CN113378879B - Postoperative tumor evaluation method and device and computer storage medium - Google Patents
Postoperative tumor evaluation method and device and computer storage medium Download PDFInfo
- Publication number
- CN113378879B CN113378879B CN202110492453.0A CN202110492453A CN113378879B CN 113378879 B CN113378879 B CN 113378879B CN 202110492453 A CN202110492453 A CN 202110492453A CN 113378879 B CN113378879 B CN 113378879B
- Authority
- CN
- China
- Prior art keywords
- image
- thermal
- ablation
- thermal ablation
- tumor
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The application provides a postoperative tumor assessment method, a postoperative tumor assessment device and a computer storage medium, which mainly comprise the steps of acquiring preoperative images and a plurality of thermal ablation images of a target tumor; according to preset treatment parameters and each thermal ablation image, obtaining each thermal dose map corresponding to each thermal ablation image; obtaining a plurality of target feature vectors according to each thermal dose map, the preoperative image, each thermal ablation image and the preset treatment parameters; and obtaining a post-operation evaluation result of the target tumor according to each target feature vector. Accordingly, the method and the device can rapidly and accurately predict the postoperative tumor recurrence risk so as to assist a clinician to more accurately control the illness state of a patient.
Description
Technical Field
The embodiment of the application relates to the technical field of artificial intelligence, in particular to a postoperative tumor evaluation method, a postoperative tumor evaluation device and a computer storage medium.
Background
Tumor ablation is a minimally invasive treatment technology, has high safety and small complications, and is an important choice for treating patients with cancer who fail radiotherapy and chemotherapy or are unsuitable to receive surgical excision.
Existing ablation devices can deliver energy directly to the target tissue and cause physical damage in situ: the thermal ablation therapy refers to heating target tissues to be higher than 60 ℃ by means of radio frequency ablation, microwave ablation and the like through a high-frequency electric field, so that proteins and cell nuclei are rapidly denatured; cryoablation is based on the Joule-Thomson principle, in which the target tissue is cooled to below-40 ℃ to destroy the cellular structure and cause apoptotic necrosis; in addition, ablative therapy combining heating and cooling can enhance the direct thermal damage and indirect immune response to tumors through rapid changes in temperature and stress within the target tissue.
In recent years, in combination with the development of medical images, techniques for evaluating tumor ablation procedures, and methods for predicting tumor volume changes in long-term follow-up after ablation have also been proposed.
It should be noted that the sensitivity of the tumor and the precise application of thermal doses during the tumor ablation treatment are key factors for the success of the treatment. However, existing post-tumor ablation evaluations still have some of the following drawbacks:
first, the thermal dose actually accepted by different patients in the treatment process is different and limited by the compatibility of the ablation device and the imaging device, the temperature field in the treatment is difficult to visually see in the navigation image, and the degree of damage to the tumor to be ablated, especially the safety boundary, is difficult to measure only by the experience of doctors and ideal preoperative planning.
Second, necrotic lesions remain in the body after ablation and cannot be removed, clinically requiring more than one year of image follow-up to evaluate the long-term local progression of the tumor after treatment. However, based on the manual diagnosis of image follow-up, only the occurrence of imaging can be measured, macroscopic tissue change can be reflected, potential performances of tumor microcirculation destruction, antigen release and the like in the image are ignored, and long-term estimation of prognosis is affected.
Third, current prognostic evaluation methods for tumor ablation are difficult to evaluate immediately after the end of treatment if the surgery is successful, nor can predictions be made as to the risk of tumor recurrence over time, mainly because the lack of relevant quantitative indicators provides physicians with a clinically instructive reference, which delays the optimal supplemental treatment time for high risk patients, bringing potential risk of recurrence.
In view of this, it is an object of the present invention to provide a technique for timely and accurately evaluating tumor recurrence after surgery.
Disclosure of Invention
In view of the above problems, the present application provides a postoperative tumor assessment method, which can rapidly predict the risk of local tumor progression after ablation, so as to help doctors to strengthen disease monitoring and timely supplement treatment. A step of
A first aspect of the present application provides a method of postoperative tumor assessment, comprising: acquiring preoperative images and a plurality of thermal ablation images of a target tumor; according to preset treatment parameters of the target tumor and each thermal ablation image, obtaining each thermal dose map corresponding to each thermal ablation image; obtaining a plurality of target feature vectors according to each thermal dose map, the preoperative image, each thermal ablation image and the preset treatment parameters; and obtaining a post-operation evaluation result of the target tumor according to each target feature vector.
A second aspect of the present application provides a computer storage medium having stored therein instructions for performing each of the steps of the method for postoperative tumor assessment described in the first aspect above.
A third aspect of the present application provides a post-operative tumor assessment apparatus, comprising: the acquisition module is used for acquiring preoperative images, a plurality of thermal ablation images and preset treatment parameters of the target tumor; the analysis module is used for obtaining each thermal dose map corresponding to each thermal ablation image according to the preset treatment parameters and each thermal ablation image, and obtaining a plurality of target feature vectors according to each thermal dose map, the preoperative image, each thermal ablation image and the preset treatment parameters; and the evaluation module is used for obtaining postoperative evaluation results of the target tumor according to each target feature vector.
In summary, the method, the device and the computer storage medium for postoperative tumor assessment provided by the embodiments of the present application can rapidly and accurately assess the risk of local progression of the postoperative tumor by combining the preoperative image, the thermal ablation image and the preset treatment parameters for analyzing the target tumor.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description will briefly introduce the drawings that are required to be used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present application, and other drawings may also be obtained according to these drawings for a person having ordinary skill in the art.
Fig. 1 is a flow chart of a method for evaluating postoperative tumor according to a first embodiment of the present application.
Fig. 2 is a flow chart of a method for postoperative tumor assessment according to a second embodiment of the present application.
Fig. 3 is a flow chart of a method for evaluating postoperative tumor according to a third embodiment of the present application.
FIG. 4 is a schematic diagram of an embodiment of a temperature field profile and a thermal dose profile.
Fig. 5 is a flow chart of a method for evaluating postoperative tumor according to a fourth embodiment of the present application.
Fig. 6 is a flow chart of a method for postoperative tumor assessment according to a fifth embodiment of the present application.
Fig. 7 is a schematic structural diagram of a postoperative tumor evaluation apparatus according to a seventh embodiment of the present application.
Element labels
700: a post-operative tumor assessment device; 702: an acquisition module; 704: an analysis module; 706: an evaluation module; 708: tumor assessment model.
