Apparatus and method for medical image reading assistant providing representative image based on medical use artificial neural network
Disclosed is an apparatus for assisting the reading of a medical image based on a medical artificial neural network, the apparatus including a computing system. An apparatus according to an embodiment of the present invention includes a computing system, and the computing system includes at least one processor. The at least one processor acquires or receives a first analysis result obtained through the inference of a first artificial neural network for a first medical image, generates a first visualization format, which is a representative visualization format of the first medical image, based on the first analysis result, and visualizes the first medical image and the first analysis result based on the first visualization format.
1 . A medical image reading assistance apparatus for assisting reading of a medical image based on a medical artificial neural network, the medical image reading assistance apparatus comprising a computing system, wherein the computing system comprises at least one processor,
wherein the at least one processor is configured to:
acquire or receive a first analysis result obtained through inference of a first artificial neural network for a first medical image;
generate a first visualization format of the first medical image, based on the first analysis result and the first medical image, wherein the first analysis result includes at least one of clinical findings, clinical diagnosis, or a quantitative measurement of a segmented object within the first medical image, and wherein the first visualization format visualizes a pre-processed result for the first analysis result including a segmentation result of the first medical image; and
visualize the first medical image based on the first visualization format.
2 . The medical image reading assistance apparatus of claim 1 , wherein the at least one processor is further configured to provide a first user menu adapted to receive information about a user's approval for the first analysis result visualized based on the first visualization format.
3 . The medical image reading assistance apparatus of claim 2 , wherein the at least one processor is further configured to, when the user does not approve the first analysis result, provide a second user menu adapted to generate a second analysis result corresponding to the first analysis result for the first medical image independently of the first analysis result.
4 . The medical image reading assistance apparatus of claim 2 , wherein the at least one processor is further configured to, when the user approves the first analysis result, store the first analysis result in a database in association with the first medical image.
5 . The medical image reading assistance apparatus of claim 4 , wherein the computing system further comprises a communication interface configured to transmit and receive data to and from the database disposed outside the computing system, and
wherein the at least one processor is further configured to store the first analysis result in the database in association with the first medical image via the communication interface.
6 . The medical image reading assistance apparatus of claim 1 , wherein the at least one processor is further configured to visualize the first analysis result by overlaying the first analysis result on the first visualization format of the first medical image.
7 . The medical image reading assistance apparatus of claim 1 , wherein the at least one processor is further configured to generate the first visualization format based on the first medical image and the first analysis result so that the first analysis result is included in the first visualization format.
8 . The medical image reading assistance apparatus of claim 1 , wherein the first visualization format comprises at least one of at least one view of the first medical image, at least part of the first medical image selected from the first medical image based on relevance to the first analysis result, or reconstruction of the first medical image, and wherein the first analysis result is visualized such that the first analysis result is distinguished based on quantitative information included in the first analysis result.
9 . The medical image reading assistance apparatus of claim 1 , wherein the first artificial neural network provides at least one of image segmentation of the first medical image, clinical diagnosis, or a quantitative measurement result of a segmented object within the first medical image as the first analysis result.
10 . The medical image reading assistance apparatus of claim 1 , wherein the computing system further comprises a communication interface configured to transmit and receive data to and from the first artificial neural network disposed outside the computing system, and
wherein the at least one processor is further configured to acquire or receive the first analysis result obtained through the inference of the first artificial neural network for the first medical image via the communication interface.
11 . A medical image reading assistance method that is performed by a computing system comprising at least one processor, comprising:
acquiring or receiving, by the at least one processor, a first analysis result obtained through inference of a first artificial neural network for a first medical image;
generating, by the at least one processor, a first visualization format of the first medical image, based on the first analysis result and the first medical image, wherein the first analysis result includes at least one of clinical findings, clinical diagnosis, or a quantitative measurement of a segmented object within the first medical image, wherein the first visualization format visualizes a pre-processed result for the first analysis result including a segmentation result of the first medical image; and
visualizing, by the at least one processor, the first medical image based on the first visualization format.
12 . The medical image reading assistance method of claim 11 , further comprising, providing, by the at least one processor, a first user menu adapted to receive information about a user's approval for the first analysis result visualized based on the first visualization format of the first medical image.
13 . The medical image reading assistance method of claim 12 , further comprising, when the user does not approve the first analysis result, providing, by the at least one processor, a second user menu adapted to generate a second analysis result corresponding to the first analysis result for the first medical image independently of the first analysis result.
14 . The medical image reading assistance method of claim 12 , further comprising, when the user approves the first analysis result, storing, by the at least one processor, the first analysis result in a database in association with the first medical image.
15 . The medical image reading assistance method of claim 14 , wherein the storing comprises storing, by the at least one processor, the first analysis result in the database in association with the first medical image via a communication interface configured to transmit and receive data to and from the database disposed outside the computing system.
16 . The medical image reading assistance method of claim 11 , wherein the first visualization format comprises at least one of at least one view of the first medical image, at least part of the first medical image selected from the first medical image based on relevance to the first analysis result, or reconstruction of the first medical image, and
wherein the visualizing comprises visualizing the first analysis result so that the first analysis result is distinguished based on quantitative information included in the first analysis result.
17 . The medical image reading assistance method of claim 11 , wherein the acquiring or receiving comprises acquiring or receiving, by the at least one processor, the first analysis result via a communication interface configured to transmit and receive data to and from the first artificial neural network disposed outside the computing system.