Sage Journals: Discover world-class research

Abstract

Background:

Previous studies have identified useful endoscopic ultrasonography (EUS) features to predict the malignant potential of gastrointestinal stromal tumors (GISTs). However, the results of the studies were not consistent. Artificial intelligence (AI) has shown promising results in medicine.

Objectives:

We aimed to build a risk stratification EUS-AI model to predict the malignancy potential of GISTs.

Design:

This was a retrospective study with external validation.

Methods:

We developed two models using EUS images from two hospitals to predict the GIST risk category. Model 1 was the four-category risk EUS-AI model, and Model 2 was the two-category risk EUS-AI model. The diagnostic performance of the models was validated with external cohorts.

Results:

A total of 1320 images (880 were very low-risk, 269 were low-risk, 68 were intermediate-risk, and 103 were high-risk) were finally chosen for building the models and test sets, and a total of 656 images (211 were very low-risk, 266 were low-risk, 88 were intermediate-risk, and 91 were high-risk) were chosen for external validation. The overall accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for the four-category risk EUS-AI model in the external validation sets by tumor were 74.50%, 55.00%, 79.05%, 53.49%, and 81.63%, respectively. The accuracy, sensitivity, specificity, PPV, and NPV for the two-category risk EUS-AI model for the prediction of very low-risk GISTs in the external validation sets by tumor were 86.25%, 94.44%, 79.55%, 79.07%, and 94.59%, respectively.

Conclusion:

We developed a EUS-AI model for the risk stratification of GISTs with promising results, which may complement current clinical practice in the management of GISTs.

Registration:

The study has been registered in the Chinese Clinical Trial Registry (No. ChiCTR2100051191).

Keywords

Artificial intelligence endoscopic ultrasonography gastric gastrointestinal stromal tumors risk

Introduction

Subepithelial lesions (SELs) are most frequently found in the stomach, most of which are gastrointestinal stromal tumors (GISTs).¹ GISTs have varying degrees of malignancy potential. For example, micro-GISTs (<10 mm) have almost no malignancy potential, whereas large GISTs and GISTs with a high mitotic count have a high metastatic probability and recurrence rate.² Numerous systems have been proposed for the risk stratification of GISTs. The most widely used systems are the National Institute of Health (NIH) criteria, modified NIH criteria, and Armed Forces Institute of Pathology (AFIP) criteria.^3–6 The variables that are included in the abovementioned systems are mainly tumor size, mitotic index, and tumor location.

The mitotic index is obtained via histopathologic sections of the resected tumor or endoscopic ultrasonography-guided fine needle aspiration or biopsy (EUS-FNA/B). If we are able to predict the malignancy potential of a suspected GIST, it could aid clinical decision-making, especially for small GISTs. Previous studies have attempted to identify useful EUS features to predict the malignant potential of GISTs, and they found that, large size, cystic change, surface ulceration, extraluminal border, depth, heterogeneity irregular borders, and a nonoval shape were potential predictors for malignancy.^7–11 However, these predictors were not consistent in the different studies; moreover, except for tumor size, the judgment of other predictors was somewhat subjective. Artificial intelligence (AI) via deep convolutional neural networks (DCNNs) has shown promising results in medicine.^12–14 Seven et al.¹⁵ built a deep learning algorithm using EUS images to predict the malignancy potential of gastric GISTs with good accuracy. Their studies used the AFIP criteria as the reference, and the sample size was relatively small and lacked external validation. A previous study indicated that the modified NIH criteria were the best criteria to identify a single high-risk group for consideration of adjuvant therapy.² Hence, we aimed to build a risk stratification EUS-AI model to predict the malignancy potential of GISTs in reference to the modified NIH criteria with larger sample sizes and external validation.

Methods

Clinical data and EUS image collection

The EUS images used to build the risk stratification EUS-AI model and used for external validation were from our previous study, in which we successfully built a EUS-AI model to differentiate GISTs and non-GISTs with good accuracy.¹⁶ EUS images obtained from The Sixth Affiliated Hospital, Sun Yat-sen University, and Guangdong Second Provincial Central Hospital were consecutively collected to build the model. For external validation, we collected EUS images from four other hospitals (Fudan University Shanghai Cancer Center, the Fourth Hospital of Hebei Medical University, Zhoushan Hospital of Zhejiang Province, and Yangjiang Hospital of Traditional Chinese Medicine). The inclusion criteria for the collected images were as follows: good quality EUS images showing the tumors; confirmed histopathology of gastric GISTs (obtained by endoscopic resection, surgery, or FNA); and modified NIH criteria risk category could be obtained. The exclusion criteria included the following: poor-quality images and repeated images. The following information about the patients was also collected: age, sex, EUS results, and histopathology results. The collected images were categorized based on the modified NIH criteria risk category.

