CN110993110A - Intestinal cancer peritoneal metastasis prediction model and construction method thereof - Google Patents
Intestinal cancer peritoneal metastasis prediction model and construction method thereof Download PDFInfo
- Publication number
- CN110993110A CN110993110A CN201911012402.2A CN201911012402A CN110993110A CN 110993110 A CN110993110 A CN 110993110A CN 201911012402 A CN201911012402 A CN 201911012402A CN 110993110 A CN110993110 A CN 110993110A
- Authority
- CN
- China
- Prior art keywords
- peritoneal metastasis
- metastasis
- model
- peritoneal
- features
- 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
Images
Classifications
-
- 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- 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
Abstract
The invention relates to the field of biomedicine, in particular to an intestinal cancer peritoneal metastasis prediction model and a construction method thereof, wherein the intestinal cancer peritoneal metastasis prediction model comprises the following steps: model 32.892+1.51 CT _ stage +1.884 turbo location +20.447 discrete measured sites-19.898 solid particulate matter-20.222 polymeric nodules; wherein CT _ stage is T stage; tumor site as tumor site; discrete metastatic sites are distant transfer sites; thickening the greater omentum by using the thick larger membrane; pelvic nodules are pelvic implant nodules. The intestinal cancer peritoneal metastasis prediction model is high in prediction accuracy, and has high sensitivity and specificity.
Description
Technical Field
The invention relates to the field of biomedicine, in particular to a intestinal cancer peritoneal metastasis prediction model and a construction method thereof.
Background
Colorectal cancer is the third most common cancer worldwide, with an estimated 10 million cases per year, the third leading cause of cancer-related death events (CA 2019). Peritoneal metastasis is considered to be the terminal stage of colorectal cancer, with the incidence of simultaneous peritoneal metastasis in colorectal cancer patients ranging from about 5-10%, with about 5% of patients found to have ectopic peritoneal metastasis after radical resection, and about 25-44% of relapsed patients having peritoneal metastasis. Recently, the treatment of peritoneal metastasis of colorectal cancer by cytoreductive surgery (CRS) in combination with intraperitoneal thermal perfusion chemotherapy (HIPEC) has been widely adopted in many centers worldwide, and this treatment modality can increase median survival of patients with peritoneal metastasis to 32 months. A complete CRS + HIPEC treatment was obtained with early diagnosis of simultaneous peritoneal metastasis, i.e. Peritoneal Cancer Index (PCI) <20 min. However, most peritoneal metastases are diagnosed at a later stage, often failing to administer complete CRS with an overall survival of 10 months. The preoperative diagnosis of the peritoneal metastasis can avoid open abdomen exploration to reduce trauma and carry out systemic adjuvant chemotherapy as early as possible. Neoadjuvant chemotherapy can shrink and control tumors, excise the primary tumor for integrity, and increase the rate of radical resection (RO resection).
Current imaging examination methods, including enhanced CT (only 11% sensitivity to <0.5cm metastases), MRI, PET-CT, etc., are not sensitive to <0.5cm peritoneal metastasis detection. The comprehensive analysis of the extracted CT features of the peritoneal metastatic carcinoma is very useful for radiologists to diagnose or find micrometastases in high-risk patients, and these features include T4 stage, peritoneal nodule shadow, peritoneal thickening, omentum thickening, etc. Therefore, integrating the specific characteristics of these peritoneal metastases, the development of CT-based nomograms (nomograms) is crucial for early diagnosis. Recently, a Nomogram based on CT phenotype, Lauren typing, proximal peritoneal features was developed to predict advanced gastric cancer cryptic peritoneal metastasis. The nomogram has a diagnostic accuracy of >0.9, and is capable of predicting insidious peritoneal metastasis with great accuracy. The study suggests that the peritoneal metastasis of colorectal cancer can be accurately predicted before surgery by combining CT imaging characteristics with clinical pathological parameters.
However, few studies are currently conducted on early diagnosis of peritoneal metastasis of colorectal cancer, and an effective prediction model and a prediction method are still lacking.
Disclosure of Invention
The invention aims to overcome at least one defect of the prior art and provides an intestinal cancer peritoneal metastasis prediction model which is a Nuomo graph of peritoneal metastasis based on CT characteristics, and has high prediction accuracy, high sensitivity and high specificity.
