Objective To investigate the performance of the combined model based on both clinicopathological features and CT texture features in predicting liver metastasis of high-risk gastrointestinal stromal tumors(GISTs). Methods The high-risk GISTs confirmed by pathology from January 2015 to December 2020 were analyzed retrospectively,including 153 cases from the Cancer Hospital of the University of Chinese Academy of Sciences and 51 cases from the Shaoxing Central Hospital.The cases were randomly assigned into a training set(n=142)and a test set(n=62)at a ratio of 7∶3.According to the results of operation or puncture,they were classified into a liver metastasis group(76 cases)and a non-metastasis group(128 cases).ITK-SNAP was employed to delineate the volume of interest of the stromal tumors.Least absolute shrinkage and selection operator(LASSO)was employed to screen out the effective features.Multivariate logistic regression was adopted to construct the models based on clinicopathological features,texture features extracted from CT scans,and the both(combined model),respectively.Receiver operating characteristic(ROC)curve and calibration curve were established to evaluate the predictive performance of the models.The area under the curve(AUC)was compared by Delong test. Results Body mass index(BMI),tumor size,Ki-67,tumor occurrence site,abdominal mass,gastrointestinal bleeding,and CA125 level showed statistical differences between groups(all P<0.05).A total of 107 texture features were extracted from CT images,from which 13 and 7 texture features were selected by LASSO from CT plain scans and CT enhanced scans,respectively.The AUC of the prediction with the training set and the test set respectively was 0.870 and 0.855 for the model based on clinicopathological features,0.918 and 0.836 for the model based on texture features extracted from CT plain scans,0.920 and 0.846 for the model based on texture features extracted from CT enhanced scans,and 0.930 and 0.889 for the combined model based on both clinicopathological features and texture features extracted from CT plain scans.Delong test demonstrated no significant difference in AUC between the models based on the texture features extracted from CT plain scans and CT enhanced scans(P=0.762),whereas the AUC of the combined model was significantly different from that of the clinicopathological feature-based model and texture feature-based model(P=0.001 and P=0.023,respectively). Conclusion Texture features extracted from CT plain scans can predict the liver metastasis of high-risk GISTs,and the model established with clinicopathological features combined with CT texture features has best prediction performance.
Gastrointestinal Stromal Tumors/diagnostic imaging* ; Humans ; Liver Neoplasms/diagnostic imaging* ; ROC Curve ; Retrospective Studies ; Tomography, X-Ray Computed/methods*

