Ultrasound imaging device and operation method thereof
Provided is an ultrasound imaging device and an operation method thereof. An embodiment of the present disclosure provides an ultrasound imaging device comprising: an ultrasound probe; a display unit; a memory for storing at least one instruction; and a processor for executing the at least one instruction stored in the memory, wherein the processor: image-processes an echo signal to acquire multiple ultrasound images; calculates suitability indicating, as a numerical value, whether the multiple acquired ultrasound images are suitable as input images for a diagnosis algorithm for diagnosing a lesion; displays the calculated suitability on the display unit; and determines an input ultrasound image, which is to be input into the diagnosis algorithm, among the multiple ultrasound images based on the suitability.
1. An operation method of an ultrasound imaging device, comprising:
obtaining, by a processor, a plurality of ultrasound images by receiving an echo signal reflected from an object using an ultrasound probe and image-processing the received echo signal;
obtaining, by the processor, a setting value of a scan parameter of each of the plurality of ultrasound images
calculating, by the processor, suitability of each of the plurality of ultrasound images as an input image for a diagnostic algorithm for diagnosing a lesion based on the setting value of the scan parameter of each of the plurality of ultrasound images, wherein the diagnostic algorithm includes at least one of a hepatorenal index (HRI) algorithm, a tissue scatter distribution image (TSI) algorithm or a tissue attenuation image (TAI) algorithm, and wherein the suitability is a numerical value;
displaying, by the processor, the calculated suitability of each of the plurality of ultrasound images on a display of the ultrasound imaging device;
automatically freezing, by the processor, at least one ultrasound image among the plurality of ultrasound images based on the calculated suitability of the at least one ultrasound image being greater than a preset threshold;
determining, by the processor, the at least one frozen ultrasound image as an input ultrasound image to be input to the diagnostic algorithm among the plurality of ultrasound images;
inputting, by the processor, the determined input ultrasound image to the diagnostic algorithm; and
measuring, by the processor, a numerical value indicating at least one of a hepatorenal index, a degree of scattering, or a degree of attenuation of the determined input ultrasound image using the diagnostic algorithm.
2. The operation method of claim 1 , wherein the calculating of the suitability further comprises calculating, by the processor, the suitability of each of the plurality of ultrasound images for the diagnostic algorithm based on at least one of an anatomical view or, quality.
3. The operation method of claim 1 , wherein the calculating of the suitability further comprises calculating, by the processor, the suitability of each of the plurality of ultrasound images for the diagnostic algorithm based on at least one of echogenicity, an anatomical view, a motion artifact, or a rate of shadows of each of the plurality of ultrasound images.
4. The operation method of claim 1 , wherein the calculating of the suitability comprises calculating, by the processor, the suitability of each of the plurality of ultrasound images for the diagnostic algorithm by using a pre-trained deep neural network using the plurality of ultrasound images as input data,
wherein the pre-trained deep neural network comprises an artificial neural network trained by using a plurality of previously obtained ultrasound images as input data, a numerical value of the suitability as an output value and a numerical value obtained by normalizing a magnetic resonance imaging derived proton density fat fraction (MRI-PDFF) value or a value of a biopsy result as ground truth,
wherein the plurality of previously obtained ultrasound images, which are used as the input data for training the deep neural network, were acquired prior to obtaining the plurality of ultrasound images used as the input data for calculating the suitability of each of the plurality of ultrasound images for the diagnostic algorithm and stored in the memory of the ultrasound imaging device.
5. The operation method of claim 1 , wherein the determining of the ultrasound image to be input to the diagnostic algorithm among the plurality of ultrasound images comprises:
receiving, by the processor, a user input for determining the input ultrasound image to be input to the diagnostic algorithm among the plurality of ultrasound images based on all of the suitability of each of the plurality of ultrasound images being equal to or less than the preset threshold.