EUS procedures

EUS was performed by experienced endosonographers with experience in more than 500 cases of SELs. The echoendoscopes that were used in the models and the external validation sets are shown in Supplemental Tables S1 and S2. The utilized frequency was 5–20 MHz.

Image processing and development of the deep learning models

The image processing, augmentation, and development of the deep learning models were supported by the Tianjin Jinyu Artificial Intelligence Medical Technology Co., Ltd. The image processing was the same as in our previous study. After selecting the qualified images, two experts in EUS marked the borderline of the tumor with LabelMe software (a polygonal and open annotation tool developed by the Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory), and the marked tumors were regarded as the regions of interest (ROIs). Afterward, the engineers trimmed the images to squares or rectangles by precisely fitting the ROI. For images with measuring lines or measuring marks, Adobe Photoshop (Version 13.0; Adobe Systems Software Ireland Ltd., Dublin, Ireland) was used to erase the lines or marks and to preserve the originality of the images as much as possible. Image augmentation technology, such as mirror flip, horizontal flip, and rotation in certain degrees of the EUS images, was applied. The preprocessed images were then changed into the RGB three-channel to be generated as the model input.

We developed two models in this study. Model 1 was a four-category risk EUS-AI model, and Model 2 was a two-category risk EUS-AI model. In Model 1, we classified the images into four categories based on the modified NIH criteria: very low-, low-, intermediate-, and high-risk. In Model 2, we classified the images into two categories: very low- and non-very low-risk (the latter included low-, intermediate-, and high-risk categories). The process was mainly implemented by Python (Version 3.7; Python Software Foundation, Wilmington, DE, USA) and PyTorch (Version 1.7.1; Facebook artificial intelligence research institute, Menlo Park, CA, USA). The chosen images were randomly divided into training sets and test sets at a ratio of 7.5:2.5, and 10-fold cross-validation was used.

We used the DCNN classifier known as ResNeSt-50 to train Model 1 (Amazon and University of California, Davis, Davis, CA, USA). ResNeSt was developed by Zhang et al.¹⁷, and it showed superiority in accuracy and latency trade-off on image classification when compared with other backbones.¹⁷ The Adam optimizer was used, which is a popular optimizer that combines the ideas of AdaGrad and RMSProp.¹⁸ The initial learning rate was set as 0.003, and cosine annealing was adopted as the attenuation method. This method took the cosine function as a period and reset the learning rate at the maximum value of each period.¹⁹ The model was trained for 300 epochs, and the final learning rate was 3e−7. When the training reached 300 epochs, the training was stopped.

As Model 1 was a four-category model (which was a multicategory task), a deeper learning model was needed to learn the characteristics. Model 2 was a two-category model, and the use of ResNeSt-34 was sufficient to train the model. The Adam optimizer was subsequently used. The initial learning rate was set as 0.003, and cosine annealing was adopted as the attenuation method. The model was trained for 500 epochs, and the final learning rate was 9e−8. When the training reached 500 epochs, the training was stopped.

The output of the model was the risk category (ranging from 0 to 100%) of the GISTs. The type with the higher probability was interpreted as the final risk category.

Statistical analysis

Data are presented as the mean (standard deviation, SD) for normally distributed continuous variables and presented as the median (range) for nonnormally distributed continuous variables. Categorical variables are expressed as numbers (percentages). A receiver operating characteristic (ROC) curve was plotted, and the area under the curve (AUC) was calculated. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of the risk category of the EUS-AI model, as well as the respective 95% confidence intervals (CIs), were calculated. The abovementioned calculation was performed by using the Scikit-learn package in Python. The reporting of this study conforms to the Standards for Reporting Diagnostic Accuracy (STARD) 2015 statement.²⁰ The study has been registered in the Chinese Clinical Trial Registry (No. ChiCTR2100051191).