Detailed Description
In order to better understand the technical solutions in the embodiments of the present application, the following descriptions will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the embodiments of the present application shall fall within the scope of protection of the embodiments of the present application.
As described in the background section, the existing tumor ablation postoperative evaluation technology mainly has the problems that the temperature field during treatment cannot be visually displayed, so that a doctor is difficult to measure the damage degree of a tumor to be ablated, especially a safety boundary, and is difficult to immediately evaluate whether the operation is successful or not after the treatment is finished, and the prediction of the tumor recurrence risk which progresses with time cannot be made.
In view of the foregoing, various embodiments of the present application provide a post-operative tumor evaluation technique, which can at least partially solve the above-mentioned technical problems.
First embodiment
Fig. 1 is a flow chart of a method for evaluating postoperative tumor according to a first embodiment of the present application. As shown in the figure, the postoperative tumor method of the present embodiment mainly includes:
step S102, acquiring preoperative images and a plurality of thermal ablation images of the target tumor.
Alternatively, one pre-operative image of the target tumor before performing the ablation procedure may be acquired, and each thermal ablation image of the target tumor corresponding to each thermal ablation procedure may be acquired.
In this embodiment, the ablation performed for the target tumor may include a single cold ablation, a single hot ablation, a combination of cold and hot ablations, or the like ablation treatment regimen.
Wherein each thermal ablation operation (e.g., radio frequency ablation) corresponds to a different ablation location of the target tumor, respectively.
Optionally, a cold ablation image of the target tumor corresponding to the cold ablation procedure may also be acquired.
In particular, the ablation performed for the target tumor may also include a cold ablation operation, which may be performed prior to the hot ablation operation.
Optionally, the preoperative image, the thermal ablation image, the cold ablation image (if present) may include an MRI image, a CT image or an ultrasound image, but is not limited thereto, and image types may be used.
In this embodiment, the preoperative image may be an MRI (magnetic resonance imaging) image, and the thermal ablation image and the cold ablation image may be CT (computed tomography) images.
Alternatively, the ablation needle for performing the ablation therapy may include a monopolar ablation needle, a bipolar ablation needle, or a multipolar ablation needle, or the like.
Step S104, according to preset treatment parameters and each thermal ablation image, each thermal dose map corresponding to each thermal ablation image is obtained.
Alternatively, preset treatment parameters may be input into a preset simulation model for inversion estimation to obtain accumulated temperature data and thermal dose data from the start of each thermal ablation operation.
In this embodiment, the preset treatment parameters refer to various treatment parameters related to tumor ablation.
Alternatively, the preset treatment parameters may include an initial impedance and an initial temperature of the human tissue, an output power of the ablation needle, a number of operations of the thermal ablation operations, respective thermal ablation durations corresponding to the respective thermal ablation operations, and the like.
Optionally, the preset treatment parameters may also include patient age, tumor type, number of tumors, treatment position, number of ablation needles for cold ablation procedures, etc.
Step S106, obtaining a plurality of target feature vectors according to each thermal dose map, the preoperative image, each thermal ablation image and preset treatment parameters.
In this embodiment, the image histology feature and the clinical feature can be obtained from each thermal dose map, the preoperative image, each thermal ablation image, and the preset treatment parameters, and the image histology feature and the clinical feature can be arbitrarily combined to obtain a plurality of target feature vectors.
Step S108, according to each target feature vector, obtaining the postoperative evaluation result of the target tumor.
Optionally, each target feature vector may be input into a trained tumor evaluation model for prediction to output a post-operative evaluation result of the target tumor.
Alternatively, the post-operative evaluation of the target tumor may include a risk score for the target tumor that is indicative of the likelihood of post-operative recurrence of the target tumor.
Optionally, the post-operative evaluation result of the target tumor may further include each survival probability value of the target tumor corresponding to each period to obtain a survival probability curve of the patient individual.
In summary, according to the postoperative tumor evaluation method of the embodiment of the present application, by combining analysis of the preoperative image, the thermal ablation image and the preset treatment parameters of the target tumor, the postoperative recurrence risk of the target tumor can be rapidly and accurately evaluated and predicted, so as to assist the clinician to better control the patient's condition.
Second embodiment
Fig. 2 shows a schematic flow chart of a second embodiment of the present application. As shown in the figure, the method for postoperative tumor assessment of the present embodiment can be performed after step S102 and before step S104, and mainly includes the following steps:
step S202, image registration is performed for the preoperative image and each thermal ablation image of the target tumor.
In this embodiment, deformable registration may be performed for the pre-operative image and rigid registration may be performed for the other thermal ablation images based on the thermal ablation image of the first thermal ablation operation.
Specifically, a proper image registration mode can be selected according to the imaging difference of the image sequence for the same tissue to be ablated (target tumor), so as to correct the body position change during treatment and the tissue deformation caused by multiple needle advance and retreat operations (one needle advance and retreat operation can be generated by one thermal ablation operation).
For example, when performing registration of pre-operative images and thermal ablation images, large deformation differences can occur due to the influence of the actual treatment positions on the target tumor and surrounding tissues, in which case MRI-CT cross-modal deformable registration can be selected to eliminate anisotropic voxel movements resulting from supine, lateral and prone treatment positions.
For example, when performing registration of respective thermal ablation images corresponding to different thermal ablation procedures, a small deformation difference may be generated due to the influence of the multiple needle advancing and retreating procedures on the target tumor and surrounding tissues thereof, in which case rigid registration of CT-CT with the same modality may be selected.
Optionally, registration may also be performed for the cold ablation image based on the thermal ablation image of the first thermal ablation operation, where the registration manner of the cold ablation image may refer to the thermal ablation image, which is not described herein.
Step S204, determining the region of interest according to the registered preoperative images and the thermal ablation images.
In this embodiment, the tumor region of the target tumor may be determined according to the pre-operative image after registration, the monitoring range region of the target tumor may be determined according to each thermal ablation image after registration, and the region of interest may be determined according to the tumor region and the monitoring range region.
In this embodiment, the monitoring range region may include the maximum ablation radius range around the ablation needle and the surrounding tissue of its target tumor.
Optionally, the frozen puck of the target tumor can also be determined according to the registered cold ablation image.
Step S206, determining the positions of the ablation needles corresponding to the thermal ablation images according to the registered thermal ablation images.
In this embodiment, the position of each ablation needle corresponding to each thermal ablation image (i.e., each thermal ablation operation) may be determined based on the cross-sectional image of each thermal ablation image.
