CN110599485A - Hepatitis C liver fibrosis characteristic information extraction method and device - Google Patents
Hepatitis C liver fibrosis characteristic information extraction method and device Download PDFInfo
- Publication number
- CN110599485A CN110599485A CN201910887661.3A CN201910887661A CN110599485A CN 110599485 A CN110599485 A CN 110599485A CN 201910887661 A CN201910887661 A CN 201910887661A CN 110599485 A CN110599485 A CN 110599485A
- Authority
- CN
- China
- Prior art keywords
- collagen
- heat map
- parameters
- ishak
- shg
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
-
- 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
-
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Radiology & Medical Imaging (AREA)
- Biomedical Technology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Bioethics (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a method and a device for extracting hepatitis C hepatic fibrosis characteristic information, which are used for imaging a non-staining section of a target sample by using SHG and TPE to obtain a target image, acquiring SHG parameters in the target image, and quantifying the SHG parameters to obtain morphological characteristics of collagen; a two-dimensional heat map is generated by predicting the histological response of a patient by specific clinical characteristics and morphological characteristics of collagen and selecting parameters which meet preset conditions with the Ishak stage change before and after treatment. The method realizes the prediction of the Ishak staged change after continuous virology reaction by utilizing the two-dimensional heat map, and obtains the prediction performance of the ISHAK fibrosis staged change. Therefore, the method realizes the purpose of predicting the fibrosis reversal of the virus infection related fibrosis before treatment by using an optical technology, so that the method can meet the current clinical requirement and provide a data base for the subsequent clinical research.
Description
Technical Field
The invention relates to the technical field of medical information processing, in particular to a method and a device for extracting hepatitis C and hepatic fibrosis characteristic information based on second harmonic and two-photon excitation fluorescence.
Background
Second Harmonic (SHG) and two-photon excited fluorescence (TPE) microscopy quantitatively assessed collagen in unstained tissue samples. In chronic fibrotic disease, scar progression and regression often proceed simultaneously, although the overall balance favors progression in view of persistent chronic injury. Since these diseases are difficult to treat, collagen parameters that identify progression and regression and/or prognosis are largely not readily available.
However, almost all patients successfully eradicate the hepatitis c virus, thereby enabling the study of the progression and reversal characteristics of hepatitis c. Furthermore, since such complete viral eradication does not necessarily mean complete resolution of fibrosis, new characterizing information is needed to characterize hepatic fibrosis of hepatitis c morphologically to enable reversal of fibrosis associated with viral infection prior to treatment to enable researchers to conduct further pathological studies based on the predicted outcome.
Disclosure of Invention
In view of the above problems, the present invention provides a method and an apparatus for extracting hepatitis c liver fibrosis characteristic information, which can obtain a two-dimensional heat map representing hepatitis c liver fibrosis characteristic information, thereby predicting fibrosis reversal of viral infection-related fibrosis before treatment.
In order to achieve the purpose, the invention provides the following technical scheme:
a hepatitis C liver fibrosis characteristic information extraction method comprises the following steps:
obtaining a target sample, the target sample being generated from a hepatitis c liver biopsy specimen;
imaging the non-staining section corresponding to the target sample through the SHG and the TPE to obtain a target image;
acquiring an SHG parameter in the target image, and quantifying the SHG parameter to obtain the morphological characteristics of the collagen;
the histological response of a patient is predicted by specific clinical characteristics and morphological characteristics of the collagen, and parameters which meet preset conditions with the Ishak stage change before and after treatment are selected to generate a two-dimensional heat map, wherein the two-dimensional heat map represents hepatitis C liver fibrosis characteristic information, so that the Ishak stage change after continuous virological response can be predicted by utilizing the two-dimensional heat map, and the prediction performance of ISHAK fibrosis stage change is obtained.
Optionally, the obtaining the target sample includes:
selecting an initial sample from the hepatitis C liver biopsy specimen according to the characteristic extraction condition;
and preprocessing and grouping the initial sample to obtain a target sample, wherein the preprocessing comprises fixing, embedding and slicing, and the target sample comprises a valid sample and an invalid sample.
Optionally, the method further comprises:
grouping collagen when quantifying the SHG parameters, wherein the collagen is divided into dispersed collagen and aggregated collagen when grouped by pattern; grouped by collagen site, the collagens are classified into portal vein collagen, septal collagen, and fibrillar collagen.
Optionally, the method further comprises:
and evaluating the statistical difference of clinical parameters and SHG parameters of patients of the effective sample and the ineffective sample before treatment by adopting a rank-sum test to obtain an evaluation result, wherein the evaluation result is used for selecting the morphological characteristics of the collagen.
Optionally, the predicting performance of the Ishak fibrosis stage change by using the two-dimensional heat map to predict the Ishak stage change after the continuous virology reaction is obtained, and the predicting performance comprises the following steps:
respectively constructing a training set and a testing set of the heat map, wherein the training set trains the heat map, and the testing set is used for training the heat map;
determining a target heat map from the training set and the test set;
predicting the Ishak staged change after the continuous virology reaction according to the target heat map to obtain the prediction performance of the ISHAK fibrosis staged change;
and calculating to obtain prediction parameters according to the prediction performance, wherein the prediction parameters comprise AUROC, a sensitivity value and a specificity value.