Results

Basic information about the training sets and the test sets

A total of 1320 images (the number of images for very low-risk, low-risk, intermediate-risk, and high-risk was 880, 269, 68, and 103, respectively) from 243 patients (245 GIST cases, of which 168 were very low-risk, 56 were low-risk, 12 were intermediate-risk, and 9 were high-risk) were chosen for analysis. The median age of the patients was 56 (29–81) years, and 104 patients (42.80%) were male. A total of 990 images were randomly divided into the training sets, and 330 images were randomly divided into the test sets. The characteristics of the chosen GISTs are summarized in Table 1.

Table 1.

The characteristics of the GISTs chosen for analysis.

Category	Very low	Low	Intermediate	High	Total
Training and test set
Total	168	56	12	9	245
Location (n, %)
Cardia	2 (1.19)	0	0	0	2 (0.82)
Gastric fundus	116 (69.05)	28 (50)	7 (58.33)	5 (55.56)	156 (63.67)
Junction of gastric fundus and gastric body	1 (0.6)	0	1 (8.33)	0	2 (0.82)
Gastric body	49 (29.17)	23 (41.07)	4 (33.33)	4 (44.44)	80 (32.65)
Gastric angle	0	2 (3.57)	0	0	2 (0.82)
Gastric antrum	0	3 (5.36)	0	0	3 (1.22)
Size (n, %)
⩾20 mm	0	54 (96.43)	11 (91.67)	9 (100)	74 (30.20)
<20 mm	168 (100)	2 (3.57)	1 (8.33)	0	171 (69.80)
External validation set
Total	36	28	7	9	80
Location (n, %)
Cardia	2 (5.56)	1 (3.57)	0	1 (11.11)	4 (5)
Gastric fundus	18 (50)	12 (42.86)	2 (28.57)	3 (33.33)	35 (43.75)
Junction of gastric fundus and gastric body	1 (2.78)	0	1 (14.29)	1 (11.11)	3 (3.75)
Gastric body	14 (38.89)	13 (46.43)	4 (57.14)	4 (44.44)	35 (43.75)
Gastric antrum	1 (2.78)	2 (7.14)	0	0	3 (3.75)
Size (n, %)
⩾20 mm	0	26 (92.86)	6 (85.71)	8 (88.89)	40 (50)
<20 mm	36 (100)	2 (7.14)	1 (14.29)	1 (11.11)	40 (50)

GIST, gastrointestinal stromal tumor.

Basic information for the external validation sets

A total of 656 images (the number of images for very low-risk, low-risk, intermediate-risk, and high-risk was 211, 266, 88, and 91, respectively) from 79 patients (80 GISTs, of which 36 were very low-risk, 28 were low-risk, 7 were intermediate-risk, and 9 were high-risk) were finally chosen in the external validation sets (Table 1). The number of images and tumors selected from each hospital are presented in Supplemental Table S3.

Diagnostic performance of the four-category risk EUS-AI model for prediction of the risk category in the test sets

The accuracy, sensitivity, specificity, PPV, and NPV for the four-category risk EUS-AI model in the test sets by images were 81.21%, 75.48%, 90.98%, 93.45%, and 68.52%, respectively, for very low-risk; 83.64%, 64.86%, 89.06%, 63.16%, and 89.76%, respectively, for low-risk; 85.15%, 55%, 87.1%, 21.57%, and 96.77%, respectively, for intermediate-risk; and 94.85%, 82.14%, 96.03%, 65.71%, and 98.31%, respectively, for high-risk (Supplemental Table S4). The overall accuracy, sensitivity, specificity, PPV, and NPV were 83.15%, 72.42%, 90.75%, 79.95%, and 77.52%, respectively. The ROC curves for each type versus other types are shown in Figure 1(a), and the confusion matrices showing the pairwise comparison (number of images) in the test sets are presented in Figure 1(d).

Figure 1.

ROCs of the four-category risk EUS-AI model for prediction of the GISTs in the: (a) test sets by images, (b) external validation sets by images, (c) external validation sets by tumors, and confusion matrices of the pairwise comparison in the (d) test sets by images, (e) external validation sets by images, and (f) external validation sets by tumors.

Diagnostic performance of the four-category risk EUS-AI model for prediction of the risk category in the external validation sets

The accuracy, sensitivity, specificity, PPV, and NPV for the four-category risk EUS-AI model in the external validation sets by images and by tumors are shown in Table 2. The overall accuracy, sensitivity, specificity, PPV, and NPV by images were 70.55%, 47.10%, 78.23%, 46.61%, and 77.88%, respectively. The overall accuracy, sensitivity, specificity, PPV, and NPV by tumor were 74.50%, 55.00%, 79.05%, 53.49%, and 81.63%, respectively. The ROC curves and the confusion matrices showing the pairwise comparison results are presented in Figure 1.

