Medical image reconstruction apparatus and method for screening for plurality of types of lung diseases
Disclosed herein is a medical image reconstruction apparatus for reconstructing a medical image to assist the reading of a medical image. The medical image reconstruction apparatus includes a computing system, which includes: a receiver interface configured to receive a first medical image to which a first reconstruction parameter adapted to diagnose or analyze a first type of lesion is applied; and at least one processor configured to generate a second reconstruction parameter to be applied to the first medical image in response to a diagnosis order for the diagnosis or analysis of a second type of lesion. The at least one processor provides the second reconfiguration parameter to a user via a user interface, or generates a second medical image for the diagnose or analysis of the second type of lesion by executing the second reconstruction parameter on the first medical image and provides the second medical image to the user.
1. A medical image reconstruction apparatus for reconstructing a medical image to assist reading of a medical image, the medical image reconstruction apparatus comprising a computing system, wherein the computing system comprises:
a receiver interface configured to receive a first medical image to which a first reconstruction parameter adapted to diagnose or analyze a first type of lesion is applied; and
at least one processor configured to:
transfer a diagnosis order for a diagnosis or analysis of a second type of lesion to a first artificial neural network; and
control the first artificial neural network to generate a second reconstruction parameter to be applied to the first medical image in response to the diagnosis order,
wherein the at least one processor provides the second reconfiguration parameter to a user via a user interface, or generates a second medical image for a diagnose or analysis of the second type of lesion by executing the second reconstruction parameter on the first medical image and provides the second medical image to the user via the user interface.
2. The medical image reconstruction apparatus of claim 1 , wherein the at least one processor is further configured to:
identify information about the first reconstruction parameter from received information of the first medical image;
transfer the information about the first reconstruction parameter and the diagnosis order to the first artificial neural network; and
control the first artificial neural network to generate the second reconstruction parameter based on the information about the first reconstruction parameter and the diagnosis order.
3. The medical image reconstruction apparatus of claim 2 , wherein the at least one processor is further configured to:
transfer information about the first type of lesion, information about the second type of lesion, and the information about the first reconstruction parameter to the first artificial neural network; and
control the first artificial neural network to generate the second reconstruction parameter by converting the first reconstruction parameter based on the information about the first type of lesion, the information about the second type of lesion, and the information about the first reconstruction parameter.
4. The medical image reconstruction apparatus of claim 2 , wherein the first artificial neural network is an artificial neural network that has received a plurality of training datasets, including a first training reconstruction parameter derived to diagnose or analyze the first type of lesion for one original medical image and a second training reconstruction parameter derived to diagnose or analyze the second type of lesion for the original medical image, and that has learned a correlation between the first training reconstruction parameter and the second training reconstruction parameter corresponding to a correlation between the first type of lesion and the second type of lesion.
5. The medical image reconstruction apparatus of claim 2 , wherein the computing system further comprises a second artificial neural network configured to perform medical image analysis on the second medical image in response to the diagnosis order, and
wherein the at least one processor is further configured to input the second medical image to the second artificial neural network and control the second artificial neural network to generate a medical image analysis result for the second medical image.
6. The medical image reconstruction apparatus of claim 1 , wherein the at least one processor is further configured to:
provide the second reconstruction parameter or the second medical image to a third artificial neural network via a transmission interface or the user interface in response to the diagnosis order; and
receive a medical image analysis result, obtained through inference in response to the diagnosis order by the third artificial neural network, via the receiver interface.
7. The medical image reconstruction apparatus of claim 1 , wherein the diagnosis order is determined based on a user command input from the user via the user interface, or is determined based on predetermined information managed by the at least one processor and information about the first type of lesion.
8. The medical image reconstruction apparatus of claim 1 , wherein the at least one processor is further configured to provide:
results of the diagnosis or analysis of the first type of lesion performed on the first medical image; and
results of the diagnosis or analysis of the second type of lesion performed on the second medical image,
together to the user via the user interface.
9. The medical image reconstruction apparatus of claim 1 , wherein the at least one processor is further configured to, when the user approves the second reconstruction parameter, store at least one of the second reconstruction parameter and the second medical image in a medical image database in association with the first medical image and the second reconstruction parameter.