A hepatitis C hepatic fibrosis characteristic information extraction element, the apparatus includes:
a sample obtaining unit for obtaining a target sample generated from a hepatitis c liver biopsy specimen;
the imaging unit is used for imaging the non-staining section corresponding to the target sample through the SHG and the TPE to obtain a target image;
the quantification unit is used for acquiring the SHG parameters in the target image and quantifying the SHG parameters to obtain morphological characteristics of the collagen;
the generating unit is used for predicting the histological response of the patient by using the specific clinical characteristics and the morphological characteristics of the collagen, selecting parameters which meet preset conditions with the Ishak stage change before and after treatment, and generating a two-dimensional heat map, wherein the two-dimensional heat map represents hepatitis C liver fibrosis characteristic information, so that the two-dimensional heat map can be used for predicting the Ishak stage change after continuous virological response, and the predicting performance of the ISHAK fibrosis stage change is obtained.
Optionally, the sample acquiring unit includes:
a selecting subunit, for selecting an initial sample from the hepatitis c liver biopsy specimen according to the feature extraction condition;
and the preprocessing subunit is used for preprocessing and grouping the initial samples to obtain target samples, wherein the preprocessing comprises fixing, embedding and slicing, and the target samples comprise valid samples and invalid samples.
Optionally, the apparatus further comprises:
a grouping unit for grouping collagen when quantifying the SHG parameter, wherein the collagen is divided into dispersed collagen and aggregated collagen when grouped according to a pattern; grouped by collagen site, the collagens are classified into portal vein collagen, septal collagen, and fibrillar collagen.
Optionally, the apparatus further comprises:
and the evaluation unit is used for evaluating the statistical difference of clinical parameters and SHG parameters of patients with effective samples and ineffective samples before treatment by adopting rank sum test to obtain an evaluation result, and the evaluation result is used for selecting the morphological characteristics of the collagen.
Optionally, the device further comprises a prediction unit, wherein the prediction unit is used for predicting the Ishak stage change after the continuous virology reaction by using the two-dimensional heat map to obtain the prediction performance of the ISHAK fibrosis stage change;
wherein the prediction unit includes:
the construction subunit is used for respectively constructing a training set and a test set of the heat map, the training set trains the heat map, and the test set is used for training the heat map;
a determining subunit for determining a target heat map from the training set and the test set;
the prediction subunit is used for predicting the Ishak stage change after the continuous virology reaction according to the target heat map to obtain the prediction performance of the ISHAK fibrosis stage change;
and the calculation subunit is used for calculating and obtaining prediction parameters according to the prediction performance, wherein the prediction parameters comprise AUROC, a sensitivity value and a specificity value.
Compared with the prior art, the invention provides a method and a device for extracting hepatitis C hepatic fibrosis characteristic information, which are used for imaging a target sample by using SHG and TPE to obtain a target image, obtaining SHG parameters in the target image, and quantifying the SHG parameters to obtain morphological characteristics of collagen; a two-dimensional heat map is generated by predicting the histological response of a patient by specific clinical characteristics and morphological characteristics of collagen and selecting parameters which meet preset conditions with the Ishak stage change before and after treatment. The method realizes the prediction of the Ishak stage change after the continuous virology reaction by utilizing the two-dimensional heat map, and obtains the prediction performance of the ISHAK fibrosis stage change. The two-dimensional heat map representing the hepatitis C liver fibrosis characteristic information can be obtained in the application, so that the fibrosis reversal of virus infection related fibrosis before treatment is predicted by using an optical technology, the current clinical requirement can be met, and a data basis is provided for subsequent clinical research.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for extracting hepatic fibrosis characteristic information of hepatitis c according to an embodiment of the present invention;
FIG. 2 is an exemplary diagram of a process for constructing a reference system using pre-treatment clinical and morphological data of a patient and the results of ISHAK changes thereof, provided by an embodiment of the present invention;
FIG. 3 is a diagram illustrating leave-one-out cross-validation according to an embodiment of the present invention;
FIG. 4 is an exemplary diagram of a heatmap provided by an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus 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 with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first" and "second," and the like in the description and claims of the present invention and the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not set forth for a listed step or element but may include steps or elements not listed.
The embodiment of the present invention provides a method for extracting hepatitis c fibrosis feature information, which can be applied to hepatitis c research, that is, the method for extracting hepatitis c fibrosis feature information provided by the embodiment of the present invention can provide data-based reference information, that is, hepatitis c fibrosis feature information, for subsequent clinical research on hepatitis c (hepatitis c is a type of hepatitis caused by Hepatitis C Virus (HCV) infection), and in the present application, the generated two-dimensional heat map is used as the feature information. Referring to fig. 1, the method includes:
and S101, acquiring a target sample.
The target sample is generated according to a hepatitis C liver biopsy specimen, and specifically comprises the following steps in the step of obtaining the target sample:
s1011, selecting an initial sample from the hepatitis C liver biopsy specimen according to the characteristic extraction condition;
and S1012, preprocessing and grouping the initial sample to obtain a target sample, wherein the preprocessing comprises fixing, embedding, slicing and slicing. The target samples include valid samples and invalid samples. Non-stained sections were obtained after the initial sample was processed. I.e., the SHG/TPE images are non-stained section images. If a stained section is obtained, it can be used in pathology assessment for training and validation 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, extraction is required according to a feature extraction condition, wherein the feature extraction condition is as follows:
the age is 20-70 years old; chronic hepatitis c infection with or without cirrhosis; HCV-RNA levels above 10000IU/ml at baseline; receiving direct acting antiviral Drug (DAA) antiviral treatment for 12 weeks or 24 weeks; the treatment was completed and received a sustained virological response (SVR, designated hepatitis c virus infection treatment) 24 weeks later. Paired liver biopsies were performed at week 24 post-treatment and at baseline.
