Search

Objective: To develop an ensemble machine learning (eML) model using multiphase computed tomography (MPCT) for distinguishing between gastric ectopic pancreas (GEP) and gastric stromal tumors (GIST) in lesions < 3 cm. Methods: In this study, we retrospectively collected MPCT images from 138 patients between April 2017 and June 2023 across two centers. Cohort 1 comprised 94 patients divided into a training cohort and an internal validation cohort, while the 44 patients from Cohort 2 constituted the external validation cohort. Deep learning (DL) models were constructed based on the lesion region, and radiomics features were extracted to develop radiomics models, which were later integrated into the fusion model. Model performance was assessed through the analysis of the area under the receiver operating characteristic curve (AUROC). The diagnostic efficacy of the optimal model was compared with that of a radiologist. Additionally, the radiologist with the assistance of the eML model provides a secondary diagnosis, to assess the potential clinical value of the model. Results: After evaluation using an external validation cohort, the radiomics model demonstrated the highest performance in the venous phase, achieving AUROC of 0.87. The DL model showed optimal performance in the non-contrast phase, with AUROC of 0.81. The eML achieved the best performance across all models, with AUROC of 0.90. The use of eML-assisted analysis resulted in a significant improvement in the junior radiologist’s accuracy, rising from 0.77 to 0.93 (p < 0.05). However, the senior radiologist’s accuracy, while improving from 0.86 to 0.95, did not exhibit a statistically significant difference. Conclusion: eML model based on MPCT can effectively distinguish between GEPs and GISTs < 3 cm. Critical relevance statement: The multiphase CT-based fusion model, incorporating radiomics and DL technology, proves effective in distinguishing between GEP and gastric stromal tumors, serving as a valuable tool to enhance diagnoses and offering references for clinical decision-making. Key Points: No studies yet differentiated these tumors via radiomics or DL. Radiomics and DL methodologies unveil potentially distinct phenotypes within lesions. Quantitative analysis on CT for GIST and ectopic pancreas. Ensemble learning aids accurate diagnoses, assisting treatment decisions. [ABSTRACT FROM AUTHOR]

Abstract Objective To develop an ensemble machine learning (eML) model using multiphase computed tomography (MPCT) for distinguishing between gastric ectopic pancreas (GEP) and gastric stromal tumors (GIST) in lesions

Abstract Objective The risk category of gastric gastrointestinal stromal tumors (GISTs) are closely related to the surgical method, the scope of resection, and the need for preoperative chemotherapy. We aimed to develop and validate convolutional neural network (CNN) models based on preoperative venous-phase CT images to predict the risk category of gastric GISTs. Method A total of 425 patients pathologically diagnosed with gastric GISTs at the authors’ medical centers between January 2012 and July 2021 were split into a training set (154, 84, and 59 with very low/low, intermediate, and high-risk, respectively) and a validation set (67, 35, and 26, respectively). Three CNN models were constructed by obtaining the upper and lower 1, 4, and 7 layers of the maximum tumour mask slice based on venous-phase CT Images and models of CNN_layer3, CNN_layer9, and CNN_layer15 established, respectively. The area under the receiver operating characteristics curve (AUROC) and the Obuchowski index were calculated to compare the diagnostic performance of the CNN models. Results In the validation set, CNN_layer3, CNN_layer9, and CNN_layer15 had AUROCs of 0.89, 0.90, and 0.90, respectively, for low-risk gastric GISTs; 0.82, 0.83, and 0.83 for intermediate-risk gastric GISTs; and 0.86, 0.86, and 0.85 for high-risk gastric GISTs. In the validation dataset, CNN_layer3 (Obuchowski index, 0.871) provided similar performance than CNN_layer9 and CNN_layer15 (Obuchowski index, 0.875 and 0.873, respectively) in prediction of the gastric GIST risk category (All P >.05). Conclusions The CNN based on preoperative venous-phase CT images showed good performance for predicting the risk category of gastric GISTs.

