JP3228085U - Liver tumor intelligence analyzer - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a liver tumor intelligent analyzer capable of interpreting a benign or malignant risk of a liver tumor by a doctor or an ultrasonic examination engineer based on an ultrasonic detection scanned image and referencing a liver tumor type diagnosis. SOLUTION: An ultrasonic detection module 1 connected to each other and an analysis module 2 for determining the benign or malignant risk of a liver tumor loaded with a machine learning algorithm are included, and the analysis modules are connected to each other. Includes image collection units, reference savings units, control units, liver tumor marking units, classification units, contrast units and benign and malignant risk prediction report generation units for liver tumors. The liver tumor intelligence analyzer is a machine learning algorithm that uses the parameters and coefficients of those experience data based on ultrasound images with marked liver tumor image points by an experienced abdominal ultrasonography specialist. So, set up an estimation model with 86% accuracy. [Selection diagram] Fig. 1

Description

The present invention relates to an intelligent liver tumor analyzer, and more particularly to a device for determining the benign or malignant risk of a liver tumor by using an ultrasonic detection module and an analysis module loaded with a machine learning algorithm. Based on the ultrasonic detection scan image, doctors and ultrasonic examination engineers can immediately interpret the benign and malignant risks of liver tumors using the liver tumor intelligence analyzer, and the doctor can refer to the diagnosis of liver tumor types. Regarding what becomes.

Liver cancer is the fourth leading cause of cancer death worldwide and the second leading cause of cancer death in Taiwan. Liver cancer is mostly due to hepatitis B and C viruses and aflatoxins in Asia, mostly due to hepatitis C virus in Western countries, and also the production of liver cancers due to steatohepatitis, diabetes and high triglycerides. , More.

Surgery is the most direct method of treating liver cancer in the immediate future, but early diagnosis of liver cancer and related prognostic indicators of postoperative patients are also important issues. Liver cancer patients with an early definitive diagnosis generally have more treatment options, and the efficacy of treatment is well responsive to patient survival. Therefore, routine examination and early diagnosis and early treatment are extremely important for the survival quality and prolongation of survival of patients.

In addition to collecting blood for early diagnosis to test for liver function, hepatitis B virus and alpha-fetoprotein, studies have shown that abdominal ultrasonography is one of the important tests for liver disease, and that Taiwan According to the first year study of Professor Xu Kanagawa, an emeritus professor at the National University of Taiwan, 1/3 of patients with small liver cancer have a liver cancer index-α-fetoprotein, which is normal even if they are collected and tested. Without this, liver cancer cannot be detected early, and abdominal echography is a key tool for liver cancer screening because of its fast, convenient, and radiation-free test characteristics.

Liver cancer diagnosis, unlike other cancers, does not require a pathological section and is directly diagnosed, for example, by abdominal ultrasound (US), computed tomography (CT) and magnetic resonance imaging. A definitive diagnosis can be made using imaging tests such as magnetic resonance imaging (MRI), and the sensitivity and specificity are 0.78 to 0.73 and 0.89 to 0.93, respectively, and 0.84 to 0.83. And 0.99-0.91, and 0.83 and 0.88.

Ultrasonography is convenient but limited, because factors such as the experience of the operator, the degree of obesity of the sick, and the presence or absence of liver fibrosis or cirrhosis affect the accuracy of ultrasound. , If you suspect a malignant tumor based on ultrasonography, perform a second imaging test, for example CT or MRI to assist in a definitive diagnosis, but these two tests are expensive and the test schedule Not only is it slow, but there is a greater risk of radiation exposure due to CT examination.

As described above, in the related technical fields, artificial intelligence analysis technology is required, and auxiliary ultrasonic detection is a device that can effectively analyze the benign or malignant of liver tumors, and magnetic resonance tomography imaging and / or computed tomography. Compared to tomography, this liver tumor intelligence analyzer makes ultrasonic image analysis more accurate and corresponds to the accuracy of CT and MRI, which allows doctors to perform ultrasonography. By using it, an accurate liver tumor type can be diagnosed quickly.

In order to eliminate the above-mentioned drawbacks, the present inventor proposes the present invention in which the above-mentioned defects can be effectively eliminated by careful research and by utilizing the theory, and the design is rational.

The main purpose of the present invention is to provide an ultrasonic detection module that can solve the above-mentioned problems of the conventional technique and an analysis module loaded with a machine learning algorithm, and to judge the properties of a liver tumor, and its accuracy. It reaches 86%, which is similar to the accuracy of CT and MRI, so doctors can quickly and accurately diagnose liver tumor types with radiation-free and safe ultrasonography.

The present invention is a liver tumor intelligent analyzer for achieving the above object, has an ultrasonic probe, emits ultrasonic waves, scans a site corresponding to the liver outside the subject, and scans the site corresponding to the liver of the subject. An ultrasound detection module that acquires an ultrasound image of a target liver tumor and an analysis module that is connected to the ultrasound detection module are included, and the analysis module uses the image collection unit to obtain the ultrasound. The target liver tumor ultrasound image of the subject imaged by the detection module is acquired, and a plurality of reference liver tumor ultrasound images including benign and malignant liver tumor ultrasound images are stored in the reference storage unit. , The analysis module stores the program, and when executed by the control unit, the clinical staff's judgment on the subject's liver tumor type and the probability of occurrence of benign or malignant risk of the subject's liver tumor. Provide predictions.