Exclusion criteria included co-infection with hepatitis b or human immune efficiency virus (HIV); other forms of chronic liver disease exist; decompensated liver disease (including ascites, variceal bleeding, or hepatic encephalopathy); alpha-fetoprotein >100ng/ml or creatinine clearance <50 ml/min; any malignant tumor; complications of any serious heart, lung, kidney, brain, blood or other important system disease; serious neurological or psychological disorders; pregnant or lactating women.
After obtaining the initial specimen, the LBX needs to be formalin-fixed, paraffin-embedded and sectioned using standard clinical techniques, wherein the sections are stained with hematoxylin and eosin (H & E), reticulin and masson trichrome for the purpose of subsequent pathology assessment.
All liver biopsy samples were evaluated by two experienced liver pathologists, and the treatment protocol, biopsy sequence, biochemical reactions and liver hardness values were not evaluated blindly, one time independently. Necrotic inflammatory activity and the degree of fibrosis were evaluated using an Ishak modified tissue activity index (HAI) grading system 10. Based on the change in the extent of Ishak fibrosis after treatment, 38 patients were divided into two groups, the effective group and the ineffective group. Effective treatment means a reduction in the stage of Ishak fibrosis.
And S102, imaging the target sample through the SHG and the TPE to obtain a target image.
A 5 micron thick section of each unstained liver biopsy sample was imaged with a Second Harmonic Generation (SHG) microscope to show collagen and a two-photon excitation (TPE) fluorescence microscope to highlight hepatocytes. The sample was laser excited at 780nm and SHG and TPEF signals were recorded at 390nm and 550nm, respectively. The images were magnified 20 times and had a resolution of 512 x 512 pixels, each representing a tissue area of 200 x 200 μm 2. Multiple adjacent images are captured to cover the entire portion.
S103, acquiring the SHG parameters in the target image, and quantifying the SHG parameters to obtain the morphological characteristics of the collagen.
The SHG parameters in the image are quantized using an algorithm in the prior art to obtain 100 morphological features. In these measurements, collagen is divided into two distinct modes: namely dispersed collagen (fine collagen fibers) and aggregated collagen (large plaques). Collagen is also grouped in different ways according to its location: i.e. portal vein collagen (portal vein dilation), septal collagen (bridging fibrosis) and fibrillar collagen (fine collagen distributed in the pericyte/perisinus space). The algorithm is an algorithm which automatically detects the position of collagen in an image, identifies portal, septa and fibrillar regions, and quantifies the characteristics of the collagen in the regions respectively.
S104, predicting the histological response of the patient by using the specific clinical characteristics and the morphological characteristics of the collagen, and selecting parameters which meet preset conditions with the Ishak stage change before and after treatment to generate a two-dimensional heat map.
The two-dimensional heat map represents hepatitis C liver fibrosis characteristic information, so that the two-dimensional heat map can be used for predicting ISHAK stage change after continuous virology reaction to obtain the prediction performance of ISHAK fibrosis stage change.
And evaluating the statistical difference of clinical parameters and SHG parameters of patients of the effective sample and the ineffective sample before treatment by adopting a rank-sum test to obtain an evaluation result, wherein the evaluation result is used for selecting the morphological characteristics of the collagen. And in the prediction process, respectively constructing a training set and a test set of the heat map, wherein the training set trains the heat map, and the test set is used for training the heat map; determining a target heat map from the training set and the test set; predicting the Ishak staged change after the continuous virology reaction according to the target heat map to obtain the prediction performance of the ISHAK fibrosis staged change; and calculating to obtain prediction parameters according to the prediction performance, wherein the prediction parameters comprise AUROC, a sensitivity value and a specificity value.
Specifically, the first step: statistical differences in clinical and SHG parameters were assessed in the pre-treatment effective and ineffective groups using the two-tailed Wilcoxon rank-sum test. Wherein, the evaluation result is used for parameter selection, and 33 morphological parameters are selected.
AUROC analysis (area of characteristic curve) was used to compare the performance of different heatmaps predicting effective fibrosis progression/regression response. The level of statistical significance was set at P < 0.05. Wherein AUROC analysis is to obtain predicted value by using heat map, and to truly analyze and calculate AUROC
The second step is that: the establishment and verification process of multi-parameter ISHAK staged change after the SVR prediction system is summarized. Wherein the parameter combinations are as follows:
clinical parameters (n ═ 7) morphological parameters (n ═ 33, p <0.05)
First group of clinical parameters only (21 combinations)
{ e.g., ALT & AST, ALT & ALB, or ALT & TBIL, … }
Second set of morphological collagen-only parameters (528 combinations)
{ for example,% SHG &% Agg,% Agg & # shortSTR, or # LongStr & StrLength }
Third group 1 clinical parameters and 1 morphological collagen parameters (231 combinations)
{ e.g., ALT &% SHG, TBIL &% StrWidth, or PLT & # StrP, … }
Figure 2 illustrates the process of constructing a reference system using pre-treatment clinical and morphological data of a patient and its results of ISHAK changes. Using this reference system, changes in fibrosis in new patients after SVR can be predicted from the patient's pre-treatment data. Illustrated using a heat map of the 2 parameter system (PLT & # ShortStrPA).
