CN113299391A - Risk assessment method for remote thyroid nodule ultrasonic image - Google Patents
Risk assessment method for remote thyroid nodule ultrasonic image Download PDFInfo
- Publication number
- CN113299391A CN113299391A CN202110567911.2A CN202110567911A CN113299391A CN 113299391 A CN113299391 A CN 113299391A CN 202110567911 A CN202110567911 A CN 202110567911A CN 113299391 A CN113299391 A CN 113299391A
- Authority
- CN
- China
- Prior art keywords
- thyroid nodule
- area
- grade
- nodule
- thyroid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 208000009453 Thyroid Nodule Diseases 0.000 title claims abstract description 439
- 208000024770 Thyroid neoplasm Diseases 0.000 title claims abstract description 425
- 238000012502 risk assessment Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000011156 evaluation Methods 0.000 claims abstract description 132
- 238000003745 diagnosis Methods 0.000 claims abstract description 37
- 210000001685 thyroid gland Anatomy 0.000 claims abstract description 13
- 238000005070 sampling Methods 0.000 claims description 109
- 238000012545 processing Methods 0.000 claims description 81
- 238000012937 correction Methods 0.000 claims description 68
- 239000011159 matrix material Substances 0.000 claims description 34
- 238000002604 ultrasonography Methods 0.000 claims description 25
- 230000002308 calcification Effects 0.000 claims description 16
- 238000012986 modification Methods 0.000 claims description 6
- 230000004048 modification Effects 0.000 claims description 6
- 239000007787 solid Substances 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000012285 ultrasound imaging Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 201000002510 thyroid cancer Diseases 0.000 description 3
- 206010028980 Neoplasm Diseases 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 208000024799 Thyroid disease Diseases 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000011337 individualized treatment Methods 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 208000021510 thyroid gland disease Diseases 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Clinical applications
- A61B8/0833—Clinical applications involving detecting or locating foreign bodies or organic structures
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention provides a risk assessment method for a remote thyroid nodule ultrasonic image, which comprises the steps of obtaining an ultrasonic image of a thyroid part and uploading the ultrasonic image to a cloud platform; after the cloud platform acquires the ultrasonic image, judging whether thyroid nodules exist in the ultrasonic image; a sample evaluation value C is set in the cloud platform, the cloud platform diagnoses the grade of the thyroid nodule according to the related information of the thyroid nodule, and risk evaluation is carried out on the thyroid nodule after grade diagnosis through the sample evaluation value C; the cloud platform returns the results of the thyroid nodule diagnosis and risk assessment to the PACS system in the hospital. According to the invention, the cloud platform is connected with the PACS system of the hospital, after the ultrasonic image of the thyroid part is obtained, the ultrasonic image is uploaded into the cloud platform, and the thyroid nodule diagnosis and risk assessment are carried out on the ultrasonic image through the cloud platform, so that the diagnosis efficiency can be greatly improved, and the misdiagnosis condition during artificial diagnosis is avoided.
Description
Technical Field
The invention relates to the technical field of ultrasonic images, in particular to a risk assessment method of a remote thyroid nodule ultrasonic image.
Background
At present, the incidence rate of thyroid cancer is rapidly increased in recent years on a global scale, and the incidence rate of thyroid cancer of women in urban areas of China is 4 th of all malignant tumors of women according to data of national tumor registration centers. Thyroid cancer continues to grow at a rate of 20% per year in our country. Ultrasonic examination is the first choice of image examination means in the thyroid disease diagnostic system. In general population, the detection rate of thyroid nodules can reach 20-76% by using ultrasonic examination, and 5-15% of the nodules are malignant. With the advent of accurate medicine and big data, patient uniqueness and nodule diversity determine tumor heterogeneity necessitating individualized treatment. Whether abroad or domestically, the work duties of the sonographer include reporting a diagnosis, selecting a review, reporting a consultation, inquiring information, and the like. However, the foreign ultrasound department belongs to the imaging department, the working personnel are divided into ultrasound technicians and sonographers, the technicians are responsible for scanning examination and data collection of patients, the physicians carry out diagnosis and consultation, the two departments are clear, the workload and the working intensity are relatively low, and the requirement on timeliness of a report is not as high as that in China. The domestic ultrasound department is an independent platform department, and as the ultrasonic examination has the advantages of convenience, economy, no damage, no radiation, quick report and the like, the requirements of clinicians and patients on ultrasonic examination and diagnosis are increased rapidly, so that the ubiquitous ultrasonic medical data information quantity is large, the workload, the working intensity and the responsibility risk of the sonographer are large, and meanwhile, the ultrasonic diagnosis is very dependent on the personal level, the clinical experience and the ultrasonic machine type definition of the sonographer. And high-level sonographers in China are mostly concentrated in large-scale three hospitals, and the problems that the diagnosis levels are different among different regions and hospitals, the subjective difference of the diagnosis levels is large, the quality is lack of unified standards and the like are solved.
How to rapidly and effectively diagnose and evaluate thyroid nodules becomes a problem to be solved urgently.
Disclosure of Invention
In view of this, the invention provides a risk assessment method for a remote thyroid nodule ultrasonic image, and aims to solve the problem of low diagnosis efficiency caused by how to reduce the dependence of ultrasonic diagnosis on an ultrasonic doctor during the ultrasonic diagnosis of thyroid nodules.
In one aspect, the invention provides a risk assessment method for remote thyroid nodule ultrasonic image, which comprises the following steps:
step S1: acquiring an ultrasonic image of a thyroid part, and uploading the ultrasonic image to a cloud platform;
step S2: after the cloud platform acquires the ultrasonic image, data processing is carried out on the ultrasonic image through a processing unit arranged in the cloud platform so as to judge whether thyroid nodules exist in the ultrasonic image:
if the thyroid nodule does not exist, the cloud platform makes a diagnosis of the thyroid gland normal;
if the thyroid nodule exists, the cloud platform acquires information related to the thyroid nodule in the ultrasonic image and carries out subsequent steps;
step S3: a sample evaluation value C is set in the cloud platform, the cloud platform diagnoses the grade of the thyroid nodule according to the related information of the thyroid nodule, and risk evaluation is carried out on the thyroid nodule after grade diagnosis through the sample evaluation value C;
step S4: the cloud platform outputs the diagnosis and risk assessment results of the thyroid nodules, and transmits the diagnosis and risk assessment results of the thyroid nodules back to a PACS (Picture Archiving and Communication Systems) of a hospital;
in step S3, after the processing unit detects the thyroid nodule from the ultrasound image, the processing module is configured to determine a property B and an aspect ratio D of the thyroid nodule, acquire an echo value Δ a of the thyroid nodule, establish a preset echo value matrix a, and set a (a 1, a2, A3, a 4), where a1 is a first preset echo value, a2 is a second preset echo value, A3 is a third preset echo value, a4 is a fourth preset echo value, and a1 < a2 < A3 < a 4; the processing module judges the grade of the thyroid nodule according to the character B, the aspect ratio D and the echo value delta A of the thyroid nodule:
when A3 is more than or equal to delta A and less than or equal to A4 or delta A is more than or equal to A4, if the property B of the thyroid nodule is cystic nodule and the aspect ratio D of the thyroid nodule is less than 1, judging the grade of the thyroid nodule to be first grade, and calculating a first sampling evaluation value C01 of the thyroid nodule;
when A2 is larger than delta A and smaller than A3, if the property B of the thyroid nodule is cystic nodule and the aspect ratio D of the thyroid nodule is smaller than 1, judging the grade of the thyroid nodule to be two-grade, and calculating a second sampling evaluation value C02 of the thyroid nodule;
when A1 is larger than delta A and smaller than A2, if the property B of the thyroid nodule is a real nodule and the aspect ratio D of the thyroid nodule is smaller than 1, judging the grade of the thyroid nodule to be three-grade, and calculating a third sampling evaluation value C03 of the thyroid nodule;
when the delta A is less than or equal to A1, if the property B of the thyroid nodule is a solid nodule and the aspect ratio D of the thyroid nodule is more than 1, judging that the grade of the thyroid nodule is four grades, and calculating a fourth sampling evaluation value C04 of the thyroid nodule;
when the ith sampling evaluation value C0i is less than C, the grade of the thyroid nodule is reduced by one grade, the lowest grade of the thyroid nodule is one grade, and the thyroid nodule is judged to be a low-risk nodule, when the ith sampling evaluation value C0i is greater than C, the grade of the thyroid nodule is increased by one grade, and the thyroid nodule is judged to be a high-risk nodule, i =1, 2, 3, 4.