In the program, a special rule is set up based on empirical rules, and a liver tumor ultrasonic image having a tumor image point site is automatically marked from the plurality of reference liver tumor ultrasonic images to perform liver tumor. For the liver tumor marking unit that identifies the type of liver tumor, the classification unit that sets up an estimation model for the liver tumor ultrasound image having those tumor image point sites by a machine learning algorithm, and the target liver tumor ultrasound image. Includes a contrasting unit that is analyzed by the putative model to provide clinical staff with a judgment on the subject's liver tumor type and a prediction of the subject's benign or malignant risk of liver tumor.

According to an embodiment of the present invention, the image collecting unit is a digital visual interface (DVI).

According to the embodiment of the present invention, the control unit is a central processing unit (CPU).

According to the embodiment of the present invention, the liver tumor marking unit automatically determines the tumor image point site from the plurality of reference liver tumor ultrasound images based on the coefficient and / or the parameter according to the experience data. Liver tumor ultrasound images with are marked.

According to the examples of the present invention, the liver tumor types include benign tumors and malignant tumors.

According to an embodiment of the present invention, the analysis module further has a predictive report generation unit for benign or malignant risk of liver tumor, which is connected to the control unit, and is generated by the control unit and by the contrast unit. In addition, the clinical staff's judgment on the liver tumor type of the subject and the prediction of the benign or malignant risk occurrence probability of the liver tumor of the subject are input to the prediction report generation unit of the benign or malignant risk of the liver tumor. Prepare a liver tumor nature diagnosis report to help the doctor's judgment.

Hereinafter, the features and technical contents of the present invention will be described in detail with reference to the drawings, but these drawings and the like are for reference and explanation, and the present invention is not limited thereto.

It is a block conceptual diagram of one better embodiment of the liver tumor intelligent analyzer according to the present invention.

FIG. 1 is a block conceptual diagram of a better embodiment of the liver tumor intelligence analyzer according to the present invention. As shown in FIG. 1, the present invention is a liver tumor intelligence analyzer, which is composed of an ultrasonic detection module 1 and an analysis module 2.

The ultrasonic detection module 1 includes an ultrasonic probe 11.

The analysis module 2 is connected to the ultrasonic detection module 1, and the image collection unit 21, the reference storage unit 22, the control unit 23, the liver tumor marking unit 24, the classification unit 25, the comparison unit 26, and the benign or malignant liver tumor. Risk prediction report generation unit 27 is included. Among them, the control unit 23 is a central processing unit (CPU), and the image collection unit 21, the reference storage unit 22, the liver tumor marking unit 24, the classification unit 25, and the comparison unit 26. And, when the benign or malignant risk prediction report generation unit 27 of the liver tumor is operated, the calculation, control, processing, coding, decoding, and various drive commands are instructed. A new liver tumor intelligence analyzer is constructed by these devices.

According to the present invention, the liver tumor intelligence analyzer according to the present invention can be executed by a computer, and then the control unit 23 is a central processing unit of the computer, the liver tumor marking unit 24 and the present invention. The classification unit 25, the comparison unit 26, and the benign or malignant risk prediction report generation unit 27 of the liver tumor are computer programs and are stored in a hard disk or memory, and the image collection unit 21 is a digital visual of the computer. It is an interface (Digital Visual Interface, DVI), and the reference storage unit 22 is a hard disk, and further has a screen, a mouse, and a keyboard for output and operation. In addition, the liver tumor intelligence analyzer according to the present invention can also be executed on a server.

According to the present invention, ultrasonic waves are emitted from the ultrasonic probe 11 of the ultrasonic detection module 1 and a site corresponding to the liver is scanned outside the subject to acquire a plurality of liver tumor ultrasonic images of the subject. However, even during the scanning period, the doctor can select at least one suspicious tumor ultrasound image as the target liver tumor ultrasound image.

The analysis module 2 uses the image collection unit 21 to acquire a target liver tumor ultrasound image of the subject imaged by the ultrasound detection module 1, and the reference savings unit 22 is benign. Multiple reference liver tumor ultrasound images are stored, including and malignant liver tumor ultrasound images. A program is stored in the analysis module 2, and when the program is executed by the control unit 23, the clinical staff judges the liver tumor type of the subject and the risk of benign or malignant liver tumor of the subject occurs. Providing prediction of probability, the program includes the liver tumor marking unit 24 and the classification unit 25, the contrast unit 26 and the benign or malignant risk prediction report generation unit 27 of the liver tumor.

