Endoscopic features of gastrointestinal stromal tumor in the small intestine

Ihara, Yutaro; Torisu, Takehiro; Moriyama, Tomohiko; Umeno, Junji; Hirano, Atsushi; Okamoto, Yasuharu; Hori, Yozo; Yamamoto, Hidetaka; Kitazono, Takanari; Esaki, Motohiro

doi:10.5217/ir.2018.00161

Cited by 4 publications

(4 citation statements)

References 16 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although it is possible to examine the entire small intestine in one endoscopic trial at times, in many cases, two or more endoscopic trials are required to examine the entire small intestine. Therefore, depending on the localization of the tumor, it may not be possible to reach the site of the tumor with a single insertion of a balloon small bowel endoscope [4, 5]. All of the previously reported cases of NF1-associated GISTs were detectable via endoscopy.…”

Section: Discussionmentioning

confidence: 99%

Multiple Small Bowel Gastrointestinal Stromal Tumors Associated with Neurofibromatosis Type 1 that Were Not Detected by Endoscopy: A Case Report

Saito

Omori

Murasugi

et al. 2023

Case Rep Gastroenterol

View full text Add to dashboard Cite

We treated a 39-year-old Japanese man who was admitted for an abdominal mass. He had had neurofibroma-like skin lesions since childhood. Computed tomography and endoscopic ultrasound results were consistent with a tumor in the small intestine. Although the tumor was undetectable by single-balloon endoscopy, the patient’s background and imaging results led us to suspect a gastrointestinal stromal tumor (GIST). He also met the diagnostic criteria for neurofibroma type 1 (NF1). We performed a surgical removal of the tumor, and the biopsy results led to a definitive diagnosis of GIST. Small bowel GISTs should be considered in cases of NF1.

show abstract

Section: Discussionmentioning

confidence: 99%

Multiple Small Bowel Gastrointestinal Stromal Tumors Associated with Neurofibromatosis Type 1 that Were Not Detected by Endoscopy: A Case Report

Saito

Omori

Murasugi

et al. 2023

Case Rep Gastroenterol

View full text Add to dashboard Cite

show abstract

“…Small bowel malignancies are rare, constituting only 1–3% of all GI malignancies [ 9 ]. Patients with small bowel tumors are usually asymptomatic or have only nonspecific symptoms, such as GI bleeding, anemia, abdominal pain, vomiting, and weight loss [ 10 , 11 ]. Previously, the diagnosis of small bowel malignancies was difficult because of the length of the small bowel and the limitations of the diagnostic tools [ 12 ].…”

Section: Small Bowel Malignanciesmentioning

confidence: 99%

“…An association between an increased risk of small bowel cancer and environmental factors, including alcohol consumption, smoking, red meat, and intake of sugary drinks, was reported, although the evidence is insufficient owing to the rarity of small bowel malignancies [17]. symptoms, such as GI bleeding, anemia, abdominal pain, vomiting, and weight loss [10,11]. Previously, the diagnosis of small bowel malignancies was difficult because of the length of the small bowel and the limitations of the diagnostic tools [12].…”

Section: Small Bowel Malignanciesmentioning

confidence: 99%

Small Bowel Malignancies in Patients Undergoing Capsule Endoscopy for Iron Deficiency Anemia

Kim

2021

Diagnostics

View full text Add to dashboard Cite

Small bowel malignancies are rare and usually asymptomatic or symptoms are nonspecific. Therefore, small bowel tumors are difficult to diagnose. In patients with iron deficiency anemia (IDA) who have negative bidirectional endoscopy results, the small bowel may be considered the source of bleeding. However, in asymptomatic IDA patients with negative bidirectional endoscopy results, evidence supporting the routine use of capsule endoscopy (CE) is insufficient. CE can be considered in selected patients with recurrent or persistent IDA. The frequency of small bowel malignancies is low in patients undergoing CE for IDA, but the usefulness of CE for the diagnosis of small bowel malignancies in younger age groups with IDA has been reported. For patients with risk factors for small bowel malignancy, investigation of the small bowel should be considered. Efforts should be made to prevent adverse events, such as capsule retention or capsule aspiration, through meticulous history taking and endoscopic capsule delivery as necessary.

show abstract

“…Although most gastric SETs do not cause symptoms and show benign progress, gastrointestinal stromal tumors (GISTs) have malignant potential. Therefore, unlike other SETs, these lesions must usually be removed by surgical resection 7–9 . However, it is challenging to differentiate GISTs from benign mesenchymal tumors, such as leiomyomas.…”

Section: Introductionmentioning

confidence: 99%

Convolutional neural network‐based object detection model to identify gastrointestinal stromal tumors in endoscopic ultrasound images

Kim

Cho

et al. 2021

J of Gastro and Hepatol

View full text Add to dashboard Cite

Background and Aim We aimed to develop a convolutional neural network (CNN)‐based object detection model for the discrimination of gastric subepithelial tumors, such as gastrointestinal stromal tumors (GISTs), and leiomyomas, in endoscopic ultrasound (EUS) images. Methods We used 376 images from 114 patients with histologically confirmed gastric GIST or leiomyoma to train the EUS‐CNN. We constructed the EUS‐CNN using an EfficientNet CNN model for feature extraction and a weighted bi‐directional feature pyramid network for object detection. We assessed the performance of our EUS‐CNN by calculating its accuracy, sensitivity, specificity, and area under receiver operating characteristic curve (AUC) using a validation set of 170 images from 54 patients. Four EUS experts and 15 EUS trainees were asked to judge the same validation dataset, and the diagnostic yields were compared between the EUS‐CNN and human assessments. Results In the per‐image analysis, the sensitivity, specificity, accuracy, and AUC of our EUS‐CNN were 95.6%, 82.1%, 91.2%, and 0.9234, respectively. In the per‐patient analysis, the sensitivity, specificity, accuracy, and AUC for our object detection model were 100.0%, 85.7%, 96.3%, and 0.9929, respectively. The EUS‐CNN outperformed human assessment in terms of accuracy, sensitivity, and negative predictive value. Conclusions We developed the EUS‐CNN system, which demonstrated high diagnostic ability for gastric GIST prediction. This EUS‐CNN system can be helpful not only for less‐experienced endoscopists but also for experienced ones. Additional EUS image accumulation and prospective studies are required alongside validation in a large multicenter trial.

show abstract

Endoscopic features of gastrointestinal stromal tumor in the small intestine

Cited by 4 publications

References 16 publications

Multiple Small Bowel Gastrointestinal Stromal Tumors Associated with Neurofibromatosis Type 1 that Were Not Detected by Endoscopy: A Case Report

Multiple Small Bowel Gastrointestinal Stromal Tumors Associated with Neurofibromatosis Type 1 that Were Not Detected by Endoscopy: A Case Report

Small Bowel Malignancies in Patients Undergoing Capsule Endoscopy for Iron Deficiency Anemia

Convolutional neural network‐based object detection model to identify gastrointestinal stromal tumors in endoscopic ultrasound images

Contact Info

Product

Resources

About