Alternatively, the ablation needle position may include tip position coordinates (x 1, y1, z 1) and handle position coordinates (x 2, y2, z 2) of the ablation needle.
In summary, the post-operation tumor evaluation method according to the embodiment of the present application performs registration processing on the obtained pre-operation image and thermal ablation image, so as to improve accuracy of the subsequent post-operation tumor evaluation result.
Third embodiment
Fig. 3 shows a flow chart of a method for postoperative tumor assessment according to a third embodiment of the present application. The embodiment is a specific implementation of the step S104, which mainly includes the following steps:
step S302, according to preset treatment parameters, obtaining data of each temperature field and data of each thermal dose corresponding to each thermal ablation image.
Optionally, a preset simulation model may be configured according to preset treatment parameters, and based on the configured preset simulation model, each temperature field data and each thermal dose data corresponding to each voxel block in the region of interest of the thermal ablation image are obtained.
In this embodiment, the steady-state temperature field and thermal dose distribution accumulated from the start of each thermal ablation operation can be inverted according to the preset treatment parameters by using a preset simulation model, and the temperature field and thermal dose lattice data are derived in the form of x-coordinate, y-coordinate, z-coordinate and temperature value T.
Alternatively, the preset treatment parameters may include an initial impedance and an initial temperature of the human tissue, an output power of the ablation needle, a number of operations of the thermal ablation operations, each of the thermal ablation durations corresponding to each of the thermal ablation operations, and the like. Wherein the output power of the ablation needle can be set according to different working segments.
Alternatively, the tip temperature of the ablation needle may be measured directly with a temperature sensor.
Alternatively, thermal dose data may be obtained by coupling a quasi-electrostatic field equation with a biological heat transfer equation.
Specifically, thermal dose data may be obtained using the following preset scaling rules:
wherein D represents thermal dose data corresponding to the voxel block, T represents a thermal ablation duration of the thermal ablation operation, and T represents a transient temperature value of the voxel block.
S304, converting the temperature field data and the thermal dose data corresponding to the thermal ablation images according to the space coordinates of the thermal ablation images to obtain the temperature field patterns and the thermal dose patterns corresponding to the thermal ablation images.
In this embodiment, the spatial coordinates of the thermal ablation image may be obtained from the information head of the thermal ablation image.
Optionally, each temperature field data and each thermal dose data corresponding to each thermal ablation image may be interpolated according to each spatial coordinate of each thermal ablation image to obtain each temperature field image gray value and each thermal dose image gray value corresponding to each thermal ablation image, and each temperature field map and each thermal dose map corresponding to each thermal ablation image may be obtained according to each temperature field image gray value and each thermal dose image gray value.
Specifically, the size of the interpolation grid can be determined according to extent, origin, spacing in the information head of the thermal ablation image, and the gray value of each temperature field image and the gray value of each thermal dose image can be interpolated by using a linear interpolation method or a cubic spline interpolation method.
And then, according to a preset temperature field lattice range threshold, marking the gray value of each temperature field image corresponding to each thermal ablation image as 37, thereby obtaining each temperature field map corresponding to each thermal ablation image.
Similarly, according to a preset thermal dose field lattice range threshold, the gray value of each thermal dose image corresponding to each thermal ablation image is marked as 0, so as to obtain each thermal dose map corresponding to each thermal ablation image.
Please refer to fig. 4 in combination, which shows a temperature field map and a thermal dose map obtained by the postoperative tumor evaluation method of the present embodiment, wherein the numbers a, b, and c correspond to three situations of supine, lateral recumbent, and prone recumbent, respectively. The sequence numbers 1 and 2 are respectively a temperature field map and a thermal dose map of the thermal ablation operation.
As can be seen from fig. 4, the temperature field map and the thermal dose map constructed in this embodiment both reflect the heat accumulation degree in the target tumor tissue, and the thermal dose map is not easily affected by the shape of the ablation needle, so that the boundary damage condition of the tissue to be ablated (i.e. the target tumor) can be better measured, so as to quickly determine whether the ablation operation is successful.
Step S306, according to the positions of the ablation needles corresponding to the thermal ablation images, registering processing is carried out on the temperature field maps and the thermal dose maps corresponding to the thermal ablation images.
In this embodiment, according to the needle tip position coordinates (x 1, y1, z 1) and the needle handle position coordinates (x 2, y2, z 2) of the ablation needle, displacement processing and/or rotation processing may be performed for each temperature field map and each thermal dose map corresponding to each thermal ablation image, so that each temperature field map and each thermal dose map corresponding to each thermal ablation image are aligned with the ablation needle position, respectively.
Specifically, the rotation angle perpendicular to the cross section of the thermal ablation image can be determined according to the needle tip position coordinates (x 1, y1, z 1) and the needle handle position coordinates (x 2, y2, z 2) of the ablation needle, so as to calculate a displacement transformation matrix and a rotation transformation matrix; and registering the temperature field map and the heat metering map according to the translation transformation matrix and the rotation transformation matrix so that the directions of the maps are respectively consistent with the inserting needle directions of the ablation needles.
Step S308, based on a preset fusion standard, fusing each registered temperature field map and each thermal dose map, a registered preoperative image and each registered thermal ablation image, and outputting a fusion result.
In this embodiment, for the case of performing multiple thermal ablation operations, the superposition of energy needs to be considered, and the method of this embodiment further includes performing a union process for each temperature field spectrum corresponding to each thermal ablation image to obtain a comprehensive temperature field spectrum, and performing a summation process for each thermal dose spectrum corresponding to each thermal ablation image to obtain a comprehensive thermal dose spectrum.
Alternatively, normalization processing may be performed on the integrated temperature field map, the integrated thermal dose map, to facilitate subsequent fusion display and feature extraction processing.
Optionally, based on a preset fusion standard, fusing each temperature field map and each thermal dose map after registration, the preoperative image after registration, each thermal ablation image after registration may include at least one of the following fusion modes:
fusing the comprehensive temperature field map and the preoperative image; fusing the comprehensive thermal dose map and the preoperative image; fusing any one thermal ablation image with a temperature field map corresponding to the thermal ablation image; and fusing any one thermal ablation image with a thermal dose map corresponding to the thermal ablation image.