Objective: Contrast-enhanced CT is an important method of preoperative diagnosis and evaluation for the malignant potential of gastric submucosal tumor (SMT). It has a high diagnostic accuracy rate in differentiating gastric gastrointestinal stromal tumor (GIST) with a diameter greater than 5 cm from gastric benign SMT. This study aimed to use deep learning algorithms to establish a diagnosis model (GISTNet) based on contrast-enhanced CT and evaluate its diagnostic value in distinguishing gastric GIST with a diameter ≤ 5 cm and other gastric SMT before surgery. Methods: A diagnostic test study was carried out. Clinicopathological data of 181 patients undergoing resection with postoperative pathological diagnosis of gastric SMT with a diameter ≤ 5 cm at Department of Gastrointestinal Surgery of Renji Hospital from September 2016 to April 2021 were retrospectively collected. After excluding 13 patients without preoperative CT or with poor CT imaging quality, a total of 168 patients were enrolled in this study, of whom, 107 were GIST while 61 were benign SMT (non-GIST), including 27 leiomyomas, 24 schwannomas, 6 heterotopic pancreas and 4 lipomas. Inclusion criteria were as follows: (1) gastric SMT was diagnosed by contrast-enhanced CT before surgery; (2) preoperative gastroscopic examination and biopsy showed no abnormal cells; (3) complete clinical and pathological data. Exclusion criteria were as follows: (1) patients received anti-tumor therapy before surgery; (2) without preoperative CT or with poor CT imaging quality due to any reason; (3) except GIST, other gastric malignant tumors were pathologically diagnosed after surgery. Based on the hold-out method, 148 patients were randomly selected as the training set and 20 patients as the test set of the GISTNet diagnosis model. After the GISTNet model was established, 5 indicators were used for evaluation in the test set, including sensitivity, specificity, positive predictive value, negative predictive value and the area under the receiver operating curve (AUC). Then GISTNet diagnosis model was compared with the GIST-risk scoring model based on traditional CT features. Besides, in order to compare the accuracy of the GISTNet diagnosis model and the imaging doctors in the diagnosis of gastric SMT imaging, 3 radiologists with 3, 9 and 19 years of work experience, respectively, blinded to clinical and pathological information, tested and judged the samples. The accuracy rate between the three doctors and the GISTNet model was compared. Results: The GISTNet model yielded an AUC of 0.900 (95% CI: 0.827-0.973) in the test set. When the threshold value was 0.345, the sensitivity specificity, positive and negative predictive values of the GISTNet diagnosis model was 100%, 67%, 75% and 100%, respectively. The accuracy rate of the GISTNet diagnosis model was better than that of the GIST-risk model and the manual readings from two radiologists with 3 years and 9 years of work experience (83% vs. 75%, 60%, 65%), and was close to the manual reading of the radiologist with 19 years of work experience (83% vs. 80%). Conclusion: The deep learning algorithm based on contrast-enhanced CT has favorable and reliable diagnostic accuracy in distinguishing gastric GIST with a diameter ≤ 5 cm and other gastric SMT before operation.
Deep Learning ; Diagnosis, Differential ; Gastrointestinal Stromal Tumors/diagnostic imaging* ; Humans ; Retrospective Studies ; Stomach Neoplasms/diagnostic imaging* ; Tomography, X-Ray Computed

To analyze the correlation of the CT imaging features and CT texture analysis (CTTA) parameters with risk stratifications of the gastric stromal tumors (GSTs).
 Methods: CT (plain scans with portal phase contrast enhanced scans) images from 98 GSTs patients before surgery were collected. CT features of the tumors were retrospectively analyzed and pathological risk stratifications were determined. Feature parameters of CTTA at plain and portal phase were obtained by using a MaZda software. The correlations of CT imaging features and CTTA parameters with the risk stratifications were analyzed.
 Results: CT imaging features including tumor size, growth pattern, shape, margin, the relationship between mass and adjacent organs, enhancement pattern, necrosis or cystic change, and the abnormal tumor vessels were associated with the risk stratifications (P<0.05). For CTTA, entropy was associated with the risk stratifications (P<0.05).
 Conclusion: Certain CT imaging features and CTTA parameters are associated with risk classifications in GSTs.
Gastrointestinal Stromal Tumors ; diagnostic imaging ; Humans ; Retrospective Studies ; Stomach Neoplasms ; diagnostic imaging ; Tomography, X-Ray Computed

Both malignant tumors derived from gastrointestinal tract and metastasis from peritoneal spread, hematogenous dissemination and lymph node can lead to acute abdomen. Such acute abdomen patients have poor prognosis, high mortality, and complex clinical manifestations. It is difficult to make a correct diagnosis in clinical practice. Recent studies show that gastrointestinal tumors are associated with clinical emergency. Malignant gastrointestinal tumors mostly result in obstruction, so upper gastrointestinal contrast for gastric cancer and post-enhanced CT for colon cancer are recommended; gastrointestinal stromal tumors usually cause bleeding, so computed tomography angiography (CTA) is the first choice for examination; primary gastrointestinal lymphoma tends to cause perforation and usually occurs in small intestine, so CT is the first examination for patients with ischemic acute abdomen, and post-enhanced CT is essential to exclude small intestine carcinoid because of its rising incidence in recent years. The possibility of gastrointestinal metastasis should be kept in mind for patients with cancer presenting acute abdomen. This article focuses on the imaging features of common gastrointestinal tumors and their acute obstruction, perforation, and hemorrhage, and aims to improve the understanding of such symptoms in clinical practice so that correct diagnosis and treatment can be made in time.
Abdomen, Acute ; diagnostic imaging ; Carcinoid Tumor ; diagnostic imaging ; Gastrointestinal Stromal Tumors ; diagnostic imaging ; Humans ; Intestinal Neoplasms ; diagnostic imaging ; Intestines ; diagnostic imaging

