Diagnosis of gastric submucosal tumors and estimation of malignant risk of GIST by endoscopic ultrasound. Comparison between B mode and contrast-harmonic mode

Artificial Intelligence in the Prediction of Gastrointestinal Stromal Tumors on Endoscopic Ultrasonography Images: Development, Validation and Comparison with Endosonographers

Background/Aims

The accuracy of endosonographers in diagnosing gastric subepithelial lesions (SELs) using endoscopic ultrasonography (EUS) is influenced by experience and subjectivity. Artificial intelligence (AI) has achieved remarkable development in this field. This study aimed to develop an AI-based EUS diagnostic model for the diagnosis of SELs, and evaluated its efficacy with external validation.

Methods

We developed the EUS-AI model with ResNeSt50 using EUS images from two hospitals to predict the histopathology of the gastric SELs originating from muscularis propria. The diagnostic performance of the model was also validated using EUS images obtained from four other hospitals.

Results

A total of 2,057 images from 367 patients (375 SELs) were chosen to build the models, and 914 images from 106 patients (108 SELs) were chosen for external validation. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the model for differentiating gastrointestinal stromal tumors (GISTs) and non-GISTs in the external validation sets by images were 82.01%, 68.22%, 86.77%, 59.86%, and 78.12%, respectively. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy in the external validation set by tumors were 83.75%, 71.43%, 89.33%, 60.61%, and 80.56%, respectively. The EUS-AI model showed better performance (especially specificity) than some endosonographers. The model helped improve the sensitivity, specificity, and accuracy of certain endosonographers.

Conclusions

We developed an EUS-AI model to classify gastric SELs originating from muscularis propria into GISTs and non-GISTs with good accuracy. The model may help improve the diagnostic performance of endosonographers. Further work is required to develop a multi-modal EUS-AI system.

Multifeature Fusion Classification Method for Adaptive Endoscopic Ultrasonography Tumor Image

Endoscopic ultrasonography (EUS) has been found to be of great advantage in the diagnosis of digestive tract submucosal tumors. However, EUS-based diagnosis is limited by variability in subjective interpretation on the part of doctors. Tumor classification of ultrasound images with the computer-aided diagnosis system can significantly improve the diagnostic efficiency and accuracy of doctors. In this study, we proposed a multifeature fusion classification method for adaptive EUS tumor images. First, for different ultrasound tumor images, we selected the region of interest based on prior information to facilitate the estimation in the subsequent works. Second, we proposed a method based on image gray histogram feature extraction with principal component analysis dimensionality reduction, which learns the gray distribution of different tumor images effectively. Third, we fused the reduced grayscale features with the improved local binary pattern features and gray-level co-occurrence matrix features, and then used the multiclassification support vector machine. Finally, in the experiment, we selected the 431 ultrasound images of 109 patients in the hospital and compared the experimental effects of different features and different classifiers. The results revealed that the proposed method performed best, with the highest accuracy of 96.18% and an area under the curve of 99%. It is evident that the method proposed in this study can efficiently contribute to the classification of EUS tumor images.

Endoscopic Ultrasound Advanced Techniques for Diagnosis of Gastrointestinal Stromal Tumours

Gastrointestinal Stromal Tumors (GISTs) are subepithelial lesions (SELs) that commonly develop in the gastrointestinal tract. GISTs, unlike other SELs, can exhibit malignant behavior, so differential diagnosis is critical to the decision-making process. Endoscopic ultrasound (EUS) is considered the most accurate imaging method for diagnosing and differentiating SELs in the gastrointestinal tract by assessing the lesions precisely and evaluating their malignant risk. Due to their overlapping imaging characteristics, endosonographers may have difficulty distinguishing GISTs from other SELs using conventional EUS alone, and the collection of tissue samples from these lesions may be technically challenging. Even though it appears to be less effective in the case of smaller lesions, histology is now the gold standard for achieving a final diagnosis and avoiding unnecessary and invasive treatment for benign SELs. The use of enhanced EUS modalities and elastography has improved the diagnostic ability of EUS. Furthermore, recent advancements in artificial intelligence systems that use EUS images have allowed them to distinguish GISTs from other SELs, thereby improving their diagnostic accuracy.

The value of contrast-enhanced harmonic endoscopic ultrasound in differential diagnosis and evaluation of malignant risk of gastrointestinal stromal tumors (<50mm)

OBJECTIVES

Contrast-enhanced harmonic endoscopic ultrasound (CEH-EUS) has been used in the differential diagnosis of benign and malignant tumors by visualization of tumor microcirculation and perfusion. However, its diagnostic role in submucosal tumors (SMTs), especially leiomyomas and gastric submucosal tumors (GISTs) was rarely studied. The aim of this study was to analyze the diagnostic role of CEH-EUS for SMTs (<50 mm) and the value of assessing the malignant potential of GISTs.

MATERIALS AND METHODS

We retrospectively included patients with tumors <50 mm in diameter who underwent preoperative EUS and CEH-EUS examination and had pathologically confirmed as leiomyomas and GISTs. To analyze the imaging features of CEH-EUS with pathological diagnosis as the gold standard and evaluate its diagnostic value.

RESULTS

This study included 10 cases of leiomyomas and 38 cases of GISTs. Under CEH-EUS detection, 86.9% of GISTs showed hyper-enhancement, 89.5% showed diffuse enhancement, 39.5% showed non-enhancing spots, and 97.4% showed obvious capsule enhancement. In contrast, the leiomyoma cases mostly showed hypo-enhancement (50.0%) or non-enhancement (30.0%) (p < 0.05). Then, the value of CEH-EUS in the differential diagnosis of benign and malignant tumors based on blood flow is significantly higher than that of B-EUS. Signal appearance time was significantly faster in the intermediate-high risk GISTs than in the very low-low risk group (5.1 s versus 15.5 s, p < 0.05), and the AUROC values predicted the risk at this time to be 0.903 (0.763-0.975). Heterogeneous perfusion and non-enhancing spots were also more common in the intermediate-high risk group. Univariate and multivariate analysis revealed that intratumoral irregularitie was an independent predictor of moderate to high risk (OR 3.99, 95%CI 1.04-90.95), with sensitivity, specificity and accuracy of 73.33%, 91.30% and 84.21%, respectively.

CONCLUSIONS

Through this study, CEH-EUS has a good differential diagnostic ability for leiomyomas and GISTs, and has a high value in predicting the risk of GISTs.

Gastric submucosal mass lesions

PURPOSE OF REVIEW

Gastric submucosal mass lesions are a collection of tumours that arise in the stomach and are deep to the mucosal layer. Distinct from gastric epithelial carcinomas, these tumours are generally more indolent. They are often found incidentally on upper endoscopy. Most often they present as smooth protuberant masses covered by normal intact gastric mucosa. The majority are asymptomatic. Endoscopic ultrasound (EUS) is frequently employed to further characterize the lesions. EUS can be diagnostic of some lesions, such as lipomas, and can be used to guide fine needle aspiration to diagnose others. Adding to the traditional management approaches of observation and surgical resection, numerous new and emerging endoscopic therapies are now being used to resect these gastric tumours.

RECENT FINDINGS

This review focuses on evolving strategies in the diagnosis and management of submucosal mass lesions. Although surgical intervention was once the lone option for intervention, there are an increasing number of endoscopic therapies. There have also been advancements in neoadjuvant therapies and in distinguishing the malignant potential of submucosal mass lesions.

SUMMARY

Gastric submucosal lesions are common. EUS is frequently indicated in the evaluation and diagnosis. For tumours for which observation is not recommended, novel endoscopic therapies may offer less invasive management options.