Further, the i-th sample evaluation value C0i = Δ a/a0+ B/B0+ D/D0+ E/E0+ F/F0, the sample evaluation value C = Δ Aa/a0+ Bb/B0+ Dd/D0+ Ee/E0+ Ff/F0, where Δ a is an echo value of a thyroid nodule, a0 a preset standard echo value of a thyroid nodule, Δ Aa is a preset echo value of a thyroid nodule, B is a trait of a thyroid nodule, B =1 when the trait of the thyroid nodule is a cystic nodule, B =2 when the trait of the thyroid nodule is a solid nodule, B0=1, Bb =1.5, D is an aspect ratio of the thyroid nodule, D is a preset standard aspect ratio D0=1 of the thyroid nodule, Dd =0.5, E is an area percentage of the thyroid gland, E0=10%, E =20%, f is the ratio of the circumference to the area of the thyroid nodule, F0 is a preset standard ratio of the circumference to the area of the thyroid nodule, and Ff is a preset ratio of the circumference to the area of the thyroid nodule.
Further, the processing module obtains an area of the thyroid nodule S1 and a calcified area of the thyroid nodule S2, E = S2/S1 x 100% after the thyroid nodule is detected;
the processing module adjusts the grade of the thyroid nodule according to the calcified area percentage E of the thyroid nodule and the standard calcified area percentage E0 of the preset thyroid nodule,
when E is larger than E0, the grade of the thyroid nodule is judged to be increased by one level;
when E is less than E0, reducing the grade of the thyroid nodule judged by one grade;
when E = E0, the grade of the thyroid nodule is not adjusted.
Further, the processing module is further configured to obtain a circumference Z of the thyroid nodule after the thyroid nodule is detected, and calculate a ratio F, F = Z/S1 of the circumference to the area of the thyroid nodule according to a ratio between the circumference Z of the thyroid nodule and the area of the thyroid nodule S1, where a preset area S3 and a preset circumference Z1 of the thyroid nodule are set in the processing module, and a preset standard ratio F0= Z1/S3 of the circumference to the area of the thyroid nodule;
the processing module adjusts the grade of the thyroid nodule after the calcified area percentage of the thyroid nodule is adjusted again according to the relation between the ratio F of the perimeter to the area of the thyroid nodule and a preset standard ratio F0 of the perimeter to the area of the thyroid nodule:
when E is larger than E0, after the judged grade of the thyroid nodule is adjusted to one grade, if F is larger than F0, the grade of the thyroid nodule is adjusted to one grade, if F is smaller than F0, the grade of the thyroid nodule is reduced by one grade, and if F = F0, the grade of the thyroid nodule is not adjusted;
when E is less than E0, after the grade of the thyroid nodule is judged to be reduced by one grade, if F is greater than F0, the grade of the thyroid nodule is increased by one grade, if F is less than F0, the grade of the thyroid nodule is reduced by one grade, and if F = F0, the grade of the thyroid nodule is not adjusted;
when E = E0, the grade of the thyroid nodule is not adjusted, if F > F0, the grade of the thyroid nodule is increased by one grade, if F < F0, the grade of the thyroid nodule is decreased by one grade, and if F = F0, the grade of the thyroid nodule is not adjusted.
Further, a compensation coefficient matrix K is set in the processing module, and the processing module compensates the ith sampling evaluation value C0i by each compensation coefficient in the compensation coefficient matrix K.
Further, for the compensation coefficient matrix K, K (K1, K2, K3, K4) is set, where K1 is a first compensation coefficient, K2 is a second compensation coefficient, K3 is a third compensation coefficient, K4 is a fourth compensation coefficient, and 1 < K1 < K2 < K3 < K4 < 1.5; a preset calcification area percentage matrix Ee0 of the thyroid nodule is also set in the processing module, and Ee0(Ee1, Ee2, Ee3 and Ee4) is set, wherein Ee1 is a first preset calcification area percentage, Ee2 is a second preset calcification area percentage, Ee3 is a third preset calcification area percentage, Ee4 is a fourth preset calcification area percentage, and Ee1 < Ee2 < Ee3 < Ee 4;
the processing module determines a compensation coefficient according to a relation between a preset calcified area percentage Ee of the thyroid nodule and each preset calcified area percentage, so as to compensate the ith sampling evaluation value C0 i:
when Ee is less than Ee1, selecting the first compensation coefficient K1 to compensate the ith sampling evaluation value C0i, wherein the compensated ith sampling evaluation value C0i is C0i × K1;
when Ee1 is not less than Ee < Ee2, selecting the second compensation coefficient K2 to compensate the ith sampling evaluation value C0i, wherein the compensated ith sampling evaluation value C0i is C0i xK 2;
when Ee2 is not less than Ee < Ee3, selecting the third compensation coefficient K3 to compensate the ith sampling evaluation value C0i, wherein the compensated ith sampling evaluation value C0i is C0i xK 3;
and when the Ee3 is not less than the Ee < Ee4, selecting the fourth compensation coefficient K4 to compensate the ith sampling evaluation value C0i, wherein the compensated ith sampling evaluation value C0i is C0i xK 4.
Further, a correction coefficient matrix T is set in the processing module, and the processing module corrects the ith sampling evaluation value C0i compensated by the compensation coefficient matrix K by each correction coefficient in the correction coefficient matrix T.
Further, for the correction coefficient matrix T, T (T1, T2, T3, T4) is set, T1 is a first correction coefficient, T2 is a second correction coefficient, T3 is a third correction coefficient, T4 is a fourth correction coefficient, and 0.9 < T1 < T2 < 1 < T3 < T4 < 1.1; a preset ratio matrix Ff0 of the circumference to the area of the thyroid nodule is further set in the processing module, and Ff0(Ff1, Ff2, Ff3 and Ff4) is set, wherein Ff1 is the ratio of the first preset circumference to the area, Ff2 is the ratio of the second preset circumference to the area, Ff3 is the ratio of the third preset circumference to the area, Ff4 is the ratio of the fourth preset circumference to the area, and Ff1 < Ff2 < Ff3 < Ff 4;
the processing module determines a correction coefficient according to a relation between a preset ratio Ff of the circumference to the area of the thyroid nodule and a ratio of each preset circumference to the area, so as to correct the ith sampling evaluation value C0i compensated by the compensation coefficient:
when Ff is less than Ff1, selecting the first correction coefficient T1 to correct the compensated ith sampling evaluation value C0i × K1, and correcting the corrected ith sampling evaluation value C0i × K1 × T1;
when the Ff1 is not less than or equal to Ff < Ff2, selecting the second correction coefficient T2 to correct the compensated ith sampling evaluation value C0i × K2, and correcting the corrected ith sampling evaluation value C0i × K2 × T2;
when the Ff2 is not less than or equal to Ff < Ff3, selecting the third correction coefficient T3 to correct the compensated ith sampling evaluation value C0i × K3, and correcting the corrected ith sampling evaluation value C0i × K3 × T3;
and when the Ff3 is not less than the Ff < Ff4, selecting the fourth correction coefficient T4 to correct the compensated ith sampling evaluation value C0i × K4, and correcting the corrected ith sampling evaluation value C0i × K4 × T4.
