Diagnostic performance of stomach CT compared with endoscopic ultrasonography in diagnosing gastric subepithelial tumors

Artificial Intelligence-Based Diagnosis of Gastric Mesenchymal Tumors Using Digital Endosonography Image Analysis

Background/Objectives: Artificial intelligence (AI)-assisted endoscopic ultrasonography (EUS) diagnostic tools have shown excellent performance in diagnosing gastric mesenchymal tumors. This study aimed to assess whether incorporating clinical and endoscopic factors into AI-assisted EUS classification models based on digital image analysis could improve the diagnostic performance of AI-assisted EUS diagnostic tools. Methods: We retrospectively analyzed the data of 464 patients who underwent both EUS and surgical resection of gastric mesenchymal tumors, including 294 gastrointestinal stromal tumors (GISTs), 52 leiomyomas, and 41 schwannomas. AI-assisted classification models for GISTs and non-GIST tumors were developed utilizing clinical and endoscopic factors and digital EUS image analysis. Results: Regarding the baseline EUS classification models, the area under the receiver operating characteristic (AUC) values of the logistic regression, decision tree, random forest, K-nearest neighbor (KNN), and support vector machine (SVM) models were 0.805, 0.673, 0.781, 0.740, and 0.791, respectively. Using the new classification models incorporating clinical and endoscopic factors into the baseline classification models, the AUC values of the logistic regression, decision tree, random forest, KNN, and SVM models increased to 0.853, 0.715, 0.896, 0.825, and 0.794, respectively. In particular, the random forest and KNN models exhibited significant improvement in performance in Delong's test (both p < 0.001). Conclusion: The diagnostic performance of the AI-assisted EUS classification models improved when clinical and endoscopic factors were incorporated. Our results provided direction for developing new AI-assisted EUS models for gastric mesenchymal tumors.

EUS-Guided Diagnosis of Gastric Subepithelial Lesions, What Is New?

Gastric subepithelial lesions (SELs) are intramural lesions that arise underneath the gastric mucosa. SELs can be benign, but can also be malignant or have malignant potential. Therefore, correct diagnosis is crucial. Endosonography has been established as the diagnostic gold standard. Although the identification of some of these lesions can be carried out immediately, solely based on their echo characteristics, for certain lesions histological examination is necessary. Sometimes histology can be inconclusive, especially for smaller lesions. Therefore, new methods have been developed in recent years to assist decision making, such as contrast enhanced endosonography, EUS elastography, and artificial intelligence systems. In this narrative review we provide a complete overview of the gastric SELs and summarize the new data of the last ten years concerning the diagnostic advances of endosonography on this topic.

Single-incision needle-knife biopsy for the diagnosis of GI subepithelial tumors: a systematic review and meta-analysis

BACKGROUND AND AIMS

A histologic diagnosis of GI subepithelial tumors (SETs) is important because of the malignant potential of these lesions. The current modalities of choice, including EUS-guided FNA and biopsy (EUS-FNA/FNB) have demonstrated suboptimal diagnostic success. Single-incision with needle-knife (SINK) biopsy has emerged as an alternative diagnostic approach to increase tissue acquisition and diagnostic success. The aim of this study was to perform a systematic review and meta-analysis to evaluate the technical success, diagnostic success, and adverse events of SINK biopsy.

METHODS

We searched multiple databases including PubMed, EMBASE, CINAHL, Cochrane, Web of Science, and Google Scholar from inception to July 2022. The primary outcomes assessed were the technical success and diagnostic success of SINK in GI SETs. The secondary outcomes assessed were adverse events and whether immunohistochemical analysis could be successfully performed on tissue samples obtained via SINK.

RESULTS

Seven studies with a total of 219 SINK biopsy procedures were included in this meta-analysis. The technical success rate was 98.1% (95% CI, 94.9%-99.3%; P = .000; I² = .0%), and the diagnostic success rate was 87.9% (95% CI, 82.6%-91.7%; P = .000; I² = .0%). The immunohistochemical success rate was 88.3% (95% CI, 78.7%-93.9%; P = .000; I² = 3.5%). The rate of adverse events was 7.5% (95% CI, 4.3%-12.7%; P = .00; I² = 7.2%), and bleeding was the most common adverse event.

CONCLUSION

SINK biopsy is a safe diagnostic procedure with a high technical and diagnostic success in patients with GI SET. Further randomized controlled trials and direct comparison studies are needed to validate these findings.

Intelligent Reconstruction Algorithm-Based Computed Tomography Images for Automatic Detection of Gastric Tumor

The aim of this study was to explore the application of computed tomography (CT) images in the diagnosis of gastric tumor under the intelligent reconstruction algorithm (IRA). 120 patients with gastric cancer were selected and all the patients underwent CT scanning, and CT images were analyzed based on the Feldkamp-Davis-Kress algorithm (FDK algorithm) to evaluate the imaging features of gastric lesions. According to biopsy or surgical pathology, the detection rate of CT images was calculated. The results showed that there were three pathological types of benign tumors (polyps, leiomyomas, and mesenchymomas) and three pathological types of malignant tumors (mesenchymomas, adenomas, and lymphomas). In addition, the detection rates of CT scans were different, reaching 94.2% on different orientations of the stomach, 90.7% of benign tumors, and 90.9% of malignant tumors, so the detection rate of different orientations was relatively high. CT images based on the FDK IRA could realize a high detection rate in diagnosis, accurately locate the lesion, and display the characteristics of the lesion and the metastasis of surrounding tissues; there were significant differences between benign and malignant gastric tumors in CT images, and the detection effect was obvious, which is worthy of clinical application and promotion.

