CN115040075A - Liver transplantation liver supply quality evaluation system and method based on hyperspectral imaging technology - Google Patents

Abstract

The invention relates to a liver transplantation liver supply quality evaluation system and method based on a hyperspectral imaging technology. The evaluation system comprises a motion control system, a mechanical arm, a hyperspectral space scanning data acquisition system, a real-time transmission processing system, a central control system and a display screen, wherein the motion control system is electrically connected with the mechanical arm; the real-time transmission processing system is electrically connected with the central control system; the central control system is electrically connected with the display screen. The invention has the advantages of novelty, capability of being used in operation, non-invasive, capability of realizing rapid evaluation of the quality of the liver and prediction of postoperative complications.

Description

Liver transplantation liver supply quality evaluation system and method based on hyperspectral imaging technology

Technical Field

The invention relates to the field of medical treatment, in particular to a liver transplantation liver supply quality evaluation system and method based on a hyperspectral imaging technology.

Background

Liver transplantation is the most effective means for treating end-stage liver diseases, and in recent years, the supply-demand imbalance between the shortage of the number of supplied livers and the increasing number of patients with end-stage liver diseases has become one of the most important factors for restricting the development of liver transplantation. Insufficient organ donation has prompted an increase in the use of Extended Criteria Donors (ECDs) for the liver. ECD for the liver includes: elderly donors (age >70 years), fatty liver (vesicular steatosis > 30% or mixed steatosis > 60%), cardiac death organ donor, liver with Warm Ischemia Time (WIT) over 30min and cold storage over 12h, etc., ECD supplies a large amount of liver, accounting for 30% -40% of the donors. Most organ donor donors have long-term hospitalization history before donation, have complicated disease conditions, and often combine multiple high-risk factors which potentially influence the quality of the liver, such as infection, hypoproteinemia, hypernatremia and the like. ECD provides poor liver quality, and the incidence of complications after transplantation is significantly increased, including Primary Graft Dysfunction (PGD), initial dysfunction (IPF), primary graft non-function (PNF), Hepatic Arterial Thrombosis (HAT), post-reperfusion syndrome (PRS), and ischemic biliary tract disease (ischemic cholestenopathy). Wherein the incidence of IPF is 5.2-36.3%, and the incidence of PNF is 0.9-7.2%. The risk factors for PGD during organ harvesting and implantation are complex. Most factors are associated with ischemia reperfusion (I/R) injury. I/R injury is considered to be the culprit of transplanted liver PGD. This is clearly associated with thermal damage caused by complex ischemic, hypoxic conditions that occur during cardiac arrest. Patients who develop PGD typically experience longer intensive care units and hospital stays, with higher mortality and graft loss rates than patients without graft dysfunction. This also causes great physical pain and economic stress on the patient. Therefore, the method is particularly important for the quality evaluation of the donor liver so as to avoid organ waste caused by abandoning the available donor liver and serious adverse effects caused by the application of the donor liver which is not suitable for the donor liver.

Evaluation of donor liver has been a major concern in the field of liver transplantation. Cold-hot ischemia time, fatty liver degree, donor blood sodium level, age, hepatitis infection, tumor, etc. are currently considered risk factors affecting donor liver quality. Currently, the clinical evaluation of the availability of the donor liver mainly depends on the subjective judgment of a transplantation physician (based on the general appearance and touch of the donor liver and the like), clinical examination and pathological biopsy results of donor liver tissues. However, research shows that the subjective judgment and clinical test result of a transplanting physician are not the most reliable method for evaluating the quality of the liver, and the pathological biopsy for liver puncture is difficult to puncture and sample every example of liver due to invasiveness and sampling errors, and meanwhile, the waiting time of the pathological biopsy is too long, so that the cold ischemia time is increased, and the anesthesia and operation risks are increased.

Therefore, the method for rapidly, reliably and non-invasively evaluating the quality of the liver is found, a new detection means is found and utilized to evaluate I/R injury, and complications such as PGD are further predicted, so that the method has important clinical significance.

Hyperspectral Imaging (HSI) is an emerging, non-destructive, advanced optical technology that has dual functions of spectroscopy and Imaging that enable Hyperspectral Imaging to provide both chemical and physical characteristics of an experimental subject. The hyperspectral imaging technology has the unique advantages of high spectral resolution and map integration, and is one of the most important technological breakthroughs since the development of the remote sensing technology. The hyperspectral imaging technology is a comprehensive technology integrating a detector technology, a precise optical machine, weak signal detection, a computer technology and an information processing technology into a whole, and simultaneously images a target area by tens of to hundreds of continuous and subdivided spectral bands in visible light, near infrared and mid-infrared areas of an electromagnetic spectrum. Hyper-spectral imaging (HSI) can enhance visualization of objects by containing spectra at visible and infrared wavelengths in the electromagnetic spectrum. In measuring the reflection and absorption of light at different wavelengths, HSI has the ability to extract spectral features of each pixel from a hyperspectral image while providing information about the different tissue components and their spatial distribution. Under specific wavelength, the chemical compositions and physical characteristics of tissues with different pathological states have different reflectivities, absorptivities and electromagnetic energy, and the difference of characteristic spectrum peaks is shown, qualitative or quantitative detection of tissue state information can be realized by analyzing the spectrum signals, and visualization of different pathological states of the tissues is realized according to spatial distribution information provided by a hyperspectral image, so that the tissue disease state is diagnosed. Hyperspectral imaging (HSI) enables rapid, non-contact, non-invasive and radiation-free assessment of tissue, allowing quantitative diagnostic examination of tissue pathology, morphology and composition.

In the field of applied medicine, HSI has become a popular research topic. HSI is increasingly used in medical diagnostics and image-guided surgery, to identify tumor tissue, to assess heart and circulatory pathology, to assess organ perfusion, to identify key anatomical structures in surgery, and many other fields.

Disclosure of Invention

In order to solve the problems existing in the rapid detection and evaluation of the liver quality in the current liver transplantation operation, based on the hyperspectral imaging technology, the invention designs a novel system and a method for evaluating the liver quality in liver transplantation based on the hyperspectral imaging technology, which can be used in the operation, are noninvasive, and can realize the rapid evaluation of the liver quality and the prediction of postoperative complications.

The technical solution of the invention is as follows: the invention relates to a liver transplantation and liver supply quality evaluation system based on a hyperspectral imaging technology, which is characterized in that: the evaluation system comprises a motion control system, a mechanical arm, a hyperspectral space scanning data acquisition system, a real-time transmission processing system, a central control system and a display screen, wherein the motion control system is electrically connected with the mechanical arm, the mechanical arm is electrically connected with the hyperspectral space scanning data acquisition system, and the real-time transmission processing system is electrically connected with the hyperspectral space scanning data acquisition system; the real-time transmission processing system is electrically connected with the central control system; the central control system is electrically connected with the display screen.

Further, the motion control system controls the mechanical arm to send the hyperspectral space scanning data acquisition system to a specified position above the liver tissue to be detected.

Furthermore, the hyperspectral space scanning data acquisition system is used for rapidly and noninvasively acquiring and detecting hyperspectral data of various substance components of the liver tissue in real time.

Further, the real-time transmission processing system sends the surface hyperspectral data of the detected liver tissue acquired by the hyperspectral space scanning data acquisition system to the central control system.

Further, the central control system is used for receiving various hyperspectral data; the high spectrum data of the tissue of the donor liver is collected and detected by a high spectrum space scanning data collection system, the property of the tissue of the donor liver is rapidly distinguished, and the tissue is displayed on a display screen in the form of an image; and the central control system receives the hyperspectral data acquired by the hyperspectral space scanning data acquisition system, judges the nature of the liver tissue and displays the characteristic on a display screen in a form of predicted incidence of related complications according to a judgment result.

A detection method of the liver transplantation liver supply quality evaluation system based on the hyperspectral imaging technology is characterized in that: the detection method comprises the following steps:

1) performing image processing and spectral information processing on the hyperspectral space data of the specific hepatic tissue to obtain characteristic hyperspectral space data of the specific hepatic tissue; obtaining characteristic hyperspectral space data of the donor liver tissues in various pathological states of different donors by the same method, and training a model;

2) performing image processing and spectral information processing on the hyperspectral space data of the contrast hepatic tissue with good pathological state to obtain characteristic hyperspectral space data of the contrast hepatic tissue with good pathological state; obtaining characteristic hyperspectral space data of different individuals in good pathological states by using the same method, wherein the characteristic hyperspectral space data are used for contrasting hepatic tissues, and training a model;

3) establishing characteristic hyperspectral space classification evaluation models of different mass donor liver tissues;

4) rapidly and noninvasively acquiring surface hyperspectral space data of an internal hepatic tissue in the liver transplantation operation process in real time, and taking the acquired hyperspectral data as a basis for judging the quality of the hepatic tissue;

5) the newly collected hyperspectral space data of the liver tissue is substituted into the model by the central control system for rapid analysis to obtain the conclusion of the quality of the liver tissue, and the probability of occurrence of related postoperative complications is obtained by analysis; determining the destination of data after the diagnosis of the postoperative pathological diagnosis is confirmed; if the pathology diagnosis confirms that the quality of the supplied liver tissue is poor or good, the newly acquired supplied liver tissue is brought into a characteristic hyperspectral spatial data training model of the supplied liver tissue and used for expanding and perfecting classification model data.

Further, the specific hepatic tissue is fatty liver or other diseased liver.

Further, the control donor tissue was donor tissue of young donors without underlying disease.

The device and the method for evaluating the quality of the liver transplantation and the liver supply provided by the invention utilize hyperspectral imaging to detect the liver supply tissue according to the surface and shallow information of the structure of the liver supply tissue in the liver transplantation operation, can quickly detect the liver supply tissue under the conditions of no contact and no invasion of the liver supply tissue, can quickly display the image state of the liver tissue, can quickly and automatically analyze various parameters of the liver supply tissue, realize the quick real-time evaluation of the liver supply quality in the liver transplantation operation process, predict the occurrence of complications such as Primary Graft Dysfunction (PGD) and the like after the recipient operation according to various parameters, and avoid the defects brought by the traditional liver supply evaluation mode. Therefore, the invention has the following beneficial effects:

1) the invention takes the hyperspectral data of the donor liver tissue collected in real time as the basis for judging the quality of the donor liver. According to the invention, the supplied liver evaluation classification model is established through the early-stage data training model and the later-stage data retraining model to judge the supplied liver property, so that the quality of the supplied liver is evaluated rapidly, and the occurrence of receptor-related complications is predicted.

2) The method for detecting the liver quality by hyperspectral imaging has an online real-time autonomous learning function, has an intelligent database of liver tissue, namely the database can be communicated with pathological diagnosis data or manually input into pathological diagnosis, and stores newly acquired hyperspectral data according to postoperative liver pathological diagnosis results. With the increase of detection time and detection quantity, the detection method continuously expands the hyperspectral database of the hepatic tissue, updates and optimizes the trained model in real time according to the new hyperspectral data of the hepatic tissue, automatically optimizes the classification method, further improves the specificity and sensitivity of the hepatic tissue property detection, and realizes rapid evaluation in the hepatic tissue operation.

3) The detection method of the invention establishes the supplied liver evaluation classification model through the early data training model and the retraining model to judge the supplied liver property, thereby quickly evaluating the quality of the supplied liver and predicting the occurrence of receptor-related complications. Meanwhile, a hyperspectral database of donor liver tissues is continuously expanded, the trained model is updated and optimized in real time according to the new hyperspectral database, and the classification method is automatically optimized.

Drawings

FIG. 1 is a system diagram of a liver transplantation liver quality assessment system based on hyperspectral imaging technology according to the invention;

fig. 2 is a schematic diagram of a detection method of the liver transplantation liver quality evaluation system based on the hyperspectral imaging technology.

Detailed Description

The general aspects of the invention will be described in further detail with reference to the following figures and specific examples:

referring to fig. 1, the structure of the specific embodiment of the liver transplantation and supply evaluation system based on hyperspectral imaging technology provided by the invention comprises: the system comprises a motion control system, a mechanical arm, a hyperspectral space scanning data acquisition system, a real-time transmission processing system, a central control system and a display screen; the motion control system is electrically connected with the mechanical arm, the mechanical arm is electrically connected with the hyperspectral space scanning data acquisition system, and the mechanical arm controlled by the motion control system sends the hyperspectral space scanning data acquisition system to a specified position above a to-be-detected liver tissue; the hyperspectral space scanning data acquisition system is used for rapidly and noninvasively acquiring and detecting hyperspectral data of various substance components of the liver tissue in real time.

The real-time transmission processing system is electrically connected with the hyperspectral space scanning data acquisition system; the real-time transmission processing system is electrically connected with the central control system; the real-time transmission processing system transmits the surface hyperspectral data of the detected liver tissue collected by the hyperspectral space scanning data collection system to the central control system in real time; the central control system is used for receiving various hyperspectral data; the central control system is electrically connected with the display screen.

The central control system is used for rapidly distinguishing the properties of the tissue of the donor liver according to the hyperspectral data of the tissue of the donor liver acquired and detected by the hyperspectral space scanning data acquisition system and displaying the properties on the display screen in the form of images; and the central control system receives the hyperspectral data acquired by the hyperspectral space scanning data acquisition system, judges the nature of the liver tissue and displays the characteristic on a display screen in a form of predicted incidence of related complications according to a judgment result.

Wherein, the motion control system and the mechanical arm adopt the prior device capable of three-dimensional motion. The hyperspectral space scanning data acquisition system, the real-time transmission processing system and the central control system can all adopt the existing devices or circuit structures.

Referring to fig. 2, the detection method of the liver transplantation liver supply quality evaluation system based on the hyperspectral imaging technology introduces the hyperspectral technology into the liver supply tissue quality detection, obtains the hyperspectral data of the liver supply tissue in a specific waveband through deep learning, judges the clinical liver supply quality according to the liver supply quality evaluation model and predicts related complications, and comprises the following steps:

1) performing image processing and spectral information processing on hyperspectral space scanning data of specific liver supply tissues (such as fatty liver) to obtain characteristic hyperspectral space data of the specific liver supply tissues (such as fatty liver); obtaining characteristic hyperspectral space data of the donor liver tissues in various pathological states of different donors by the same method, and training a model;

2) performing image processing and spectral information processing on hyperspectral space data of a control liver-supplying tissue (such as a liver-supplying tissue of a young donor without a basic disease) with a good pathological state to obtain characteristic hyperspectral space data of the control liver-supplying tissue (such as a liver-supplying tissue of a young donor without a basic disease) with a good pathological state; obtaining characteristic hyperspectral space data of different individuals in good pathological states by using the same method, wherein the characteristic hyperspectral space data are used for contrasting hepatic tissues, and training a model;

3) establishing characteristic hyperspectral space classification evaluation models of different mass donor liver tissues;

4) rapidly and noninvasively acquiring surface hyperspectral space data of a liver tissue in the liver transplantation operation process in real time, and taking the acquired hyperspectral data as a basis for judging the quality of the liver tissue;

5) the newly collected hyperspectral space data of the liver tissue is substituted into the model by the central control system to be analyzed to obtain the conclusion of the quality of the liver tissue, and the probability of occurrence of related postoperative complications is analyzed. Determining the destination of data after the diagnosis of the postoperative pathology diagnosis is confirmed; if the pathology diagnosis confirms that the quality of the supplied liver tissue is poor or good, the newly acquired supplied liver tissue is brought into a characteristic hyperspectral spatial data training model of the supplied liver tissue and used for expanding and perfecting classification model data.

The present invention and the technical contents not specifically described in the above embodiments are the same as the prior art.

The above are only specific embodiments disclosed in the present invention, but the scope of the present invention is not limited thereto, and the scope of the present invention should be determined by the scope of the claims.

Claims (8)

1. A liver transplantation supplies liver quality evaluation system based on hyperspectral imaging technique which characterized in that: the evaluation system comprises a motion control system, a mechanical arm, a hyperspectral space scanning data acquisition system, a real-time transmission processing system, a central control system and a display screen, wherein the motion control system is electrically connected with the mechanical arm, the mechanical arm is electrically connected with the hyperspectral space scanning data acquisition system, and the real-time transmission processing system is electrically connected with the hyperspectral space scanning data acquisition system; the real-time transmission processing system is electrically connected with the central control system; the central control system is electrically connected with the display screen.

2. The hyperspectral imaging technology-based liver transplantation liver quality assessment system according to claim 1, wherein: and the motion control system controls the mechanical arm to send the hyperspectral space scanning data acquisition system to a specified position above the liver tissue to be detected.

3. The hyperspectral imaging technology-based liver transplantation liver supply quality assessment system according to claim 1, wherein: the hyperspectral space scanning data acquisition system is used for rapidly and noninvasively acquiring and detecting hyperspectral data of various material components of a liver tissue in real time.

4. The hyperspectral imaging technology-based liver transplantation liver supply quality assessment system according to claim 1, wherein: the real-time transmission processing system sends the surface hyperspectral data of the detected liver tissue collected by the hyperspectral space scanning data collection system to the central control system.

5. The hyperspectral imaging technology-based liver transplantation liver quality assessment system according to claim 1, wherein: the central control system is used for receiving various hyperspectral data; the high spectrum data of the tissue of the donor liver is collected and detected by a high spectrum space scanning data collection system, the property of the tissue of the donor liver is rapidly distinguished, and the tissue is displayed on a display screen in the form of an image; and the central control system receives the hyperspectral data acquired by the hyperspectral space scanning data acquisition system, judges the nature of the liver tissue and displays the characteristic on a display screen in a form of predicted incidence of related complications according to a judgment result.

6. A detection method of a liver transplantation and supply evaluation system based on hyperspectral imaging technology according to claim 1 is characterized in that: the detection method comprises the following steps:

1) performing image processing and spectral information processing on the hyperspectral space data of the specific hepatic tissue to obtain characteristic hyperspectral space data of the specific hepatic tissue; obtaining characteristic hyperspectral space data of the donor liver tissues in various pathological states of different donors by the same method, and training a model;

2) performing image processing and spectral information processing on the hyperspectral space data of the contrast hepatic tissue with good pathological state to obtain characteristic hyperspectral space data of the contrast hepatic tissue with good pathological state; obtaining characteristic hyperspectral space data of different individuals in good pathological states by using the same method, wherein the characteristic hyperspectral space data are used for contrasting hepatic tissues, and training a model;

3) establishing characteristic hyperspectral space classification evaluation models of different mass donor liver tissues;

4) rapidly and noninvasively acquiring surface hyperspectral space data of an internal hepatic tissue in the liver transplantation operation process in real time, and taking the acquired hyperspectral data as a basis for judging the quality of the hepatic tissue;

5) the newly collected hyperspectral space data of the liver tissue is substituted into the model by the central control system for analysis to obtain the conclusion of the quality of the liver tissue, and the probability of occurrence of related postoperative complications is obtained through analysis; determining the destination of data after the diagnosis of the postoperative pathology diagnosis is confirmed; if the pathology diagnosis confirms that the quality of the supplied liver tissue is poor or good, the newly acquired supplied liver tissue is brought into a characteristic hyperspectral spatial data training model of the supplied liver tissue and used for expanding and perfecting classification model data.

7. The detection method for the liver transplantation liver quality evaluation system based on the hyperspectral imaging technology as claimed in claim 6, wherein: the specific hepatic tissue is fatty liver or other diseased liver.

8. The detection method of the liver transplantation liver quality assessment system based on the hyperspectral imaging technology according to claim 6, characterized in that: the control donor liver tissue is donor liver tissue of a young donor without a fundamental disease.

Images