Furthermore, a preset thyroid nodule area correction matrix P0 is set in the processing module, and P0(P1, P2, P3, P4) is set, wherein P1 is a first preset area correction coefficient, P2 is a second preset area correction coefficient, P3 is a third preset area correction coefficient, P4 is a fourth preset area correction coefficient, and 1 < P1 < P2 < P3 < P4 < 1.2;
the processing module is further configured to obtain an average value Δ q of the gray values of the thyroid nodule, a standard gray average value q0 of the thyroid nodule is preset in the processing module, and the processing module selects a preset area correction coefficient to correct the area S1 of the thyroid nodule according to a relationship between the average value Δ q of the gray values and the standard gray average value q0, and a relationship between a ratio F of the circumference to the area of the thyroid nodule and a preset standard ratio F0 of the circumference to the area of the thyroid nodule,
when F is less than F0 and Δ q is more than q0, selecting the first preset area correction coefficient P1 to correct the area S1 of the thyroid nodule, wherein the corrected area of the thyroid nodule is S1 × P1;
when F is less than F0 and Δ q is less than or equal to q0, selecting the second preset area correction coefficient P2 to correct the area S1 of the thyroid nodule, wherein the corrected area of the thyroid nodule is S1 × P2;
when F is larger than F0 and Δ q is larger than q0, selecting the third preset area correction coefficient P3 to correct the area S1 of the thyroid nodule, wherein the corrected area of the thyroid nodule is S1 × P3;
when F is larger than F0 and Δ q is less than or equal to q0, selecting the fourth preset area correction coefficient P4 to correct the area S1 of the thyroid nodule, wherein the corrected area of the thyroid nodule is S1 × P4;
after the thyroid nodule corrected area was determined, E, E0, Ee, F0 and Ff were calculated using the thyroid nodule corrected area as S1 × Pi as the thyroid nodule area, i =1, 2, 3, 4.
Compared with the prior art, the cloud platform is connected with the PACS system of the hospital, when the PACS system of the hospital acquires the ultrasonic image of the thyroid part, the ultrasonic image is uploaded into the cloud platform, and the ultrasonic image is subjected to thyroid nodule diagnosis and risk assessment through the cloud platform, so that the diagnosis efficiency can be greatly improved, and the misdiagnosis condition during artificial diagnosis is avoided.
Furthermore, the ratio summation calculation is carried out between the detected properties, echo values, aspect ratios, calcified areas and the ratios of circumferences to areas of the thyroid nodules and preset standard values respectively to obtain sampling evaluation values, the sample evaluation values are calculated through the sum of the ratios between the corresponding preset values and the preset standard values, and the risks of the thyroid nodules are estimated through the size relationship between the sampling evaluation values and the calculated sample evaluation values, so that the accuracy of risk estimation can be greatly improved.
Furthermore, the grade of the thyroid nodule is adjusted according to the calcified area percentage of the thyroid nodule, so that the grade of the thyroid nodule can be timely adjusted when the calcified area of the thyroid nodule exceeds a preset standard value, and the accuracy of a diagnosis result and the accuracy of subsequent risk assessment are improved.
Further, the grade of the thyroid nodule is adjusted again according to the relation between the ratio of the circumference to the area of the thyroid nodule and the preset standard ratio, so that the grade judgment accuracy of the thyroid nodule can be greatly improved, and the accuracy of a subsequent risk assessment result is greatly improved.
Further, corresponding compensation coefficients are selected according to the percentage of calcified area of the thyroid nodule to compensate the sampling evaluation value, an influence relation is established between the sampling evaluation value and the percentage of calcified area of the thyroid nodule, namely, the percentage of calcified area of the thyroid nodule influences the final sampling evaluation value, so that the final result of the sampling evaluation value is more accurate, the sampling evaluation value can accurately reflect the disease degree of the thyroid nodule, and the risk degree of the thyroid nodule can be more accurately evaluated through the sampling evaluation value.
The correction coefficient is determined according to the relationship between the preset ratio Ff of the circumference to the area of the thyroid nodule and the ratio of each preset circumference to the area, so that the ith sampling evaluation value C0i compensated by the compensation coefficient is corrected, and after the compensated ith sampling evaluation value C0i is corrected by the correction coefficient, the calculation of the sampling evaluation value can be more accurate, the acquisition of the sampling evaluation value is influenced by the ratio of the circumference to the area of the thyroid nodule, the thyroid nodule can be effectively evaluated according to the complexity of the contour of the thyroid nodule, and the accuracy of the risk evaluation result of the thyroid nodule can be improved.
Furthermore, the accuracy of the results of the ratio F of the circumference to the area of the thyroid nodule, the preset standard ratio F0 of the circumference to the area of the thyroid nodule, the preset ratio Ff of the circumference to the area of the thyroid nodule, the calcified area percentage E of the thyroid nodule, the standard calcified area percentage E0 of the thyroid nodule and the preset calcified area percentage Ee of the thyroid nodule can be greatly improved by correcting the area of the thyroid nodule, so that the subsequent diagnosis and the apple efficiency can be improved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart of a risk assessment method for remote thyroid nodule ultrasound images according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a risk assessment system for remote thyroid nodule ultrasound images according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
Referring to fig. 1, the present embodiment provides a risk assessment method for remote thyroid nodule ultrasound image, including the following steps:
step S1: acquiring an ultrasonic image of a thyroid part, and uploading the ultrasonic image to a cloud platform;
step S2: after the cloud platform acquires the ultrasonic image, data processing is carried out on the ultrasonic image through a processing unit arranged in the cloud platform so as to judge whether thyroid nodules exist in the ultrasonic image:
if the thyroid nodule does not exist, the cloud platform makes a diagnosis of the thyroid gland normal;
if the thyroid nodule exists, the cloud platform acquires information related to the thyroid nodule in the ultrasonic image and carries out subsequent steps;
step S3: a sample evaluation value C is set in the cloud platform, the cloud platform diagnoses the grade of the thyroid nodule according to the related information of the thyroid nodule, and risk evaluation is carried out on the thyroid nodule after grade diagnosis through the sample evaluation value C;
step S4: the cloud platform outputs the diagnosis and risk assessment results of the thyroid nodules, and returns the diagnosis and risk assessment results of the thyroid nodules to a PACS (Picture archiving and communication System) of a hospital;
in step S3, after the processing unit detects the thyroid nodule from the ultrasound image, the processing module is configured to determine a property B and an aspect ratio D of the thyroid nodule, acquire an echo value Δ a of the thyroid nodule, establish a preset echo value matrix a, and set a (a 1, a2, A3, a 4), where a1 is a first preset echo value, a2 is a second preset echo value, A3 is a third preset echo value, a4 is a fourth preset echo value, and a1 < a2 < A3 < a 4; the processing module judges the grade of the thyroid nodule according to the character B, the aspect ratio D and the echo value delta A of the thyroid nodule:
when A3 is more than or equal to delta A and less than or equal to A4 or delta A is more than or equal to A4, if the property B of the thyroid nodule is cystic nodule and the aspect ratio D of the thyroid nodule is less than 1, judging the grade of the thyroid nodule to be first grade, and calculating a first sampling evaluation value C01 of the thyroid nodule;
when A2 is larger than delta A and smaller than A3, if the property B of the thyroid nodule is cystic nodule and the aspect ratio D of the thyroid nodule is smaller than 1, judging the grade of the thyroid nodule to be two-grade, and calculating a second sampling evaluation value C02 of the thyroid nodule;
when A1 is larger than delta A and smaller than A2, if the property B of the thyroid nodule is a real nodule and the aspect ratio D of the thyroid nodule is smaller than 1, judging the grade of the thyroid nodule to be three-grade, and calculating a third sampling evaluation value C03 of the thyroid nodule;
when the delta A is less than or equal to A1, if the property B of the thyroid nodule is a solid nodule and the aspect ratio D of the thyroid nodule is more than 1, judging that the grade of the thyroid nodule is four grades, and calculating a fourth sampling evaluation value C04 of the thyroid nodule;
when the ith sampling evaluation value C0i is less than C, the grade of the thyroid nodule is reduced by one grade, the lowest grade of the thyroid nodule is one grade, and the thyroid nodule is judged to be a low-risk nodule, when the ith sampling evaluation value C0i is greater than C, the grade of the thyroid nodule is increased by one grade, and the thyroid nodule is judged to be a high-risk nodule, i =1, 2, 3, 4.