Primary malignant small bowel tumor as a rare kind of intestinal tumor is associated with a poor prognosis. The pathological types were various and complicated, such as adenocarcinoma, neuroendocrine tumor, malignant lymphoma, and malignant stromal tumor. The atypical early stage symptom resulted in difficult diagnosis at early stage, high misdiagnosis rate and lack of standard therapy schemes and means. In the past, X-ray, CT, MRI, and PET-CT were the main examination methods for primary small bowel tumor. However, with the development of radiology, a series of new diagnosis methods, including electronic enteroscopy, capsule endoscopy, multi-slice spiral CT enteroclysis and so on, promotes the diagnosis accurate rate. Surgery is still the most important method in the small bowel tumor treatment, and the alternative of the surgical method should depend on the tumor location, size and relationship with the adjacent organs. Application of the laparoscopic surgery for the small bowel tumor is still in the initial stage. Besides, some researches have confirmed that chemotherapy, radiotherapy, target therapy and endocrinotherapy have effects on the specific kind of small bowel tumor. Therefore this article will review the epidemiology, pathology, diagnosis and treatment of the primary malignant small bowel tumors.
Adenocarcinoma ; diagnosis ; epidemiology ; pathology ; therapy ; Capsule Endoscopy ; Gastrointestinal Stromal Tumors ; diagnosis ; epidemiology ; pathology ; therapy ; Humans ; Intestinal Neoplasms ; diagnosis ; epidemiology ; pathology ; therapy ; Intestine, Small ; diagnostic imaging ; pathology ; Laparoscopy ; methods ; Lymphoma ; diagnosis ; epidemiology ; pathology ; therapy ; Neuroendocrine Tumors ; diagnosis ; epidemiology ; pathology ; therapy ; Tomography, Spiral Computed

Abdominal Pain ; etiology ; Gastrointestinal Stromal Tumors ; complications ; diagnostic imaging ; Humans ; Jejunal Neoplasms ; complications ; diagnostic imaging ; Male ; Middle Aged ; Neurofibromatosis 1 ; complications ; Radiography ; Tomography, X-Ray Computed

BACKGROUND/AIMS: Gastric schwannoma (GS), a rare neurogenic mesenchymal tumor, is usually benign, slow-growing, and asymptomatic. However, GS is often misdiagnosed as gastrointestinal stromal tumors (GIST) on endoscopic and radiological examinations. The purpose of this study was to evaluate EUS characteristics of GS distinguished from GIST. METHODS: A total of 119 gastric subepithelial lesions, including 31 GSs and 88 GISTs, who were histologically identified and underwent EUS, were enrolled in this study. We evaluated the EUS characteristics, including location, size, gross morphology, mucosal lesion, layer of origin, border, echogenic pattern, marginal halo, and presence of an internal echoic lesion by retrospective review of the medical records. RESULTS: GS patients comprised nine males and 22 females, indicating female predominance. In the gross morphology according to Yamada's classification, type I was predominant in GS and type III was predominant in GIST. In location, GSs were predominantly located in the gastric body and GISTs were predominantly located in the cardia or fundus. The frequency of 4th layer origin and isoechogenicity as compared to the echogenicity of proper muscle layer was significantly more common in GS than GIST. Although not statistically significant, marginal halo was more frequent in GS than GIST. The presence of an internal echoic lesion was significantly more common in GIST than GS. CONCLUSIONS: The EUS characteristics, including tumor location, gross morphology, layer of origin, echogenicity in comparison with the normal muscle layer, and presence of an internal echoic lesion may be useful in distinguishing between GS and GIST.
Adult ; Aged ; Diagnosis, Differential ; Endosonography ; Female ; Gastric Fundus/pathology ; Gastrointestinal Stromal Tumors/*diagnosis/diagnostic imaging/pathology ; Humans ; Male ; Middle Aged ; Neoplasm Staging ; Neurilemmoma/*diagnosis/diagnostic imaging/pathology ; Retrospective Studies ; Stomach Neoplasms/*diagnosis/diagnostic imaging/pathology