Correlation between pneumo-computed tomography and pathology findings for subepithelial gastric lesions

OBJECTIVE

This article aims to show the usefulness of the pneumo-computed tomography gastric distention technique in the detection and morphological characterization of subepithelial gastric lesions. We correlate the pneumo-computed tomography and pathology findings in lesions studied at our institution and review the relevant literature.

CONCLUSION

Pneumo-computed tomography, combined with multiplanar reconstructions, three-dimensional reconstructions, and virtual endoscopy, is useful for delineating the morphological details of subepithelial gastric lesions, thanks to the additional gastric distention. This technique better delimits and characterizes the upper and lower margins of the lesions. Pneumo-computed tomography can be considered a useful noninvasive imaging techniques for characterizing these lesions.

Endoscopic management of subepithelial lesions including neuroendocrine neoplasms: European Society of Gastrointestinal Endoscopy (ESGE) Guideline

1: ESGE recommends endoscopic ultrasonography (EUS) as the best tool to characterize subepithelial lesion (SEL) features (size, location, originating layer, echogenicity, shape), but EUS alone is not able to distinguish among all types of SEL.Strong recommendation, moderate quality evidence. 2: ESGE suggests providing tissue diagnosis for all SELs with features suggestive of gastrointestinal stromal tumor (GIST) if they are of size > 20 mm, or have high risk stigmata, or require surgical resection or oncological treatment.Weak recommendation, very low quality evidence. 3: ESGE recommends EUS-guided fine-needle biopsy (EUS-FNB) or mucosal incision-assisted biopsy (MIAB) equally for tissue diagnosis of SELs ≥ 20 mm in size.Strong recommendation, moderate quality evidence. 4: ESGE recommends against surveillance of asymptomatic gastrointestinal (GI) tract leiomyomas, lipomas, heterotopic pancreas, granular cell tumors, schwannomas, and glomus tumors, if the diagnosis is clear.Strong recommendation, moderate quality evidence. 5: ESGE suggests surveillance of asymptomatic esophageal and gastric SELs without definite diagnosis, with esophagogastroduodenoscopy (EGD) at 3-6 months, and then at 2-3-year intervals for lesions < 10 mm in size, and at 1-2-year intervals for lesions 10-20 mm in size. For asymptomatic SELs > 20 mm in size that are not resected, ESGE suggests surveillance with EGD plus EUS at 6 months and then at 6-12-month intervals.Weak recommendation, very low quality evidence. 6: ESGE recommends endoscopic resection for type 1 gastric neuroendocrine neoplasms (g-NENs) if they grow larger than 10 mm. The choice of resection technique should depend on size, depth of invasion, and location in the stomach.Strong recommendation, low quality evidence. 7: ESGE suggests considering removal of histologically proven gastric GISTs smaller than 20 mm as an alternative to surveillance. The decision to resect should be discussed in a multidisciplinary meeting. The choice of technique should depend on size, location, and local expertise.Weak recommendation, very low quality evidence. 8: ESGE suggests that, to avoid unnecessary follow-up, endoscopic resection is an option for gastric SELs smaller than 20 mm and of unknown histology after failure of attempts to obtain diagnosis.Weak recommendation, very low quality evidence. 9: ESGE recommends basing the surveillance strategy on the type and completeness of resection. After curative resection of benign SELs no follow-up is advised, except for type 1 gastric NEN for which surveillance at 1-2 years is advised.Strong recommendation, low quality evidence. 10: For lower or upper GI NEN with a positive or indeterminate margin at resection, ESGE recommends repeating endoscopy at 3-6 months and another attempt at endoscopic resection in the case of residual disease.Strong recommendation, low quality evidence.

Prediction of Gastric Gastrointestinal Stromal Tumors before Operation: A Retrospective Analysis of Gastric Subepithelial Tumors

Gastrointestinal stromal tumors (GISTs), leiomyomas, and schwannomas are the most common gastric subepithelial tumors (GSETs) with similar endoscopic findings. Preoperative prediction of GSETs is difficult. This study analyzed and predicted GSET diagnosis through a retrospective review of 395 patients who underwent surgical resection of GISTs, leiomyomas, and schwannomas measuring 2–10 cm. GSETs were divided by size (group 2–5, >2 and ≤5 cm; group 5–10, >5 and ≤10 cm) for analysis. Demographics, clinical symptoms, and images were analyzed. A recursive partitioning analysis (RPA) was used to identify optimal classifications for specific GSET diagnoses. GIST patients were relatively older than other patients. Both groups had higher proportions of UGI bleeding, lower hemoglobin (Hb) levels, and a higher ratio of necrosis on their computed tomography (CT) scans. The RPA tree showed that (a) age ≤ 55, Hb ≥ 10.7, and CT necrosis; (b) age ≤ 55 and Hb < 10.7; (c) age >55 and Hb < 12.9; and (d) age >55 and CT hetero-/homogeneity can predict high GIST risk in group 2–5. Positive or negative CT necrosis, with age >55, can predict high GIST risk in group 5–10. GIST patients were older and presented with low Hb levels and tumor necrosis. In RPA, the accuracy reached 85% and 89% in groups 2–5 and 5–10, respectively.