Specifically, after the processing unit detects the thyroid nodule from the ultrasound image, the processing module is configured to obtain calcification information of the thyroid nodule and information of a perimeter and an area of the thyroid nodule.
It can be seen that, this embodiment is connected with the PACS system of hospital through setting up the cloud platform, and after the PACS system of hospital obtained the ultrasound image of thyroid gland position, upload the ultrasound image to the cloud platform in, carry out thyroid nodule through the cloud platform to the ultrasound image and diagnose and risk assessment to can greatly improve diagnostic efficiency, avoid the misdiagnosis condition when the artificial diagnosis takes place.
Specifically, the i-th sampling evaluation value C0i = Δ a/a0+ B/B0+ D/D0+ E/E0+ F/F0, the sample evaluation value C = Δ Aa/a0+ Bb/B0+ Dd/D0+ Ee/E0+ Ff/F0, where Δ a is an echo value of a thyroid nodule, a0 a preset standard echo value of a thyroid nodule, Δ Aa a preset echo value of a thyroid nodule, B is a trait of a thyroid nodule, B =1 when the trait of a thyroid nodule is a cystic nodule, B =2 when the trait of a thyroid nodule, B0=1, Bb =1.5, D is an aspect ratio of a thyroid nodule, a preset standard aspect ratio D0=1 of a thyroid nodule, a preset aspect ratio Dd =0.5, E is an area percentage of a thyroid gland, E = 4610%, Ee =20%, f is the ratio of the circumference to the area of the thyroid nodule, F0 is a preset standard ratio of the circumference to the area of the thyroid nodule, and Ff is a preset ratio of the circumference to the area of the thyroid nodule.
Specifically, the processing unit acquires the calcified area information of the thyroid nodule after acquiring the area information of the thyroid nodule, acquires the calcified area percentage E of the thyroid nodule according to the calcified area of the thyroid nodule and the area of the thyroid nodule, and presets the standard calcified area percentage E0 of the thyroid nodule and the preset calcified area percentage Ee of the thyroid nodule.
It can be seen that the detected characteristics, echo value, aspect ratio, calcified area and ratio of perimeter to area of the thyroid nodule are respectively summed with preset standard values to obtain a sampling evaluation value, a sample evaluation value is calculated through the sum of the ratios of the corresponding preset values and the preset standard values, and the risk of the thyroid nodule is estimated through the magnitude relation between the sampling evaluation value and the calculated sample evaluation value, so that the accuracy of risk estimation can be greatly improved.
Specifically, the processing module acquires an area of the thyroid nodule S1 and a calcified area of the thyroid nodule S2, E = S2/S1 × 100%, after the detected thyroid nodule;
the processing module adjusts the grade of the thyroid nodule according to the calcified area percentage E of the thyroid nodule and the standard calcified area percentage E0 of the preset thyroid nodule,
when E is larger than E0, the grade of the thyroid nodule is judged to be increased by one level;
when E is less than E0, reducing the grade of the thyroid nodule judged by one grade;
when E = E0, the grade of the thyroid nodule is not adjusted.
Specifically, the grade of the thyroid nodule is the lowest grade, and when the grade of the thyroid nodule is the first grade, the thyroid nodule is adjusted to be increased only when the thyroid nodule meets the increase adjustment condition, and the thyroid nodule is not subjected to the grade reduction operation.
It can be seen that the grade of the thyroid nodule is adjusted according to the calcified area percentage of the thyroid nodule, so that the grade of the thyroid nodule can be timely adjusted when the calcified area of the thyroid nodule exceeds a preset standard value, and the accuracy of a diagnosis result and the accuracy of subsequent risk assessment are improved.
Specifically, the processing module is further configured to obtain a circumference Z of the thyroid nodule after the thyroid nodule is detected, and calculate a ratio F, F = Z/S1 of the circumference to the area of the thyroid nodule according to a ratio between the circumference Z of the thyroid nodule and an area S1 of the thyroid nodule, a preset area S3 and a preset circumference Z1 of the thyroid nodule are set in the processing module, and a preset standard ratio F0= Z1/S3 of the circumference to the area of the thyroid nodule;
the processing module adjusts the grade of the thyroid nodule after the calcified area percentage of the thyroid nodule is adjusted again according to the relation between the ratio F of the perimeter to the area of the thyroid nodule and a preset standard ratio F0 of the perimeter to the area of the thyroid nodule:
when E is larger than E0, after the judged grade of the thyroid nodule is adjusted to one grade, if F is larger than F0, the grade of the thyroid nodule is adjusted to one grade, if F is smaller than F0, the grade of the thyroid nodule is reduced by one grade, and if F = F0, the grade of the thyroid nodule is not adjusted;
when E is less than E0, after the grade of the thyroid nodule is judged to be reduced by one grade, if F is greater than F0, the grade of the thyroid nodule is increased by one grade, if F is less than F0, the grade of the thyroid nodule is reduced by one grade, and if F = F0, the grade of the thyroid nodule is not adjusted;
when E = E0, the grade of the thyroid nodule is not adjusted, if F > F0, the grade of the thyroid nodule is increased by one grade, if F < F0, the grade of the thyroid nodule is decreased by one grade, and if F = F0, the grade of the thyroid nodule is not adjusted.
It can be seen that the grade of the thyroid nodule is adjusted again according to the relation between the ratio of the circumference to the area of the thyroid nodule and the preset standard ratio, so that the grade judgment accuracy of the thyroid nodule can be greatly improved, and the accuracy of a subsequent risk assessment result is greatly improved.
Specifically, a compensation coefficient matrix K is set in the processing module, and the processing module compensates the i-th sampling evaluation value C0i by each compensation coefficient in the compensation coefficient matrix K.
Specifically, K (K1, K2, K3, K4) is set for the compensation coefficient matrix K, where K1 is a first compensation coefficient, K2 is a second compensation coefficient, K3 is a third compensation coefficient, K4 is a fourth compensation coefficient, and 1 < K1 < K2 < K3 < K4 < 1.5; a preset calcification area percentage matrix Ee0 of the thyroid nodule is also set in the processing module, and Ee0(Ee1, Ee2, Ee3 and Ee4) is set, wherein Ee1 is a first preset calcification area percentage, Ee2 is a second preset calcification area percentage, Ee3 is a third preset calcification area percentage, Ee4 is a fourth preset calcification area percentage, and Ee1 < Ee2 < Ee3 < Ee 4;
the processing module determines a compensation coefficient according to a relation between a preset calcified area percentage Ee of the thyroid nodule and each preset calcified area percentage, so as to compensate the ith sampling evaluation value C0 i:
when Ee is less than Ee1, selecting the first compensation coefficient K1 to compensate the ith sampling evaluation value C0i, wherein the compensated ith sampling evaluation value C0i is C0i × K1;
when Ee1 is not less than Ee < Ee2, selecting the second compensation coefficient K2 to compensate the ith sampling evaluation value C0i, wherein the compensated ith sampling evaluation value C0i is C0i xK 2;
when Ee2 is not less than Ee < Ee3, selecting the third compensation coefficient K3 to compensate the ith sampling evaluation value C0i, wherein the compensated ith sampling evaluation value C0i is C0i xK 3;
and when the Ee3 is not less than the Ee < Ee4, selecting the fourth compensation coefficient K4 to compensate the ith sampling evaluation value C0i, wherein the compensated ith sampling evaluation value C0i is C0i xK 4.