Another object of the present invention is to provide a method for constructing the intestinal cancer peritoneal metastasis prediction model.
The technical scheme adopted by the invention is as follows:
a prediction model of intestinal cancer peritoneal metastasis is as follows:
Model＝32.892+1.51*CT_stage+1.884*tumor location+20.447*distantmetastatic sites–19.898*thickened greater omentum–20.222*pelvic nodules；
wherein CT _ stage is T stage; tumor site as tumor site; distant metastatissites are distant transfer sites; thickening the greater omentum by using the thick larger membrane; pelvic nodules are pelvic implant nodules.
The intestinal cancer peritoneal metastasis prediction model is a Nomogram (Nomogram) based on a CT image, incorporates a T stage, a tumor part, a distant metastasis part, omentum thickening and a pelvic cavity planting nodule, can be used for early preoperative colorectal cancer diagnosis and peritoneal metastasis, can accurately perform individualized scoring on each intestinal cancer patient, and can predict the risk of peritoneal metastasis preoperatively, and is high in prediction accuracy, high in sensitivity and specificity. The model can be applied to preoperative risk assessment (non-diagnostic property) of colorectal cancer combined with early peritoneal metastasis, follow-up monitoring is carried out on the risk of peritoneal metastasis of each patient according to preoperative prediction of the model, and then different prevention and treatment measures are taken, so that the survival rate of the patient is improved.
The construction method of the intestinal cancer peritoneal metastasis prediction model comprises the following steps:
s1, selecting modeling variables: 150-200 colorectal cancer cases are selected, randomly divided into a training set and a verification set, and respectively comprise a peritoneal metastasis group and a non-peritoneal metastasis group, wherein specific CT image parameters of the peritoneal metastasis cancer comprise 13 items: tumor location (left or right), T stage, proximal organ invasion (T4b), N status, peritoneal plaque shadow, tumor enhancement, necrosis, perforation, PC metastasis, distant metastasis, ascites, omentum thickening, pelvic implant nodules;
s2, screening modeling variables: on a training set, firstly, screening a variable set related to a peritoneal metastasis dependent variable in the peritoneal metastasis characteristics of the enhanced CT by using a Boruta algorithm, specifically:
(1) create shadow feature (shadow feature): randomly disordering the sequence of each real feature R to obtain a shadow feature matrix S, splicing the shadow feature matrix S behind the real features to form a new feature matrix N ═ R, S ];
(2) a new feature matrix N is used as an input training model, a feature weight (feature) model can be output, and the weights of the real feature and the shadow feature are obtained;
(3) taking the maximum value W of the feature weight of the shadow features, recording one-time hit when the weight in the real features is larger than W;
(4) accumulating hits by using the real characteristics recorded in the step (3), marking the characteristics to be important or unimportant, adding FDR correction in a Boruta algorithm, and switching two detection methods by using two-step parameters; the Bonferroni correction is considered too conservative in the Boruta algorithm, so the FDR correction is increased by default;
(5) deleting unimportant features and repeating 1-4 until all features are marked;
s3, construction of a multivariate regression model: applying forward stepwise regression (Forwardstein) to the selected variable set, further screening according to AIC criterion (Chichi information criterion), and finally obtaining 5 variables of tumor part, T stage, distant metastasis part, omentum majus thickening and pelvic cavity implantation nodule which are closely related to peritoneal metastasis; and then, modeling the screened 5 variables by adopting a logistic regression model to obtain the intestinal cancer peritoneal metastasis prediction model.
Preferably, the method further comprises the following steps of processing the continuous variables before the screening of the modeling variables: carcinoembryonic antigen level (CEA level) is at the demarcation point of 5ng/ml, low level less than 5ng/ml and high level more than 5 ng/ml; age: dividing 50 and 70 into young (<50), middle aged (50-69) and old (> 70).
Preferably, in step S2, the weight model is Random Forest, lightgbm or xgboost.