FIG. 3 illustrates the "leave-one-out cross-validation" method used in the present invention. 37 patients were used as a training set to construct the heatmap, and the remaining 38 patients were used to test the accuracy of the heatmap predictions. This process was repeated 38 times and all patients were used as test patients. Finally, AUROC and sensitivity and specificity values were calculated based on the predictive performance of the changes in the stages of ISHAK fibrosis.
The invention provides a hepatitis C liver fibrosis characteristic information extraction method, which comprises the steps of imaging a target sample by using SHG and TPE to obtain a target image, obtaining SHG parameters in the target image, and quantifying the SHG parameters to obtain morphological characteristics of collagen; a two-dimensional heat map is generated by performing histological reaction on a predicted patient by using specific clinical characteristics and morphological characteristics of collagen, and selecting parameters which meet preset conditions with Ishak stage change before and after treatment. The method realizes the prediction of the Ishak stage change after the continuous virology reaction by utilizing the two-dimensional heat map, and obtains the prediction performance of the ISHAK fibrosis stage change. The two-dimensional heat map representing the hepatitis C liver fibrosis characteristic information can be obtained in the application, so that the fibrosis reversal of virus infection related fibrosis before treatment is predicted by using an optical technology, the current clinical requirement can be met, and a data basis is provided for subsequent clinical research.
By way of example, archival LBX studies were performed on 38 pre-and post-treatment biopsy patients with persistent virological response (SVR) with staging of ISHAK fibrosis. 13 patients were defined as "effectively reversed", i.e. the extent of Ishak fibrosis decreased after treatment. 23 patients were defined as "null reversal-staging unchanged", i.e. maintaining the same ISHAK staging. Two patients showed a staged increase in ISHAK and were assigned as "ineffective reversal-staged increase". The sample ISHAK staging changes are summarized in table 1. The collagen area ratio (CPA) of each group before and after treatment is shown in table 2. The "effective reversal" group (0.40%) had a significant decrease in fibrotic collagen, the "ineffective reversal-staging increase" group (2.13%) had a significant increase, but the "ineffective reversal-staging unchanged" group (0.26%) had no significant trend.
All 7 clinical parameters were selected as prognostic assays, but 33 (100) specific morphological collagen parameters were selected as parameters associated with the change in the stage of ISHAK fibrosis after SVR, these parameters p < 0.05. These parameters were paired into three groups (table 3): (A) group 1-clinical only parameters, (B) group 2-morphological only collagen parameters, and (C) group 3-use 1 clinical and 1 morphological collagen parameters. Selection was made from a total of 21528231 combinations generated for groups (A), (B) and (C), respectively. All combinations were associated with staged changes in ISHAK before and after treatment. The combination with the highest aurora value was selected (see table 3). Five parameters (PLT, TBILI, # LongStr,% Agg, # ShortStrPA) were thus determined and then used for heatmap prediction.
Furthermore, 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. We obtained the best aurora value of 0.911 but not the best sensitivity or specificity values in combination with all 5 parameters. Overall, the best performance was a combination of 4 features-3 morphological parameters including LongStr (total number of collagen bundles >40 microns),% Agg (proportion of polymerized collagen) and ShortStrPA (total number of collagen short bundles in the zone of the funnel <40 microns) and 1 clinical Parameter (PLT).
To illustrate how this multi-parameter system can be used to predict changes in ISHAK staging during treatment, only the two parameter combinations shown in tables 3(A), (B) and (C) were used first. A heatmap generated from all 38 patients using these 5 parameters is shown in figure 4. Using these heat maps, the patient's fibrotic changes following SVR are predicted by locating the patient's position in the heat maps and the patient's clinical and/or morphological data prior to treatment.
Figure 2 shows the process of constructing a reference system (heatmap) using pre-treatment clinical and morphological collagen data of patients, and their results for ishak changes. Using this reference system, we can predict fibrotic changes in new patients after SVR from the patient's pre-treatment data. FIG. 2 illustrates an example of a heatmap using a 2 parameter system. (PLT & # ShortStrPA).
The validation method used in this study, "leave-one-out cross-validation" is shown in figure 3. In this method, 37 patients were used as a training set to construct a heatmap, and the remaining patients (38 patients) were used to test the accuracy of the structure prediction. Heat map. This procedure was then repeated 38 times with all the different patients as test patients. Finally, AUROC, sensitivity and specificity were calculated based on the predicted performance of the ishak fibrosis stage change.
SHG/TPE has shown promise for the evaluation of fibrotic diseases involving inflammation and tumors in clinical human specimens and animal model tissues, liver and other organs. It is well known that the process of chronic fibrosis is usually bidirectional, with progression and reversal occurring simultaneously. Fibrosis associated with wound repair is usually halted and reversed, but disease-related fibrosis (e.g., chronic liver disease, nephrosclerosis, idiopathic pulmonary fibrosis, scleroderma) does not get very good results, so only the progressive changes in fibrosis are well studied. In this case, the clinical and prognostic utility of SHG/TPE is limited. Recent successful treatment of chronic hepatitis c infection has changed this situation, providing a model for potentially larger clinical applications of SHG/TPE analysis, able to assess subtle changes in fibrotic degeneration better than standard histological stages.