Objective: The risk category of gastric gastrointestinal stromal tumors (GISTs) are closely related to the surgical method, the scope of resection, and the need for preoperative chemotherapy. We aimed to develop and validate convolutional neural network (CNN) models based on preoperative venous-phase CT images to predict the risk category of gastric GISTs. Method: A total of 425 patients pathologically diagnosed with gastric GISTs at the authors' medical centers between January 2012 and July 2021 were split into a training set (154, 84, and 59 with very low/low, intermediate, and high-risk, respectively) and a validation set (67, 35, and 26, respectively). Three CNN models were constructed by obtaining the upper and lower 1, 4, and 7 layers of the maximum tumour mask slice based on venous-phase CT Images and models of CNN_layer3, CNN_layer9, and CNN_layer15 established, respectively. The area under the receiver operating characteristics curve (AUROC) and the Obuchowski index were calculated to compare the diagnostic performance of the CNN models. Results: In the validation set, CNN_layer3, CNN_layer9, and CNN_layer15 had AUROCs of 0.89, 0.90, and 0.90, respectively, for low-risk gastric GISTs; 0.82, 0.83, and 0.83 for intermediate-risk gastric GISTs; and 0.86, 0.86, and 0.85 for high-risk gastric GISTs. In the validation dataset, CNN_layer3 (Obuchowski index, 0.871) provided similar performance than CNN_layer9 and CNN_layer15 (Obuchowski index, 0.875 and 0.873, respectively) in prediction of the gastric GIST risk category (All P >.05). Conclusions: The CNN based on preoperative venous-phase CT images showed good performance for predicting the risk category of gastric GISTs. [ABSTRACT FROM AUTHOR]

Abstract Background The most prevalent mesenchymal-derived gastrointestinal cancers are gastric stromal tumors (GSTs), which have the highest incidence (60–70%) of all gastrointestinal stromal tumors (GISTs). However, simple and effective diagnostic and screening methods for GST remain a great challenge at home and abroad. This study aimed to build a GST early warning system based on a combination of machine learning algorithms and routine blood, biochemical and tumour marker indicators. Methods In total, 697 complete samples were collected from four hospitals in Gansu Province, including 42 blood indicators from 318 pretreatment GST patients, 180 samples of gastric polyps and 199 healthy individuals. In this study, three algorithms, gradient boosting machine (GBM), random forest (RF), and logistic regression (LR), were chosen to build GST prediction models for comparison. The performance and stability of the models were evaluated using two different validation techniques: 5-fold cross-validation and external validation. The DeLong test assesses significant differences in AUC values by comparing different ROC curves, the variance and covariance of the AUC value. Results The AUC values of both the GBM and RF models were higher than those of the LR model, and this difference was statistically significant (P

Background: The Armed Forces Institute of Pathology (AFIP) had higher accuracy and reliability in prognostic assessment and treatment strategies for patients with gastric stromal tumors (GSTs). The AFIP classification is frequently used in clinical applications. But the risk classification is only available for patients who are previously untreated and received complete resection. We aimed to investigate the feasibility of multi-slice MSCT features of GSTs in predicting AFIP risk classification preoperatively. Methods: The clinical data and MSCT features of 424 patients with solitary GSTs were retrospectively reviewed. According to pathological AFIP risk criteria, 424 GSTs were divided into a low-risk group (n = 282), a moderate-risk group (n = 72), and a high-risk group (n = 70). The clinical data and MSCT features of GSTs were compared among the three groups. Those variables (p < 0.05) in the univariate analysis were included in the multivariate analysis. The nomogram was created using the rms package. Results: We found significant differences in the tumor location, morphology, necrosis, ulceration, growth pattern, feeding artery, vascular-like enhancement, fat-positive signs around GSTs, CT value in the venous phase, CT value increment in the venous phase, longest diameter, and maximum short diameter (all p < 0.05). Two nomogram models were successfully constructed to predict the risk of GSTs. Low- vs. high-risk group: the independent risk factors of high-risk GSTs included the location, ulceration, and longest diameter. The area under the receiver operating characteristic curve (AUC) of the prediction model was 0.911 (95% CI: 0.872–0.951), and the sensitivity and specificity were 80.0% and 89.0%, respectively. Moderate- vs. high-risk group: the morphology, necrosis, and feeding artery were independent risk factors of a high risk of GSTs, with an AUC value of 0.826 (95% CI: 0.759–0.893), and the sensitivity and specificity were 85.7% and 70.8%, respectively. Conclusions: The MSCT features of GSTs and the nomogram model have great practical value in predicting pathological AFIP risk classification between high-risk and non-high-risk groups before surgery. [ABSTRACT FROM AUTHOR]