Specifically, the preset standard calcified area percentage E0 of the thyroid nodule is a standard reference value, that is, when the thyroid nodule is calcified and is a normal nodule, the ratio between the area of the calcified region and the area of the nodule at the time is denoted as E0, that is, E0 represents the ratio between the area of the calcified region and the area of the nodule when the thyroid nodule is normal. The preset calcified area percentage Ee of the thyroid nodule is a preset reference value, the Ee is expressed as a maximum threshold value of a ratio between the area of a calcified area and the area of the nodule when the thyroid nodule is a normal nodule, the Ee can be obtained according to the ratio between the area of the calcified area of the normal thyroid nodule and the area of the nodule in past case data, and is preset according to the maximum ratio, so that the Ee is obtained.
It can be seen that the corresponding compensation coefficient is selected according to the percentage of the calcified area of the thyroid nodule to compensate the sampling evaluation value, an influence relation is established between the sampling evaluation value and the percentage of the calcified area of the thyroid nodule, namely, the percentage of the calcified area of the thyroid nodule influences the final sampling evaluation value, so that the final result of the sampling evaluation value is more accurate, the sampling evaluation value can accurately reflect the disease degree of the thyroid nodule, and the risk degree of the thyroid nodule can be more accurately evaluated through the sampling evaluation value.
Specifically, a correction coefficient matrix T is set in the processing module, and the processing module corrects the i-th sampling evaluation value C0i compensated by the compensation coefficient matrix K by each correction coefficient in the correction coefficient matrix T.
Specifically, for the correction coefficient matrix T, T (T1, T2, T3, T4) is set, T1 is a first correction coefficient, T2 is a second correction coefficient, T3 is a third correction coefficient, T4 is a fourth correction coefficient, and 0.9 < T1 < T2 < 1 < T3 < T4 < 1.1; a preset ratio matrix Ff0 of the circumference to the area of the thyroid nodule is further set in the processing module, and Ff0(Ff1, Ff2, Ff3 and Ff4) is set, wherein Ff1 is the ratio of the first preset circumference to the area, Ff2 is the ratio of the second preset circumference to the area, Ff3 is the ratio of the third preset circumference to the area, Ff4 is the ratio of the fourth preset circumference to the area, and Ff1 < Ff2 < Ff3 < Ff 4;
the processing module determines a correction coefficient according to a relation between a preset ratio Ff of the circumference to the area of the thyroid nodule and a ratio of each preset circumference to the area, so as to correct the ith sampling evaluation value C0i compensated by the compensation coefficient:
when Ff is less than Ff1, selecting the first correction coefficient T1 to correct the compensated ith sampling evaluation value C0i × K1, and correcting the corrected ith sampling evaluation value C0i × K1 × T1;
when the Ff1 is not less than or equal to Ff < Ff2, selecting the second correction coefficient T2 to correct the compensated ith sampling evaluation value C0i × K2, and correcting the corrected ith sampling evaluation value C0i × K2 × T2;
when the Ff2 is not less than or equal to Ff < Ff3, selecting the third correction coefficient T3 to correct the compensated ith sampling evaluation value C0i × K3, and correcting the corrected ith sampling evaluation value C0i × K3 × T3;
and when the Ff3 is not less than the Ff < Ff4, selecting the fourth correction coefficient T4 to correct the compensated ith sampling evaluation value C0i × K4, and correcting the corrected ith sampling evaluation value C0i × K4 × T4.
Specifically, the preset standard ratio F0 of the circumference to the area of the thyroid nodule is a standard reference value, that is, when the thyroid nodule is a normal nodule, the ratio between the circumference of the thyroid nodule and the area of the nodule at this time is denoted as F0, that is, F0 represents the ratio between the circumference of the thyroid nodule and the area of the nodule when the thyroid nodule is normal. The preset ratio Ff of the circumference to the area of the thyroid nodule is a preset reference value, and is represented as a maximum threshold value of the ratio of the circumference to the area of the thyroid nodule when the thyroid nodule is a normal nodule, the Ff can acquire data according to the ratio between the circumference and the area of the normal thyroid nodule in past case data, and is preset according to the maximum ratio, so that the Ff is acquired.
It can be seen that, by determining a correction coefficient according to a relationship between a preset ratio Ff of the circumference to the area of the thyroid nodule and each preset ratio of the circumference to the area, so as to correct the i-th sampling evaluation value C0i compensated by the compensation coefficient, and after correcting the compensated i-th sampling evaluation value C0i by the correction coefficient, the calculation of the sampling evaluation value can be made more accurate, and by influencing the acquisition of the sampling evaluation value by the ratio of the circumference to the area of the thyroid nodule, the thyroid nodule can be effectively evaluated according to the complexity of the contour of the thyroid nodule, and the accuracy of the risk evaluation result of the thyroid nodule can be improved.
Specifically, a preset thyroid nodule area correction matrix P0 is set in the processing module, and P0(P1, P2, P3 and P4) is set, wherein P1 is a first preset area correction coefficient, P2 is a second preset area correction coefficient, P3 is a third preset area correction coefficient, P4 is a fourth preset area correction coefficient, and 1 < P1 < P2 < P3 < P4 < 1.2;
the processing module is further configured to obtain an average value Δ q of the gray values of the thyroid nodule, a standard gray average value q0 of the thyroid nodule is preset in the processing module, and the processing module selects a preset area correction coefficient to correct the area S1 of the thyroid nodule according to a relationship between the average value Δ q of the gray values and the standard gray average value q0, and a relationship between a ratio F of the circumference to the area of the thyroid nodule and a preset standard ratio F0 of the circumference to the area of the thyroid nodule,
when F is less than F0 and Δ q is more than q0, selecting the first preset area correction coefficient P1 to correct the area S1 of the thyroid nodule, wherein the corrected area of the thyroid nodule is S1 × P1;
when F is less than F0 and Δ q is less than or equal to q0, selecting the second preset area correction coefficient P2 to correct the area S1 of the thyroid nodule, wherein the corrected area of the thyroid nodule is S1 × P2;
when F is larger than F0 and Δ q is larger than q0, selecting the third preset area correction coefficient P3 to correct the area S1 of the thyroid nodule, wherein the corrected area of the thyroid nodule is S1 × P3;
when F is larger than F0 and Δ q is less than or equal to q0, selecting the fourth preset area correction coefficient P4 to correct the area S1 of the thyroid nodule, wherein the corrected area of the thyroid nodule is S1 × P4;
after the thyroid nodule corrected area was determined, E, E0, Ee, F0 and Ff were calculated using the thyroid nodule corrected area as S1 × Pi as the thyroid nodule area, i =1, 2, 3, 4.
It can be seen that the accuracy of the results of the ratio F of the circumference to the area of the thyroid nodule, the preset standard ratio F0 of the circumference to the area of the thyroid nodule, the preset ratio Ff of the circumference to the area of the thyroid nodule, the calcified area percentage E of the thyroid nodule, the standard calcified area percentage E0 of the thyroid nodule and the preset calcified area percentage Ee of the thyroid nodule can be greatly improved by correcting the area of the thyroid nodule, so that the subsequent diagnosis and the apple efficiency can be improved.
Referring to fig. 2, in another preferred implementation manner based on the above embodiment, the implementation manner provides a risk assessment system for a remote thyroid nodule ultrasonic image, which includes a cloud platform 1, an ultrasonic image acquisition room 2, and a PACS system 3 of a hospital, where the ultrasonic image acquisition room 2 is in data communication connection with the cloud platform 1 through the PACS system 3 of the hospital. The ultrasound image acquisition room 2 is used for acquiring ultrasound images and uploading the ultrasound images to the cloud platform 1 through a PACS system 3 of a hospital, and the cloud platform 1 is used for processing the ultrasound images and outputting diagnosis results and risk assessment results.