For example, assuming that three thermal ablation operations are performed for the target tumor, wherein three temperature field spectrums corresponding to the three thermal ablation operations are respectively identified as A1, A2, A3, three thermal dose spectrums corresponding to the three thermal ablation operations are respectively identified as A0, B1, B2, B3, the integrated thermal dose spectrum is identified as B0, one pre-operative image after registration is identified as C, and three thermal ablation images corresponding to the three thermal ablation operations are identified as D1, D2, D3, the fusion manner of the above data may include the following four types:
mode one: fusion of a0+c; mode two: fusion of b0+c; mode three: fusion of the thermal map and the thermal ablation image (e.g., a1+d1, a2+d2, a3+d3, and so on) corresponding to the same thermal ablation operation; and a fusion mode is four: fusion of thermal dose maps and thermal ablation images (e.g., b1+d1, b2+d2, b3+d3, and so on) corresponding to the same thermal ablation operation.
In summary, the postoperative tumor evaluation method of the present embodiment inverts the temperature field map and the thermal dose map corresponding to each thermal ablation operation according to the preset treatment parameters, and selectively fuses each registered temperature field map and each thermal dose map, the registered preoperative image and each registered thermal ablation image to generate a plurality of fusion results, so as to facilitate a doctor to check the edge treatment condition of the tissue to be ablated (target tumor) in a linkage manner, and ensure the technical success of the ablation operation.
Furthermore, the postoperative tumor evaluation method of the embodiment considers the specificity of the thermal dose actually received by the patient in the treatment process, accurately inverts the temperature field through clinical treatment parameters, brings the influence of the thermal dose into postoperative evaluation of tumor ablation, and realizes fusion of the temperature field map, the thermal dose map, the preoperative image and the intraoperative image of the target tumor so as to intuitively display the temperature and energy information of each voxel on the tumor.
Fourth embodiment
Fig. 5 shows a flow chart of a method for postoperative tumor assessment according to a fourth embodiment of the present application, which mainly shows a specific embodiment of the above step S106, which mainly includes the following steps:
step S502, based on the preoperative image and the comprehensive thermal dose map, a plurality of image histology features corresponding to the tumor region and the monitoring range region are obtained respectively.
Alternatively, the image histology features may include any one of gray scale features, geometric features, texture features, and higher order features acquired using a neural network.
In this embodiment, for the preoperative image, a tumor region may be used as a mask to extract various texture features, including Tamara features, law features, gray level co-occurrence matrix features, and the like, and to extract the geometric features of the target tumor.
In this embodiment, for the comprehensive thermal energy spectrum, the monitoring range area may be used as a mask to extract the first-order gray features and the texture features as described above.
In this embodiment, for the cold ablation image, the monitoring range area may also be used as a mask to extract the geometric features of the frozen puck.
Optionally, the 3D region of interest in the preoperative image and the cryoablation image may be divided according to the cross section to obtain a plurality of two-dimensional slices, and the extraction operation of the image histology features may be performed based on each two-dimensional switch.
Step S504, obtaining a plurality of clinical features based on preset treatment parameters.
Optionally, the preset treatment parameters may include medical record information counted by the medical record system and treatment parameters of the ablation device.
For example, the medical record information can include parameters of age, tumor type, number of tumors, etc., and the treatment parameters can include treatment position, average power of the cold ablation operation, average power of the hot ablation operation, total duration of the cold ablation operation, number of cryoneedles of the cold ablation operation, number of hot ablation operations, etc.
Alternatively, normalization processing may be performed for each clinical feature that is digitized, and encoding processing (e.g., one-Hot encoding) may be performed for each clinical feature that is not digitized.
Step S506, obtaining each target feature vector according to the image histology feature and the clinical feature.
In this embodiment, classification may be performed for each image histology feature and each clinical feature based on the treatment order and the feature source, to obtain each class of features; screening various types of features based on preset screening rules to obtain various candidate features; and combining the candidate features at will to obtain the target feature vectors.
Optionally, the category characteristics include at least one of clinical category characteristics, preoperative tumor category characteristics, intraoperative thermal dose category characteristics.
Optionally, the preset screening rule may include a nonlinear screening mode and/or a linear screening mode.
For example, a Lasso screening method (i.e., nonlinear screening) may be used to screen each classification feature with a non-zero value, and a linear screening method may be used to screen each classification feature with a coefficient value less than 0.6, so as to obtain each candidate feature.
It should be noted that other screening methods may be used to obtain candidate features from the classification features, which is not limited in this application.
In summary, by using the postoperative tumor assessment method according to the embodiment of the present application, feature extraction is performed on a thermal dose map, a preoperative image, each thermal ablation image, and a preset treatment parameter to combine into a target feature vector, where the generated target feature vector includes a clinical feature, a preoperative tumor feature, and a thermal dose feature, so that not only can tissue characteristics of a tumor be represented, but also applied specific energy can be reflected, and heat is a root cause of a therapeutic effect generated by thermal physical ablation, regardless of direct cell necrosis or indirect immune injury, so that the present application has a good prediction potential for short-term prediction and long-term estimation of tumor ablation risk.
Fifth embodiment
Fig. 6 shows a postoperative tumor evaluation method according to a fifth embodiment of the present application, and the present embodiment mainly shows a training flow of a tumor evaluation model, which mainly includes:
step S602, training a tumor evaluation model by using each target feature vector to obtain each performance parameter corresponding to each target feature vector.
In this embodiment, the tumor evaluation model can be constructed based on any one of a support vector machine, a random forest, and a neural network.
In this embodiment, the different combinations of target feature vectors may be, for example, combinations of clinical features, pre-operative tumor features, conventional post-operative ablation zone features; the combination of clinical features, preoperative tumor features, intraoperative thermal dose features, etc., but is not limited thereto, and other combination patterns may be employed to generate the target feature vector.
In this embodiment, the tumor evaluation model may be trained based on a preset optimal super-parameter first:
for example, according to the calculation cost and the prediction error, determining the optimal tree number n_tree of the living random forest, where the optimal tree number determined in this embodiment may be n_tree=880 in consideration of the calculation cost and the prediction accuracy; the grid search is performed by GridSearchCV to determine the optimal superparameters max_features, max_depth, min_node_size. And then training a survival random forest model on the training set by using the optimal super parameters, and calculating a consistency coefficient C-index by the training set through 10-fold cross validation until the training set is iterated to the optimal training set C-index, thereby completing training of the tumor evaluation model.
The fully trained tumor assessment model can then be validated on the test set.
For example: dividing the test set into 10 parts, and alternately calculating the consistency coefficient C-index of each 9 parts to obtain simple statistical distribution of the performance of the test set; and calculating time dependent AUC (iAUC), brier error (iBS) based on the predicted test set risk scores to verify the global predictive performance of the tumor assessment model over the entire follow-up time.