The aim of the present study was to investigate the diagnostic value of the contrast-enhanced ultrasonography for gastrointestinal stromal tumors (GISTs). The conventional transabdominal ultrasonography and contrast-enhanced ultrasonography using an intraluminal contrast agent were performed in 66 cases. The different diagnostic value between conventional transabdominal ultrasonography and contrast-enhanced hydrocolon ultrasonography was compared, including the depiction ratio and location accuracy. The morpholpgical features of GISTs were observed. The sensitivity of the contrast-enhanced hydrocolon ultrasonography in the depiction of the GISTs (57/66, 86.4%) was higher than that of the conventional transabdominal ultrasonography(33/66, 50%, P<0. 05). Furthermore, the accuracy of the contrast-enhanced ultrasonography in the location of the GISTs (52/57, 91. 2%) was higher than that of the conventional transabdominal ultrasonography (13/33, 39. 4%, P<0. 05). The GISTs with higher or lower risk have different ultrasonic features. The contrast-enhanced ultrasonography was a more valuable diagnostic method for GIST than the conventional transabdominal ultrasonography.
Adult ; Aged ; Contrast Media ; administration & dosage ; Endosonography ; methods ; Female ; Gastrointestinal Neoplasms ; diagnostic imaging ; Gastrointestinal Stromal Tumors ; diagnostic imaging ; Humans ; Male ; Middle Aged

OBJECTIVETo analyze the association between CT features and survival rate of GIST, and to elucidate the significance of CT features for prognosis.

METHODSClinical data of 38 patients with pathologically and immunohistochemically proven GISTs, including 11 patients at high biological risk, 13 at moderate risk, 10 at low risk and 4 at very low risk. Patients who underwent CT examination for primary tumors were included. Association between CT features and survival rate was examined.

RESULTSThe mean follow-up period of 38 cases was 42.6 months and the 3-year survival rate was 86.8%. Univariate analysis revealed that tumor growth pattern, diameter, lobulated shape, irregular margin, necrosis, ulceration, adjacent invasion, and liver metastasis were associated factors of 3-year survival rate. Circumference invasion and hepatic metastases predicted poor 3-year survival rate (P<0.05). Calcification and intensity were not associated with prognosis (P>0.05).

CONCLUSIONSCT can demonstrate the tumor growth pattern, size, shape, boundary, density, necrosis, hemorrhage, calcification, ulcer, enhance features and metastasis. CT can play an important role in estimating the survival rate of GIST.

Adult ; Aged ; Female ; Follow-Up Studies ; Gastrointestinal Neoplasms ; diagnostic imaging ; Gastrointestinal Stromal Tumors ; diagnostic imaging ; Humans ; Male ; Middle Aged ; Prognosis ; Survival Rate ; Tomography, X-Ray Computed ; methods

Imaging study is the primary method to evaluate the efficacy of targeted therapy for gastrointestinal stromal tumor(GIST). The application of RECIST morphological criteria has limitations in the evaluation of targeted therapy, which may result in incorrect reflection of responses by conventional size-based criteria. Recent proposed Choi criteria, which combined the size and the CT value, has extended the application of radiology in the evaluation of GIST. The early change of apparent diffusion coefficient(ADC) values on diffusion-weighted imaging(DWI) can reflect the response of GIST to targeted therapy. The prominent change of ADC can be detected within one week after therapy. Through comprehensive analysis of the imaging characteristics associated with the biological behavior of GIST, new approaches may be developed in the evaluation of response of GIST to targeted therapy.
Diagnostic Imaging ; Diffusion Magnetic Resonance Imaging ; Gastrointestinal Stromal Tumors ; drug therapy ; Humans ; Prognosis ; Treatment Outcome