Table 2.

Diagnostic performance of the four-category risk EUS-AI model for prediction of the risk category of GISTs in the external validation sets.

Risk stratification	Very low	Low	Intermediate	High
By images
Accuracy	77.59% (74.25–80.62%)	59.6% (55.80–63.29%)	76.98% (73.61–80.04%)	80.03% (76.80–82.91%)
Sensitivity	73.46% (67.12–78.96%)	42.86% (37.05–48.86%)	15.91% (9.72–24.95%)	28.57% (20.31–38.57%)
Specificity	79.55% (75.56–83.04%)	71.03% (66.34–75.31%)	86.44% (83.38–89.02%)	88.32% (85.41–90.71%)
PPV	63.01% (56.82–68.80%)	50.22% (43.77–56.67%)	15.38% (9.39–24.18%)	28.26% (20.08–38.19%)
NPV	86.34% (82.68–89.33%)	64.57% (59.93–68.95%)	86.9% (83.87–89.44%)	88.48% (85.58–90.85%)
By tumors
Accuracy	78.75% (68.58–86.29%)	63.75% (52.81–73.43%)	83.75% (74.16–90.25%)	83.75% (74.16–90.25%)
Sensitivity	86.11% (71.34–93.92%)	32.14% (17.93–50.66%)	14.29% (2.57–51.31%)	33.33% (12.06–64.58%)
Specificity	72.73% (58.15–83.65%)	80.77% (68.10–68.29%)	90.41% (81.50–95.28%)	90.14% (81.02–95.14%)
PPV	72.09% (57.31–82.35%)	47.37% (27.33–68.29%)	12.5% (2.24–47.09%)	30% (10.78–60.32%)
NPV	86.49% (72.02–94.09%)	68.85% (56.41–79.06%)	91.67% (82.99–96.12%)	91.43% (82.53–96.01%)

AI, artificial intelligence; EUS, endoscopic ultrasonography; GIST, gastrointestinal stromal tumor; NPV, negative predictive value; PPV, positive predictive value.

Diagnostic performance of the two-category risk EUS-AI model for prediction of the risk category in the test sets

In Model 2, we classified the images into two categories: very low and non-very low-risk. The accuracy, sensitivity, specificity, PPV, and NPV for the two-category risk EUS-AI model for the prediction of very low-risk GISTs in the test sets by images were 90.91%, 90.38%, 91.80%, 94.95%, and 84.85%, respectively (Table 3). The ROC curve is presented in Figure 2(a).

Table 3.

Diagnostic performance of the two-category risk EUS-AI model for prediction of the very low-risk GISTs in different sets.

Risk stratification	Test sets by images	External validation sets by images	External validation sets by tumors
Accuracy	90.91% (87.32–93.56%)	82.77% (79.70–85.47%)	86.25% (77.03–92.15%)
Sensitivity	90.38% (85.62–93.69%)	85.31% (79.90–89.45%)	94.44% (81.86–98.46%)
Specificity	91.80% (85.57–95.49%)	81.57% (77.71–84.90%)	79.55% (65.50–88.85%)
PPV	94.95% (90.95–97.23%)	68.70% (62.85–74.01%)	79.07% (64.79–88.58%)
NPV	84.85% (77.75–89.97%)	92.13% (89.05–94.40%)	94.59% (82.30–98.50%)

AI, artificial intelligence; EUS, endoscopic ultrasonography; GIST, gastrointestinal stromal tumor; NPV, negative predictive value; PPV, positive predictive value.

Figure 2.

ROCs of the two-category risk EUS-AI model for prediction of the very low-risk GISTs in the: (a) test sets by images, (b) external validation sets by images, and (c) external validation sets by tumors.

Diagnostic performance of the two-category risk EUS-AI model for prediction of the risk category in the external validation sets

The accuracy, sensitivity, specificity, PPV, and NPV for the two-category risk EUS-AI model for the prediction of very low-risk GISTs in the external validation sets by image were 82.77%, 85.31%, 81.57%, 68.70%, and 92.13%, respectively, and those by tumor were 86.25%, 94.44%, 79.55%, 79.07%, and 94.59%, respectively (Table 3). The ROC curves are presented in Figure 2(b) and (c).