10. A medical image reconstruction apparatus for reconstructing a medical image to assist reading of a medical image based on a medical artificial neural network, the medical image reconstruction apparatus comprising a computing system, wherein the computing system comprises:
a receiver interface configured to receive a plurality of training datasets, including a first training reconstruction parameter derived to diagnose or analyze a first type of lesion for one original medical image, and a second training reconstruction parameter derived to diagnose or analyze a second type of lesion for the original medical image;
at least one processor; and
an artificial neural network,
wherein the at least one processor is configured to:
transfer the plurality of training datasets to the artificial neural network; and
control the artificial neural network to learn a correlation between the first training reconstruction parameter and the second training reconstruction parameter corresponding to a correlation between the first type of lesion and the second type of lesion.
11. A medical image reconstruction method for reconstructing a medical image to assist reading of a medical image, the medical image reconstruction method being executed by a computing system, the computing system comprising at least one processor and a receiver interface, the medical image reconstruction method comprising:
receiving, by the at least one processor, a first medical image, to which a first reconstruction parameter adapted to diagnose or analyze a first type of lesion is applied, via the receiver interface;
transferring, by the at least one processor, a diagnosis order for a diagnosis or analysis of a second type of lesion to a first artificial neural network; and
controlling, by the at least one processor, the first artificial neural network to generate a second medical image adapted to diagnose or analyze the second type of lesion by reconstructing the first medical image or a second reconstruction parameter to be applied to the first medical image for generating the second medical image in response to the diagnosis order.
12. The medical image reconstruction method of claim 11 , further comprising:
providing, by the at least one processor, the second reconfiguration parameter to a user via a user interface.
13. The medical image reconstruction method of claim 11 , further comprising:
generating, by the at least one processor, a the second medical image for a diagnose or analysis of the second type of lesion by executing the second reconstruction parameter on the first medical image and providing, by the at least one processor, the second medical image to the user via the user interface.
14. The medical image reconstruction method of claim 11 , further comprising:
identifying, by the at least one processor, information about the first reconstruction parameter from received information of the first medical image;
transferring, by the at least one processor, the information about the first reconstruction parameter and the diagnosis order to the first artificial neural network; and
controlling, by the at least one processor, the first artificial neural network to generate the second reconstruction parameter based on the information about the first reconstruction parameter and the diagnosis order.
15. The medical image reconstruction method of claim 14 , further comprising:
inputting, by the at least one processor, the second medical image by executing the second reconstruction parameter on the first medical image, to the second artificial neural network configured to analyze the second medical image in response to the diagnosis order; and
controlling, by the at least one processor, the second artificial neural network to generate a medical image analysis result for the second medical image.
16. The medical image reconstruction method of claim 11 , further comprising:
providing, by the at least one processor, the second reconstruction parameter or a-the second medical image by executing the second reconstruction parameter on the first medical image, to a third artificial neural network via a transmission interface or the user interface in response to the diagnosis order; and
receiving, by the at least one processor, a medical image analysis result, obtained through inference in response to the diagnosis order by the third artificial neural network, via the receiver interface.
17. The medical image reconstruction method of claim 11 , further comprising providing, by the at least one processor:
results of the diagnosis or analysis of the first type of lesion performed on the first medical image; and
results of the diagnosis or analysis of the second type of lesion performed on the second medical image,
together to the user via the user interface.
18. The medical image reconstruction method of claim 11 , further comprising:
when the user approves the second reconstruction parameter, storing, by the at least one processor, at least one of the second reconstruction parameter and the second medical image in a medical image database in association with the first medical image and the second reconstruction parameter.
19. A medical image reconstruction apparatus for reconstructing a medical image to assist reading of a medical image, the medical image reconstruction apparatus comprising a computing system, wherein the computing system comprises:
a receiver interface configured to receive a first medical image adapted to diagnose or analyze a first type of lesion is applied; and
at least one processor configured to:
transfer a diagnosis order for a diagnosis or analysis of a second type of lesion to an artificial neural network; and
control the artificial neural network to generate a second medical image adapted to diagnose or analyze the second type of lesion by reconstructing the first medical image in response to the diagnosis order; and
provide the second medical image to a user via a user interface.
20. The medical image reconstruction method of claim 19 , wherein a first reconstruction parameter adapted to diagnose or analyze a first type of lesion is applied to the first medical image, and
wherein the at least one processor is further configured to control the artificial neural network to generate the second medical image by applying a second reconstruction parameter adapted to diagnose or analyze the second type of lesion to reconstruct the first medical image.