Compared with the prior art, the invention has the beneficial effects that: the invention discovers that 5 factors of a tumor part, a T stage, a distant metastasis part, a omentum thickness and a pelvic cavity planting nodule have obvious correlation with intestinal cancer peritoneal metastasis, constructs a Nomogram (Nomogram) based on a CT image by utilizing multivariate regression, incorporates the T stage, the tumor part, the distant metastasis part, the omentum majus and the pelvic cavity planting nodule, can accurately carry out individual scoring on each intestinal cancer patient, and predicts the risk of peritoneal metastasis before operation, and has high prediction accuracy, high sensitivity and specificity. The model can be applied to preoperative risk assessment (non-diagnostic property) of colorectal cancer combined with early peritoneal metastasis, follow-up monitoring is carried out on the risk of peritoneal metastasis of each patient according to preoperative prediction of the model, and then different prevention and treatment measures are taken, so that the survival rate of the patient is improved.
Drawings
FIG. 1 is a typical feature map of peritoneal metastasis in enhanced CT.
FIG. 2 is a graph showing preoperative prediction of peritoneal metastasis by the CT-based model using ROC curves.
Fig. 3 is a CT-based Nomogram used to predict risk of peritoneal metastasis.
Fig. 4 is a decision curve and a calibration curve of CT-based Nomogram maps in the training set (a, B) and the test set (C, D).
Detailed Description
The drawings are only for purposes of illustration and are not to be construed as limiting the invention. For a better understanding of the following embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
Example 1
A prediction model of intestinal cancer peritoneal metastasis is constructed by the following steps:
1. modeling variable selection: 170 colorectal cancer cases are selected, randomly divided into a training set and a verification set, and respectively comprise a peritoneal metastasis group and a non-peritoneal metastasis group, wherein specific CT image parameters of the peritoneal metastatic cancers comprise 13 items: tumor location (left or right), T stage, proximal organ invasion (T4b), N status, peritoneal plaque shadow, tumor enhancement, necrosis, perforation, PC metastasis, distant metastasis, ascites, omentum thickening, pelvic implant nodules, as shown in fig. 1, fig. 1 is a typical feature of enhancing peritoneal metastasis in CT, fig. 1A: t4b, tumor invasion locally adjacent to the peritoneum; FIG. 1B: pelvic ascites; FIG. 1C: ovarian metastasis; FIG. 1D: peritoneal metastasis tumor invades the urinary system.
2. Processing of continuous variables: carcinoembryonic antigen level (CEA level) is at the demarcation point of 5ng/ml, low level less than 5ng/ml and high level more than 5 ng/ml; age: dividing 50 and 70 into young (<50), middle aged (50-69) and old (> 70).
3. Screening modeling variables: on a training set, firstly, screening a variable set related to a peritoneal metastasis dependent variable in the peritoneal metastasis characteristics of the enhanced CT by using a Boruta algorithm, specifically:
(1) create shadow feature (shadow feature): randomly disordering the sequence of each real feature R to obtain a shadow feature matrix S, splicing the shadow feature matrix S behind the real features to form a new feature matrix N ═ R, S ];
(2) a new feature matrix N is used as an input training model, a weight (feature) model of the feature, such as Random Forest, lightgbm and xgboost, can be output, and the feature importance of the real feature and the shadow feature is obtained;
(3) taking the maximum value W of the weight of the shadow features, recording one-time hit when the weight in the real features is larger than W;
(4) accumulating hits by using the real characteristics recorded in the step (3), marking the characteristics to be important or unimportant, adding FDR correction in a Boruta algorithm, and switching two detection methods by using two-step parameters; the Bonferroni correction is considered too conservative in the Boruta algorithm, so the FDR correction is increased by default;
(5) insignificant features are deleted and 1-4 repeated until all features are marked. Results the site of primary tumor (left or right), T stage, tumor enhancement, peritoneal metastasis, distant metastasis, thickening of the greater omentum, and pelvic implant nodules associated with peritoneal metastasis of intestinal cancer.
4. Constructing a multivariate regression model: applying Forward stepwise regression (Forward step) to the selected variable set, further screening according to AIC criterion (erythropool information criterion), and finally obtaining 5 variables of tumor part, T stage, distant metastasis part, omentum majus thickening and pelvic cavity implantation nodule which are closely related to peritoneal metastasis; then, modeling the screened 5 variables by adopting a logistic regression model to obtain a intestinal cancer peritoneal metastasis prediction model:
Model＝32.892+1.51*CT_stage+1.884*tumor location+20.447*distantmetastatic sites–19.898*thickened greater omentum–20.222*pelvic nodules。
the invention also verifies it: verification of multivariate regression model: area under the curve (AUC) of the training set: 0.929, (95% CI:0.879-0.979), sensitivity: 0.732, specificity: 0.983, positive predictive value: 82.26%, negative predictive value 100%.