Discussion

In this study, we built two risk stratification EUS-AI models to predict the malignant potential of GISTs in reference to the modified NIH criteria, and the accuracy of the four-category risk EUS-AI model was not significantly good; however, the accuracy of the two-category risk EUS-AI model was much better with external validation.

Risk stratification of GISTs tries to evaluate the risk of poor outcomes and to choose patients who may benefit from adjuvant therapy.²¹ Independent prognostic factors for GIST include the mitotic index, tumor size, tumor location (gastric versus non-gastric), and tumor rupture.² Patients in the low-risk group generally have favorable outcomes and may not require adjuvant therapy or frequent surveillance. In the past few years, several studies have explored AI applications in GISTs which not only include differentiating GISTs from non-GISTs,^{13,14,22–24} but also risk stratification and prediction of prognosis.¹⁵ Most of the previous studies regarding AI applications in GIST risk stratification were computed tomography (CT)-derived analyses and only a few studies have researched the performance of EUS-derived images. Two major machine learning methodologies, radiomic analysis and DCNNs have shown promise in pattern classification in previous studies.^15,25

Seven et al.¹⁵ investigated AI via DCNNs in predicting the malignant potential of GISTs. The overall sensitivity, specificity, and accuracy of the AI system for predicting four-category malignancy risk based on AFIP criteria in their study were 83%, 94%, and 82%, respectively, in the training dataset, and 75%, 73%, and 66%, respectively, in the validation cohort. When patients were divided into two categories: low-risk (including very low-risk and low-risk groups) and high-risk groups (including intermediate-risk and high-risk groups), the sensitivity, specificity, and accuracy in the validation cohort increased to 99.7%, 99.7%, and 99.6%, respectively.

In our study, the overall accuracy, sensitivity, and specificity of the four-category risk EUS-AI model by tumor in the external validation set were 74.50%, 55.00%, and 79.05%, respectively, which is comparable to the results of the validation cohort in Seven’s study. The overall performance of AI in the four-category risk EUS-AI model was not satisfactory because the sensitivity was observed to be relatively low. One possible reason for this phenomenon was that, in our study, the distribution of patients in each risk group of the training set was not balanced, and there were more patients in the very low-risk group than in the other three groups. Therefore, we may not have obtained optimized results for unbalanced classes, as the model did not obtain a sufficient understanding of the underlying classes. This imbalance is naturally inherent in our real-life medical practice. Intermediate and high-risk GISTs were usually larger in size and accompanied by ulceration which could be diagnosed by biopsies alone in most cases; thus, EUS was not required in the diagnosis and preoperative management. Additionally, some of the patients with intermediate- or high-risk GISTs underwent surgery directly after CT examinations with no additional required EUS in our center. These factors can explain the low number of patients in the higher-risk group.

When patients were divided into very low-risk and non-very low-risk groups according to modified NIH criteria, the two-category EUS-AI model that we built showed better accuracy, sensitivity, and specificity of 86.25%, 94.44%, and 79.55%, respectively, by tumor in the external validation sets. Previous studies^15,25 have combined the very low-risk and low-risk groups together, which was different from our study. According to European guidelines,²⁶ very low-risk GISTs probably do not require routine follow-up. National Comprehensive Cancer Network guideline 2022 version²⁷ also mentioned that less frequent surveillance is acceptable for very small tumors (<2 cm), which is consistent with the modified NIH criteria for the very low-risk group. These results indicate that the very low-risk group has a much lower risk of recurrence compared to the other risk groups; therefore, dividing patients into very low-risk and non-very low-risk groups may be of more clinical significance because the management and follow-up strategy would be different. Our EUS-AI models demonstrated encouraging results in differentiating very low-risk GISTs from other risk groups, which can benefit actual clinical work.

In the study of Li et al.,²⁵ an EUS-derived radiomics model was developed to differentiate GISTs of the higher-risk classification (intermediate-risk and high-risk) from the lower-risk classification (very low-risk and low-risk). The accuracy, sensitivity, and specificity were 82.3%, 81.3%, and 82.6%, respectively. However, they did not specify which classification criteria were used in their study. The radiomics model has been investigated in many previous studies for the risk stratification of GISTs; however, most of the studies²⁸ were focused on the performance of AI using CT images. Li’s study demonstrated that a EUS-derived radiomics model could increase preoperative diagnostic accuracy and provide a valuable reference in physicians’ decision-making. The steps of radiomics analysis include the first extraction of numerous handcrafted imaging features, followed by feature selection and machine learning-based classification. However, handcrafted features are limited to the current knowledge of medical imaging, which may limit the potential of the predictive model.