In this embodiment, the tumor evaluation model may be trained based on preset performance metrics, where the preset performance metrics include: c-index (consistency coefficient) =0.92±0.012, iaauc (calculation time dependence) =0.889, ibs (Brier error) =0.041.
Step S604, according to each performance parameter corresponding to each target feature vector, obtaining the optimal combination of the target feature vectors and the tumor evaluation model trained based on the target feature vectors of the optimal combination.
In this embodiment, an optimal combination of the target feature vectors can be obtained by comparing the performance parameters, and the tumor evaluation model trained based on the optimal combination of the target feature vectors is used as the optimal tumor evaluation model.
In summary, the tumor evaluation model constructed by the embodiment can predict the risk score of the target tumor and each survival probability value of the target tumor corresponding to each period, and can give quantitative information of time dependence.
Sixth embodiment
A sixth embodiment of the present application provides a computer storage medium having stored therein instructions for executing each of the steps of the postoperative tumor assessment method described in any one of the first to fifth embodiments.
Seventh embodiment
Fig. 7 shows a postoperative tumor evaluation apparatus according to a seventh embodiment of the present application. As shown in the figure, the postoperative tumor evaluation apparatus 700 of the present embodiment mainly includes: an acquisition module 702, an analysis module 704, an evaluation module 706.
The acquisition module 702 is configured to acquire preoperative images, a plurality of thermal ablation images, and preset treatment parameters of a target tumor.
Optionally, the acquiring module 702 is further configured to acquire the preoperative image of the target tumor before performing an ablation procedure; acquiring each thermal ablation image of the target tumor corresponding to each thermal ablation operation; wherein each of the thermal ablation procedures corresponds to a different ablation location of the target tumor, respectively.
Optionally, the preoperative image and the thermal ablation image comprise any one of an MRI image, a CT image and an ultrasound image.
The analysis module 704 is configured to obtain each thermal dose map corresponding to each thermal ablation image according to the preset treatment parameters and each thermal ablation image, and obtain a plurality of target feature vectors according to each thermal dose map, the preoperative image, each thermal ablation image, and the preset treatment parameters.
Optionally, the analysis module 704 is further configured to perform image registration for the pre-operative image and each of the thermal ablation images of the target tumor; determining a region of interest according to the pre-operative image and each of the thermal ablation images after registration; and determining the positions of the ablation needles corresponding to the thermal ablation images according to the registered thermal ablation images.
Optionally, the analysis module 704 is further configured to perform deformable registration for the pre-operative image based on the thermal ablation image of the first thermal ablation operation; and performing a rigid registration for each of the other thermal ablation images based on the thermal ablation image of the first thermal ablation operation.
Optionally, the analysis module 704 is further configured to determine a tumor area of the target tumor according to the pre-operative image after registration; determining a monitoring range area of the target tumor according to each registered thermal ablation image; and determining the region of interest in the preoperative image and the thermal ablation image according to the tumor region and the monitoring range region and the tumor region and the monitoring range region.
Optionally, the analysis module 704 is further configured to obtain, according to the preset treatment parameter, each temperature field data and each thermal dose data corresponding to each thermal ablation image; according to each space coordinate of each thermal ablation image, converting each temperature field data and each thermal dose data corresponding to each thermal ablation image to obtain each temperature field map and each thermal dose map corresponding to each thermal ablation image; performing registration processing for each of the temperature field maps and each of the thermal dose maps corresponding to each of the thermal ablation images according to each of the ablation needle positions corresponding to each of the thermal ablation images; based on a preset fusion standard, fusing the registered temperature field maps, the registered thermal dose maps, the registered preoperative images and the registered thermal ablation images, and outputting a fusion result.
Optionally, the analysis module 704 is further configured to configure a preset simulation model according to the preset treatment parameters; and obtaining the temperature field data and the thermal dose data corresponding to each voxel block in the region of interest based on the configured preset simulation model.
Optionally, the analysis module 704 is further configured to obtain the thermal dose data based on a preset conversion rule; the preset conversion rule is expressed as:
wherein D represents the thermal dose data corresponding to the voxel block, T represents a thermal ablation duration of the thermal ablation operation, and T represents a transient temperature value of the voxel block.
Optionally, the preset treatment parameters include an initial impedance and an initial temperature of human tissue, an output power of an ablation needle, a number of operations of the thermal ablation operations, and each of the thermal ablation durations corresponding to each of the thermal ablation operations.
Optionally, the analysis module 704 is further configured to interpolate, according to each spatial coordinate of each thermal ablation image, each temperature field data and each thermal dose data corresponding to each thermal ablation image, and obtain each temperature field image gray value and each thermal dose image gray value corresponding to each thermal ablation image; according to a preset temperature field lattice range threshold, each temperature field image gray value corresponding to each thermal ablation image is obtained, and each temperature field map corresponding to each thermal ablation image is obtained; and according to a preset thermal dose field lattice range threshold, each thermal dose image gray value corresponding to each thermal ablation image is obtained, and each thermal dose map corresponding to each thermal ablation image is obtained.
Optionally, the ablation needle position includes a needle tip position coordinate and a needle handle position coordinate of the ablation needle, and the analysis module 704 is further configured to perform displacement processing and/or rotation processing on each of the temperature field maps and each of the thermal dose maps corresponding to each of the thermal ablation images according to the needle tip position coordinate and the needle handle position coordinate of the ablation needle.
Optionally, the analysis module 704 is further configured to perform union processing on each of the temperature field maps corresponding to each of the thermal ablation images, so as to obtain a comprehensive temperature field map; and executing addition processing on each thermal dose map corresponding to each thermal ablation image so as to obtain a comprehensive thermal dose map.
Optionally, the analysis module 704 further includes fusing the integrated temperature field map and the preoperative image, and outputting the fusion result.
Optionally, the analysis module 704 further includes fusing the integrated thermal dose map and the preoperative image, and outputting the fusion result.
Optionally, the analysis module 704 further includes fusing any one of the thermal ablation images and the temperature field map corresponding to the thermal ablation image, and outputting the fused result.
Optionally, the analysis module 704 further includes fusing any one of the thermal ablation images and the thermal dose map corresponding to the thermal ablation image, and outputting the fused result.
Optionally, the analysis module 704 is further configured to obtain a plurality of image histology features corresponding to the tumor region and to the monitoring range region, respectively, based on the preoperative image and the comprehensive thermal dose map; obtaining a plurality of clinical features based on the preset treatment parameters; and obtaining each target feature vector according to the image histology features and the clinical features.