Background: The most prevalent mesenchymal-derived gastrointestinal cancers are gastric stromal tumors (GSTs), which have the highest incidence (60–70%) of all gastrointestinal stromal tumors (GISTs). However, simple and effective diagnostic and screening methods for GST remain a great challenge at home and abroad. This study aimed to build a GST early warning system based on a combination of machine learning algorithms and routine blood, biochemical and tumour marker indicators. Methods: In total, 697 complete samples were collected from four hospitals in Gansu Province, including 42 blood indicators from 318 pretreatment GST patients, 180 samples of gastric polyps and 199 healthy individuals. In this study, three algorithms, gradient boosting machine (GBM), random forest (RF), and logistic regression (LR), were chosen to build GST prediction models for comparison. The performance and stability of the models were evaluated using two different validation techniques: 5-fold cross-validation and external validation. The DeLong test assesses significant differences in AUC values by comparing different ROC curves, the variance and covariance of the AUC value. Results: The AUC values of both the GBM and RF models were higher than those of the LR model, and this difference was statistically significant (P < 0.05). The GBM model was considered to be the optimal model, as a larger area was enclosed by the ROC curve, and the axes indicated robust model classification performance according to the accepted model discriminant. Finally, the integration of 8 top-ranked blood indices was proven to be able to distinguish GST from gastric polyps and healthy people with sensitivity, specificity and area under the curve of 0.941, 0.807 and 0.951 for the cross-validation set, respectively. Conclusion: The GBM demonstrated powerful classification performance and was able to rapidly distinguish GST patients from gastric polyps and healthy individuals. This identification system not only provides an innovative strategy for the diagnosis of GST but also enables the exploration of hidden associations between blood parameters and GST for subsequent studies on the prevention and disease surveillance management of GST. The GST discrimination system is available online for free testing of doctors and high-risk groups at https://jzlyc.gsyy.cn/bear/mobile/index.html. [ABSTRACT FROM AUTHOR]

Background: The Armed Forces Institute of Pathology (AFIP) had higher accuracy and reliability in prognostic assessment and treatment strategies for patients with gastric stromal tumors (GSTs). The AFIP classification is frequently used in clinical applications. But the risk classification is only available for patients who are previously untreated and received complete resection. We aimed to investigate the feasibility of multi-slice MSCT features of GSTs in predicting AFIP risk classification preoperatively. Methods: The clinical data and MSCT features of 424 patients with solitary GSTs were retrospectively reviewed. According to pathological AFIP risk criteria, 424 GSTs were divided into a low-risk group (n = 282), a moderate-risk group (n = 72), and a high-risk group (n = 70). The clinical data and MSCT features of GSTs were compared among the three groups. Those variables (p < 0.05) in the univariate analysis were included in the multivariate analysis. The nomogram was created using the rms package. Results: We found significant differences in the tumor location, morphology, necrosis, ulceration, growth pattern, feeding artery, vascular-like enhancement, fat-positive signs around GSTs, CT value in the venous phase, CT value increment in the venous phase, longest diameter, and maximum short diameter (all p < 0.05). Two nomogram models were successfully constructed to predict the risk of GSTs. Low- vs. high-risk group: the independent risk factors of high-risk GSTs included the location, ulceration, and longest diameter. The area under the receiver operating characteristic curve (AUC) of the prediction model was 0.911 (95% CI: 0.872–0.951), and the sensitivity and specificity were 80.0% and 89.0%, respectively. Moderate- vs. high-risk group: the morphology, necrosis, and feeding artery were independent risk factors of a high risk of GSTs, with an AUC value of 0.826 (95% CI: 0.759–0.893), and the sensitivity and specificity were 85.7% and 70.8%, respectively. Conclusions: The MSCT features of GSTs and the nomogram model have great practical value in predicting pathological AFIP risk classification between high-risk and non-high-risk groups before surgery.

