Back to results
US 12,575,785 B2Granted
Method, apparatus and computer program for reading rotator cuff tear state or muscle fat degeneration disorder based on artificial intelligence
AssigneeSeeAnn Solution Co., Ltd.
InventorsAnna Seo, Youngjin Jeong, Seokwon Chung
Life of this patent
Estimating the term…
Abstract
Provided is a method performed by an apparatus for reading a shoulder disorder, the method including acquiring medical data including a shoulder image; preprocessing the acquired medical data; inputting the preprocessed medical data into a pre-trained neural network model to read a tear state of a rotator cuff; and generating result information on the medical data based on the read tear state of the rotator cuff.
Claims13
A method of reading a shoulder disorder, which is a method performed by an apparatus for reading a shoulder disorder, the method comprising:
- acquiring medical data including a shoulder image;
- preprocessing the acquired medical data;
- inputting the preprocessed medical data into a pre-trained neural network model, and performing reading of a tear state of a rotator cuff or reading of a fat degeneration state of the rotator cuff,
- wherein the reading of the tear state of the rotator cuff comprises:
- calculating a shading change rate of each region of the shoulder image;
- detecting a target region in which the calculated shading change rate is greater than or equal to a reference value;
- performing a first segmentation of the target region from the shoulder image;
- performing a second segmentation of the target region into a plurality of regions by dividing the target region in an X-axis direction or a Y-axis direction;
- and
- reading the tear state of the rotator cuff in each of the plurality of regions of the second segmentation, and
- wherein the reading of the fat degeneration state of the rotator cuff comprises:
- calculating the shading change rate of each region of the shoulder image;
- detecting the target region in which the calculated shading change rate is greater than or equal to the reference value;
- performing the first segmentation of the target region from the shoulder image;
- performing a third segmentation of the target region into a plurality of regions including a supraspinatus (SS) region, an infraspinatus (IS) region, a teres minor (TM) region, and a subscapularis (Su) region;
- and
- reading the fat degeneration state of the rotator cuff in each of the plurality of regions of the third segmentation;
- and
- generating result information on the medical data based on the read tear state of the rotator cuff or the read fat degeneration state of the rotator cuff.
16 more elements
A non-transitory computer readable recording medium storing a computer program, the computer program that, when executed by one or more processors, performs the following operations for reading a shoulder disorder, the operations comprising:
- an operation of acquiring medical data including a shoulder image;
- an operation of preprocessing the acquired medical data;
- an operation of inputting the preprocessed medical data into a pre-trained neural network model, and performing reading of a tear state of a rotator cuff or reading of a fat degeneration of the rotator cuff,
- wherein the reading of the tear state of the rotator cuff comprises:
- calculating a shading change rate of each region of the shoulder image;
- detecting a target region in which the calculated shading change rate is greater than or equal to a reference value;
- performing a first segmentation of the target region from the shoulder image;
- performing a second segmentation of the target region into a plurality of regions by dividing the target region in an X-axis direction or a Y-axis direction;
- and
- reading the tear state of the rotator cuff in each of the plurality of regions of the second segmentation, and
- wherein the reading of the fat degeneration state of the rotator cuff comprises:
- calculating the shading change rate of each region of the shoulder image;
- detecting the target region in which the calculated shading change rate is greater than or equal to the reference value;
- performing the first segmentation of the target region from the shoulder image;
- performing a third segmentation of the target region into a plurality of regions including a supraspinatus (SS) region, an infraspinatus (IS) region, a teres minor (TM) region, and a subscapularis (Su) region;
- and
- reading the fat degeneration state of the rotator cuff in each of the plurality of regions of the third segmentation;
- and
- an operation of generating result information on the medical data based on the read tear state of the rotator cuff or the read fat degeneration state of the rotator cuff.
16 more elements
A computing device for providing a method of reading a shoulder disorder, the computing device comprising:
- a processor including one or more cores;
- and
- a memory,
- wherein the processor is configured to:
- acquire medical data including a shoulder image;
- preprocess the acquired medical data;
- input the preprocessed medical data into a pre-trained neural network model, and perform reading of a tear state of a rotator cuff or reading of a fat degeneration of the rotator cuff,
- wherein the reading of the tear state of the rotator cuff comprises:
- calculating a shading change rate of each region of the shoulder image;
- detecting a target region in which the calculated shading change rate is greater than or equal to a reference value;
- performing a first segmentation of the target region from the shoulder image;
- performing a second segmentation of the target region into a plurality of regions by dividing the target region in an X-axis direction or a Y-axis direction;
- and
- reading the tear state of the rotator cuff in each of the plurality of regions of the second segmentation, and
- wherein the reading of the fat degeneration state of the rotator cuff comprises:
- calculating the shading change rate of each region of the shoulder image;
- detecting the target region in which the calculated shading change rate is greater than or equal to the reference value;
- performing the first segmentation of the target region from the shoulder image;
- performing a third segmentation of the target region into a plurality of regions including a supraspinatus (SS) region, an infraspinatus (IS) region, a teres minor (TM) region, and a subscapularis (Su) region;
- and
- reading the fat degeneration state of the rotator cuff in each of the plurality of regions of the third segmentation;
- and
- generate result information on the medical data based on the read tear state of the rotator cuff or the read fat degeneration state of the rotator cuff.
20 more elements
Dependencies are inferred from the claim text.