Optionally, the image histology features include any one of gray scale features, geometric features, texture features, and higher order features acquired using a neural network.
Optionally, the region of interest is a three-dimensional region, and the analysis module 704 is further configured to divide the region of interest in the preoperative image according to a cross section to obtain a plurality of two-dimensional slices; based on each of the two-dimensional slices, the image histology features corresponding to the tumor region are obtained from the pre-operative image.
Optionally, the analysis module 704 is further configured to perform normalization processing for each of the clinical features that are digitized, and perform encoding processing for each of the clinical features that are not digitized.
Optionally, the analysis module 704 is further configured to perform classification for each of the image histology features and each of the clinical features based on the treatment sequence and the feature source, to obtain each class of features; screening each category characteristic based on a preset screening rule to obtain each candidate characteristic; and randomly combining the candidate features to obtain the target feature vectors.
Optionally, the category characteristics include at least one of clinical category characteristics, preoperative tumor category characteristics, intraoperative thermal dose category characteristics.
Optionally, the analysis module 704 is further configured to use Lasso to screen out each of the classification features with non-zero values to obtain each of the candidate features.
The evaluation module 706 is configured to obtain a post-operation evaluation result of the target tumor according to each of the target feature vectors.
Optionally, the evaluation module 706 is configured to use the trained tumor evaluation model 708 to perform prediction according to the target feature vector, so as to obtain a post-operation evaluation result of the target tumor.
Optionally, the post-operation evaluation result of the target tumor comprises a risk score of the target tumor and each survival probability value of the target tumor corresponding to each period, wherein the risk score of the target tumor is used for representing the postoperative recurrence probability of the target tumor.
Alternatively, each of the target feature vectors may be used to train the tumor evaluation model 708, obtain each of the performance parameters corresponding to each of the target feature vectors, and obtain an optimal combination of the target feature vectors and a tumor evaluation model 708 trained based on the optimal combination of the target feature vectors according to each of the performance parameters corresponding to each of the target feature vectors.
Optionally, the tumor assessment model 708 is constructed based on any of a support vector machine, a random forest, a neural network.
Alternatively, the tumor assessment model 708 may be trained based on preset performance metrics, including a consistency factor of 0.92±0.012, a calculated time dependence of 0.889, and a brier error of 0.041.
In addition, the postoperative tumor evaluation apparatus 700 of the present embodiment may be further used to implement other steps in the postoperative tumor evaluation method according to any one of the foregoing first to fifth embodiments, and has the beneficial effects of the corresponding method step embodiments, which are not described herein.
Therefore, the postoperative tumor evaluation method, device and computer storage medium provided by the embodiments of the present application can rapidly and accurately predict the postoperative tumor recurrence risk, so as to assist the clinician to more accurately control the patient's condition.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the embodiments of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (28)
1. A method of postoperative tumor assessment comprising:
acquiring preoperative images and a plurality of thermal ablation images of a target tumor;
performing image registration for the preoperative image and each thermal ablation image of the target tumor, determining a region of interest according to the pre-operative image and each thermal ablation image after registration, and determining each ablation needle position corresponding to each thermal ablation image according to each thermal ablation image after registration;
according to preset treatment parameters of the target tumor, obtaining temperature field data and thermal dose data corresponding to each thermal ablation image, converting the temperature field data and the thermal dose data corresponding to each thermal ablation image according to each spatial coordinate of each thermal ablation image, obtaining temperature field maps and thermal dose maps corresponding to each thermal ablation image, executing registration processing on each temperature field map and each thermal dose map corresponding to each thermal ablation image according to each ablation needle position corresponding to each thermal ablation image, fusing each registered temperature field map and each thermal dose map, the pre-operative image after registration and each registered thermal ablation image according to preset fusion standards, and outputting fusion results;
Obtaining a plurality of target feature vectors according to each thermal dose map, the preoperative image, each thermal ablation image and the preset treatment parameters; and
and obtaining a postoperative evaluation result of the target tumor according to each target feature vector.
2. The method of claim 1, wherein the acquiring the pre-operative image and the plurality of thermal ablation images of the target tumor comprises:
acquiring the preoperative image of the target tumor before performing an ablation operation; and
acquiring each thermal ablation image of the target tumor corresponding to each thermal ablation operation;
wherein each of the thermal ablation procedures corresponds to a different ablation location of the target tumor, respectively.
3. The method of claim 2, wherein the pre-operative image and the thermal ablation image comprise any one of an MRI image, a CT image, and an ultrasound image.
4. The method of claim 1, wherein performing image registration of the pre-operative image and each of the thermal ablation images for the target tumor comprises:
performing deformable registration for the pre-operative image based on the thermal ablation image of the first thermal ablation operation; and
Based on the thermal ablation images of the first thermal ablation operation, a rigid registration is performed for each of the other thermal ablation images.
5. The method of claim 1, wherein the determining a region of interest from the pre-operative image and each of the thermal ablation images after registration comprises:
determining a tumor region of the target tumor according to the registered preoperative image;
determining a monitoring range area of the target tumor according to each registered thermal ablation image; and
and determining the interested areas in the preoperative image and the thermal ablation image according to the tumor area and the monitoring range area.
6. The method of claim 1, wherein obtaining the temperature field data and the thermal dose data corresponding to each of the thermal ablation images according to the preset treatment parameters comprises:
configuring a preset simulation model according to the preset treatment parameters;
and obtaining the temperature field data and the thermal dose data corresponding to each voxel block in the region of interest based on the configured preset simulation model.
7. The method of claim 6, further comprising obtaining the thermal dose data based on a preset scaling rule;
the preset conversion rule is expressed as:
wherein D represents the thermal dose data corresponding to the voxel block, t represents a thermal ablation duration of the thermal ablation operation, and R represents a transient temperature value of the voxel block.
8. The method of claim 6, wherein the predetermined treatment parameters include an initial impedance and an initial temperature of human tissue, an output power of an ablation needle, a number of thermal ablation operations, and a respective thermal ablation duration corresponding to each of the thermal ablation operations.
9. The method according to claim 1, wherein the converting the temperature field data and the thermal dose data corresponding to the thermal ablation images according to the spatial coordinates of the thermal ablation images, and obtaining the temperature field maps and the thermal dose maps corresponding to the thermal ablation images comprises:
according to the space coordinates of each thermal ablation image, interpolating and calculating each temperature field data and each thermal dose data corresponding to each thermal ablation image to obtain each temperature field image gray value and each thermal dose image gray value corresponding to each thermal ablation image;
According to a preset temperature field lattice range threshold, each temperature field image gray value corresponding to each thermal ablation image is obtained, and each temperature field map corresponding to each thermal ablation image is obtained;
and according to a preset thermal dose field lattice range threshold, each thermal dose image gray value corresponding to each thermal ablation image is obtained, and each thermal dose map corresponding to each thermal ablation image is obtained.