Objective: To explore the clinical efficacy of endoscopic submucosal dissection (ESD) in the treatment of gastric stromal tumors and the risk factors for postoperative bleeding. Methods: 135 cases of gastric stromal tumors who were diagnosed and treated in our hospital from February 2018 to March 2020 were selected as the research object, and the clinical indicators were counted. The changes of cellular immune function and gastrointestinal hormones were compared before and after treatment. According to whether bleeding occurred after ESD treatment, patients were further divided into 12 cases of postoperative bleeding group and 123 cases of postoperative non-bleeding group. The influencing factors of bleeding after ESD in patients with gastric stromal tumors were analyzed. Results: The average operation time of 135 patients was(45.89± 8.79)min, the average postoperative feeding time was(3.05± 0.98)d, and the average hospital stay was (6.11± 0.95)d. The complete cut rate was 96.30%, the incidence of postoperative bleeding was 8.89%. The incidence of posterior perforation was 5.19%, and the incidence of postoperative infection was 9.63%. Single factor analysis showed that bleeding after ESD treatment was associated with hypertension, diabetes mellitus, platelets(PLT), serum procalcitonin (PCT) and C-reactive protein (CRP)(P<0.05). Compared with before treatment, the levels of CD3+, CD4+, CD4+/CD8+, serum motilin (MTL), gastrin (GAS) and growth hormone releasing peptide(Ghrelin) in patients after treatment decreased significantly, while the CD8+ increased significantly (P<0.05). Further multivariate Logistic regression analysis showed that the risk factors for bleeding after ESD operation included with hypertension, with diabetes mellitus, PCT>2.73 ng/mL, and CRP>62.19 ng/mL (P<0.05), while the protective factor was PLT>151.38× 109/L (P<0.05). Conclusion: ESD is effective and safe in the treatment of patients with gastric stromal tumor, but it will cause decreased cellular immune function and gastrointestinal hormone secretion in patients with gastric stromal tumor. Meanwhile, hypertension, diabetes mellitus, PCT>2.73ng/mL and CRP>62.19 ng/mL are risk factors for bleeding after ESD operation in patients with gastric stromal tumor. [ABSTRACT FROM AUTHOR]

Purpose of Review Gastrointestinal stromal tumors (GISTs) are both relatively common. Management of these lesions has been challenging with emerging interest in the endoscopic approach for both diagnostic and therapeutic interventions. Recent Findings Although these can be visualized on CT scan, endoscopic ultrasound (EUS) represents the standard method of evaluation and characterization using fine needle aspiration cytology (FNA) when indicated. While EUS-FNA can yield diagnostic cells, full characterization requires a sufficient volume of viable cells to do molecular analysis for c-KIT and determine the mitotic index. A new generation of fine needle biopsy (FNB) needles holds promise for improving our ability to fully characterize these lesions which will hopefully lead to improved management. Very small GISTs (< 1 cm) can probably be ignored, those between 1 and 2 cm are often surveyed, and those > 2 cm should be resected if the patient is fit and the lesion is in an accessible location. Though laparoscopic wedge resection is considered the standard of care, for small GISTs, those that are endophytic and/or located in a difficult position, pure endoscopic or hybrid laparoscopic-endoscopic approaches offer promise. Summary This review highlights the emerging advanced endoscopic approaches to GISTs. Although endoscopic removal of GISTs has two major advantages-precise localization of the lesion and gastric preservation, best practice strategies should focus on available expertise of expert endoscopists. [ABSTRACT FROM AUTHOR]

Gastric stromal tumors are the most common submucosal mass found in the stomach. These tumors are most often diagnosed at endoscopy and can be accurately characterized by endoscopic ultrasound. They typically require surgical resection, and an increasing number of patients undergo laparoscopic resection. A combined laparoscopic/endoscopic, intragastric enucleation technique is described, and results are reported in 10 patients. Eleven nonmalignant lesions were excised, with a mean size of 4.12 (2.0 to 7.0) cm. There were no complications, and the median length of stay was 3.5 days. This surgical approach appears appropriate for predominantly intraluminal, benign-appearing lesions of the proximal stomach. [ABSTRACT FROM AUTHOR]