6. The operation method of claim 1 , further comprising:
loading, by the processor, at least one ultrasound image previously captured and stored in a memory of the ultrasound imaging device;
measuring, by the processor, a similarity between the at least one loaded ultrasound image and the plurality of obtained ultrasound images; and
determining, by the processor, at least one ultrasound image of which the measured similarity is greater than a threshold preset in relation to the similarity,
wherein the calculating of the suitability comprises calculating suitability of the at least one determined ultrasound image for the diagnostic algorithm.
7. An ultrasound imaging device comprising:
an ultrasound probe configured to transmit an ultrasound signal to an object and receive an echo signal reflected from the object;
a display;
a memory storing at least one instruction; and
a processor configured to execute the at least one instruction stored in the memory,
wherein the processor is configured to:
obtain a plurality of ultrasound images by image-processing the echo signal;
obtain a setting value of a scan parameter of each of the plurality of ultrasound images:
calculate suitability of each of the plurality of ultrasound images as an input image for a diagnostic algorithm for diagnosing a lesion based on the setting value of the scan parameter of each of the plurality of ultrasound images, wherein the diagnostic algorithm includes at least one of a hepatorenal index (HRI) algorithm, a tissue scatter distribution image (TSI) algorithm or a tissue attenuation image (TAI) algorithm, and wherein the suitability is a numerical value;
control the display to display the calculated suitability of each of the plurality of ultrasound images on the display;
based on the calculated suitability of at least one ultrasound image being greater than a preset threshold, automatically freezing the at least one ultrasound image among the plurality of ultrasound images;
determine the at least one frozen ultrasound image as an input ultrasound image to be input to the diagnostic algorithm among the plurality of ultrasound images;
input the determined input ultrasound image to the diagnostic algorithm; and
measure a numerical value indicating at least one of a hepatorenal index, a degree of scattering, or a degree of attenuation of the determined input ultrasound image using the diagnostic algorithm.
8. The ultrasound imaging device of claim 7 , wherein the processor is further configured to calculate the suitability of each of the plurality of ultrasound images for the diagnostic algorithm based on at least one of an anatomical view or, quality.
9. The ultrasound imaging device of claim 7 , wherein the processor is further configured to calculate the suitability of each of the plurality of ultrasound images for the diagnostic algorithm based on at least one of echogenicity, an anatomical view, a motion artifact, or a rate of shadows of each of the plurality of ultrasound images.
10. The ultrasound imaging device of claim 7 , wherein the processor is configured to calculate the suitability of each of the plurality of ultrasound images for the diagnostic algorithm by using a pre-trained deep neural network using the plurality of ultrasound images as input data, and
wherein the pre-trained deep neural network comprises an artificial neural network trained by using a plurality of previously obtained ultrasound images as input data, a numerical value of the suitability as an output value and a numerical value obtained by normalizing a magnetic resonance imaging derived proton density fat fraction (MRI-PDFF) value or a value of a biopsy result as ground truth,
wherein the plurality of previously obtained ultrasound images, which are used as the input data for training the deep neural network, were acquired prior to obtaining the plurality of ultrasound images used as the input data for calculating the suitability of each of the plurality of ultrasound images for the diagnostic algorithm and stored in the memory of the ultrasound imaging device.
11. The ultrasound imaging device of claim 7 , further comprising a user inputter including at least one of a button, a touch pad, or a control panel, and
wherein the processor is further configured to, based on all of the suitability of each of the plurality of ultrasound images being equal to or less than the preset threshold obtain a user input for determining the input ultrasound image to be input to the diagnostic algorithm among the plurality of ultrasound images through the user inputter.
12. The ultrasound imaging device of claim 7 , wherein the processor is configured to, based on all of the suitability of each of the plurality of ultrasound images being equal to or less than the preset threshold, control the display to display a user interface (UI) for receiving the user input for determining the input ultrasound image to be input to the diagnostic algorithm among the plurality of ultrasound images through the user inputter.
13. One or more non-transitory computer-readable recording media storing computer-executable instructions that, when executed by one or more processors individually or collectively, cause the one or more processors to perform the method of claim 1 in a computer.