In this study, a group of successfully cured chronic hepatitis c patients were biopsied pre-and post-treatment, and 100 fibrous collagen morphological parameters and 7 clinical (biochemical) parameters were evaluated. Based on histological (ISHAK) staging and CPA changes, patients were divided into ISHAK staging and CPA concurrent decrease ("effective reversal"), ISHAK staging unchanged but CPA decreased ("ineffective reversal-staging unchanged"), and ISHAK staging and CPA concurrent increase ("ineffective reversal-staging increase"). CPA values are significantly more reflective of improvement in fibrosis than ISHAK staging, as previously indicated in fibrosis regression studies.
However, further multi-step statistical analysis yielded data that exceeded standard histological grading. Correlation of clinical and morphological parameters with the results first determined a pair of clinical parameters (tbili and plt) and 33 morphological parameters associated with the improvement phase. Using the heat map prediction system, these parameters were again paired for comparison with the results. The best values of these correlations are then analyzed in 3, 4 and 5 parameter sets. AUROC and sensitivity/specificity analysis showed that the best feature set of the prediction results was: # LongStr,% Agg, # ShortStrPA, and PLT.
These parameters may have pathophysiological significance in relation to the progression of chronic viral hepatitis fibrosis, in particular whether the main pathway of progression is focused on events at the cellular level (i.e. hepatic stellate cell activation) or at the tissue level (the first priority of vascular thrombotic events), and new approaches are proposed to mimic the pathophysiology in this clinical setting. Together, # LongStr and% Agg reflect the collagen morphology of progressing liver fibrosis. Increasing the values of both, not surprisingly, indicates a reduced probability of regression of the fibrosis, a finding that is consistent with both of these assumptions, since these properties may make them more resistant to dissolution. However, # ShortStrPA may represent a change limited to portal interstitium, a structural feature recently demonstrated in small mall spaces, and a link between portal blood vessel (venous, sinusoidal, lymphatic) inflow and outflow. PLT represents a secondary decrease in platelet circulation following portal hypertension. Thus, these portal lymphatic vascular features contribute to the theoretical importance of vascular changes during fibrosis formation.
More practically, the fine-grained data obtained from the SHG/TPE histological examination, in combination with conventional clinical parameters, clearly provides new prognostic information for pre-treatment LBX that predicts post-treatment clinical outcome. The clinical significance of this cannot be underestimated: up to 15% of patients with end-stage liver disease have progressive fibrosis formation (leading to death or transplantation) despite the cure of the underlying infection. For the prognostic systems currently in use, it relies on histological findings of biopsy specimens following treatment for hepatitis b, in which viral replication is only inhibited and the post-factual changes are identified to predict near-term outcome. On the other hand, this thermographic approach yields true prognostic data based on pre-treatment biopsies after complete cure. Identification of these patients from a pre-treatment biopsy perspective, once an SVR is obtained, may result in significant modification to long-term clinical follow-up without further biopsy.
Therefore, SHG/TPE may become the center of patient care in clinically cured hepatitis c, a delicate treatment based on application of photonic technology to liver disease. Although treatment of other chronic fibrotic diseases remains uncertain, we expect that similar analyses and eventual prognostic value may be obtained for patients with newly developed anti-fibrotic drugs (currently undergoing clinical trials). Changing the balance between progression and regression. The analytical methods presented herein may be helpful in assessing and/or predicting the response of such clinical trials, and ultimately in treatment assessment when such treatments reach routine clinical use.
The SHG-based predictive model developed in the present invention may be less innovative in optics/methodology, but places emphasis on clinical validation of well-designed clinical trial-based patient cohorts. The method can meet the requirements of evaluating and predicting antiviral treatment effect and clinical requirements in future clinical practice.
TABLE 138 Change in the Ishak fibrosis staging before and after treatment with direct-acting antiviral drugs
TABLE 2 mean and standard deviation of collagen area ratio (CPA) values for each group before and after direct action antiviral Drugs (DAAs)
TABLE 3 AUROC values for 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, an apparatus for extracting hepatic fibrosis feature information of hepatitis c is further provided, where the apparatus includes:
a sample obtaining unit 10 for obtaining a target sample generated from a hepatitis c liver biopsy specimen;
the imaging unit 20 is configured to image a non-stained section corresponding to the target sample through the SHG and the TPE to obtain a target image;
the quantification unit 30 is configured to obtain an SHG parameter in the target image, and quantify the SHG parameter to obtain a morphological feature of collagen;
the generation unit 40 is used for predicting the histological response of the patient by using the specific clinical characteristics and the morphological characteristics of the collagen, and selecting parameters which meet preset conditions with the Ishak stage change before and after treatment to generate a two-dimensional heat map, wherein the two-dimensional heat map represents hepatitis C liver fibrosis characteristic information, so that the two-dimensional heat map can be used for predicting the Ishak stage change after continuous virological response to obtain the prediction performance of the ISHAK fibrosis stage change.
