specific lesions are easily omitted, among regions within the medical image data. Preferably, the information processing apparatus is provided, wherein the display related data includes at least 1 of a display setting value, a display specification, a viewer setting value, and a display measurement value, the display setting value is a setting value for defining a presentation form of an image displayed on the display unit, the display specification indicates a characteristic of the display in advance, the viewer setting value is a setting value for defining a presentation form of an image displayed on the display unit, and the display measurement value is a measurement value of luminance or chromaticity of the display unit. Preferably, there is provided the information processing apparatus, wherein the environment data includes at least 1 of an illuminance value indicating illuminance around the display portion and a ranging value indicating a distance between the display and a human body. Preferably, the information processing apparatus is provided, wherein the data operation unit calculates the probability based on a learning model in which the medical image data and the additional data are input and a probability indicating whether or not the lesion is easily ignored is output, and the data operation unit generates the omission sup