Advancements in the Diagnosis of Gastric Subepithelial Tumors

A diagnosis of subepithelial tumors (SETs) is sometimes difficult due to the existence of overlying mucosa on the lesions, which hampers optical diagnosis by conventional endoscopy and tissue sampling with standard biopsy forceps. Imaging modalities, by using computed tomography and endoscopic ultrasonography (EUS) are mandatory to noninvasively collect the target's information and to opt candidates for further evaluation. Particularly, EUS is an indispensable diagnostic modality for assessing the lesions precisely and evaluating the possibility of malignancy. The diagnostic ability of EUS appears increased by the combined use of contrast-enhancement or elastography. Histology is the gold standard for obtaining the final diagnosis. Tissue sampling requires special techniques to break the mucosal barrier. Although EUS-guided fine-needle aspiration (EUS-FNA) is commonly applied, mucosal cutting biopsy and mucosal incision-assisted biopsy are comparable methods to definitively obtain tissues from the exposed surface of lesions and seem more useful than EUS-FNA for small SETs. Recent advancements in artificial intelligence (AI) have a potential to drastically change the diagnostic strategy for SETs. Development and establishment of noninvasive methods including AI-assisted diagnosis are expected to provide an alternative to invasive, histological diagnosis.

Comparison of the Diagnostic Ability of Endoscopic Ultrasonography and Abdominopelvic Computed Tomography in the Diagnosis of Gastric Subepithelial Tumors

Background/Aims

Endoscopic ultrasonography (EUS) is the most efficient imaging modality for gastric subepithelial tumors (SETs). However, abdominopelvic computed tomography (APCT) has other advantages in evaluating the characteristics, local extension, or invasion of SETs to adjacent organs. This study aimed to compare the diagnostic ability of EUS and APCT based on surgical histopathology results.

Methods

We retrospectively reviewed data from 53 patients who underwent both EUS and APCT before laparoscopic wedge resection for gastric SETs from January 2010 to December 2017 at a single institution. On the basis of histopathology results, we assessed the diagnostic ability of the 2 tests.

Results

The overall accuracy of EUS and APCT was 64.2% and 50.9%, respectively. In particular, the accuracy of EUS vs. APCT for the diagnosis of gastrointestinal stromal tumors (GISTs), leiomyomas, and ectopic pancreas was 83.9% vs. 74.2%, 37.5% vs. 0.0%, and 57.1% vs. 14.3%, respectively. Most of the incorrect diagnoses with EUS involved hypoechoic lesions originating in the fourth echolayer, with the most common misdiagnosed lesions being GISTs mistaken for leiomyomas and vice versa.

Conclusions

APCT showed a lower overall accuracy than EUS; however, APCT remains a useful modality for malignant/potentially malignant gastric SETs.

CT Versus Endoscopic Ultrasound for Differentiating Small (2-5 cm) Gastrointestinal Stromal Tumors From Leiomyomas

OBJECTIVE. Abdominal CT or endoscopic ultrasound is recommended for the evaluation of gastric subepithelial tumors. However, few studies have compared the diagnostic performance of these two methods. We compared the diagnostic performance of CT versus endoscopic ultrasound for gastric subepithelial tumors smaller than 5 cm. We also identified significant CT findings associated with the diagnosis of gastrointestinal stromal tumors. MATERIALS AND METHODS. Seventy-one patients with pathologically proven gastric subepithelial tumors were enrolled. We examined the diagnostic performance of CT compared with endoscopic ultrasound. We analyzed CT findings, including the location, long diameter (LD), short diameter (SD), LD-SD ratio, contour, margin, growth pattern, degree and pattern of enhancement, attenuation value, intralesional necrosis, calcification, hemorrhage, surface dimpling, and perilesional lymph node. RESULTS. Endoscopic ultrasound had a sensitivity of 77.6%, specificity of 61.5%, PPV of 90.0%, NPV of 38.1%, and accuracy of 74.6%. CT had a sensitivity of 84.5%, specificity of 53.8%, PPV of 89.1%, NPV of 43.8%, and accuracy of 78.9%. Multivariate analysis revealed that the presence of intralesional necrosis (odds ratio [OR], 10.88; p = 0.037) and an LD-SD ratio less than 1.5 (OR, 32.37; p = 0.002) were independent CT findings for the diagnosis of gastrointestinal stromal tumors. CONCLUSION. CT is as effective as endoscopic ultrasound for the diagnosis of gastric subepithelial tumors smaller than 5 cm. Tumors with intralesional necrosis and an LD-SD ratio less than 1.5 may require further pathologic diagnosis.