Optionally, the sample acquiring unit includes:
a selecting subunit, for selecting an initial sample from the hepatitis c liver biopsy specimen according to the feature extraction condition;
and the preprocessing subunit is used for preprocessing and grouping the initial samples to obtain target samples, wherein the preprocessing comprises fixing, embedding and slicing, and the target samples comprise valid samples and invalid samples.
Optionally, the apparatus further comprises:
a grouping unit for grouping collagen when quantifying the SHG parameter, wherein the collagen is divided into dispersed collagen and aggregated collagen when grouped according to a pattern; grouped by collagen site, the collagens are classified into portal vein collagen, septal collagen, and fibrillar collagen.
Optionally, the apparatus further comprises:
and the evaluation unit is used for evaluating the statistical difference of clinical parameters and SHG parameters of patients with effective samples and ineffective samples before treatment by adopting rank sum test to obtain an evaluation result, and the evaluation result is used for selecting the morphological characteristics of the collagen.
Optionally, the device further comprises a prediction unit, wherein the prediction unit is used for predicting the Ishak stage change after the continuous virology reaction by using the two-dimensional heat map to obtain the prediction performance of the ISHAK fibrosis stage change;
wherein the prediction unit includes:
the construction subunit is used for respectively constructing a training set and a test set of the heat map, the training set trains the heat map, and the test set is used for training the heat map;
a determining subunit for determining a target heat map from the training set and the test set;
the prediction subunit is used for predicting the Ishak stage change after the continuous virology reaction according to the target heat map to obtain the prediction performance of the ISHAK fibrosis stage change;
and the calculation subunit is used for calculating and obtaining prediction parameters according to the prediction performance, wherein the prediction parameters comprise AUROC, a sensitivity value and a specificity value.
The invention provides a hepatitis C liver fibrosis characteristic information extraction device, which images a target sample by using SHG and TPE to obtain a target image, obtains SHG parameters in the target image, and quantizes the SHG parameters to obtain morphological characteristics of collagen; a two-dimensional heat map is generated by performing histological reaction on a predicted patient by using specific clinical characteristics and morphological characteristics of collagen, and selecting parameters which meet preset conditions with Ishak stage change before and after treatment. The method realizes the prediction of the Ishak stage change after the continuous virology reaction by utilizing the two-dimensional heat map, and obtains the prediction performance of the ISHAK fibrosis stage change. The two-dimensional heat map representing the hepatitis C liver fibrosis characteristic information can be obtained in the application, so that the fibrosis reversal of virus infection related fibrosis before treatment is predicted by using an optical technology, the current clinical requirement can be met, and a data basis is provided for subsequent clinical research.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A hepatitis C liver fibrosis characteristic information extraction method is characterized by comprising the following steps:
obtaining a target sample, the target sample being generated from a hepatitis c liver biopsy specimen;
imaging the non-staining section corresponding to the target sample through the SHG and the TPE to obtain a target image;
acquiring an SHG parameter in the target image, and quantifying the SHG parameter to obtain the morphological characteristics of the collagen;
the histological response of a patient is predicted by specific clinical characteristics and morphological characteristics of the collagen, and parameters which meet preset conditions with the Ishak stage change before and after treatment are selected to generate a two-dimensional heat map, wherein the two-dimensional heat map represents hepatitis C liver fibrosis characteristic information, so that the Ishak stage change after continuous virological response can be predicted by utilizing the two-dimensional heat map, and the prediction performance of ISHAK fibrosis stage change is obtained.
2. The method of claim 1, wherein said obtaining a target sample comprises:
selecting an initial sample from the hepatitis C liver biopsy specimen according to the characteristic extraction condition;
and preprocessing and grouping the initial samples to obtain target samples, wherein the preprocessing comprises fixing, embedding and slicing processing, and the target samples comprise valid samples and invalid samples.
3. The method of claim 1, further comprising:
grouping collagen when quantifying the SHG parameters, wherein the collagen is divided into dispersed collagen and aggregated collagen when grouped by pattern; grouped by collagen site, the collagens are classified into portal vein collagen, septal collagen, and fibrillar collagen.
4. The method of claim 2, further comprising:
and evaluating the statistical difference of clinical parameters and SHG parameters of patients of the effective sample and the ineffective sample before treatment by adopting a rank-sum test to obtain an evaluation result, wherein the evaluation result is used for selecting the morphological characteristics of the collagen.
5. The method of claim 1, wherein said using the two-dimensional heat map to predict Ishak stage changes after a sustained virological response to obtain a predictive performance of Ishak fibrosis stage changes comprises:
respectively constructing a training set and a testing set of the heat map, wherein the training set trains the heat map, and the testing set is used for training the heat map;
determining a target heat map from the training set and the test set;
predicting the Ishak staged change after the continuous virology reaction according to the target heat map to obtain the prediction performance of the ISHAK fibrosis staged change;
and calculating to obtain prediction parameters according to the prediction performance, wherein the prediction parameters comprise AUROC, a sensitivity value and a specificity value.