Specifically, the cloud platform 1 includes a processing unit 4, and after the ultrasound image is acquired by the cloud platform 1, the ultrasound image is subjected to data processing by the processing unit 4 arranged in the cloud platform, so as to determine whether a thyroid nodule exists in the ultrasound image:
if the thyroid nodule does not exist, the cloud platform makes a diagnosis of the thyroid gland normal;
if the thyroid nodule exists, the cloud platform acquires information related to the thyroid nodule in the ultrasonic image and carries out subsequent steps;
after the processing unit detects the thyroid nodule from the ultrasonic image, the processing module is configured to determine a property B and an aspect ratio D of the thyroid nodule, and the processing module is further configured to obtain an echo value Δ a of the thyroid nodule, establish a preset echo value matrix a, and set a (a 1, a2, A3, a 4), where a1 is a first preset echo value, a2 is a second preset echo value, A3 is a third preset echo value, a4 is a fourth preset echo value, and a1 < a2 < A3 < a 4; the processing module judges the grade of the thyroid nodule according to the character B, the aspect ratio D and the echo value delta A of the thyroid nodule:
when A3 is more than or equal to delta A and less than or equal to A4 or delta A is more than or equal to A4, if the property B of the thyroid nodule is cystic nodule and the aspect ratio D of the thyroid nodule is less than 1, judging the grade of the thyroid nodule to be first grade, and calculating a first sampling evaluation value C01 of the thyroid nodule;
when A2 is larger than delta A and smaller than A3, if the property B of the thyroid nodule is cystic nodule and the aspect ratio D of the thyroid nodule is smaller than 1, judging the grade of the thyroid nodule to be two-grade, and calculating a second sampling evaluation value C02 of the thyroid nodule;
when A1 is larger than delta A and smaller than A2, if the property B of the thyroid nodule is a real nodule and the aspect ratio D of the thyroid nodule is smaller than 1, judging the grade of the thyroid nodule to be three-grade, and calculating a third sampling evaluation value C03 of the thyroid nodule;
when the delta A is less than or equal to A1, if the property B of the thyroid nodule is a solid nodule and the aspect ratio D of the thyroid nodule is more than 1, judging that the grade of the thyroid nodule is four grades, and calculating a fourth sampling evaluation value C04 of the thyroid nodule;
when the ith sampling evaluation value C0i is less than C, the grade of the thyroid nodule is reduced by one grade, the lowest grade of the thyroid nodule is one grade, and the thyroid nodule is judged to be a low-risk nodule, when the ith sampling evaluation value C0i is greater than C, the grade of the thyroid nodule is increased by one grade, and the thyroid nodule is judged to be a high-risk nodule, i =1, 2, 3, 4.
Therefore, the system can automatically diagnose thyroid nodules and evaluate risks, greatly save labor and improve diagnosis efficiency and accuracy.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (9)
1. A risk assessment method of remote thyroid nodule ultrasonic image is characterized by comprising the following steps:
step S1: acquiring an ultrasonic image of a thyroid part, and uploading the ultrasonic image to a cloud platform;
step S2: after the cloud platform acquires the ultrasonic image, data processing is carried out on the ultrasonic image through a processing unit arranged in the cloud platform so as to judge whether thyroid nodules exist in the ultrasonic image:
if the thyroid nodule does not exist, the cloud platform makes a diagnosis of the thyroid gland normal;
if the thyroid nodule exists, the cloud platform acquires information related to the thyroid nodule in the ultrasonic image and carries out subsequent steps;
step S3: a sample evaluation value C is set in the cloud platform, the cloud platform diagnoses the grade of the thyroid nodule according to the related information of the thyroid nodule, and risk evaluation is carried out on the thyroid nodule after grade diagnosis through the sample evaluation value C;
step S4: the cloud platform outputs the diagnosis and risk assessment results of the thyroid nodules, and returns the diagnosis and risk assessment results of the thyroid nodules to a PACS (Picture archiving and communication System) of a hospital;
in step S3, after the processing unit detects the thyroid nodule from the ultrasound image, the processing module is configured to determine a property B and an aspect ratio D of the thyroid nodule, acquire an echo value Δ a of the thyroid nodule, establish a preset echo value matrix a, and set a (a 1, a2, A3, a 4), where a1 is a first preset echo value, a2 is a second preset echo value, A3 is a third preset echo value, a4 is a fourth preset echo value, and a1 < a2 < A3 < a 4; the processing module judges the grade of the thyroid nodule according to the character B, the aspect ratio D and the echo value delta A of the thyroid nodule:
when A3 is more than or equal to delta A and less than or equal to A4 or delta A is more than or equal to A4, if the property B of the thyroid nodule is cystic nodule and the aspect ratio D of the thyroid nodule is less than 1, judging the grade of the thyroid nodule to be first grade, and calculating a first sampling evaluation value C01 of the thyroid nodule;
when A2 is larger than delta A and smaller than A3, if the property B of the thyroid nodule is cystic nodule and the aspect ratio D of the thyroid nodule is smaller than 1, judging the grade of the thyroid nodule to be two-grade, and calculating a second sampling evaluation value C02 of the thyroid nodule;
when A1 is larger than delta A and smaller than A2, if the property B of the thyroid nodule is a real nodule and the aspect ratio D of the thyroid nodule is smaller than 1, judging the grade of the thyroid nodule to be three-grade, and calculating a third sampling evaluation value C03 of the thyroid nodule;
when the delta A is less than or equal to A1, if the property B of the thyroid nodule is a solid nodule and the aspect ratio D of the thyroid nodule is more than 1, judging that the grade of the thyroid nodule is four grades, and calculating a fourth sampling evaluation value C04 of the thyroid nodule;
when the ith sampling evaluation value C0i is less than C, the grade of the thyroid nodule is reduced by one grade, the lowest grade of the thyroid nodule is one grade, and the thyroid nodule is judged to be a low-risk nodule, when the ith sampling evaluation value C0i is greater than C, the grade of the thyroid nodule is increased by one grade, and the thyroid nodule is judged to be a high-risk nodule, i =1, 2, 3, 4.
2. The risk assessment method of remote ultrasound imaging of thyroid nodules according to claim 1,
the i-th sample evaluation value C0i = Δ a/a0+ B/B0+ D/D0+ E/E0+ F/F0, the sample evaluation value C = Δ Aa/a0+ Bb/B0+ Dd/D0+ Ee/E0+ Ff/F0, wherein Δ a is an echo value of a thyroid nodule, a0 is a preset standard echo value of a thyroid nodule, Δ Aa is a preset echo value of a thyroid nodule, B is a trait of a thyroid nodule, B =1 when the trait of a thyroid nodule is a cystic nodule, B =2 when the trait of a thyroid nodule is a solid nodule, B0=1, Bb =1.5, D is an aspect ratio of a thyroid nodule, a preset standard aspect ratio D0=1 of a thyroid nodule, a preset aspect ratio Dd =0.5, E is an area percentage of a thyroid nodule, E0=10%, E =20%, and a ratio of a perimeter of an area of a thyroid nodule to a calcified thyroid nodule, f0 preset standard ratio of circumference to area of thyroid nodule, and preset ratio of circumference to area of Ff thyroid nodule.
3. The method for risk assessment of remote ultrasound thyroid nodule images according to claim 2, wherein the processing module obtains the area of the thyroid nodule S1 and the calcified area of the thyroid nodule S2 after the thyroid nodule is detected, E = S2/S1 x 100%;
the processing module adjusts the grade of the thyroid nodule according to the calcified area percentage E of the thyroid nodule and the standard calcified area percentage E0 of the preset thyroid nodule,
when E is larger than E0, the grade of the thyroid nodule is judged to be increased by one level;
when E is less than E0, reducing the grade of the thyroid nodule judged by one grade;
when E = E0, the grade of the thyroid nodule is not adjusted.
