Blood vessel status evaluation method and blood vessel status evaluation device
View Patent ↗A blood vessel status evaluation method and a blood vessel status evaluation device are provided. The method includes: obtaining at least one angiography image corresponding to a target user; analyzing the angiography image by a first deep learning model to select a target image from the angiography image; analyzing the target image by at least one second deep learning model to determine a blood vessel type of the target user and divide a target blood vessel pattern in the target image into a plurality of scoring segments; and analyzing an output of the second deep learning model by a third deep learning model to obtain a blood vessel status of the target user.
1. A blood vessel status evaluation method, comprising:
obtaining at least one angiography image corresponding to a target patient;
analyzing the at least one angiography image by a first deep learning model to select a target image from the at least one angiography image;
analyzing the target image by at least one second deep learning model to determine a blood vessel type of the target patient and divide a target blood vessel pattern in the target image into a plurality of scoring segments; and
analyzing an output of the at least one second deep learning model by a third deep learning model to obtain a blood vessel status of the target patient,
wherein the step of analyzing the output of the at least one second deep learning model by the third deep learning model to obtain the blood vessel status of the target patient comprises:
obtaining a plurality of first type images corresponding to the target image, wherein each of the first type images presents the target image with one single color;
obtaining a plurality of second type images according to the scoring segments, wherein each of the second type images is used for analyzing a blood vessel status in one of the scoring segments; and
analyzing the first type images and the second type images to obtain the blood vessel status of the target patient.
2. The blood vessel status evaluation method according to claim 1 , wherein the step of analyzing the at least one angiography image by the first deep learning model to select the target image from the at least one angiography image comprises:
determining a probability value corresponding to a first image in the at least one angiography image by the first deep learning model; and
if the probability value is higher than a preset value, determining the first image as the target image.
3. The blood vessel status evaluation method according to claim 1 , wherein the blood vessel type of the target patient comprises one of left dominance and right dominance.
4. The blood vessel status evaluation method according to claim 1 , wherein division of the plurality of scoring segments conforms to a SYNTAX scoring standard.
5. The blood vessel status evaluation method according to claim 1 , wherein the blood vessel type of the target patient comprises a first type and a second type, and a distribution of the scoring segments being divided from the target blood vessel pattern in the target image in response to the blood vessel type of the target patient being determined as the first type is different from a distribution of the scoring segments being divided from the target blood vessel pattern in the target image in response to the blood vessel type of the target patient being determined as the second type.
6. The blood vessel status evaluation method according to claim 1 , wherein the at least one angiography image comprises a plurality of images from different camera angles, and the step of analyzing the output of the at least one second deep learning model by the third deep learning model to obtain the blood vessel status of the target patient comprises:
generating a plurality of scoring results corresponding to a target scoring segment; and
taking a maximum value corresponding to the target scoring segment in the plurality of scoring results as a final scoring result to describe a blood vessel status of the target scoring segment.
7. A blood vessel status evaluation device, comprising:
a storage device, used for storing at least one angiography image corresponding to a target patient; and
a processor, coupled to the storage device,
wherein the processor is used for analyzing the at least one angiography image by a first deep learning model to select a target image from the at least one angiography image,
the processor is further used for analyzing the target image by at least one second deep learning model to determine a blood vessel type of the target patient and divide a target blood vessel pattern into the target image to a plurality of scoring segments, and
the processor is further used for analyzing an output of the at least one second deep learning model by a third deep learning model to obtain a blood vessel status of the target patient,
wherein the operation of analyzing the output of the at least one second deep learning model by the third deep learning model to obtain the blood vessel status of the target patient comprises:
obtaining a plurality of first type images corresponding to the target image, wherein each of the first type images presents the target image with one single color;
obtaining a plurality of second type images according to the scoring segments, wherein each of the second type images is used for analyzing a blood vessel status in one of the scoring segments; and
analyzing the first type images and the second type images to obtain the blood vessel status of the target patient.
8. The blood vessel status evaluation device according to claim 7 , wherein the operation that the processor analyzes the at least one angiography image by the first deep learning model to select the target image from the at least one angiography image comprises:
determining a probability value corresponding to a first image in the at least one angiography image by the first deep learning model; and
if the probability value is higher than a preset value, determining the first image as the target image.
9. The blood vessel status evaluation device according to claim 7 , wherein the blood vessel type of the target patient comprises one of left dominance and right dominance.
10. The blood vessel status evaluation device according to claim 7 , wherein division of the plurality of scoring segments conforms to a SYNTAX scoring standard.
11. The blood vessel status evaluation device according to claim 7 , wherein the blood vessel type of the target patient comprises a first type and a second type, and a distribution of the scoring segments being divided from the target blood vessel pattern in the target image in response to the blood vessel type of the target patient being determined as the first type is different from a distribution of the scoring segments being divided from the target blood vessel pattern in the target image in response to the blood vessel type of the target patient being determined as the second type.
12. The blood vessel status evaluation device according to claim 7 , wherein the at least one angiography image comprises a plurality of images from different camera angles, and the operation that the processor analyzes the output of the at least one second deep learning model by the third deep learning model to obtain the blood vessel status of the target patient comprises:
generating a plurality of scoring results corresponding to a target scoring segment; and
taking a maximum value corresponding to the target scoring segment in the plurality of scoring results as a final scoring result to describe a blood vessel status of the target scoring segment.