The liver tumor marking unit 24 automatically marks a liver tumor ultrasound image having a tumor image point site from the plurality of reference liver tumor ultrasound images based on a coefficient and / or a parameter adjusted to the experience data. To identify the type of liver tumor. For example, the liver tumor marking unit 24 can be marked according to the experience of a doctor. The classification unit 25 further sets up an estimation model by a machine learning algorithm using the liver tumor ultrasound image having the tumor image point sites. The contrast unit 26 provides the target liver tumor ultrasound image to clinical staff who analyze the target liver tumor ultrasound image with the estimation model to determine the liver tumor nature of the subject, and benign of the subject's liver tumor. Predict the probability of malignant risk. Finally, the benign or malignant risk prediction report generation unit 27 of the liver tumor is used to judge the liver tumor type of the subject by the clinical staff generated by the comparison unit 26, and the benign or malignant liver tumor of the subject. A prediction of the risk occurrence probability is input, and the benign or malignant risk prediction report generation unit 27 of the liver tumor prepares a liver tumor property diagnosis report that helps the doctor's judgment.

As a result, the liver tumor intelligence analyzer according to the present invention can be used by an experienced abdominal ultrasonography specialist to obtain the parameters and coefficients of their experience data based on the ultrasonic image having the liver tumor image point site marked. Use it to set up an estimation model with 86% accuracy using machine learning algorithms. This allows doctors and ultrasound technicians to immediately interpret the benign and malignant risks of liver tumors using a liver tumor intelligence analyzer based on ultrasound detection and scanning images, allowing doctors to identify liver tumor types. It will be helpful for diagnosis.

As described above, the liver tumor intelligent analyzer according to the present invention can effectively eliminate various conventional drawbacks, and the benign liver tumor can be used by using the ultrasonic detection module and the analysis module loaded with the machine learning algorithm. Judging the risk of malignancy and malignancy, and marking liver tumor ultrasound images with tumor image points based on coefficients and / or parameters matched to experience data, and machine learning algorithm to improve accuracy to 86% The present invention is more progressive, more practical, and methodatic because it allows the doctor to quickly and accurately diagnose liver tumor types with radiation-free and safe ultrasonography. Apply for a practical new proposal registration request according to the above.

The above is merely a better embodiment of the present invention, and the present invention is not limited thereto, and is equivalent to the present invention based on the scope of claims for utility model registration and the contents of the specification. All changes and amendments are included in the claims for utility model registration of the present invention.

1 Ultrasound detection module 11 Ultrasound probe 2 Analysis module 21 Image collection unit 22 Reference storage unit 23 Control unit 24 Liver tumor marking unit 25 Classification unit 26 Comparison unit 27 Benign and malignant risk prediction report generation unit for liver tumors

Claims (6)

An ultrasonic detection module that has an ultrasonic probe, emits ultrasonic waves, scans a site corresponding to the liver outside the subject, and acquires an ultrasonic image of the target liver tumor of the subject.
The analysis module, which is connected to the ultrasonic detection module, is included.
The analysis module uses the image collection unit to acquire the target liver tumor ultrasound image of the subject imaged by the ultrasound detection module, and the reference savings unit includes benign and malignant liver tumors. Multiple Reference Liver Tumors including Ultrasonic Images Liver tumors of the subject in clinical staff when an ultrasonic image is stored and a program is stored in the analysis module and the program is executed by the control unit. It provides judgment on the type and prediction of the probability of occurrence of benign or malignant liver tumor in the subject, sets up special rules based on empirical rules in the program, and automatically sets up the multiple reference liver tumors. Regarding the liver tumor marking unit that identifies the type of liver tumor by marking the liver tumor ultrasonic image having the tumor image point site from the ultrasonic image, and the liver tumor ultrasonic image having those tumor image point sites. The classification unit that sets up the estimation model by the machine learning algorithm and the target liver tumor ultrasonic image are analyzed by the estimation model, and the clinical staff can judge the liver tumor type of the subject and the liver tumor of the subject. Includes contrasting units, which provide predictions of benign and malignant risk occurrences,
A liver tumor intelligent analyzer characterized by this. The liver tumor intelligent analyzer according to claim 1, wherein the image collecting unit is a digital visual interface. The liver tumor intelligence analyzer according to claim 1, wherein the control unit is a central processing unit. The liver tumor marking unit automatically marks a liver tumor ultrasound image having a tumor image point site from the plurality of reference liver tumor ultrasound images based on a coefficient and / or a parameter adjusted to the experience data. The liver tumor intelligent analyzer according to claim 1, wherein the liver tumor is characterized by the above. The liver tumor intelligence analyzer according to claim 1, wherein the liver tumor type includes a benign tumor and a malignant tumor. The analysis module also has a predictive report generation unit for the risk of benign or malignant liver tumors, which is connected to the control unit, and the control unit generates the liver of the subject of the clinical staff, which is generated by the contrast unit. It is characterized by inputting the judgment on the tumor type and the prediction of the probability of occurrence of liver tumor benign risk of the subject into the prediction report generation unit of the benign or malignant risk of the liver tumor to prepare a liver tumor property diagnosis report. The liver tumor intelligent analyzer according to claim 1.

Images