4. The method for risk assessment of remote thyroid nodule ultrasound images according to claim 3, wherein the processing module is further configured to obtain a circumference Z of the thyroid nodule after the thyroid nodule is detected, and calculate a circumference-to-area ratio F, F = Z/S1 according to a ratio between the circumference Z of the thyroid nodule and an area S1 of the thyroid nodule, wherein the processing module is configured with a preset area S3 and a preset circumference Z1 of the thyroid nodule, and a preset standard ratio F0= Z1/S3 of the circumference-to-area of the thyroid nodule;
the processing module adjusts the grade of the thyroid nodule after the calcified area percentage of the thyroid nodule is adjusted again according to the relation between the ratio F of the perimeter to the area of the thyroid nodule and a preset standard ratio F0 of the perimeter to the area of the thyroid nodule:
when E is larger than E0, after the judged grade of the thyroid nodule is adjusted to one grade, if F is larger than F0, the grade of the thyroid nodule is adjusted to one grade, if F is smaller than F0, the grade of the thyroid nodule is reduced by one grade, and if F = F0, the grade of the thyroid nodule is not adjusted;
when E is less than E0, after the grade of the thyroid nodule is judged to be reduced by one grade, if F is greater than F0, the grade of the thyroid nodule is increased by one grade, if F is less than F0, the grade of the thyroid nodule is reduced by one grade, and if F = F0, the grade of the thyroid nodule is not adjusted;
when E = E0, the grade of the thyroid nodule is not adjusted, if F > F0, the grade of the thyroid nodule is increased by one grade, if F < F0, the grade of the thyroid nodule is decreased by one grade, and if F = F0, the grade of the thyroid nodule is not adjusted.
5. The method for risk assessment of remote thyroid nodule ultrasound images according to claim 4, wherein a compensation coefficient matrix K is set in the processing module, and the processing module compensates the ith sampling evaluation value C0i by each compensation coefficient in the compensation coefficient matrix K.
6. The method for risk assessment of remote thyroid nodule ultrasound images according to claim 5, wherein K (K1, K2, K3, K4) is set for the compensation coefficient matrix K, wherein K1 is a first compensation coefficient, K2 is a second compensation coefficient, K3 is a third compensation coefficient, K4 is a fourth compensation coefficient, and 1 < K1 < K2 < K3 < K4 < 1.5; a preset calcification area percentage matrix Ee0 of the thyroid nodule is also set in the processing module, and Ee0(Ee1, Ee2, Ee3 and Ee4) is set, wherein Ee1 is a first preset calcification area percentage, Ee2 is a second preset calcification area percentage, Ee3 is a third preset calcification area percentage, Ee4 is a fourth preset calcification area percentage, and Ee1 < Ee2 < Ee3 < Ee 4;
the processing module determines a compensation coefficient according to a relation between a preset calcified area percentage Ee of the thyroid nodule and each preset calcified area percentage, so as to compensate the ith sampling evaluation value C0 i:
when Ee is less than Ee1, selecting the first compensation coefficient K1 to compensate the ith sampling evaluation value C0i, wherein the compensated ith sampling evaluation value C0i is C0i × K1;
when Ee1 is not less than Ee < Ee2, selecting the second compensation coefficient K2 to compensate the ith sampling evaluation value C0i, wherein the compensated ith sampling evaluation value C0i is C0i xK 2;
when Ee2 is not less than Ee < Ee3, selecting the third compensation coefficient K3 to compensate the ith sampling evaluation value C0i, wherein the compensated ith sampling evaluation value C0i is C0i xK 3;
and when the Ee3 is not less than the Ee < Ee4, selecting the fourth compensation coefficient K4 to compensate the ith sampling evaluation value C0i, wherein the compensated ith sampling evaluation value C0i is C0i xK 4.
7. The method as claimed in claim 6, wherein a correction coefficient matrix T is set in the processing module, and the processing module corrects the ith sampling evaluation value C0i compensated by the compensation coefficient matrix K through each correction coefficient in the correction coefficient matrix T.
8. The method of claim 7, wherein for the modification coefficient matrix T, T (T1, T2, T3, T4) is set, T1 is a first modification coefficient, T2 is a second modification coefficient, T3 is a third modification coefficient, T4 is a fourth modification coefficient, and 0.9 < T1 < T2 < 1 < T3 < T4 < 1.1; a preset ratio matrix Ff0 of the circumference to the area of the thyroid nodule is further set in the processing module, and Ff0(Ff1, Ff2, Ff3 and Ff4) is set, wherein Ff1 is the ratio of the first preset circumference to the area, Ff2 is the ratio of the second preset circumference to the area, Ff3 is the ratio of the third preset circumference to the area, Ff4 is the ratio of the fourth preset circumference to the area, and Ff1 < Ff2 < Ff3 < Ff 4;
the processing module determines a correction coefficient according to a relation between a preset ratio Ff of the circumference to the area of the thyroid nodule and a ratio of each preset circumference to the area, so as to correct the ith sampling evaluation value C0i compensated by the compensation coefficient:
when Ff is less than Ff1, selecting the first correction coefficient T1 to correct the compensated ith sampling evaluation value C0i × K1, and correcting the corrected ith sampling evaluation value C0i × K1 × T1;
when the Ff1 is not less than or equal to Ff < Ff2, selecting the second correction coefficient T2 to correct the compensated ith sampling evaluation value C0i × K2, and correcting the corrected ith sampling evaluation value C0i × K2 × T2;
when the Ff2 is not less than or equal to Ff < Ff3, selecting the third correction coefficient T3 to correct the compensated ith sampling evaluation value C0i × K3, and correcting the corrected ith sampling evaluation value C0i × K3 × T3;
and when the Ff3 is not less than the Ff < Ff4, selecting the fourth correction coefficient T4 to correct the compensated ith sampling evaluation value C0i × K4, and correcting the corrected ith sampling evaluation value C0i × K4 × T4.
9. The method for risk assessment of remote thyroid nodule ultrasound images according to claim 8, wherein the processing module is configured with a preset thyroid nodule area correction matrix P0, and P0(P1, P2, P3, P4), wherein P1 is a first preset area correction coefficient, P2 is a second preset area correction coefficient, P3 is a third preset area correction coefficient, P4 is a fourth preset area correction coefficient, and 1 < P1 < P2 < P3 < P4 < 1.2;
the processing module is further configured to obtain an average value Δ q of the gray values of the thyroid nodule, a standard gray average value q0 of the thyroid nodule is preset in the processing module, and the processing module selects a preset area correction coefficient to correct the area S1 of the thyroid nodule according to a relationship between the average value Δ q of the gray values and the standard gray average value q0, and a relationship between a ratio F of the circumference to the area of the thyroid nodule and a preset standard ratio F0 of the circumference to the area of the thyroid nodule,
when F is less than F0 and Δ q is more than q0, selecting the first preset area correction coefficient P1 to correct the area S1 of the thyroid nodule, wherein the corrected area of the thyroid nodule is S1 × P1;
when F is less than F0 and Δ q is less than or equal to q0, selecting the second preset area correction coefficient P2 to correct the area S1 of the thyroid nodule, wherein the corrected area of the thyroid nodule is S1 × P2;
when F is larger than F0 and Δ q is larger than q0, selecting the third preset area correction coefficient P3 to correct the area S1 of the thyroid nodule, wherein the corrected area of the thyroid nodule is S1 × P3;
when F is larger than F0 and Δ q is less than or equal to q0, selecting the fourth preset area correction coefficient P4 to correct the area S1 of the thyroid nodule, wherein the corrected area of the thyroid nodule is S1 × P4;