Deep learning improves these handcrafted features by automatically learning discriminative features directly from images.²⁹ A previous study³⁰ demonstrated that a hybrid structure that includes different features selected with a radiomics model and DCNNs (AUC: 0.882, 95% CI: 0.816–0.947) outperforms independent radiomics (AUC: 0.807, 95% CI: 0.724–0.892) and CNNs (AUC: 0.826, 95% CI: 0.795–0.856) approaches for the classification of GISTs at CT. Moreover, deep learning also has advantages and applications in other related fields, such as sequence methods and synthesis generation. Future studies that explore AI models integrating radiomics and DCNN features for the risk classification of GISTs using EUS images would likely add valuable information to this topic.

There were several limitations of our study. First, this was a retrospective study, and we did not perform prospective validation. It would be better to validate the EUS-AI model in a prospective cohort prior to its application in clinical practice. Another shortcoming, as was mentioned above, is that the number of intermediate- and high-risk GISTs was too small relative to very low-risk GISTs. In future studies, we need to enroll more patients with non-very low-risk to improve the imbalanced dataset model and to make it more stable. Despite these limitations, our results are of value in that our EUS-AI model was trained on a relatively large dataset and validated in an external validation cohort including four hospitals.

In conclusion, we developed a EUS-AI model for the risk stratification of GISTs with promising results. The accuracy and sensitivity of the two-category risk EUS-AI model were high with external validation, which may complement current clinical practice in the management of GISTs.

Supplemental Material

sj-docx-1-tag-10.1177_17562848231177156 – Supplemental material for Artificial intelligence in endoscopic ultrasonography: risk stratification of gastric gastrointestinal stromal tumors

Supplemental material, sj-docx-1-tag-10.1177_17562848231177156 for Artificial intelligence in endoscopic ultrasonography: risk stratification of gastric gastrointestinal stromal tumors by Yi Lu, Lu Chen, Jiachuan Wu, Limian Er, Huihui Shi, Weihui Cheng, Ke Chen, Yuan Liu, Bingfeng Qiu, Qiancheng Xu, Yue Feng, Nan Tang, Fuchuan Wan, Jiachen Sun and Min Zhi in Therapeutic Advances in Gastroenterology

Footnotes

Acknowledgements

The authors thank all the members of Tianjin Economic-Technological Development Area (TEDA) Yujin Digestive Health Industry Research Institute who have made contributions to this program.

Declarations

ORCID iDs

Yi Lu

Jiachen Sun

Supplemental material

Supplemental material for this article is available online.

References

Deprez

Moons

LMG

OʼToole

, et al. Endoscopic management of subepithelial lesions including neuroendocrine neoplasms: European Society of Gastrointestinal Endoscopy (ESGE) Guideline. Endoscopy 2022; 54: 412–429.

Joensuu

Vehtari

Riihimäki

, et al. Risk of recurrence of gastrointestinal stromal tumour after surgery: an analysis of pooled population-based cohorts. Lancet Oncol 2012; 13: 265–274.

Joensuu

Risk stratification of patients diagnosed with gastrointestinal stromal tumor. Hum Pathol 2008; 39: 1411–1419.

Khoo

Chai

Quek

, et al. Systematic review of current prognostication systems for primary gastrointestinal stromal tumors. Eur J Surg Oncol 2018; 44: 388–394.

Miettinen

Lasota

Gastrointestinal stromal tumors: pathology and prognosis at different sites. Semin Diagn Pathol 2006; 23: 70–83.

Fletcher

CDM

Berman

Corless

, et al. Diagnosis of gastrointestinal stromal tumors: a consensus approach. Hum Pathol 2002; 33: 459–465.

Jeon

Park

Chung

, et al. Gastrointestinal stromal tumors of the stomach: endosonographic differentiation in relation to histological risk. J Gastroenterol Hepatol 2007; 22: 2069–2075.

Shah

Gao

Edmundowicz

, et al. Predicting malignant potential of gastrointestinal stromal tumors using endoscopic ultrasound. Dig Dis Sci 2009; 54: 1265–1269.

Chen

Hsu

Chu

, et al. Association of endoscopic ultrasonographic parameters and gastrointestinal stromal tumors (GISTs): can endoscopic ultrasonography be used to screen gastric GISTs for potential malignancy? Scand J Gastroenterol 2016; 51: 374–377.

