Could texture features from preoperative CT image be used for predicting occult peritoneal carcinomatosis in patients with advanced gastric cancer? PLoS One. 2018;13:e0194755. [PMID: 29596522 PMCID: PMC5875782 DOI: 10.1371/journal.pone.0194755]

Utility of Combined Use of Imaging Features From Abdominopelvic CT and CA 125 to Identify Presence of CT Occult Peritoneal Metastases in Advanced Gastric Cancer

OBJECTIVE

The purpose of this study is to identify the presence of occult peritoneal metastasis (OPM) in patients with advanced gastric cancer (AGC) by using clinical characteristics and abdominopelvic computed tomography (CT) features.

METHODS

This retrospective study included 66 patients with OPM and 111 patients without peritoneal metastasis (non-PM [NPM]) who underwent preoperative contrast-enhanced CT between January 2020 and December 2021. Occult PMs means PMs that are missed by CT but later diagnosed by laparoscopy or laparotomy. Patients with NPM means patients have neither PM nor other distant metastases, indicating there is no evidence of distant metastases in patients with AGC. Patients' clinical characteristics and CT features such as tumor marker, Borrmann IV, enhancement patterns, and pelvic ascites were observed by 2 experienced radiologists. Computed tomography features and clinical characteristics were combined to construct an indicator for identifying the presence of OPM in patients with AGC based on a logistic regression model. Receiver operating characteristic curves and the area under the receiver operating characteristic curve (AUC) were generated to assess the diagnostic performance of the combined indicator.

RESULTS

Four independent predictors (Borrmann IV, pelvic ascites, carbohydrate antigen 125, and normalized arterial CT value) differed significantly between OPM and NPM and performed outstandingly in distinguishing patients with OPM from those without PM (AUC = 0.643-0.696). The combined indicator showed a higher AUC value than the independent risk factors (0.820 vs 0.643-0.696).

CONCLUSIONS

The combined indicator based on abdominopelvic CT features and carbohydrate antigen 125 may assist clinicians in identifying the presence of CT OPMs in patients with AGC.

CT texture analysis for differentiating between peritoneal carcinomatosis and peritoneal tuberculosis: a cross-sectional study

PURPOSE

Peritoneal carcinomatosis (PC) and peritoneal tuberculosis (PTB) have similar clinical and radiologic imaging features, which make it very difficult to differentiate between the two entities clinically. Our aim was to determine if the CT textural parameters of omental lesions among patients with PC were different from those with PTB.

METHODS

All patients who had undergone omental biopsy at our institution from January 2010 to December 2018 and had a tissue diagnosis of PC or PTB were eligible for inclusion. Patients who did not have a contrast-enhanced CT abdomen within one month of the omental biopsy were excluded. A region of interest (ROI) was manually drawn over omental lesions and radiomic features were extracted using open-source LIFEx software. Statistical analysis was performed to compare mean differences in CT texture parameters between the PC and PTB groups.

RESULTS

A total of 66 patients were included in the study of which 38 and 28 had PC and PTB, respectively. Omental lesions in patients with PC had higher mean radiodensity (mean difference: +32.4; p = 0.001), higher mean entropy (mean difference: +0.11; p < 0.001), and lower mean energy (mean difference: -0.024; p = 0.001) compared to those in PTB. Additionally, omental lesions in the PC group had lower gray-level co-occurrence matrix (GLCM) homogeneity (mean difference: -0.073; p < 0.001) and higher GLCM dissimilarity (mean difference: +0.480; p < 0.001) as compared to the PTB group.

CONCLUSION

CT texture parameters of omental lesions differed significantly between patients with PTB and those with PC, which may help clinicians in differentiating between the two entities.

Prediction of occult peritoneal metastases or positive cytology using CT in gastric cancer

OBJECTIVE

Accurate prediction of preoperative occult peritoneal metastasis (OPM) is critical to selecting appropriate therapeutic regimen for gastric cancer (GC). Considering the clinical practicability, we develop and validate a visible nomogram that integrates the CT images and clinicopathological parameters for the individual preoperative prediction of OPM in GC.

METHODS

This retrospective study included 520 patients who underwent staged laparoscopic exploration or peritoneal lavage cytology (PLC) examination. Univariate and multivariate logistic regression results were used to screen model predictors and construct nomograms of OPM risk. The performance of the model was detected by using ROC, accuracy, and C-index. The bootstrap resampling method was considered internal validation of the model. The Delong test was used to evaluate the difference in AUC between the two models.

RESULTS

Grade 2 mural stratification, tumor thickness, and the Lauren classification diffuse were significant predictors of OPM (p < 0.05). The nomogram of these three factors (compared with the original model) showed a higher predictive effect (p < 0.001). The area under the curve (AUC) of the model was 0.830 (95% CI 0.788-0.873), and the internally validated AUC of 1000 bootstrap samples was 0.826 (95% CI 0.756-0.870). The sensitivity, specificity, and accuracy were 76.0%, 78.8%, and 78.3%, respectively.