10. The method of claim 1, wherein the method comprises the steps of,
the position of the ablation needle comprises the needle point position coordinate and the needle handle position coordinate of the ablation needle;
performing registration processing on each of the temperature field maps and each of the thermal dose maps corresponding to each of the thermal ablation images according to each of the ablation needle positions corresponding to each of the thermal ablation images includes;
and according to the needle point position coordinates and the needle handle position coordinates of the ablation needle, performing displacement processing and/or rotation processing on each temperature field map and each thermal dose map corresponding to each thermal ablation image.
11. The method of claim 5, further comprising:
performing union processing on each of the temperature field patterns corresponding to each of the thermal ablation images to obtain a comprehensive temperature field pattern;
And executing addition processing on each thermal dose map corresponding to each thermal ablation image so as to obtain a comprehensive thermal dose map.
12. The method of claim 11, wherein the fusing each of the temperature field maps and each of the thermal dose maps after registration, the preoperative image after registration, and each of the thermal ablation images after registration based on a preset fusion criterion, and outputting a fusion result comprises at least one of the following fusion modes:
fusing the comprehensive temperature field map and the preoperative image, and outputting the fusion result;
fusing the comprehensive thermal dose map and the preoperative image, and outputting the fusion result;
fusing any one of the thermal ablation images and the temperature field map corresponding to the thermal ablation image, and outputting the fusion result;
and fusing any one of the thermal ablation images and the thermal dose map corresponding to the thermal ablation image, and outputting the fusion result.
13. The method of claim 11, wherein the obtaining a plurality of target features from each of the thermal dose map, the preoperative image, each of the thermal ablation images, the preset treatment parameters comprises:
Based on the preoperative image and the comprehensive thermal dose map, respectively obtaining a plurality of image histology features corresponding to the tumor region and to the monitoring range region;
obtaining a plurality of clinical features based on the preset treatment parameters;
and obtaining each target feature vector according to the image histology features and the clinical features.
14. The method of claim 13, wherein the method comprises the steps of,
the image histology features include any one of gray features, geometric features, texture features, and higher-order features acquired using a neural network.
15. The method of claim 13, wherein the region of interest is a three-dimensional region, the method comprising:
dividing the region of interest in the preoperative image according to a cross section to obtain a plurality of two-dimensional slices;
based on each of the two-dimensional slices, the image histology features corresponding to the tumor region are obtained from the pre-operative image.
16. The method of claim 13, further comprising:
a normalization process is performed for each of the clinical features that are digitized, and a coding process is performed for each of the clinical features that are not digitized.
17. The method of claim 16, wherein the obtaining each of the target feature vectors from the image histology feature and the clinical feature comprises:
based on the treatment sequence and the feature sources, performing classification for each of the image histology features and each of the clinical features to obtain each class of features;
screening each category characteristic based on a preset screening rule to obtain each candidate characteristic;
and randomly combining the candidate features to obtain the target feature vectors.
18. The method of claim 17, wherein the class features comprise at least one of clinical class features, preoperative tumor class features, intraoperative thermal dose class features.
19. The method of claim 17, wherein the method comprises the steps of,
the preset screening rule comprises a nonlinear screening mode and/or a linear screening mode;
and wherein the nonlinear screening mode comprises Lasso screening.
20. The method of claim 17, wherein obtaining the post-operative evaluation result of the target tumor according to each of the target feature vectors comprises:
And utilizing the trained tumor evaluation model to execute prediction according to the target feature vector so as to obtain a postoperative evaluation result of the target tumor.
21. The method of claim 20, wherein the post-operative evaluation result of the target tumor comprises a risk score of the target tumor and each survival probability value of the target tumor for each time period, wherein the risk score of the target tumor is used to represent the level of post-operative recurrence probability of the target tumor.
22. The method of claim 20, further comprising training the tumor assessment model comprising:
respectively training the tumor evaluation model by utilizing each target feature vector to obtain each performance parameter corresponding to each target feature vector;
and obtaining an optimal combination of the target feature vectors and a tumor evaluation model trained based on the target feature vectors of the optimal combination according to the performance parameters corresponding to the target feature vectors.
23. The method of claim 22, wherein the tumor assessment model is constructed based on any one of a support vector machine, a random forest, a neural network.
24. The method of claim 22, further comprising training the tumor assessment model based on a preset performance index, wherein the preset performance index comprises a consistency coefficient of 0.92±0.012, a calculated time dependence of 0.889, and a brier error of 0.041.
25. The method of claim 13, further comprising:
obtaining a cold ablation image of the target tumor corresponding to a cold ablation operation;
performing registration for the cold ablation image based on the hot ablation image of the first time of the hot ablation operation;
determining a frozen puck region according to the registered cold ablation image;
based on the cold ablation image, the image histology features corresponding to the frozen puck region are obtained.
26. The method of claim 25, wherein the preset treatment parameters further comprise the number of ablation needles for the cold ablation procedure.
27. A computer storage medium having instructions stored therein for performing the steps of the post-operative tumor assessment method according to any one of claims 1 to 26.