And (4) verification set: AUC: 0.855, (95% CI:0.764-0.946), sensitivity: 0.727, specificity: 0.933. positive predictive value: 82.35%, negative predictive value 88.89%.
FIG. 2 is a graph showing pre-operative prediction of peritoneal metastasis by the CT-based model according to the ROC curve, wherein the left graph is a training set and the right graph is a validation set. By comparing the training set with the verification set, the preoperative prediction accuracy of the intestinal cancer peritoneal metastasis prediction model CT-based model on peritoneal metastasis is high.
Fig. 3 is a graph showing the risk prediction of peritoneal metastasis before the prediction of the peritoneal metastasis by the intestinal cancer peritoneal metastasis prediction model CT-based nomogram.
Intestinal cancer peritoneal metastasis prediction model CT-based nomogram was evaluated as follows: the performance of the CT-based nomogram was evaluated on the test and validation groups, respectively, using two methods, namely a calibration curve (CALIBRATION CURE) and a decision curve (precision CURE analysis). The modeling, data screening and drawing are realized by R software (version number 3.3.1), and the following modules are adopted: c060, glmnet, rms, pec, surfminer, surfMisc, match, and programs of precision curved analysis.
Training set: the calibration curve is very close to the ideal diagonal of 45 degrees, indicating that the accuracy of pre-operative prediction of peritoneal metastasis of the CT characteristic nomogram is high (fig. 4A), while the DCR curve shows that the nomogram can bring significant benefit to clinical decision (diagnosis of whether peritoneal metastasis is present) (fig. 4C).
And (4) verification set: the calibration curves also showed that the nomogram was very accurate (fig. 4B), and the DCA curves showed that the nomogram predicted a great benefit in peritoneal metastasis (fig. 4D).
According to the experiment, the intestinal cancer peritoneal metastasis prediction model CT-based nomogram has high accuracy and clinical application value on early preoperative diagnosis of peritoneal metastasis.
It should be understood that the above-mentioned embodiments of the present invention are only examples for clearly illustrating the technical solutions of the present invention, and are not intended to limit the specific embodiments of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention claims should be included in the protection scope of the present invention claims.
Claims (4)
1. A prediction model of intestinal cancer peritoneal metastasis is characterized in that the prediction model comprises the following steps:
Model＝32.892+1.51*CT_stage+1.884*tumor location+20.447*distantmetastatic sites–19.898*thickened greater omentum–20.222*pelvic nodules；
wherein CT _ stage is T stage; tumor site as tumor site; discrete metastatic sites are distant transfer sites; thickening the greater omentum by using the thick larger membrane; pelvic nodules are pelvic implant nodules.
2. The method for constructing a model for predicting peritoneal metastasis of intestinal cancer according to claim 1, comprising the steps of:
s1, selecting modeling variables: 150-200 colorectal cancer cases are selected, randomly divided into a training set and a verification set, and respectively comprise a peritoneal metastasis group and a non-peritoneal metastasis group, wherein specific CT image parameters of the peritoneal metastasis cancer comprise 13 items: tumor location, T stage, proximal organ invasion, N state, peritoneal plaque shadow, tumor enhancement, necrosis, perforation, PC metastasis, distant metastasis, ascites, omentum majus thickening, pelvic implant nodules;
s2, screening modeling variables: on a training set, firstly, screening a variable set related to a peritoneal metastasis dependent variable in the peritoneal metastasis characteristics of the enhanced CT by using a Boruta algorithm, specifically:
(1) creating shadow features: randomly disordering the sequence of each real feature R to obtain a shadow feature matrix S, splicing the shadow feature matrix S behind the real features to form a new feature matrix N ═ R, S ];
(2) the new feature matrix N is used as an input training model, a weight model of the features can be output, and the weights of the real features and the shadow features are obtained;
(3) taking the maximum value W of the weight of the shadow features, recording one-time hit when the weight in the real features is larger than W;
(4) accumulating hits by using the real characteristics recorded in the step (3), marking the characteristics to be important or unimportant, adding FDR correction in a Boruta algorithm, and switching two detection methods by using two-step parameters;
(5) deleting unimportant features and repeating 1-4 until all features are marked;
s3, construction of a multivariate regression model: applying forward stepwise regression to the selected variable set, further screening according to AIC criterion, and finally obtaining 5 variables of tumor part, T stage, distant metastasis part, omentum majus thickening and pelvic cavity implanted nodule which are closely related to peritoneal metastasis; and then, modeling the screened 5 variables by adopting a logistic regression model to obtain the intestinal cancer peritoneal metastasis prediction model.
3. The construction method according to claim 2, further comprising the step of processing the continuous variables before the modeling variable screening: carcinoembryonic antigen level takes 5ng/ml as a demarcation point, less than 5ng/ml as a low level and more than 5ng/ml as a high level; age: dividing 50 and 70 into young (<50), middle aged (50-69) and old (> 70).
4. The building method according to claim 2, wherein in step S2, the weight model is RandomForest, lightgmbm, or xgboost.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911012402.2A CN110993110B (en) | 2019-10-23 | 2019-10-23 | Intestinal cancer peritoneal metastasis prediction model and construction method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911012402.2A CN110993110B (en) | 2019-10-23 | 2019-10-23 | Intestinal cancer peritoneal metastasis prediction model and construction method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110993110A true CN110993110A (en) | 2020-04-10 |
| CN110993110B CN110993110B (en) | 2023-06-02 |
Family
ID=70082437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911012402.2A Active CN110993110B (en) | 2019-10-23 | 2019-10-23 | Intestinal cancer peritoneal metastasis prediction model and construction method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110993110B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111653355A (en) * | 2020-04-16 | 2020-09-11 | 中山大学附属第六医院 | Artificial intelligent prediction model for intestinal cancer peritoneal metastasis and construction method of model |
| CN112837815A (en) * | 2021-02-04 | 2021-05-25 | 复旦大学附属中山医院 | Model for evaluating gastric cancer prognosis based on Lauren typing and postoperative residual lymph node and application |
| CN113936804A (en) * | 2021-08-23 | 2022-01-14 | 四川大学华西医院 | System for constructing model for predicting risk of continuous air leakage after lung cancer resection |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107545144A (en) * | 2017-09-05 | 2018-01-05 | 上海市内分泌代谢病研究所 | pheochromocytoma branch prediction system based on molecular marker |
| CN107563134A (en) * | 2017-08-30 | 2018-01-09 | 中山大学 | A kind of system for being used to precisely predict patients with gastric cancer prognosis |
| CN107586852A (en) * | 2017-11-06 | 2018-01-16 | 福建医科大学附属协和医院 | Gastric cancer peritoneum branch prediction model and its application based on 22 genes |
| CN107881239A (en) * | 2017-12-27 | 2018-04-06 | 广西壮族自治区肿瘤防治研究所 | The miRNA marker related to colorectal cancer transfer and its application in blood plasma |
| CN110004226A (en) * | 2019-02-14 | 2019-07-12 | 辽宁省肿瘤医院 | A kind of method and model application based on carcinoma of the rectum transcript profile gene and methylation Conjoint Analysis prediction prognosis |
-
2019
- 2019-10-23 CN CN201911012402.2A patent/CN110993110B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563134A (en) * | 2017-08-30 | 2018-01-09 | 中山大学 | A kind of system for being used to precisely predict patients with gastric cancer prognosis |
| CN107545144A (en) * | 2017-09-05 | 2018-01-05 | 上海市内分泌代谢病研究所 | pheochromocytoma branch prediction system based on molecular marker |
| CN107586852A (en) * | 2017-11-06 | 2018-01-16 | 福建医科大学附属协和医院 | Gastric cancer peritoneum branch prediction model and its application based on 22 genes |
| CN107881239A (en) * | 2017-12-27 | 2018-04-06 | 广西壮族自治区肿瘤防治研究所 | The miRNA marker related to colorectal cancer transfer and its application in blood plasma |
| CN110004226A (en) * | 2019-02-14 | 2019-07-12 | 辽宁省肿瘤医院 | A kind of method and model application based on carcinoma of the rectum transcript profile gene and methylation Conjoint Analysis prediction prognosis |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111653355A (en) * | 2020-04-16 | 2020-09-11 | 中山大学附属第六医院 | Artificial intelligent prediction model for intestinal cancer peritoneal metastasis and construction method of model |
| CN111653355B (en) * | 2020-04-16 | 2023-12-26 | 中山大学附属第六医院 | Intestinal cancer peritoneal metastasis artificial intelligent prediction model and construction method thereof |
| CN112837815A (en) * | 2021-02-04 | 2021-05-25 | 复旦大学附属中山医院 | Model for evaluating gastric cancer prognosis based on Lauren typing and postoperative residual lymph node and application |
| CN113936804A (en) * | 2021-08-23 | 2022-01-14 | 四川大学华西医院 | System for constructing model for predicting risk of continuous air leakage after lung cancer resection |
| CN113936804B (en) * | 2021-08-23 | 2023-03-28 | 四川大学华西医院 | System for constructing model for predicting risk of continuous air leakage after lung cancer resection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110993110B (en) | 2023-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110993110A (en) | Intestinal cancer peritoneal metastasis prediction model and construction method thereof | |
| Park et al. | Long-term oncologic outcomes of robotic low anterior resection for rectal cancer: a comparative study with laparoscopic surgery | |
| Cucchetti et al. | Preoperative prediction of hepatocellular carcinoma tumour grade and micro-vascular invasion by means of artificial neural network: a pilot study | |
| Gupta et al. | Machine learning model for breast cancer prediction | |
| Karachristos et al. | CA 19-9 levels predict results of staging laparoscopy in pancreatic cancer | |
| Bollschweiler et al. | Artificial neural network for prediction of lymph node metastases in gastric cancer: a phase II diagnostic study | |
| Kessler et al. | Extended lymphadenectomy in colon cancer is crucial | |
| Oguro et al. | Optimal indications for additional resection of the invasive cancer-positive proximal bile duct margin in cases of advanced perihilar cholangiocarcinoma | |
| Sherman et al. | Biopsy for liver cancer: how to balance research needs with evidence‐based clinical practice | |
| Goel et al. | Robotic surgery for gallbladder cancer: Operative technique and early outcomes | |
| Xynos et al. | Clinical practice guidelines for the surgical management of colon cancer: a consensus statement of the Hellenic and Cypriot Colorectal Cancer Study Group by the HeSMO | |
| Zhong et al. | Tumor radiomics signature for artificial neural network-assisted detection of neck metastasis in patient with tongue cancer | |
| CN109124660B (en) | Gastrointestinal stromal tumor postoperative risk detection method and system based on deep learning | |
| Doornebosch et al. | Is the increasing role of Transanal Endoscopic Microsurgery in curation for T1 rectal cancer justified? A systematic review | |
| Xu et al. | The accuracy of frozen section diagnosis of pulmonary nodules: evaluation of inflation method during intraoperative pathology consultation with cryosection | |
| Urken et al. | The impact of metastatic lymph nodes on risk stratification in differentiated thyroid cancer: have we reached a higher level of understanding? | |
| Lodder et al. | Can extranodal spread in head and neck cancer be detected on MR imaging | |
| CN113671186A (en) | Method of scoring a sample comprising tumor tissue | |
| CN110916666B (en) | Imaging omics feature processing method for predicting recurrence of hepatocellular carcinoma after surgical resection | |
| Kim et al. | Is lymph node size a reliable factor for estimating lymph node metastasis in early gastric cancer? | |
| Nakakura | Challenges staging neuroendocrine tumors of the pancreas, jejunum and ileum, and appendix | |
| Ferenschild et al. | Total mesorectal excision for rectal cancer in an unselected population: quality assessment in a low volume center | |
| CN111653355B (en) | Intestinal cancer peritoneal metastasis artificial intelligent prediction model and construction method thereof | |
| Choi et al. | Identifying predictors of lymph node metastasis after endoscopic resection in patients with minute submucosal cancer of the stomach | |
| Lei et al. | Prognostic impact of the number of examined lymph nodes in stage II colorectal adenocarcinoma: a retrospective study |
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 |