Our study aimed to explore the value of applying the CT-based radiomic nomogram for predicting recurrence and/or metastasis (RM) of gastric stromal tumors (GSTs). During the past ten years, a total of 236 patients with GST were analyzed retrospectively. According to the postoperative follow-up classification, the patients were divided into two groups, namely non-recurrence/metastasis group (non-RM) and RM group. All the cases were randomly divided into primary cohort and validation cohort according to the ratio of 7:3. Standardized CT images were segmented by radiologists using ITK-SNAP software manually. Texture features were extracted from all segmented lesions, then radiomic features were selected and the radiomic nomogram was built using least absolute shrinkage and selection operator (LASSO) method. The clinical features with the greatest correlation with RM of GST were selected by univariate analysis, and used as parameters to build the clinical feature model. Eventually, model of radiomic and clinical features were fitted to construct the clinical + radiomic feature model. The performance of each model was evaluated by the area under receiver operating characteristic (ROC) curve (AUC). A total of 1223 features were extracted from all the segmentation regions of each case, and features were selected via the least absolute shrinkage and LASSO binary logistic regression model. After deletion of redundant features, four key features were obtained, which were used as the parameters to build a radiomic signature. The AUCs of radiomic nomogram in primary cohort and validation cohort were 0.816 and 0.946, respectively. The AUCs of clinical + radiomic feature model in primary cohort and validation cohort were 0.833 and 0.937, respectively. Using DeLong test, the differences of AUC values between radiomic nomogram and clinical + radiomic feature model in primary cohort (P = 0.840) and validation cohort (P = 0.857) were not statistically significant. To sum up, CT-based radiomic nomogram is of great potential in predicting the RM of GST non-invasively before operation., Competing Interests: None., (AJCR Copyright © 2021.)

Objectives: To determine the association of FAP expression with the prognosis of gastric stromal tumors (GSTs)., Methods: Paraffin-embedded GSTs samples were collected from January 2010 to December 2013 in the department of pathology of our hospital. FAP expression was examined by immunohistochemistry staining. Its correlations with clinical pathological characteristics and prognosis of GSTs were analyzed., Results: A total of 98 cases were included in this study. FAP was expressed in the cytoplasm of GSTs cells, with a positive rate of 42.9%. No FAP expression was found in normal gastric tissues. No differences of FAP expression were found in patients with different gender, age and tumor mitotic counts ( P >0.05). Tumor diameter and risk classification were associated with FAP expression ( P <0.05). Higher levels of FAP expression were found in larger and higher risk tumors. No significant correlations between FAP expression and routine immunohistochemical markers were found. Log-rank univariate survival analysis showed that mitotic counts, tumor size, postoperative IM and FAP expression were associated with recurrence free survival of GSTs patients with intermediate-high risks ( P <0.05). Cox multivariate survival analysis showed that mitotic counts, tumor size, postoperative IM and FAP were independent predictors for the prognosis of GSTs patients with intermediate-high risks ( P <0.05)., Conclusion: FAP is expressed in the cytoplasm of gastric GIST cells, but not in normal gastric tissues. FAP is a predictor for the prognosis of GSTs patients with intermediate-high risks.

Aim: To assess the effectiveness of endoscopic full-thickness resection (EFR) and laparoscopic surgery in the treatment of gastric stromal tumors arising from the muscularis propria., Methods: Out of 62 gastric stromal tumors arising from the muscularis propria, each > 1.5 cm in diameter, 32 were removed by EFR, and 30 were removed by laparoscopic surgery. The tumor expression of CD34, CD117, Dog-1, S-100, and SMA was assessed immunohistochemically. The operative time, complete resection rate, length of hospital stay, incidence of complications, and recurrence rate were compared between the two groups. Continuous data were compared using independent samples t-tests, and categorical data were compared using χ (2) tests., Results: The 32 gastric stromal tumors treated by EFR and the 30 treated by laparoscopic surgery showed similar operative time [20-155 min (mean, 78.5 ± 30.1 min) vs 50-120 min (mean, 80.9 ± 46.7 min), P > 0.05], complete resection rate (100% vs 93.3%, P > 0.05), and length of hospital stay [4-10 d (mean, 5.9 ± 1.4 d) vs 4-19 d (mean, 8.9 ± 3.2 d), P >0.05]. None of the patients treated by EFR experienced complications, whereas two patients treated by laparoscopy required a conversion to laparotomy, and one patient had postoperative gastroparesis. No recurrences were observed in either group. Immunohistochemical staining showed that of the 62 gastric stromal tumors diagnosed by gastroscopy and endoscopic ultrasound, six were leiomyomas (SMA-positive), one was a schwannoglioma (S-100 positive), and the remaining 55 were stromal tumors., Conclusion: Some gastric stromal tumors arising from the muscularis propria can be completely removed by EFR. EFR could likely replace surgical or laparoscopic procedures for the removal of gastric stromal tumors.