CONCLUSIONS

CT phenotype-based nomogram demonstrates favorable discrimination and calibration, and it can be conveniently used for preoperative individual risk rating of OPM in GC.

CLINICAL RELEVANCE STATEMENT

In this study, the preoperative OPM prediction model based on CT images (mural stratification, tumor thickness) combined with pathological parameters (the Lauren classification) showed excellent predictive ability in GC, and it is also suitable for clinicians to use rather than limited to professional radiologists.

KEY POINTS

• Nomogram based on CT image analysis can effectively predict occult peritoneal metastasis in gastric cancer (training area under the curve (AUC) = 0.830 and bootstrap AUC = 0.826). • Nomogram model combined with CT features performed better than the original model (established using only clinicopathological parameters) in differentiating occult peritoneal metastasis of gastric cancer.

Systematic review of diagnostic tools for peritoneal metastasis in gastric cancer-staging laparoscopy and its alternatives

BACKGROUND

Gastric cancer is one of the leading causes of cancer burden and mortality, often resulting in peritoneal metastasis in advanced stages with negative survival outcomes. Staging laparoscopy has become standard practice for suspected cases before a definitive gastrectomy or palliation. This systematic review aims to compare the efficacy of other diagnostic modalities instead of staging laparoscopy as the alternatives are able to reduce cost and invasive staging procedures. Recently, a radiomic model based on computed tomography and positron emission tomography (PET) has also emerged as another method to predict peritoneal metastasis.

AIM

To determine if the efficacy of computed tomography, magnetic resonance imaging and PET is comparable with staging laparoscopy.

METHODS

Articles comparing computed tomography, PET, magnetic resonance imaging, and radiomic models based on computed tomography and PET to staging laparoscopies were filtered out from the Cochrane Library, EMBASE, PubMed, Web of Science, and Reference Citations Analysis (https://www.referencecitationanalysis.com/). In the search for studies comparing computed tomography (CT) to staging laparoscopy, five retrospective studies and three prospective studies were found. Similarly, five retrospective studies and two prospective studies were also included for papers comparing CT to PET scans. Only one retrospective study and one prospective study were found to be suitable for papers comparing CT to magnetic resonance imaging scans.

RESULTS

Staging laparoscopy outperformed computed tomography in all measured aspects, namely sensitivity, specificity, positive predictive value and negative predictive value. Magnetic resonance imaging and PET produced mixed results, with the former shown to be only marginally better than computed tomography. CT performed slightly better than PET in most measured domains, except in specificity and true negative rates. We speculate that this may be due to the limited F-fluorodeoxyglucose uptake in small peritoneal metastases and in linitis plastica. Radiomic modelling, in its current state, shows promise as an alternative for predicting peritoneal metastases. With further research, deep learning and radiomic modelling can be refined and potentially applied as a preoperative diagnostic tool to reduce the need for invasive staging laparoscopy.

CONCLUSION

Staging laparoscopy was superior in all measured aspects. However, associated risks and costs must be considered. Refinements in radiomic modelling are necessary to establish it as a reliable screening technique.

Development and validation of a CT radiomics and clinical feature model to predict omental metastases for locally advanced gastric cancer

""We employed radiomics and clinical features to develop and validate a preoperative prediction model to estimate the omental metastases status of locally advanced gastric cancer (LAGC). A total of 460 patients (training cohort, n = 250; test cohort, n = 106; validation cohort, n = 104) with LAGC who were confirmed T3/T4 stage by postoperative pathology were continuously collected retrospectively, including clinical data and preoperative arterial phase computed tomography images (APCT). Dedicated radiomics prototype software was used to segment the lesions and extract features from the preoperative APCT images. The least absolute shrinkage and selection operator (LASSO) regression was used to select the extracted radiomics features, and a radiomics score model was constructed. Finally, a prediction model of omental metastases status and a nomogram were constructed combining the radiomics scores and selected clinical features. An area under the curve (AUC) of the receiver operating characteristic curve (ROC) was used to validate the capability of the prediction model and nomogram in the training cohort. Calibration curves and decision curve analysis (DCA) were used to evaluate the prediction model and nomogram. The prediction model was internally validated by the test cohort. In addition, 104 patients from another hospital's clinical and imaging data were gathered for external validation. In the training cohort, the combined prediction (CP) model (AUC 0.871, 95% CI 0.798-0.945) of the radiomics scores combined with the clinical features, compared with clinical features prediction (CFP) model (AUC 0.795, 95% CI 0.710-0.879) and radiomics scores prediction (RSP) model (AUC 0.805, 95% CI 0.730-0.879), had the better predictive ability. The Hosmer-Lemeshow test of the CP model showed that the prediction model did not deviate from the perfect fitting (p = 0.893). In the DCA, the clinical net benefit of the CP model was higher than that of the CFP model and RSP model. In the test and validation cohorts, the AUC values of the CP model were 0.836 (95% CI 0.726-0.945) and 0.779 (95% CI 0.634-0.923), respectively. The preoperative APCT-based clinical-radiomics nomogram showed good performance in predicting omental metastases status in LAGC, which may contribute to clinical decision-making.

