Medical image analysis system and similar case retrieval system using quantitative parameters, and methods for the same
Disclosed herein is a computing system for performing medical image analysis. A computing system for performing medical image analysis according to an embodiment of the present invention includes at least one processor. The at least one processor performs image processing on a first medical image, and segments at least one anatomical region in the first medical image. The at least one processor generates a first quantitative parameter for the at least one anatomical region based on quantitative measurement conditions that can be measured in the first medical image, and stores the first quantitative parameter in a database in association with the first medical image and the at least one anatomical region.
1. A case retrieval method that is performed by a computing system, the case retrieval method comprising:
receiving a first medical image via user input;
obtaining information of at least one anatomical region in the first medical image segmented by image processing for the first medical image;
obtaining at least one first region providing information for assisting a diagnosis for a specified disease for the at least one anatomical region;
generating a first quantitative parameter for the at least one anatomical region based on a quantitative measurement condition capable of being measured for the at least one first region in the first medical image; and
retrieving at least one second medical image having a second quantitative parameter based on the first quantitative parameter of the first medical image from a database,
wherein the first quantitative parameter and the second quantitative parameter are related to a quantitative measurement of the at least one first region segmented into respective clusters classified into a plurality of groups that are classified by size of the at least one first region, and
wherein the retrieving the at least one second medical image retrieves the at least one second medical image using the first quantitative parameter and the second quantitative parameter related to the at least one first region extracted as at least one Low Attenuation Area (LAA) or at least one air trap region within the at least one anatomical region.
2. The case retrieval method of claim 1 , wherein, the quantitative measurement of the at least one first region segmented into respective clusters classified into the plurality of groups includes a number, a volume, or a volume ratio of the at least one first region.
3. The case retrieval method of claim 1 , wherein the retrieving the at least one second medical image retrieves the at least one second medical image using the first quantitative parameter and the second quantitative parameter related to a number of the at least one LAA or the at least one air trap region classified into the plurality of groups by the size of the at least one LAA or the at least one air trap region, a volume or volume ratio of the at least one LAA or the at least one air trap region classified into the plurality of groups by the size of the at least one LAA or the at least one air trap region.
4. A case retrieval method that is performed by a computing system, the case retrieval method comprising:
receiving a first medical image via user input;
obtaining information of at least one anatomical region in the first medical image segmented by image processing for the first medical image;
obtaining at least one first region providing information for assisting a diagnosis for a specified disease for the at least one anatomical region;
generating a first quantitative parameter for the at least one anatomical region based on a quantitative measurement condition capable of being measured for the at least one first region in the first medical image; and
retrieving at least one second medical image having a second quantitative parameter based on the first quantitative parameter of the first medical image from a database,
wherein the first quantitative parameter and the second quantitative parameter are related to at least one of a normalized wall thickness of the at least one first region when the at least one first region has a tubular structure having a wall and a lumen and the lumen is assumed to have a reference diameter, or wall thickness values of the at least one first region relative to a direction toward microstructure of a hierarchical branch of a tubular structure.
5. A computing system for performing case retrieval, the computing system comprising at least one processor, wherein the at least one processor is configured to:
receive a first medical image via user input;
obtain information of at least one anatomical region in the first medical image segmented by image processing for the first medical image;
obtain at least one first region providing information for assisting a diagnosis for a specified disease for the at least one anatomical region;
generate a first quantitative parameter for the at least one anatomical region based on a quantitative measurement condition capable of being measured for the at least one first region in the first medical image; and
retrieve at least one second medical image having a second quantitative parameter based on the first quantitative parameter of the first medical image from a database,
wherein the first quantitative parameter and the second quantitative parameter are related to a quantitative measurement of the at least one first region segmented into respective clusters classified into a plurality of groups that are classified by size of the at least one first region, and
wherein the first quantitative parameter and the second quantitative parameter are related to the at least one first region extracted as at least one Low Attenuation Area (LAA) or at least one air trap region within the at least one anatomical region.
6. The computing system of claim 5 , wherein the at least one processor is further configured to retrieve the at least one second medical image using the first quantitative parameter and the second quantitative parameter, wherein the quantitative measurement of the at least one first region segmented into respective clusters classified into the plurality of groups includes a number, a volume, or a volume ratio of the at least one first region.