10.

Chen

Dong

, et al. The roles of CT and EUS in the preoperative evaluation of gastric gastrointestinal stromal tumors larger than 2 cm. Eur Radiol 2019; 29: 2481–2489.

11.

Brand

Oesterhelweg

Binmoeller

, et al. Impact of endoscopic ultrasound for evaluation of submucosal lesions in gastrointestinal tract. Dig Liver Dis 2002; 34: 290–297.

12.

Marya

Powers

Chari

, et al. Utilisation of artificial intelligence for the development of an EUS-convolutional neural network model trained to enhance the diagnosis of autoimmune pancreatitis. Gut 2021; 70: 1335–1344.

13.

Seven

Silahtaroglu

Seven

, et al. Differentiating gastrointestinal stromal tumors from leiomyomas using a neural network trained on endoscopic ultrasonography images. Dig Dis 2022; 40: 427–435.

14.

Yang

Wang

Dong

, et al. An artificial intelligence system for distinguishing between gastrointestinal stromal tumors and leiomyomas using endoscopic ultrasonography. Endoscopy 2022; 54: 251–261.

15.

Seven

Silahtaroglu

Kochan

, et al. Use of artificial intelligence in the prediction of malignant potential of gastric gastrointestinal stromal tumors. Dig Dis Sci 2022; 67: 273–281.

16.

, et al. Artificial intelligence in the prediction of gastrointestinal stromal tumors on endoscopic ultrasonography images: development, validation and comparison with endosonographers. Gut Liver Epub ahead of print 26 January 2023. DOI: 10.5009/gnl220347.

17.

Zhang

, et al. ResNeSt: split-attention networks, https://arxiv.org/pdf/2004.08955.pdf, 2020.

18.

Cortiñas-Lorenzo

Pérez-González

Adam and the ants: on the influence of the optimization algorithm on the detectability of DNN watermarks. Entropy 2020; 22: 1–36.

19.

Xie

A robust fabric defect detection method based on improved RefineDet. Sensors 2020; 20: 1–24.

20.

Korevaar

Cohen

Reitsma

, et al. Updating standards for reporting diagnostic accuracy: the development of STARD 2015. Res Integr Peer Rev 2016; 1: 7.

21.

Tirumani

Baheti

Tirumani

, et al. Update on gastrointestinal stromal tumors for radiologists. Korean J Radiol 2017; 18: 84–93.

22.

Kim

, et al. Application of a convolutional neural network in the diagnosis of gastric mesenchymal tumors on endoscopic ultrasonography images. J Clin Med 2020; 9: 1–11.

23.

Minoda

Ihara

Komori

, et al. Efficacy of endoscopic ultrasound with artificial intelligence for the diagnosis of gastrointestinal stromal tumors. J Gastroenterol 2020; 55: 1119–1126.

24.

Kim

Cho

, et al. Convolutional neural network-based object detection model to identify gastrointestinal stromal tumors in endoscopic ultrasound images. J Gastroenterol Hepatol 2021; 36: 3387–3394.

25.

Jiang

Guo

, et al. Computer-aided diagnosis of gastrointestinal stromal tumors: a radiomics method on endoscopic ultrasound image. Int J Comput Assist Radiol Surg 2019; 14: 1635–1645.

26.

Casali

Blay

JY.

Gastrointestinal stromal tumours: ESMO clinical practice guidelines for diagnosis, treatment and follow-up. Ann Oncol 2022; 33: 20–33.

27.

National Comprehensive Cancer Network. Gastrointestinal stromal tumors (GISTs) (Version 1.2022), https://www.nccn.org/professionals/physician_gls/pdf/gist.pdf (accessed 21 January 2022)

28.

Yang

Liu

, et al. Current and potential applications of artificial intelligence in gastrointestinal stromal tumor imaging. Contrast Media Mol Imaging 2020; 2020: 6058159.

29.

Sun

Lin

Zhao

, et al. Deep learning vs. Radiomics for predicting axillary lymph node metastasis of breast cancer using ultrasound images: don’t forget the peritumoral region. Front Oncol 2020; 10: 53.

30.

Ning

Luo

, et al. Pattern classification for gastrointestinal stromal tumors by integration of radiomics and deep convolutional features. IEEE J Biomed Health Inform 2019; 23: 1181–1191.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.02 MB