Can visceral fat parameters based on computed tomography be used to predict occult peritoneal metastasis in gastric cancer?

BACKGROUND

The preoperative prediction of peritoneal metastasis (PM) in gastric cancer would prevent unnecessary surgery and promptly indicate an appropriate treatment plan.

AIM

To explore the predictive value of visceral fat (VF) parameters obtained from preoperative computed tomography (CT) images for occult PM and to develop an individualized model for predicting occult PM in patients with gastric carcinoma (GC).

METHODS

A total of 128 confirmed GC cases (84 male and 44 female patients) that underwent CT scans were analyzed and categorized into PM-positive (n = 43) and PM-negative (n = 85) groups. The clinical characteristics and VF parameters of two regions of interest (ROIs) were collected. Univariate and stratified analyses based on VF volume were performed to screen for predictive characteristics for occult PM. Prediction models with and without VF parameters were established by multivariable logistic regression analysis.

RESULTS

The mean attenuations of VF_{ROI 1} and VF_{ROI 2} varied significantly between the PM-positive and PM-negative groups (P = 0.044 and 0.001, respectively). The areas under the receiver operating characteristic curves (AUCs) of VF_{ROI 1} and VF_{ROI 2} were 0.599 and 0.657, respectively. The mean attenuation of VF_{ROI 2} was included in the final prediction combined model, but not an independent risk factor of PM (P = 0.068). No significant difference was observed between the models with and without mean attenuation of VF (AUC: 0.749 vs 0.730, P = 0.339).

CONCLUSION

The mean attenuation of VF is a potential auxiliary parameter for predicting occult PM in patients with GC.

Practical nomogram based on comprehensive CT texture analysis to preoperatively predict peritoneal occult metastasis of gastric cancer patients

Objectives

This study aims to evaluate whether a nomogram based on comprehensive CT texture analysis of primary tumor and peritoneotome combined with conventional CT signs can preoperatively predict peritoneal occult metastasis in gastric cancer patients.

Methods

A total of 1,251 patients with gastric cancer (GC) were retrospectively analyzed in Fujian Province Hospital between 2008 and 2020. Patients from the occult peritoneal metastasis (PM) group were initially diagnosed as PM-negative on CT and later confirmed as PM-positive through laparoscopy or surgery. The group without PM was randomly sampled from patients without PM. The preoperative CT signs and texture features and clinical characteristics of patients were retrospectively analyzed. Hazard factors of occult PM were identified by univariate analysis and multivariate logistic regression analysis, which were intended for creating prediction models. A nomogram was established based on the model with the highest predictive efficacy and clinical application value.

Results

A total of 31 patients with occult PM and 165 patients without PM were enrolled in this study. The maximum size, thickness, enhancement, serous involvement of primary GC tumor and ascites on CT, and texture features such as inhomogeneity of the primary tumor, standard deviation, and inhomogeneity of the peritoneum were determined as independent predictors that could be jointly applied to predict occult PM. We separately constructed five forecast models using CT signs, primary tumor texture, peritoneum texture, primary tumor texture + peritoneum texture, and their combination for predicting occult PM. These five prediction models achieved an AUC value of 0.832, 0.70, 0.784, 0.838, and 0.941, respectively. The DeLong test and Decision Curve Analysis (DCA) showed that the joint model, containing three meaningful CT signs (maximum size, thickness, and ascites) and two meaningful texture parameters (inhomogeneity of the primary tumor and inhomogeneity of the peritoneum), possessed the best predictive performance and clinical application (p&lt;0.05). A forecast nomogram was subsequently established from the model above-mentioned. The calibration curves of the nomogram indicated a good consistency (a concordance index of 0.807) between the projection and the actual observation of occult PM.

Conclusions

A practical projection nomogram based on the comprehensive CT texture analysis of a primary tumor and peritoneotome combined with conventional CT signs was constructed in our study, which can be conveniently used in preoperative personalized prediction of occult PM for GC patients, and acts as a recommendation for the optimization of clinical management.

The Value of Whole-Tumor Histogram and Texture Analysis Using Intravoxel Incoherent Motion in Differentiating Pathologic Subtypes of Locally Advanced Gastric Cancer

Purpose

To determine if whole-tumor histogram and texture analyses using intravoxel incoherent motion (IVIM) parameters values could differentiate the pathologic characteristics of locally advanced gastric cancer.