6. The utility model provides a hepatitis C fibrosis characteristic information extraction element which characterized in that, the device includes:
a sample obtaining unit for obtaining a target sample generated from a hepatitis c liver biopsy specimen;
the imaging unit is used for imaging the non-staining section corresponding to the target sample through the SHG and the TPE to obtain a target image;
the quantification unit is used for acquiring the SHG parameters in the target image and quantifying the SHG parameters to obtain morphological characteristics of the collagen;
the generating unit is used for predicting the histological response of the patient by using the specific clinical characteristics and the morphological characteristics of the collagen, selecting parameters which meet preset conditions with the Ishak stage change before and after treatment, and generating a two-dimensional heat map, wherein the two-dimensional heat map represents hepatitis C liver fibrosis characteristic information, so that the two-dimensional heat map can be used for predicting the Ishak stage change after continuous virological response, and the predicting performance of the ISHAK fibrosis stage change is obtained.
7. The apparatus of claim 6, wherein the sample acquisition unit comprises:
a selecting subunit, for selecting an initial sample from the hepatitis c liver biopsy specimen according to the feature extraction condition;
and the preprocessing subunit is used for preprocessing and grouping the initial samples to obtain target samples, wherein the preprocessing comprises fixing, embedding and slicing, and the target samples comprise valid samples and invalid samples.
8. The apparatus of claim 6, further comprising:
a grouping unit for grouping collagen when quantifying the SHG parameter, wherein the collagen is divided into dispersed collagen and aggregated collagen when grouped according to a pattern; grouped by collagen site, the collagens are classified into portal vein collagen, septal collagen, and fibrillar collagen.
9. The apparatus of claim 7, further comprising:
and the evaluation unit is used for evaluating the statistical difference of clinical parameters and SHG parameters of patients with effective samples and ineffective samples before treatment by adopting rank sum test to obtain an evaluation result, and the evaluation result is used for selecting the morphological characteristics of the collagen.
10. The apparatus of claim 6, further comprising a prediction unit configured to predict the Ishak stage change after the sustained virologic response using the two-dimensional heat map to obtain a prediction performance of the Ishak fibrosis stage change;
wherein the prediction unit includes:
the construction subunit is used for respectively constructing a training set and a test set of the heat map, the training set trains the heat map, and the test set is used for training the heat map;
a determining subunit for determining a target heat map from the training set and the test set;
the prediction subunit is used for predicting the Ishak stage change after the continuous virology reaction according to the target heat map to obtain the prediction performance of the ISHAK fibrosis stage change;
and the calculation subunit is used for calculating and obtaining prediction parameters according to the prediction performance, wherein the prediction parameters comprise AUROC, a sensitivity value and a specificity value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910887661.3A CN110599485B (en) | 2019-09-19 | 2019-09-19 | Hepatitis C liver fibrosis characteristic information extraction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910887661.3A CN110599485B (en) | 2019-09-19 | 2019-09-19 | Hepatitis C liver fibrosis characteristic information extraction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110599485A true CN110599485A (en) | 2019-12-20 |
| CN110599485B CN110599485B (en) | 2022-04-15 |
Family
ID=68861236
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910887661.3A Active CN110599485B (en) | 2019-09-19 | 2019-09-19 | Hepatitis C liver fibrosis characteristic information extraction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110599485B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111667482A (en) * | 2020-06-30 | 2020-09-15 | 杭州筹图科技有限公司 | Region division method and related equipment |
| WO2021051335A1 (en) * | 2019-09-19 | 2021-03-25 | 北京大学人民医院(北京大学第二临床医学院) | Hepatitis c liver fibrosis feature information extraction method and apparatus |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101811956A (en) * | 2010-04-15 | 2010-08-25 | 施冬云 | Preparation method and application of trans-crocetin |
| WO2014109708A1 (en) * | 2013-01-08 | 2014-07-17 | Agency For Science, Technology And Research | A method and system for assessing fibrosis in a tissue |
| EP2772882A1 (en) * | 2013-03-01 | 2014-09-03 | Universite D'angers | Automatic measurement of lesions on medical images |
| US20150148658A1 (en) * | 2012-07-11 | 2015-05-28 | University Of Mississippi Medical Center | Method for the detection and staging of liver fibrosis from image acquired data |
| CN105335425A (en) * | 2014-08-07 | 2016-02-17 | 新加坡赫斯托因德私人有限公司 | Fibrosis value assessing method and apparatus and fibrosis dynamic assessing method and system |
| CN107895368A (en) * | 2017-11-24 | 2018-04-10 | 北京大学人民医院 | Application of the parameter as the characteristic parameter by stages of the liver fibrosis of adult or children in SHG/TPEF images |
| CN109473175A (en) * | 2018-11-07 | 2019-03-15 | 中山大学附属第三医院（中山大学肝脏病医院） | A kind of Noninvasive serology Rating Model and its design method for liver fibrosis |
-
2019