28. A post-operative tumor assessment apparatus, comprising:
the acquisition module is used for acquiring preoperative images, a plurality of thermal ablation images and preset treatment parameters of the target tumor;
the analysis module is used for executing image registration on the preoperative image and each thermal ablation image of the target tumor, determining a region of interest according to the registered preoperative image and each thermal ablation image, and determining each ablation needle position corresponding to each thermal ablation image according to each registered thermal ablation image; according to preset treatment parameters of the target tumor, obtaining temperature field data and thermal dose data corresponding to each thermal ablation image, converting the temperature field data and the thermal dose data corresponding to each thermal ablation image according to each spatial coordinate of each thermal ablation image, obtaining temperature field maps and thermal dose maps corresponding to each thermal ablation image, executing registration processing on each temperature field map and each thermal dose map corresponding to each thermal ablation image according to each ablation needle position corresponding to each thermal ablation image, fusing each registered temperature field map and each thermal dose map, the pre-operative image after registration and each registered thermal ablation image according to preset fusion criteria, outputting fusion results, and obtaining a plurality of target feature vectors according to each thermal dose map, the pre-operative image, the thermal ablation image and the preset treatment parameters;
And the evaluation module is used for obtaining postoperative evaluation results of the target tumor according to each target feature vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110492453.0A CN113378879B (en) | 2021-05-06 | 2021-05-06 | Postoperative tumor evaluation method and device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110492453.0A CN113378879B (en) | 2021-05-06 | 2021-05-06 | Postoperative tumor evaluation method and device and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113378879A CN113378879A (en) | 2021-09-10 |
| CN113378879B true CN113378879B (en) | 2023-06-30 |
Family
ID=77570382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110492453.0A Active CN113378879B (en) | 2021-05-06 | 2021-05-06 | Postoperative tumor evaluation method and device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113378879B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116077170B (en) * | 2023-01-08 | 2024-02-06 | 天津市鹰泰利安康医疗科技有限责任公司 | Ablation regulation control method and system |
| CN116687353B (en) * | 2023-08-01 | 2023-12-19 | 宁波杜比医疗科技有限公司 | New adjuvant chemotherapy curative effect evaluation system, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109498155A (en) * | 2019-01-10 | 2019-03-22 | 上海交通大学 | Quick planning system and method in ablation art |
| CN110151309A (en) * | 2018-02-14 | 2019-08-23 | 上海交通大学 | The preoperative planing method of multi-modal ablation and its equipment |
| CN110246586A (en) * | 2019-05-28 | 2019-09-17 | 南京航空航天大学 | A kind of finite element model method for building up of the preoperative emulation of liver tumour microwave ablation |
| CN111700678A (en) * | 2020-06-23 | 2020-09-25 | 南京诺源医疗器械有限公司 | Control method of microwave ablation treatment dosage for liver tumor |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101859341A (en) * | 2009-04-13 | 2010-10-13 | 盛林 | Image-guided ablation surgery planning device |
| CN107049475A (en) * | 2017-04-19 | 2017-08-18 | 纪建松 | Liver cancer local ablation method and system |
| CN110265095A (en) * | 2019-05-22 | 2019-09-20 | 首都医科大学附属北京佑安医院 | For HCC recurrence and construction method and the application of the prediction model and nomogram of RFS |
| CN110910406B (en) * | 2019-11-20 | 2022-08-26 | 中国人民解放军总医院 | Method and system for evaluating three-dimensional space curative effect after liver tumor ablation |
| CN110882056B (en) * | 2019-12-11 | 2022-12-06 | 南京亿高微波系统工程有限公司 | Accurate tumor microwave ablation system under CT |
| CN111528918B (en) * | 2020-04-30 | 2023-02-21 | 深圳开立生物医疗科技股份有限公司 | Tumor volume change trend graph generation device after ablation, equipment and storage medium |
| CN111973271B (en) * | 2020-08-31 | 2021-12-14 | 北京理工大学 | Preoperative ablation region simulation method and device for tumor thermal ablation |
| CN112562859A (en) * | 2020-10-20 | 2021-03-26 | 应葵 | Intelligent simulation model training system and training method for tumor thermal ablation operation |
-
2021
- 2021-05-06 CN CN202110492453.0A patent/CN113378879B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110151309A (en) * | 2018-02-14 | 2019-08-23 | 上海交通大学 | The preoperative planing method of multi-modal ablation and its equipment |
| CN109498155A (en) * | 2019-01-10 | 2019-03-22 | 上海交通大学 | Quick planning system and method in ablation art |
| CN110246586A (en) * | 2019-05-28 | 2019-09-17 | 南京航空航天大学 | A kind of finite element model method for building up of the preoperative emulation of liver tumour microwave ablation |
| CN111700678A (en) * | 2020-06-23 | 2020-09-25 | 南京诺源医疗器械有限公司 | Control method of microwave ablation treatment dosage for liver tumor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113378879A (en) | 2021-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6568478B2 (en) | Planning, guidance and simulation system and method for minimally invasive treatment | |
| EP2621388B1 (en) | System for temperature feedback for adaptive radio frequency ablation | |
| CN113378879B (en) | Postoperative tumor evaluation method and device and computer storage medium | |
| US11844560B2 (en) | Path planning device for multi-probe joint cryoablation | |
| US20090318804A1 (en) | Cryotherapy Planning and Control System | |
| CN101859341A (en) | Image-guided ablation surgery planning device | |
| Singla et al. | Intra‐operative ultrasound‐based augmented reality guidance for laparoscopic surgery | |
| CN105096270B (en) | A kind of calcified plaque minimizing technology in coronary artery three-dimensional reconstruction | |
| US10713802B2 (en) | Ultrasonic image processing system and method and device thereof, ultrasonic diagnostic device | |
| Orczyk et al. | Imaging of prostate cancer: a platform for 3D co-registration of in-vivo MRI ex-vivo MRI and pathology | |
| Li et al. | Augmenting intraoperative ultrasound with preoperative magnetic resonance planning models for percutaneous renal access | |
| Pheiffer et al. | Model-based correction of tissue compression for tracked ultrasound in soft tissue image-guided surgery | |
| KR20140113172A (en) | Method and apparatus for making a plan of ultrasonic irradiation, and an ultrasonic irradiation method | |
| US20200179051A1 (en) | Therapeutic guidance compute node controller | |
| Lyons et al. | Ablation planning software for optimizing treatment: challenges, techniques, and applications | |
| JP7022723B2 (en) | Systems and methods for multiprobe guidance | |
| Yavariabdi et al. | Mapping and characterizing endometrial implants by registering 2D transvaginal ultrasound to 3D pelvic magnetic resonance images | |
| Golkar et al. | GPU-based 3D iceball modeling for fast cryoablation simulation and planning | |
| Shen et al. | Transrectal ultrasound image-based real-time augmented reality guidance in robot-assisted laparoscopic rectal surgery: a proof-of-concept study | |
| Duan et al. | Probabilistic finite element method for large tumor radiofrequency ablation simulation and planning | |
| Laura et al. | Accurate physics-based registration for the outcome validation of minimal invasive interventions and open liver surgeries | |
| Weihusen et al. | Workflow oriented software support for image guided radiofrequency ablation of focal liver malignancies | |
| CN115886999A (en) | Operation guiding method, device and control system based on simulation virtual technology | |
| Chen et al. | An automatic prostate surgical region reconstruction method based on multilevel learning | |
| Golkar et al. | Fast GPU computation of 3D isothermal volumes in the vicinity of major blood vessels for multiprobe cryoablation simulation |
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 |