Methods

Eighty patients with histologically confirmed locally advanced gastric cancer who received surgery in our institution were retrospectively enrolled into our study between April 2017 and December 2018. Patients were excluded if they had lesions with the smallest diameter < 5 mm and severe image artifacts. MR scanning included IVIM sequences (9 b values, 0, 20, 40, 60, 100, 150,200, 500, and 800 s/mm²) used in all patients before treatment. Whole tumors were segmented by manually drawing the lesion contours on each slice of the diffusion-weighted imaging (DWI) images (with b=800). Histogram and texture metrics for IVIM parameters values and apparent diffusion coefficient (ADC) values were measured based on whole-tumor volume analyses. Then, all 24 extracted metrics were compared between well, moderately, and poorly differentiated tumors, and between different Lauren classifications, signet-ring cell carcinomas, and other poorly cohesive carcinomas using univariate analyses. Multivariate logistic analyses and multicollinear tests were used to identify independent influencing factors from the significant variables of the univariate analyses to distinguish tumor differentiation and Lauren classifications. ROC curve analyses were performed to evaluate the diagnostic performance of these independent influencing factors for determining tumor differentiation and Lauren classifications and identifying signet-ring cell carcinomas. The interobserver agreement was also conducted between the two observers for image quality evaluations and parameter metric measurements.

Results

For diagnosing tumor differentiation, the ADC_median, pure diffusion coefficient median (Dslow_median), and pure diffusion coefficient entropy (Dslow_entropy) showed the greatest AUCs: 0.937, 0.948, and 0.850, respectively, and no differences were found between the three metrics, P>0.05). The 95th percentile perfusion factor (FP _P95th) was the best metric to distinguish diffuse-type GCs vs. intestinal/mixed (AUC=0.896). The ROC curve to distinguish signet-ring cell carcinomas from other poorly cohesive carcinomas showed that the Dslow_median had AUC of 0.738. For interobserver reliability, image quality evaluations showed excellent agreement (interclass correlation coefficient [ICC]=0.85); metrics measurements of all parameters indicated good to excellent agreement (ICC=0.65-0.89), except for the Dfast metric, which showed moderate agreement (ICC=0.41-0.60).

Conclusions

The whole-tumor histogram and texture analyses of the IVIM parameters based on the biexponential model provided a non-invasive method to discriminate pathologic tumor subtypes preoperatively in patients with locally advanced gastric cancer. The metric FP _P95th derived from IVIM performed better in determining Lauren classifications than the mono-exponential model.

Comparison of clinical-computed tomography model with 2D and 3D radiomics models to predict occult peritoneal metastases in advanced gastric cancer

PURPOSE

To compare the ability of a clinical-computed tomography (CT) model vs. 2D and 3D radiomics models for predicting occult peritoneal metastasis (PM) in patients with advanced gastric cancer (AGC).

METHODS

In this retrospective study, we included 49 patients with occult PM and 49 control patients (without PM) who underwent preoperative CT and subsequent surgery between January 2016 and December 2018. Clinical information and CT semantic features were collected, and CT radiomics features were extracted. A predictive clinical-CT model was created using multivariate logistic regression. The least absolute shrinkage and selection operator algorithm and logistic regression were used for constructing 2D and 3D radiomics models. These models were validated with an external cohort (n = 30). Receiver operating characteristics curve with area under the curve (AUC), sensitivity, and specificity were used to evaluate predictive performance.

RESULTS

Tumor size, mild ascites, and serum CA125 were independent factors predictive of occult PM. The clinical-CT model of these independent factors showed better diagnostic performance than 2D and 3D radiomics models. In the external validation cohort, the AUCs of different models were as follows-clinical-CT model: 0.853 (sensitivity, 66.7%; specificity, 93.3%); 2D radiomics model: 0.622 (sensitivity, 80.0%; specificity, 46.7%); and 3D radiomics model: 0.676 (sensitivity, 60.0%; specificity, 86.0%). The clinical-CT model nomogram showed good clinical predictive efficiency to assess occult PM.

CONCLUSION

The clinical-CT model was better than the radiomics models in predicting occult PM in AGC.

A Bounding Box-Based Radiomics Model for Detecting Occult Peritoneal Metastasis in Advanced Gastric Cancer: A Multicenter Study

Purpose

To develop a bounding box (BBOX)-based radiomics model for the preoperative diagnosis of occult peritoneal metastasis (OPM) in advanced gastric cancer (AGC) patients.

Materials and Methods

599 AGC patients from 3 centers were retrospectively enrolled and were divided into training, validation, and testing cohorts. The minimum circumscribed rectangle of the ROIs for the largest tumor area (R_BBOX), the nonoverlapping area between the tumor and R_BBOX (peritumoral area; PERI) and the smallest rectangle that could completely contain the tumor determined by a radiologist (M_BBOX) were used as inputs to extract radiomic features. Multivariate logistic regression was used to construct a radiomics model to estimate the preoperative probability of OPM in AGC patients.