- 2019-09-19 CN CN201910887661.3A patent/CN110599485B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101811956A (en) * | 2010-04-15 | 2010-08-25 | 施冬云 | Preparation method and application of trans-crocetin |
| US20150148658A1 (en) * | 2012-07-11 | 2015-05-28 | University Of Mississippi Medical Center | Method for the detection and staging of liver fibrosis from image acquired data |
| WO2014109708A1 (en) * | 2013-01-08 | 2014-07-17 | Agency For Science, Technology And Research | A method and system for assessing fibrosis in a tissue |
| CN105009174A (en) * | 2013-01-08 | 2015-10-28 | 新加坡科技研究局 | Method and system for assessing fibrosis in tissue |
| US20150339816A1 (en) * | 2013-01-08 | 2015-11-26 | Agency For Science, Technology And Research | A method and system for assessing fibrosis in a tissue |
| EP2772882A1 (en) * | 2013-03-01 | 2014-09-03 | Universite D'angers | Automatic measurement of lesions on medical images |
| US20180075600A1 (en) * | 2013-03-01 | 2018-03-15 | Universite D'angers | Automatic measurement of lesions on medical images |
| CN105335425A (en) * | 2014-08-07 | 2016-02-17 | 新加坡赫斯托因德私人有限公司 | Fibrosis value assessing method and apparatus and fibrosis dynamic assessing method and system |
| CN107895368A (en) * | 2017-11-24 | 2018-04-10 | 北京大学人民医院 | Application of the parameter as the characteristic parameter by stages of the liver fibrosis of adult or children in SHG/TPEF images |
| CN109473175A (en) * | 2018-11-07 | 2019-03-15 | 中山大学附属第三医院（中山大学肝脏病医院） | A kind of Noninvasive serology Rating Model and its design method for liver fibrosis |
Non-Patent Citations (2)
| Title |
|---|
| JÉRÔME BOURSIER等: "New sequential combinations of noninvasive fibrosis tests provide an accurate diagnosis of advanced", 《JOURNAL OF HEPATOLOGY》 * |
| 王晓晓等: "二次谐波/双光子激发荧光显微成像技术定量评估非酒精性脂肪性肝病小鼠模型肝纤维化的价值", 《临床肝胆病杂志》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021051335A1 (en) * | 2019-09-19 | 2021-03-25 | 北京大学人民医院(北京大学第二临床医学院) | Hepatitis c liver fibrosis feature information extraction method and apparatus |
| CN111667482A (en) * | 2020-06-30 | 2020-09-15 | 杭州筹图科技有限公司 | Region division method and related equipment |
| CN111667482B (en) * | 2020-06-30 | 2023-08-22 | 杭州筹图科技有限公司 | Region dividing method and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110599485B (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wakabayashi et al. | Radiomics in hepatocellular carcinoma: a quantitative review | |
| US20200359969A1 (en) | Method for integrating large scale biological data with imaging | |
| WO2021020198A1 (en) | Information processing device, program, learned model, diagnostic assistance device, learning device, and method for generating prediction model | |
| Huang et al. | CHI3L1 is a liver-enriched, noninvasive biomarker that can be used to stage and diagnose substantial hepatic fibrosis | |
| Salvatore et al. | Radiomics approach in the neurodegenerative brain | |
| CN110599485B (en) | Hepatitis C liver fibrosis characteristic information extraction method and device | |
| Shao et al. | Ordinal multi-modal feature selection for survival analysis of early-stage renal cancer | |
| Florez et al. | Emergence of radiomics: novel methodology identifying imaging biomarkers of disease in diagnosis, response, and progression | |
| CN110916666A (en) | Imaging omics feature processing method for predicting recurrence of hepatocellular carcinoma after surgical resection based on multi-modal MRI (magnetic resonance imaging) images | |
| Pujadas et al. | Prediction of incident cardiovascular events using machine learning and CMR radiomics | |
| Almutlaq et al. | Evaluation of Monoexponential, Stretched‐Exponential and Intravoxel Incoherent Motion MRI Diffusion Models in Early Response Monitoring to Neoadjuvant Chemotherapy in Patients With Breast Cancer—A Preliminary Study | |
| Joshi et al. | Current and future applications of artificial intelligence in cardiac CT | |
| Elsheikh et al. | Multi-stage association analysis of glioblastoma gene expressions with texture and spatial patterns | |
| Chen et al. | Matrisome gene-based subclassification of patients with liver fibrosis identifies clinical and molecular heterogeneities | |
| Xie et al. | Evaluation of diffuse glioma grade and proliferation activity by different diffusion-weighted-imaging models including diffusion kurtosis imaging (DKI) and mean apparent propagator (MAP) MRI | |
| Catalano et al. | Evolving determinants of carotid atherosclerosis vulnerability in asymptomatic patients from the MAGNETIC observational study | |
| Caballero et al. | Deep-learning and hpc to boost biomedical applications for health (deephealth) | |
| US20110124947A1 (en) | Method for integrating large scale biological data with imaging | |
| Niemann et al. | Interactive exploration of a 3D intracranial aneurysm wall model extracted from histologic slices | |
| JP2018512208A (en) | Computerized optical analysis method of MR (magnetic resonance) images for quantifying or determining liver lesions | |
| WO2021051335A1 (en) | Hepatitis c liver fibrosis feature information extraction method and apparatus | |
| Chen et al. | Auxiliary recognition of alzheimer’s disease based on gaussian probability brain image segmentation model | |
| Liu et al. | Artificial Intelligence—A Good Assistant to Multi-Modality Imaging in Managing Acute Coronary Syndrome | |
| Zhang et al. | Predicting major adverse cardiovascular events within 3 years by optimization of radiomics model derived from pericoronary adipose tissue on coronary computed tomography angiography: a case-control study | |
| Wang et al. | MRI-based clinical-radiomics nomogram to predict early neurological deterioration in isolated acute pontine infarction: a two-center study in Northeast China |
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 |