Device and method for determining extent of liver examination

1 . A method of determining an extent of liver examination performed by a device for determining the extent of the liver examination, the method comprising:

receiving an ultrasound image taken of a region of a liver as input;

extracting features from the ultrasound image;

determining one of a plurality of preset cross-sections of the liver for which the ultrasound image was taken on the basis of the extracted features; and

determining a detailed site among a plurality of detailed sites of the liver examination taken in the ultrasound image on the basis of the determined one of the plurality of preset cross-sections of the liver.

2 . The method of claim 1 , wherein in the extracting of the features, features for the liver, blood vessels around the liver, and organs around the liver included in the ultrasound image are extracted.

3 . The method of claim 1 , wherein each of the plurality of preset cross-sections of the liver is at least one of an epigastrium longitudinal scan, an epigastrium transverse scan, a right subcostal scan-hepatic portal vein, a right subcostal-hepatic right lobe transverse scan, a liver dome scan, a right subcostal scan-hepatic vein, a gallbladder longitudinal scan, an extrahepatic bile duct longitudinal scan, an intercostal scan of right lobe of liver including right hepatic portal vein, a right posterior intercostal scan, or a right lower liver and right renal cortex scan.

4 . The method of claim 1 , wherein in the determining the detailed site of the liver examination taken, one of the plurality of detailed sites is determined according to Couinaud classification of hepatic subsegments.

5 . The method of claim 1 , wherein the determining of the one of the plurality of preset cross-sections of the liver includes classifying the ultrasound image into one of at least eleven predefined standard liver scan views.

6 . The method of claim 1 , wherein the determining of the one of the plurality of preset cross-sections is based on a spatial relationship between the liver and at least one surrounding organ or blood vessel identified in the extracted features.

7 . The method of claim 1 , wherein extracting features from the ultrasound image comprises applying a deep learning-based segmentation network to the ultrasound image to perform pixel-wise labeling of anatomical structures.

8 . A device for determining an extent of liver examination, the device comprising:

a memory including instructions to execute a method of determining the extent of the liver examination; and

a processor configured to, by executing the instructions, receive an ultrasound image taken of a region of a liver as input, extract features from the ultrasound image, determine one of a plurality of preset cross-sections of the liver for which the ultrasound image was taken on the basis of the extracted features, and determine a detailed site among a plurality of detailed sites of the liver included in the ultrasound image on the basis of the determined one of the plurality of preset cross-sections of the liver.

9 . The device of claim 8 , wherein the processor is configured to extract features for the liver, blood vessels around the liver, and organs around the liver included in the ultrasound image.

10 . The device of claim 8 , wherein each of the plurality of preset cross-sections of the liver is at least one of an epigastrium longitudinal scan, an epigastrium transverse scan, a right subcostal scan-hepatic portal vein, a right subcostal-hepatic right lobe transverse scan, a liver dome scan, a right subcostal scan-hepatic vein, a gallbladder longitudinal scan, an extrahepatic bile duct longitudinal scan, an intercostal scan of right lobe of liver including right hepatic portal vein, a right posterior intercostal scan, or a right lower liver and right renal cortex scan.

11 . The device of claim 8 , wherein the processor is configured to determine one of the plurality of detailed sites according to Couinaud classification of hepatic subsegments.

12 . A non-transitory computer-readable recording medium storing a computer program, the computer program comprising instructions, when executed by a processor, to allow the processor to perform a method of determining an extent of liver examination, the method including:

receiving an ultrasound image taken of a region of a liver as input;

extracting features from the ultrasound image;

determining one of a plurality of preset cross-sections of the liver for which the ultrasound image was taken on the basis of the extracted features; and

determining a detailed site among a plurality of detailed sites of the liver examination taken in the ultrasound image on the basis of the determined one of the plurality of preset cross-sections of the liver.

13 . The non-transitory computer-readable recording medium of claim 12 , wherein in the extracting of the features, features for the liver, blood vessels around the liver, and organs around the liver included in the ultrasound image are extracted.

14 . The non-transitory computer-readable recording medium of claim 12 , wherein each of the plurality of preset cross-sections of the liver is at least one of an epigastrium longitudinal scan, an epigastrium transverse scan, a right subcostal scan-hepatic portal vein, a right subcostal-hepatic right lobe transverse scan, a liver dome scan, a right subcostal scan-hepatic vein, a gallbladder longitudinal scan, an extrahepatic bile duct longitudinal scan, an intercostal scan of right lobe of liver including right hepatic portal vein, a right posterior intercostal scan, or a right lower liver and right renal cortex scan.

15 . The non-transitory computer-readable recording medium of claim 12 , wherein in the determining the detailed site of the liver examination taken, one of the plurality of detailed sites is determined according to Couinaud classification of hepatic subsegments.