Results

The M_BBOX model was not significantly different from R_BBOX in the validation cohort [AUC: M_BBOX model 0.871 (95% CI, 0.814–0.940) vs. R_BBOX model 0.873 (95% CI, 0.820–0.940); p = 0.937]. M_BBOX was selected as the final radiomics model because of its extremely low annotation cost and superior OPM discrimination performance (sensitivity of 85.7% and specificity of 82.8%) over the clinical model, and this radiomics model showed comparable diagnostic efficacy in the testing cohort.

Conclusions

The BBOX-based radiomics could serve as a simpler reliable and powerful tool for the preoperative diagnosis of OPM in AGC patients. And M_BBOX-based radiomics is simpler and less time consuming.

Imaging of Gastric Carcinomatosis

Diagnosing the absence or presence of peritoneal carcinomatosis in patients with gastric cancer, including its extent and distribution, is an essential step in patients' therapeutic management. Such diagnosis still remains a radiological challenge. In this article, we review the strengths and weaknesses of the different imaging techniques for the diagnosis of peritoneal carcinomatosis of gastric origin as well as the techniques' imaging features. We also discuss the assessment of response to treatment and present recommendations for the follow-up of patients with complete surgical resection according to the presence of risk factors of recurrence, as well as discussing future directions for imaging improvement.

Adrenal Nodules Detected at Staging CT in Patients with Resectable Gastric Cancers Have a Low Incidence of Malignancy

Background Guidelines recommending additional imaging for adrenal nodules lack relevant epidemiologic evidence. Purpose To measure the prevalence of adrenal nodules detected at staging CT in patients with potentially resectable gastric cancer and the proportion of patients with malignant nodules among them. Materials and Methods This retrospective study included 10 250 consecutive patients (median age, 63 years; interquartile range, 53-71 years; 6884 men) who underwent staging CT and had potentially resectable gastric cancer in a tertiary center (May 2003 to December 2018). All 10 250 CT studies were retrospectively reviewed, and patients with adrenal nodules (or thickening ≥10 mm) were identified to measure the prevalence of adrenal nodules. Among patients with adrenal nodules, the per-patient proportions of malignant nodules, adrenal metastasis from gastric cancer, and additional adrenal examinations were measured. A secondary analysis was performed by using data from the original CT reports. The same metrics that were used in the retrospective review were assessed. Results The prevalence of adrenal nodules was 4.5% (95% CI: 4.1, 4.9; 462 of 10 250). The proportions of malignant nodules and adrenal metastasis from gastric cancer were 0.4% ( 95% CI: 0.1, 1.6; two of 462) and 0% (95% CI: 0.0, 0.8; 0 of 462), respectively. A total of 27% of the patients (95% CI: 23, 31; 123 of 462) underwent additional adrenal examination. According to original CT reports, the prevalence of adrenal nodules and the proportions of malignant nodules, adrenal metastases from gastric cancer, and additional adrenal examination were 2.7% (95% CI: 2.4, 3.0; 272 of 10 250), 0.7% (95% CI: 0.1, 2.6; two of 272), 0% (95% CI: 0.0, 1.4; 0 of 272), and 42.6% (95% CI: 36.7, 48.8; 116 of 272), respectively. Conclusion Although adrenal nodules were detected frequently on staging CT images of patients with otherwise resectable gastric cancer, these nodules were rarely malignant. ©RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Baumgarten in this issue.

Predicting Peritoneal Metastasis of Gastric Cancer Patients Based on Machine Learning

OBJECTIVE

The aim is to explore the prediction effect of 5 machine learning algorithms on peritoneal metastasis of gastric cancer.

METHODS

1080 patients with postoperative gastric cancer were divided into a training group and test group according to the ratio of 7:3. The model of peritoneal metastasis was established by using 5 machine learning (gbm(Light Gradient Boosting Machine), GradientBoosting, forest, Logistic and DecisionTree). Python pair was used to analyze the machine learning algorithm. Gbm algorithm is used to show the weight proportion of each variable to the result.

RESULT

Correlation analysis showed that tumor size and depth of invasion were positively correlated with the recurrence of patients after gastric cancer surgery. The results of the gbm algorithm showed that the top 5 important factors were albumin, platelet count, depth of infiltration, preoperative hemoglobin and weight, respectively. In training group: Among the 5 algorithm models, the accuracy of GradientBoosting and gbm was the highest (0.909); the AUC values of the 5 algorithms are gbm (0.938), GradientBoosting (0.861), forest (0.796), Logistic(0.741) and DecisionTree(0.712) from high to low. In the test group: among the 5 algorithm models, the accuracy of forest, DecisionTree and gbm was the highest (0.907); AUC values ranged from high to low to gbm (0.745), GradientBoosting (0.725), forest (0.696), Logistic (0.680) and DecisionTree (0.657).

CONCLUSION

Machine learning can predict the peritoneal metastasis in patients with gastric cancer.

Computed tomography radiomics to predict EBER positivity in Epstein-Barr virus-associated gastric adenocarcinomas: a retrospective study

BACKGROUND

The relevance of Epstein-Barr virus (EBV) in gastric carcinoma has been represented by the existence of EBV-encoded small RNA (EBER) in the tumor cells and has prognostic significance in gastric cancer, while gastric adenocarcinoma represents the most frequently occurring gastric malignancy.

PURPOSE

To observe the capacity of radiomic features extracted from contrast-enhanced computed tomography (CE-CT) images to differentiate EBER-positive gastric adenocarcinoma from EBER-negative ones.

MATERIAL AND METHODS

A total of 54 patients with gastric adenocarcinoma (EBER-positive: 27, EBER-negative: 27) were retrospectively examined. Radiomic imaging features were extracted from all regions of interest (ROI) delineated by two experienced radiologists on late arterial phase CT images. We distinguished related radiomic features through the two-tailed t test and applied them to construct a decision tree model to evaluate whether EBER in situ hybridization positive had appeared.

RESULTS

Nine radiomics features were significantly related to EBER in situ hybridization status (P < 0.05), four of which were used to build the decision tree through backward elimination: Correlation_ AllDirection_offset7, Correlation_ angle135_offset7, RunLengthNonuniformity_ AllDirection_offset1_SD, and HighGreyLevelRunEmphasis_ AllDiretion_offset1_SD. The decision tree model consisted of seven decision nodes and six terminal nodes, three of which demonstrated positive EBER in situ hybridization. The specificity, sensitivity, and accuracy of the model were 84%, 80%, and 81.7%, respectively. The area under the curve of the decision tree model was 0.87.

CONCLUSION

Radiomics based on CE-CT could be applied to predict EBER in situ hybridization status preoperatively in patients with gastric adenocarcinoma.

Noninvasive Prediction of Occult Peritoneal Metastasis in Gastric Cancer Using Deep Learning

IMPORTANCE

Occult peritoneal metastasis frequently occurs in patients with advanced gastric cancer and is poorly diagnosed with currently available tools. Because the presence of peritoneal metastasis precludes the possibility of curative surgery, there is an unmet need for a noninvasive approach to reliably identify patients with occult peritoneal metastasis.

OBJECTIVE

To assess the use of a deep learning model for predicting occult peritoneal metastasis based on preoperative computed tomography images.

DESIGN, SETTING, AND PARTICIPANTS

In this multicenter, retrospective cohort study, a deep convolutional neural network, the Peritoneal Metastasis Network (PMetNet), was trained to predict occult peritoneal metastasis based on preoperative computed tomography images. Data from a cohort of 1225 patients with gastric cancer who underwent surgery at Sun Yat-sen University Cancer Center (Guangzhou, China) were used for training purposes. To externally validate the model, data were collected from 2 independent cohorts comprising a total of 753 patients with gastric cancer who underwent surgery at Nanfang Hospital (Guangzhou, China) or the Third Affiliated Hospital of Southern Medical University (Guangzhou, China). The status of peritoneal metastasis for all patients was confirmed by pathological examination of pleural specimens obtained during surgery. Detailed clinicopathological data were collected for each patient. Data analysis was performed between September 1, 2019, and January 31, 2020.

MAIN OUTCOMES AND MEASURES

The area under the receiver operating characteristic curve (AUC) and decision curve were analyzed to evaluate performance in predicting occult peritoneal metastasis.

RESULTS

A total of 1978 patients (mean [SD] age, 56.0 [12.2] years; 1350 [68.3%] male) were included in the study. The PMetNet model achieved an AUC of 0.946 (95% CI, 0.927-0.965), with a sensitivity of 75.4% and a specificity of 92.9% in external validation cohort 1. In external validation cohort 2, the AUC was 0.920 (95% CI, 0.848-0.992), with a sensitivity of 87.5% and a specificity of 98.2%. The discrimination performance of PMetNet was substantially higher than conventional clinicopathological factors (AUC range, 0.51-0.63). In multivariable logistic regression analysis, PMetNet was an independent predictor of occult peritoneal metastasis.

CONCLUSIONS AND RELEVANCE

The findings of this cohort study suggest that the PMetNet model can serve as a reliable noninvasive tool for early identification of patients with clinically occult peritoneal metastasis, which will inform individualized preoperative treatment decision-making and may avoid unnecessary surgery and complications. These results warrant further validation in prospective studies.

An Intraoperative Model for Predicting Survival and Deciding Therapeutic Schedules: A Comprehensive Analysis of Peritoneal Metastasis in Patients With Advanced Gastric Cancer

Background and Objective: No specialized prognostic model for patients with gastric cancer with peritoneal metastasis (GCPM) exists for intraoperative clinical decision making. This study aims to establish a new prognostic model to provide individual treatment decisions for patients with GCPM.

Method: This retrospective analysis included 324 patients with GCPM diagnosed pathologically by laparoscopy from January 2007 to January 2018 who were randomly assigned to different sets (227 in the training set and 97 in the internal validation set). A nomogram was established from preoperative and intraoperative variables determined by a Cox model. The predictive ability and clinical applicability of the PM nomogram (PMN) were compared with the 15th Japanese Classification of Gastric Carcinoma (JCGC) Staging Guidelines for PM (P1abc). Additional external validation was performed using a dataset (n = 39) from the First Affiliated Hospital of University of Science and Technology of China.

Results: The median survival time was 8 (range, 1–90) months. In the training set, each PMN substage had significantly different survival curves (P < 0.001), and the PMN was superior to the P1abc based on the results of time-dependent receiver operating characteristic curve, C-index, Akaike information criterion and likelihood ratio chi-square analyses. In the internal and external validation sets, the PMN was also better than the P1abc in terms of its predictive ability. Of the PMN1 patients, those undergoing palliative resection had better overall survival (OS) than those undergoing exploratory surgery (P < 0.05). Among the patients undergoing exploratory surgery, those who received chemotherapy exhibited better OS than those who did not (P < 0.05). Among the patients who received palliative resection, only PMN1 patients exhibited better OS following chemotherapy (P < 0.05).

Conclusion: We developed and validated a simple, specific PM model for patients with GCPM that can predict prognosis well and guide treatment decisions.

Diagnostic advances of artificial intelligence and radiomics in gastroenterology

Traditional medical imaging, including ultrasound, computed tomography, magnetic resonance imaging, or positron emission tomography, remains widely used diagnostic modalities for gastrointestinal diseases at present. These modalities are used to assess changes in morphology, attenuation, signal intensity, and enhancement characteristics. Gastrointestinal tumors, especially malignant tumors, are commonly seen in clinical practice with an increasing number of deaths each year. Because the imaging manifestations of different diseases usually overlap, accurate early diagnosis of tumor lesions, noninvasive and effective evaluation of tumor staging, and prediction of prognosis remain challenging. Fortunately, traditional medical images contain a great deal of important information that cannot be recognized by human eyes but can be extracted by artificial intelligence (AI) technology, which can quantitatively assess the heterogeneity of lesions and provide valuable information, including therapeutic effects and patient prognosis. With the development of computer technology, the combination of medical imaging and AI technology is considered to represent a promising field in medical image analysis. This new emerging field is called “radiomics”, which makes big data mining and extraction from medical imagery possible and can help clinicians make effective decisions and develop personalized treatment plans. Recently, AI and radiomics have been gradually applied to lesion detection, qualitative and quantitative diagnosis, histopathological grading and staging of tumors, therapeutic efficacy assessment, and prognosis evaluation. In this minireview, we briefly introduce the basic principles and technology of radiomics. Then, we review the research and application of AI and radiomics in gastrointestinal diseases, especially diagnostic advancements of radiomics in the differential diagnosis, treatment option, assessment of therapeutic efficacy, and prognosis evaluation of esophageal, gastric, hepatic, pancreatic, and colorectal diseases.

Development and validation of an individualized nomogram to identify occult peritoneal metastasis in patients with advanced gastric cancer

Background

Occult peritoneal metastasis (PM) in advanced gastric cancer (AGC) patients is highly possible to be missed on computed tomography (CT) images. Patients with occult PMs are subject to late detection or even improper surgical treatment. We therefore aimed to develop a radiomic nomogram to preoperatively identify occult PMs in AGC patients.

Patients and methods

A total of 554 AGC patients from 4 centers were divided into 1 training, 1 internal validation, and 2 external validation cohorts. All patients’ PM status was firstly diagnosed as negative by CT, but later confirmed by laparoscopy (PM-positive n = 122, PM-negative n = 432). Radiomic signatures reflecting phenotypes of the primary tumor (RS1) and peritoneum region (RS2) were built as predictors of PM from 266 quantitative image features. Individualized nomograms of PM status incorporating RS1, RS2, or clinical factors were developed and evaluated regarding prediction ability.

Results

RS1, RS2, and Lauren type were significant predictors of occult PM (all P < 0.05). A nomogram of these three factors demonstrated better diagnostic accuracy than the model with RS1, RS2, or clinical factors alone (all net reclassification improvement P < 0.05). The area under curve yielded was 0.958 [95% confidence interval (CI) 0.923–0.993], 0.941 (95% CI 0.904–0.977), 0.928 (95% CI 0.886–0.971), and 0.920 (95% CI 0.862–0.978) for the training, internal, and two external validation cohorts, respectively. Stratification analysis showed that this nomogram had potential generalization ability.

Conclusion

CT phenotypes of both primary tumor and nearby peritoneum are significantly associated with occult PM status. A nomogram of these CT phenotypes and Lauren type has an excellent prediction ability of occult PM, and may have significant clinical implications on early detection of occult PM for AGC.

Computed tomography texture analysis in patients with gastric cancer: a quantitative imaging biomarker for preoperative evaluation before neoadjuvant chemotherapy treatment

PURPOSE

The aim of the study is to explore the role of computed tomography texture analysis (CT-TA) for predicting clinical T and N stages and tumor grade before neoadjuvant chemotherapy treatment in gastric cancer (GC) patients during the preoperative period.

MATERIALS AND METHODS

CT images of 114 patients with GC were included in this retrospective study. Following pre-processing steps, textural features were extracted using MaZda software in the portal venous phase. We evaluated and analyzed texture features of six principal categories for differentiating between T stages (T1,2 vs T3,4), N stages (N+ vs N-) and grades (low-intermediate vs. high). Classification was performed based on texture parameters with high model coefficients in linear discriminant analysis (LDA).

RESULTS

Dimension-reduction steps yielded five textural features for T stage, three for N stage and two for tumor grade. The discriminatory capacities of T stage, N stage and tumor grade were 90.4%, 81.6% and 64.5%, respectively, when LDA algorithm was employed.

CONCLUSION

CT-TA yields potentially useful imaging biomarkers for predicting the T and N stages of patients with GC and can be used for preoperative evaluation before neoadjuvant treatment planning.

Issues on peritoneal metastasis of gastric cancer: an update

Background

Peritoneal metastasis (PM) is one of the most common forms of metastasis with a very poor prognosis in patients with gastric cancer (GC). The mechanisms, diagnosis, and management of PM remain controversial.

Main body

Stephen Paget’s “seed-and-soil” hypothesis gives us an illustration of the mechanisms of PM. Recently, hematogenous metastasis and exosomes from GC are identified as novel mechanisms for PM. Diagnostic accuracy of conventional imaging modalities for PM is not satisfactory, but texture analysis may be a useful adjunct for the prediction of PM. Biological markers in peritoneal washings are helpful in identifying patients at high risk of PM, but many limitations remain to be overcome. Response of PM from systemic chemotherapy alone is very limited. However, conversion therapy is confirmed to be safe and able to prolong the survival of GC patients with PM. As an important part of conversion therapy, intraperitoneal chemotherapy with taxanes has become an ideal approach with several advantages. Additionally, gastrectomy should be considered in patients who would tolerate surgery if a remarkable response to chemotherapy was observed.

Conclusion

Texture analysis is a reliable adjunct for the prediction of PM, and conversion therapy provides a new choice for GC patients with PM. The underlying mechanisms and new biological markers for GC patients with PM should be the direction of future studies. Furthermore, significant aspects of conversion therapy, such as timing and method of the operation, and the indications remain to be clarified.

Imaging biomarkers in upper gastrointestinal cancers

In parallel with the increasingly widespread availability of high performance imaging platforms and recent progresses in pathobiological characterisation and treatment of gastrointestinal malignancies, imaging biomarkers have become a major research topic due to their potential to provide additional quantitative information to conventional imaging modalities that can improve accuracy at staging and follow-up, predict outcome, and guide treatment planning in an individualised manner. The aim of this review is to briefly examine the status of current knowledge about imaging biomarkers in the field of upper gastrointestinal cancers, highlighting their potential applications and future perspectives in patient management from diagnosis onwards.

Feasibility of CT radiomics to predict treatment response of individual liver metastases in esophagogastric cancer patients

In this study we investigate a CT radiomics approach to predict response to chemotherapy of individual liver metastases in patients with esophagogastric cancer (EGC). In eighteen patients with metastatic EGC treated with chemotherapy, all liver metastases were manually delineated in 3D on the pre-treatment and evaluation CT. From the pre-treatment CT scans 370 radiomics features were extracted per lesion. Random forest (RF) models were generated to discriminate partial responding (PR, >65% volume decrease, including 100% volume decrease), and complete remission (CR, only 100% volume decrease) lesions from other lesions. RF-models were build using a leave one out strategy where all lesions of a single patient were removed from the dataset and used as validation set for a model trained on the lesions of the remaining patients. This process was repeated for all patients, resulting in 18 trained models and one validation set for both the PR and CR datasets. Model performance was evaluated by receiver operating characteristics with corresponding area under the curve (AUC). In total 196 liver metastases were delineated on the pre-treatment CT, of which 99 (51%) lesions showed a decrease in size of more than 65% (PR). From the PR set a total of 47 (47% of RL, 24% of initial) lesions were no longer detected in CT scan 2 (CR). The RF-model for PR lesions showed an average training AUC of 0.79 (range: 0.74-0.83) and 0.65 (95% ci: 0.57-0.73) for the combined validation set. The RF-model for CR lesions had an average training AUC of 0.87 (range: 0.83-0.90) and 0.79 (95% ci 0.72-0.87) for the validation set. Our findings show that individual response of liver metastases varies greatly within and between patients. A CT radiomics approach shows potential in discriminating responding from non-responding liver metastases based on the pre-treatment CT scan, although further validation in an independent patient cohort is needed to validate these findings.