after the thyroid nodule corrected area was determined, E, E0, Ee, F0 and Ff were calculated using the thyroid nodule corrected area as S1 × Pi as the thyroid nodule area, i =1, 2, 3, 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567911.2A CN113299391B (en) | 2021-05-25 | 2021-05-25 | Risk assessment method for remote thyroid nodule ultrasound image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567911.2A CN113299391B (en) | 2021-05-25 | 2021-05-25 | Risk assessment method for remote thyroid nodule ultrasound image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113299391A true CN113299391A (en) | 2021-08-24 |
| CN113299391B CN113299391B (en) | 2023-11-03 |
Family
ID=77324449
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110567911.2A Active CN113299391B (en) | 2021-05-25 | 2021-05-25 | Risk assessment method for remote thyroid nodule ultrasound image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113299391B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113842166A (en) * | 2021-10-25 | 2021-12-28 | 上海交通大学医学院 | Ultrasonic image acquisition method based on ultrasonic imaging equipment and related device |
| CN114332003A (en) * | 2021-12-27 | 2022-04-12 | 什维新智医疗科技(上海)有限公司 | Thyroid nodule texture analysis device |
| CN117274244A (en) * | 2023-11-17 | 2023-12-22 | 艾迪普科技股份有限公司 | Medical imaging inspection method, system and medium based on three-dimensional image recognition processing |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110142301A1 (en) * | 2006-09-22 | 2011-06-16 | Koninklijke Philips Electronics N. V. | Advanced computer-aided diagnosis of lung nodules |
| CN107247971A (en) * | 2017-06-28 | 2017-10-13 | 中国人民解放军总医院 | The intelligent analysis method and system of a kind of ultrasonic thyroid nodule risk indicator |
| CN109411080A (en) * | 2018-09-18 | 2019-03-01 | 北京大学 | A kind of man-machine coordination tubercle risk rating system based on ultrasound data |
| CN109498061A (en) * | 2018-12-27 | 2019-03-22 | 深圳开立生物医疗科技股份有限公司 | Ultrasound image processing method, device, equipment and computer readable storage medium |
| US20200143532A1 (en) * | 2018-11-07 | 2020-05-07 | Wonkwang University Center For Industry-Academy Cooperation | Method and apparatus for analyzing abdominal disease based on medical image |
| CN111341443A (en) * | 2020-03-09 | 2020-06-26 | 西安中科长青医疗科技研究院有限公司 | Ultrasonic thyroid nodule intelligent evaluation method based on deep learning |
| CN112382392A (en) * | 2020-11-25 | 2021-02-19 | 珠海圣美生物诊断技术有限公司 | System for be used for pulmonary nodule risk assessment |
| US10993653B1 (en) * | 2018-07-13 | 2021-05-04 | Johnson Thomas | Machine learning based non-invasive diagnosis of thyroid disease |
| CN112767355A (en) * | 2021-01-20 | 2021-05-07 | 北京小白世纪网络科技有限公司 | Method and device for constructing thyroid nodule Tirads grading automatic identification model |
-
2021
- 2021-05-25 CN CN202110567911.2A patent/CN113299391B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110142301A1 (en) * | 2006-09-22 | 2011-06-16 | Koninklijke Philips Electronics N. V. | Advanced computer-aided diagnosis of lung nodules |
| CN107247971A (en) * | 2017-06-28 | 2017-10-13 | 中国人民解放军总医院 | The intelligent analysis method and system of a kind of ultrasonic thyroid nodule risk indicator |
| US10993653B1 (en) * | 2018-07-13 | 2021-05-04 | Johnson Thomas | Machine learning based non-invasive diagnosis of thyroid disease |
| CN109411080A (en) * | 2018-09-18 | 2019-03-01 | 北京大学 | A kind of man-machine coordination tubercle risk rating system based on ultrasound data |
| US20200143532A1 (en) * | 2018-11-07 | 2020-05-07 | Wonkwang University Center For Industry-Academy Cooperation | Method and apparatus for analyzing abdominal disease based on medical image |
| CN109498061A (en) * | 2018-12-27 | 2019-03-22 | 深圳开立生物医疗科技股份有限公司 | Ultrasound image processing method, device, equipment and computer readable storage medium |
| CN111341443A (en) * | 2020-03-09 | 2020-06-26 | 西安中科长青医疗科技研究院有限公司 | Ultrasonic thyroid nodule intelligent evaluation method based on deep learning |
| CN112382392A (en) * | 2020-11-25 | 2021-02-19 | 珠海圣美生物诊断技术有限公司 | System for be used for pulmonary nodule risk assessment |
| CN112767355A (en) * | 2021-01-20 | 2021-05-07 | 北京小白世纪网络科技有限公司 | Method and device for constructing thyroid nodule Tirads grading automatic identification model |
Non-Patent Citations (5)
| Title |
|---|
| ""超声联合甲状腺影像报告和数据系统评估甲状腺结节恶性风险"", 《中国医学影像技术》, pages 1790 - 1794 * |
| PROF SUI PENG PHD: ""Deep learning-based artificial intelligence model to assist thyroid nodule diagnosis and management: a multicentre diagnostic study"", "THE LANCET DIGITAL HEALTH", vol. 03, no. 04, pages 250 * |
| 刘如玉等: "甲状腺结节的影像报告与数据系统分级与2015年美国甲状腺学会推荐超声恶性风险分层的比较研究", 中华医学超声杂志(电子版), no. 04, pages 263 - 268 * |
| 吴琼;李玉宏;: "常规超声联合SWE及CEUS对甲状腺良恶性结节的鉴别诊断价值", 中国全科医学, no. 3, pages 400 - 402 * |
| 杨敏: ""常规超声诊断甲状腺结节良恶性质的价值探讨"", 《中国硕士论文医药卫生科技》, no. 02, pages 060 - 17 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113842166A (en) * | 2021-10-25 | 2021-12-28 | 上海交通大学医学院 | Ultrasonic image acquisition method based on ultrasonic imaging equipment and related device |
| CN114332003A (en) * | 2021-12-27 | 2022-04-12 | 什维新智医疗科技(上海)有限公司 | Thyroid nodule texture analysis device |
| CN117274244A (en) * | 2023-11-17 | 2023-12-22 | 艾迪普科技股份有限公司 | Medical imaging inspection method, system and medium based on three-dimensional image recognition processing |
| CN117274244B (en) * | 2023-11-17 | 2024-02-20 | 艾迪普科技股份有限公司 | Medical imaging inspection method, system and medium based on three-dimensional image recognition processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113299391B (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113299391B (en) | Risk assessment method for remote thyroid nodule ultrasound image | |
| CN110503652B (en) | Method and device for determining relationship between mandible wisdom tooth and adjacent teeth and mandible tube, storage medium and terminal | |
| US20110268336A1 (en) | System for monitoring medical abnormalities and method of operation thereof | |
| CN109255354B (en) | Medical CT-oriented computer image processing method and device | |
| CN1923140A (en) | Image measuring device, method and image instrumentation system of glomerular filtration rate | |
| CN110458837B (en) | Image post-processing method and device, electronic equipment and storage medium | |
| CN111127430A (en) | Method and device for determining medical image display parameters | |
| CN107397557A (en) | Breast ultrasound ripple audit report generates system and method | |
| CN104091309B (en) | Balanced display method and system for flat-plate X-ray image | |
| CN106659480A (en) | Ultrasound diagnostic image generating device and method | |
| Yu et al. | Artificial intelligence-based myocardial texture analysis in etiological differentiation of left ventricular hypertrophy | |
| EP3346297B1 (en) | Image analysis approach for assessing image data | |
| EP3758602A1 (en) | Neural network classification of osteolysis and synovitis near metal implants | |
| CN115661149A (en) | Lung image processing system based on lung tissue data | |
| CN107798678A (en) | Type B ultrasonoscopy the best visual effect Automatic Optimal system and control method | |
| JP2002269539A (en) | Image processor, image processing method, and computer- readable storage medium with image processing program stored therein, and diagnosis support system using them | |
| US11250564B2 (en) | Methods and systems for automatic measurement of strains and strain-ratio calculation for sonoelastography | |
| CN107358594A (en) | Galactophore image processing system and method based on X ray and ultrasonic examination | |
| CN100361632C (en) | X-ray computerised tomograph capable of automatic eliminating black false image | |
| CN101836868B (en) | Method and equipment for adaptively adjusting dynamic range | |
| US8116545B2 (en) | Method and system for analysis of bone density | |
| CN112508942B (en) | Method and system for acquiring BI-RADS grade | |
| CN113100742A (en) | Mammary gland MR image intelligent diagnosis method, device and equipment | |
| CN116196034B (en) | Ultrasonic imaging method and system | |
| CN112070089A (en) | Ultrasonic image-based intelligent diagnosis method and system for diffuse thyroid diseases |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |