WO2021051335A1

WO2021051335A1 - Hepatitis c liver fibrosis feature information extraction method and apparatus

Info

Publication number: WO2021051335A1
Application number: PCT/CN2019/106611
Authority: WO
Inventors: 饶慧瑛; 刘峰; 魏来; 任亚运; 滕霄; 戴其尚
Original assignee: 北京大学人民医院(北京大学第二临床医学院); 杭州筹图科技有限公司
Priority date: 2019-09-19
Filing date: 2019-09-19
Publication date: 2021-03-25

Abstract

A hepatitis C liver fibrosis feature information extraction method and apparatus. The non-stained section of a target sample is imaged by using SHG and TPE to obtain a target image; an SHG parameter in the target image is obtained, and the SHG parameter is quantized to obtain the morphological feature of collagen; a patient's histological response is predicted by means of a specific clinical feature and the morphological feature of the collagen, and the parameter that meets a preset condition with the change in Ishak staging before and after treatment is selected to generate a two-dimensional heat map. The two-dimensional heat map is used for predicting the change in Ishak staging after continuous virological response to obtain the prediction performance of ISHAK fibrosis staging change. Thus, optical technology is used for predicting the reversal of fibrosis associated with viral infection before treatment, so that the current clinical requirement can be satisfied, and a data basis is provided for the subsequent clinical research.

Description

Hepatitis C liver fibrosis feature information extraction method and device

Technical field

The invention relates to the technical field of medical information processing, in particular to a method and device for extracting hepatitis C fibrosis feature information based on second harmonic and two-photon excitation fluorescence.

Background technique

Second harmonic (SHG) and two-photon excitation fluorescence (TPE) microscopy quantitatively evaluate collagen in unstained tissue samples. In chronic fibrous diseases, scar progression and regression often proceed at the same time. Although continuous chronic damage is taken into account, the overall balance is conducive to progression. Due to the difficulty in the treatment of these diseases, collagen parameters for identifying progression and regression and/or prognosis are not easily available to a large extent.

However, almost all patients can successfully eradicate the hepatitis C virus, so that the characteristics of the progression and reversal of hepatitis C can be studied. In addition, since this complete virus eradication does not necessarily mean the complete solution of fibrosis, new feature information is needed to characterize the morphological characteristics of hepatitis C hepatitis fibrosis in order to achieve the reversal of fibrosis associated with viral infection before treatment. In order to enable researchers to conduct further pathological studies based on the predicted results.

Summary of the invention

In view of the above-mentioned problems, the present invention provides a method and device for extracting hepatitis C fibrosis characteristic information, which can obtain a two-dimensional heat map that characterizes hepatitis C hepatitis fibrosis, so as to treat fibrosis related to fibrosis before viral infection. Forecast of reversal.

In order to achieve the above objective, the present invention provides the following technical solutions:

A method for extracting hepatitis C liver fibrosis feature information, the method comprising:

Obtaining a target sample, the target sample being generated based on a hepatitis C liver biopsy specimen;

Imaging the non-stained section corresponding to the target sample by SHG and TPE to obtain a target image;

Acquiring SHG parameters in the target image, and quantifying the SHG parameters to obtain the morphological characteristics of collagen;

The histological response of the patient is predicted by the specific clinical characteristics and the morphological characteristics of the collagen, and the parameters that meet the preset conditions with the changes in Ishak staging before and after treatment are selected to generate a two-dimensional heat map, the two-dimensional heat map Characterizing hepatitis C liver fibrosis characteristic information enables the use of the two-dimensional heat map to predict changes in Ishak staging after continuous virological response, and obtain the predictive performance of changes in ISHAK fibrosis staging.

Optionally, the obtaining the target sample includes:

According to the feature extraction conditions, select the initial sample from the hepatitis C liver biopsy specimen;

The initial sample is preprocessed and grouped to obtain a target sample. The preprocessing includes fixing, embedding and slicing, and the target sample includes valid samples and invalid samples.

Optionally, the method further includes:

When quantifying the SHG parameters, the collagens are grouped. When grouping according to the model, the collagen is divided into dispersed collagen and aggregated collagen; grouped according to the position of the collagen, the collagen is divided into portal vein collagen and septal collagen And fibrous collagen.

Optionally, the method further includes:

The rank sum test is used to evaluate the statistical difference between the clinical parameters and SHG parameters of the effective and ineffective samples before treatment, and the evaluation results are obtained, which are used for the selection of the morphological characteristics of collagen.

Optionally, said using the two-dimensional heat map to predict changes in Ishak staging after continuous virological response to obtain the predictive performance of changes in ISHAK fibrosis staging includes:

Separately constructing a training set and a test set of the heat map, the training set is used to train the heat map, and the test set is used to train the heat map;

Determine the target heat map according to the training set and the test set;

Predicting changes in Ishak staging after sustained virological response according to the target heat map, and obtaining the predictive performance of changes in ISHAK fibrosis staging;

According to the prediction performance, a prediction parameter is calculated, and the prediction parameter includes an AUROC, a sensitivity value, and a specificity value.

A device for extracting hepatitis C liver fibrosis feature information, the device comprising:

A sample acquisition unit for acquiring a target sample, the target sample being generated based on a hepatitis C liver biopsy specimen;

An imaging unit, configured to image the non-stained section corresponding to the target sample through SHG and TPE to obtain a target image;

The quantification unit is used to obtain the SHG parameters in the target image, and quantify the SHG parameters to obtain the morphological characteristics of the collagen;

The generating unit is used to predict the histological response of the patient by the specific clinical characteristics and the morphological characteristics of the collagen, and select the parameters that meet the preset conditions with the changes in Ishak staging before and after treatment to generate a two-dimensional heat map. The two-dimensional heat map characterizes the characteristic information of hepatitis C fibrosis, so that the two-dimensional heat map can be used to predict changes in Ishak staging after continuous virological response, and obtain the predictive performance of changes in ISHAK fibrosis staging.

Optionally, the sample acquisition unit includes:

The selection subunit is used to select the initial sample from the hepatitis C liver biopsy specimen according to the feature extraction conditions;

The preprocessing subunit is used to preprocess and group the initial samples to obtain target samples. The preprocessing includes fixing, embedding and slicing, and the target samples include valid samples and invalid samples.

Optionally, the device further includes:

The grouping unit is used to group collagen when the SHG parameters are quantified. When grouping according to the mode, the collagen is divided into dispersed collagen and aggregated collagen; grouped according to the position of the collagen, the collagen is divided into Portal vein collagen, septal collagen and fibrous collagen.

Optionally, the device further includes:

The evaluation unit is used to use the rank sum test to evaluate the statistical difference between the clinical parameters and the SHG parameters of the effective sample and the invalid sample before treatment, and obtain the evaluation result, which is used to select the morphological characteristics of the collagen.

Optionally, the device further includes a prediction unit configured to use the two-dimensional heat map to predict changes in Ishak staging after continuous virological response, and obtain the predictive performance of changes in ISHAK fibrosis staging;

Wherein, the prediction unit includes:

Constructing a subunit for separately constructing a training set and a test set of the heat map, the training set is used for training the heat map, and the test set is used for the heat map;

A determining subunit for determining a target heat map according to the training set and the test set;

The prediction subunit is used to predict the Ishak staging change after the continuous virological response according to the target heat map, and obtain the predictive performance of the ISHAK fibrosis staging change;

The calculation subunit is configured to calculate and obtain a prediction parameter according to the prediction performance, and the prediction parameter includes an AUROC, a sensitivity value, and a specificity value.

Compared with the prior art, the present invention provides a method and device for extracting hepatitis C hepatitis fibrosis feature information, which uses SHG and TPE to image a target sample to obtain a target image, obtain SHG parameters in the target image, and compare the SHG parameters. Perform quantification to obtain the morphological characteristics of collagen; predict the histological response of the patient by specific clinical characteristics and morphological characteristics of collagen, and select the parameters that meet the preset conditions with the changes in Ishak staging before and after treatment to generate two-dimensional heat Figure. Realize the use of two-dimensional heat maps to predict Ishak staging changes after continuous virological response, and obtain the predictive performance of ISHAK fibrosis staging changes. In this application, a two-dimensional heat map that characterizes hepatitis C fibrosis can be obtained, so as to realize the use of optical technology to predict the fibrosis reversal of fibrosis related to viral infection before treatment, so that it can meet current clinical needs and serve as a follow-up clinic. Research provides a basis for data.

Description of the drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only It is an embodiment of the present invention. For those of ordinary skill in the art, without creative work, other drawings can be obtained according to the provided drawings.

FIG. 1 is a schematic flowchart of a method for extracting hepatitis C fibrosis feature information according to an embodiment of the present invention;

2 is an example diagram of a process of constructing a reference system using pre-treatment clinical and morphological data of a patient according to an embodiment of the present invention and an example diagram of the result of ISHAK change;

FIG. 3 is an example diagram of a leave-one-out cross-validation provided by an embodiment of the present invention;

FIG. 4 is an example diagram of a heat map provided by an embodiment of the present invention;

Fig. 5 is a schematic structural diagram of a device for extracting hepatitis C fibrosis feature information according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

The terms "first" and "second" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific sequence. In addition, the terms "include" and "have" and any variations of them are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not set in the listed steps or units, but may include steps or units that are not listed.

In the embodiment of the present invention, a method for extracting hepatitis C fibrosis feature information is provided, which can be applied to the study of hepatitis C, that is, the method for extracting hepatitis C fibrosis feature information provided according to the embodiment of the present invention can be a follow-up method for hepatitis C fibrosis. Hepatitis C (hepatitis C is a type of hepatitis caused by hepatitis C virus (HCV) infection) clinical research provides data-based reference information, that is, hepatitis C hepatic fibrosis feature information, in this application is the two-dimensional fever that will be generated The figure serves as the feature information. Referring to Figure 1, the method includes:

S101. Obtain a target sample.

The target sample is generated based on the hepatitis C liver biopsy specimen, and specifically the target sample acquisition includes:

S1011, according to the feature extraction conditions, select an initial sample from the hepatitis C liver biopsy specimen;

S1012. Perform preprocessing and grouping on the initial sample to obtain a target sample. The preprocessing includes fixing, embedding, slicing, and slicing. The target samples include valid samples and invalid samples. After processing the initial sample, a non-stained section is obtained. That is, the SHG/TPE image is a non-stained slice image. If a stained section is obtained, it can be used for pathological evaluation, for training and verification of results.

In the examples of this application, 38 pairs of hepatitis C liver biopsy specimens (LBX) were selected to obtain clinical and pathological characteristics from the patient's pathology. When selecting LBX, it needs to be extracted according to the feature extraction conditions, which are as follows:

Age 20-70 years; Chronic hepatitis C infection with or without cirrhosis; HCV-RNA level at baseline is higher than 10000IU/ml; Receive direct-acting antiviral drugs (DAA) antiviral therapy for 12 or 24 weeks; treatment completed Received sustained virological response (SVR, named Hepatitis C Virus Infection Treatment) after 24 weeks. A paired liver biopsy was performed at 24 weeks after treatment and at baseline.

Exclusion criteria include co-infection with hepatitis B or human immune efficiency virus (HIV); the presence of other forms of chronic liver disease; decompensated liver disease (including ascites, variceal bleeding or hepatic encephalopathy); alpha-fetoprotein >100ng/ml Or creatinine clearance rate <50ml/min; any malignant tumor; any serious heart, lung, kidney, brain, blood disease or other complications of important system diseases; serious neurological or psychological diseases; pregnant or lactating women.

After obtaining the initial sample, standard clinical techniques need to be used for formalin fixation, paraffin embedding, and sectioning of LBX. The sections are stained with hematoxylin and eosin (H&E), reticulin and Mason's trichrome. The purpose of staining is for subsequent pathological evaluation.

All liver biopsy samples were evaluated by two experienced liver pathologists. The treatment plan, biopsy sequence, biochemical response, and liver stiffness values were not blinded, and were independently evaluated. The Ishak modified tissue activity index (HAI) grading system 10 was used to evaluate the necrotic inflammation activity and the degree of fibrosis. According to the changes in the degree of Ishak fibrosis after treatment, 38 patients were divided into two groups: effective group and ineffective group. Effective treatment means reducing the stage of Ishak fibrosis.

S102, imaging the target sample by SHG and TPE to obtain a target image.

A 5-micron thick section of each unstained liver biopsy sample was imaged, where a second harmonic generation (SHG) microscope was used to show collagen and a two-photon excitation (TPE) fluorescence microscope to highlight liver cells. The sample was excited by a 780nm laser, and SHG and TPEF signals were recorded at 390nm and 550nm, respectively. The image is magnified 20 times, with a resolution of 512×512 pixels, and each image represents a tissue area of 200×200μm2. Multiple adjacent images are captured to cover the entire part.

S103: Acquire SHG parameters in the target image, and quantify the SHG parameters to obtain morphological characteristics of collagen.

The algorithm in the prior art is used to quantify the SHG parameters in the image to obtain 100 morphological features. In these measurements, collagen is divided into two different modes: namely, dispersed collagen (fine collagen fibers) and aggregated collagen (large plaques). Collagen is also grouped in different ways according to its location: portal vein collagen (portal vein dilation), septal collagen (bridging fibrosis), and fibrous collagen (fine collagen distributed in the pericellular/perisinus space). Among them, the algorithm is an algorithm that automatically detects the position of collagen in the image, and recognizes the portal, septa, and fibrillar regions, and quantifies the characteristics of collagen on these regions.

S104: Predict the histological response of the patient by the specific clinical characteristics and the morphological characteristics of the collagen, and select the parameters that meet the preset conditions with the changes in Ishak staging before and after treatment, to generate a two-dimensional heat map.

The two-dimensional heat map characterizes hepatitis C fibrosis characteristic information, so that the two-dimensional heat map can be used to predict changes in Ishak staging after continuous virological response, and obtain the predictive performance of changes in ISHAK fibrosis staging.

The rank sum test is used to evaluate the statistical difference between the clinical parameters and SHG parameters of the effective and ineffective samples before treatment, and the evaluation results are obtained, which are used for the selection of the morphological characteristics of collagen. And in the prediction process, the training set and the test set of the heat map are constructed separately. The training set trains the heat map, and the test set is used to calculate the heat map; the target heat map is determined according to the training set and the test set. Figure; according to the target heat map to predict the changes in Ishak staging after sustained virological response, and obtain the predictive performance of ISHAK fibrosis staging changes; according to the predictive performance, calculate and obtain predictive parameters, the predictive parameters include AUROC, sensitive Sexual value and specificity value.

Specifically, the first step: using the two-tailed Wilcoxon rank sum test to evaluate the statistical differences between the clinical parameters and SHG parameters of the effective group and the ineffective group before treatment. Among them, the evaluation results are used for parameter selection, and 33 morphological parameters are selected.

AUROC analysis (characteristic curve area) is used to compare the performance of different heat maps to predict effective fibrosis progression/regression response. The statistical significance level was set at P<0.05. Among them, the AUROC analysis is to use the heat map to obtain the predicted value, and the real analysis to calculate the AUROC

Step 2: Summarize the establishment and verification process of multi-parameter ISHAK staging changes after SVR prediction system. Among them, the parameter combination is as follows:

Clinical parameters (n=7) Morphological parameters (n=33, p<0.05)

The first set of clinical parameters only (21 combinations)

{E.g. ALT&AST, ALT&ALB, or ALT&TBIL,...}

The second group only has morphological collagen parameters (528 combinations)

{E.g. %SHG&%Agg, %Agg&#shortSTR, or#LongStr&StrLength}

The third group has 1 clinical parameter and 1 morphological collagen parameter (231 combinations)

{E.g. ALT&%SHG, TBIL&%StrWidth, or PLT&#StrP,...}

Figure 2 illustrates the process of constructing a reference system using the patient's pre-treatment clinical and morphological data and its ISHAK change results. Using this reference system, the fibrosis changes of new patients after SVR can be predicted based on the patient's pre-treatment data. Use the heat map of the 2 parameter system (PLT&#ShortStrPA) as an example.

Figure 3 illustrates the "leave-one-out cross-validation" method used in the present invention. Thirty-seven patients were used as the training set to construct the heat map, and the remaining 38 patients were used to test the accuracy of the heat map prediction. This process was repeated 38 times, and all patients were used as test patients. Finally, the AUROC and sensitivity and specificity values were calculated based on the predictive performance of ISHAK fibrosis stage changes.

The present invention provides a method for extracting hepatitis C fibrosis feature information, which uses SHG and TPE to image a target sample to obtain a target image, obtains SHG parameters in the target image, and quantifies the SHG parameters to obtain the morphological characteristics of collagen ; Through the specific clinical characteristics and the morphological characteristics of collagen to predict the histological response of the patient, and select the parameters that meet the preset conditions with the changes in Ishak staging before and after treatment, to generate a two-dimensional heat map. Realize the use of two-dimensional heat maps to predict Ishak staging changes after continuous virological response, and obtain the predictive performance of ISHAK fibrosis staging changes. In this application, a two-dimensional heat map that characterizes hepatitis C fibrosis can be obtained, so as to realize the use of optical technology to predict the fibrosis reversal of fibrosis related to viral infection before treatment, so that it can meet current clinical needs and serve as a follow-up clinic. Research provides a basis for data.

As an example, an archival LBX study was conducted on 38 patients with sustained virological response (SVR) and ISHAK fibrosis staging before and after treatment. 13 patients were defined as "effective reversal", that is, the degree of Ishak fibrosis decreased after treatment. 23 patients were defined as "invalid reversal-unchanged staging", that is, maintaining the same ISHAK staging. Two patients showed an increase in ISHAK staging and were designated as "invalid reversal—increased staging." See Table 1 for a summary of the ISHAK staging changes of the sample. The collagen area ratio (CPA) of each group before and after treatment is shown in Table 2. Fibrotic collagen decreased significantly in the "effective reversal" group (0.40%), and increased significantly in the "invalid reversal-increased stage" group (2.13%), but there was no obvious trend in the "ineffective reversal-stage unchanged" group (0.26%).

All 7 clinical parameters were selected for prognostic analysis, but 33 (100) specific morphological collagen parameters were selected as parameters related to changes in ISHAK fibrosis stage after SVR. These parameters p<0.05. These parameters were paired into three groups (Table 3): (A) group 1-clinical parameters only, (B) group 2-morphological collagen parameters only, and (C) group 3-using 1 clinical and 1 morphological collagen parameter. Choose from a total of 21,528,231 combinations generated for groups (A), (B), and (C). All combinations are related to changes in ISHAK staging before and after treatment. Choose the combination with the highest auroral value (see Table 3). From this, five parameters (PLT, TBILI, #LongStr, %Agg, #ShortStrPA) are determined, and then used to compile heat map predictions.

In addition, these 5 parameters are combined as follows: (D) any 3 of the 5 parameters, (E) any 4 of the 5 parameters, and (F) all 5 parameters. The combination with the highest AUROC value is also shown in Table 3. Combining all 5 parameters, we got the best auroral value of 0.911, but did not get the best sensitivity or specificity value. In general, the best performance is the combination of 4 features-3 morphological parameters, including LongStr (total number of collagen bundles> 40 microns), %Agg (proportion of polymerized collagen) and ShortStrPA (portal area collagen) The total number of protein short bundles <40 microns) and 1 clinical parameter (PLT).

In order to illustrate how to use this multi-parameter system to predict changes in ISHAK staging during treatment, first only use the two parameter combinations shown in Table 3 (A), (B) and (C). The heat map generated from all 38 patients using these 5 parameters is shown in Figure 4. Using these heat maps, by locating the patient's position in the heat map and the clinical and/or morphological data of the patient before treatment, predict the fibrosis changes of the patient after SVR.

Figure 2 shows the process of constructing a reference system (heat map) using the patient's pre-treatment clinical and morphological collagen data, and the results of their isak changes. Using this reference system, we can predict fibrosis changes in new patients after SVR based on the patient's pre-treatment data. Figure 2 illustrates an example, using a heat map of a 2 parameter system. (PLT&#ShortStrPA).

The verification method "leave-one-out cross-validation" used in this study is shown in Figure 3. In this method, 37 patients were used as the training set for constructing the heat map, and the remaining patients (38 patients) were used to test the accuracy of the structure prediction. Heat map. This process was then repeated 38 times with all different patients as test patients. Finally, the AUROC, sensitivity and specificity were calculated based on the predictive performance of the stage changes of ishak fibrosis.

SHG/TPE has shown the promise of evaluating fibrotic diseases involving inflammation and tumors in clinical human samples and animal model tissues, liver and other organs. As we all know, the process of chronic fibrosis is usually two-way, progress and reversal occur at the same time. Fibrosis related to wound repair usually stops and reverses, but disease-related fibrosis (such as chronic liver disease, nephrosclerosis, idiopathic pulmonary fibrosis, scleroderma) will not get a good effect, so only Progressive changes in fibrosis have been well studied. In this case, the clinical and prognostic utility of SHG/TPE is limited. The recent successful treatment of chronic hepatitis C infection has changed this situation, providing a model for the potentially larger clinical application of SHG/TPE analysis, capable of assessing subtle changes in fibrotic degeneration better than the standard histological stage.

In this study, a group of successfully cured patients with chronic hepatitis C were subjected to pre-treatment and post-treatment biopsy, and 100 fibrous collagen morphological parameters and 7 clinical (biochemical) parameters were evaluated. According to histological (ISHAK) staging and CPA changes, patients were divided into ISHAK staging and CPA decreased at the same time ("effective reversal"), ISHAK staging remained unchanged but CPA decreased ("invalid reversal-staging unchanged") and ISHAK staging and CPA simultaneously Elevated ("invalid reversal-increased staging"). The CPA value is obviously better than the ISHAK staging to reflect the improvement of fibrosis, as pointed out in the previous fibrosis regression study.

However, further multi-step statistical analysis resulted in data that exceeded the standard histological classification. The correlation between clinical and morphological parameters and results firstly determined a pair of clinical parameters (tbili and plt) and 33 morphological parameters related to the improvement stage. Using the heat map prediction system, these parameters are paired again to compare with the results. Then analyze the best values of these correlations in 3, 4, and 5 parameter groups. AUROC and sensitivity/specificity analysis show that the best feature set for prediction results is: #LongStr,%Agg, #ShortStrPA, and PLT.

These parameters may have pathophysiological significance related to the progression of chronic viral hepatitis fibrosis, especially whether the main path of progression is concentrated on the cellular level (ie activation of hepatic stellate cells) or tissue level events (the primacy of vascular thrombotic events) , And proposed new methods to simulate the pathophysiology in this clinical environment. #LongStr and %Agg together reflect the collagen morphology of advanced liver fibrosis. Increasing the values of both, not surprisingly, indicates that the possibility of fibrosis is reduced. This finding is consistent with these two hypotheses, because these properties may make them more resistant to dissolution. However, #ShortStrPA may represent a change that is limited to the interstitium of the portal vein. It has recently been confirmed to be a structural feature of the small shopping mall space, which is the connection between the inflow and outflow of blood vessels (venous, sinusoidal, lymph) in the portal vein. PLT stands for decreased platelet circulation secondary to portal hypertension. Therefore, these hilar lymphatic vascular characteristics contribute to the theoretical importance of vascular changes in the process of fibrosis.

More practically, the fine-grained data obtained from the SHG/TPE tissue examination, combined with routine clinical parameters, clearly provides new prognostic information for predicting the clinical outcome of LBX before treatment. The clinical significance of this point cannot be underestimated: up to 15% of patients with advanced liver disease have been cured of the underlying infection, but still have progressive fibrosis (resulting in death or transplantation). For the currently used prognostic system, it relies on the histological findings of biopsy specimens after hepatitis B treatment. In this system, virus replication is only inhibited, and changes after facts are identified to predict recent results. On the other hand, this heat map method is based on a pre-treatment biopsy after a complete cure to obtain true prognostic data. Identifying these patients from the perspective of pre-treatment biopsy, once SVR is obtained, may lead to important modifications to long-term clinical follow-up without the need for further biopsy.

Therefore, in the clinically cured hepatitis C, SHG/TPE may become the center of patient care, which is a precision treatment method based on photon technology applied to liver disease. Although the treatment of other chronic fibrotic diseases is still uncertain, we expect that for patients with newly developed anti-fibrotic drugs (currently undergoing clinical trials), similar analysis and final prognostic value may be obtained. Change the balance between progress and regression. The analytical methods presented in this article may help to evaluate and/or predict the response of such clinical trials, and ultimately perform treatment evaluations when such treatments reach routine clinical applications.

The SHG-based predictive model developed in the present invention may not be so innovative in terms of optics/methodology, but focuses on the clinical validation of a well-designed patient cohort based on clinical trials. This method can meet the needs of evaluating and predicting the effect of antiviral treatment, as well as the clinical needs in future clinical practice.

Table 1 Changes in Ishak fibrosis stages before and after treatment with direct-acting antiviral drugs in 38 cases

Table 2 The average value and standard deviation of the collagen area ratio (CPA) value of each group before and after treatment with direct-acting antiviral drugs (DAAs)

Table 3 AUROC values of different combinations of clinical and morphological parameters and their corresponding sensitivity/specificity values

Correspondingly, referring to FIG. 5, in an embodiment of the present invention, a device for extracting hepatitis C hepatitis fibrosis feature information is also provided, and the device includes:

The sample obtaining unit 10 is configured to obtain a target sample, the target sample being generated based on a hepatitis C liver biopsy specimen;

The imaging unit 20 is configured to image the non-stained section corresponding to the target sample through SHG and TPE to obtain a target image;

The quantification unit 30 is configured to obtain the SHG parameters in the target image, and quantify the SHG parameters to obtain the morphological characteristics of collagen;

The generating unit 40 is used to predict the histological response of the patient by the specific clinical characteristics and the morphological characteristics of the collagen, and select the parameters that meet the preset conditions with the changes in Ishak staging before and after treatment to generate a two-dimensional heat map, The two-dimensional heat map characterizes hepatitis C fibrosis characteristic information, so that the two-dimensional heat map can be used to predict changes in Ishak staging after continuous virological response, and obtain the predictive performance of changes in ISHAK fibrosis staging.

Optionally, the sample acquisition unit includes:

Optionally, the device further includes:

Wherein, the prediction unit includes:

The invention provides a hepatitis C hepatitis fibrosis feature information extraction device, which uses SHG and TPE to image a target sample to obtain a target image, obtains SHG parameters in the target image, and quantifies the SHG parameters to obtain the morphological characteristics of collagen ; Through the specific clinical characteristics and the morphological characteristics of collagen to predict the histological response of the patient, and select the parameters that meet the preset conditions with the changes in Ishak staging before and after treatment, to generate a two-dimensional heat map. Realize the use of two-dimensional heat maps to predict Ishak staging changes after continuous virological response, and obtain the predictive performance of ISHAK fibrosis staging changes. In this application, a two-dimensional heat map that characterizes hepatitis C fibrosis can be obtained, so as to realize the use of optical technology to predict the fibrosis reversal of fibrosis related to viral infection before treatment, so that it can meet current clinical needs and serve as a follow-up clinic. Research provides a basis for data.

The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown in this document, but should conform to the widest scope consistent with the principles and novel features disclosed in this document.

Claims

A method for extracting hepatitis C liver fibrosis characteristic information, which is characterized in that the method includes:

Obtaining a target sample, the target sample being generated based on a hepatitis C liver biopsy specimen;

Imaging the non-stained section corresponding to the target sample by SHG and TPE to obtain a target image;

Acquiring SHG parameters in the target image, and quantifying the SHG parameters to obtain the morphological characteristics of collagen;

The histological response of the patient is predicted by the specific clinical characteristics and the morphological characteristics of the collagen, and the parameters that meet the preset conditions with the changes in Ishak staging before and after treatment are selected to generate a two-dimensional heat map, the two-dimensional heat map Characterizing hepatitis C liver fibrosis characteristic information enables the use of the two-dimensional heat map to predict changes in Ishak staging after continuous virological response, and obtain the predictive performance of changes in ISHAK fibrosis staging.
The method according to claim 1, wherein said obtaining a target sample comprises:

According to the feature extraction conditions, select the initial sample from the hepatitis C liver biopsy specimen;

The initial samples are preprocessed and grouped to obtain target samples. The preprocessing includes fixation, embedding, and slicing. The target samples include valid samples and invalid samples.
The method according to claim 1, wherein the method further comprises:

When quantifying the SHG parameters, the collagens are grouped. When grouping according to the model, the collagen is divided into dispersed collagen and aggregated collagen; grouped according to the position of the collagen, the collagen is divided into portal vein collagen and septal collagen And fibrous collagen.
The method according to claim 2, wherein the method further comprises:

The rank sum test is used to evaluate the statistical difference between the clinical parameters and SHG parameters of the effective and ineffective samples before treatment, and the evaluation results are obtained, which are used for the selection of the morphological characteristics of collagen.
The method of claim 1, wherein the using the two-dimensional heat map to predict the changes in Ishak staging after continuous virological response to obtain the predictive performance of the changes in ISHAK fibrosis staging comprises:

Separately constructing a training set and a test set of the heat map, the training set is used to train the heat map, and the test set is used to train the heat map;

Determine the target heat map according to the training set and the test set;

Predicting changes in Ishak staging after sustained virological response according to the target heat map, and obtaining the predictive performance of changes in ISHAK fibrosis staging;

According to the prediction performance, a prediction parameter is calculated, and the prediction parameter includes an AUROC, a sensitivity value, and a specificity value.
A device for extracting hepatitis C liver fibrosis characteristic information, characterized in that the device comprises:

A sample acquisition unit for acquiring a target sample, the target sample being generated based on a hepatitis C liver biopsy specimen;

An imaging unit, configured to image the non-stained section corresponding to the target sample through SHG and TPE to obtain a target image;

The quantification unit is used to obtain the SHG parameters in the target image, and quantify the SHG parameters to obtain the morphological characteristics of the collagen;

The generating unit is used to predict the histological response of the patient by the specific clinical characteristics and the morphological characteristics of the collagen, and select the parameters that meet the preset conditions with the changes in Ishak staging before and after treatment to generate a two-dimensional heat map. The two-dimensional heat map characterizes the characteristic information of hepatitis C fibrosis, so that the two-dimensional heat map can be used to predict changes in Ishak staging after continuous virological response, and obtain the predictive performance of changes in ISHAK fibrosis staging.
The device according to claim 6, wherein the sample acquisition unit comprises:

The selection subunit is used to select the initial sample from the hepatitis C liver biopsy specimen according to the feature extraction conditions;

The preprocessing subunit is used to preprocess and group the initial samples to obtain target samples. The preprocessing includes fixing, embedding and slicing, and the target samples include valid samples and invalid samples.
The device according to claim 6, wherein the device further comprises:

The grouping unit is used to group collagen when the SHG parameters are quantified. When grouping according to the mode, the collagen is divided into dispersed collagen and aggregated collagen; grouped according to the position of the collagen, the collagen is divided into Portal vein collagen, septal collagen and fibrous collagen.
The device according to claim 7, wherein the device further comprises:

The evaluation unit is used to use the rank sum test to evaluate the statistical difference between the clinical parameters and the SHG parameters of the effective sample and the invalid sample before treatment, and obtain the evaluation result, which is used to select the morphological characteristics of the collagen.
The device according to claim 6, characterized in that the device further comprises a prediction unit configured to use the two-dimensional heat map to predict changes in Ishak staging after continuous virological response to obtain ISHAK fibers The predictive performance of chemical stage changes;

Wherein, the prediction unit includes:

Constructing a subunit for separately constructing a training set and a test set of the heat map, the training set is used for training the heat map, and the test set is used for the heat map;

A determining subunit for determining a target heat map according to the training set and the test set;

The prediction subunit is used to predict the Ishak staging change after the continuous virological response according to the target heat map, and obtain the predictive performance of the ISHAK fibrosis staging change;

The calculation subunit is configured to calculate and obtain a prediction parameter according to the prediction performance, and the prediction parameter includes an AUROC, a sensitivity value, and a specificity value.