<b>Gastrointestinal Stromal Tumors of the Stomach:</b> CT Findings and Prediction of Malignancy

Kim, Hyo Cheol; Lee, Jeong Min; Kim, Kyung Won; Park, Seong Ho; Kim, Se Hyung; Lee, Jae Young; Han, Joon Koo; Choi, Byung Ihn

doi:10.2214/ajr.183.4.1830893

Cited by 102 publications

(112 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the review of literature, the gastric body was the segment most affected by GIST (38%-75%) (16,21,23) , with average size varying between 5.4 and 13.0 cm (2,20) , similarly to what was found in the present study. Tumors smaller than 5 cm present, still, predominantly intraluminal growth and homogeneous enhancement by venous contrast, while tumors bigger than 10 cm present extraluminal component and heterogeneous enhancement in most cases (3,13,16,20,27,32) .…”

Section: Discussionsupporting

confidence: 89%

“…Tumors smaller than 5 cm present, still, predominantly intraluminal growth and homogeneous enhancement by venous contrast, while tumors bigger than 10 cm present extraluminal component and heterogeneous enhancement in most cases (3,13,16,20,27,32) . This trend was also observed in our results, where there was a bigger predominance of extraluminal growth among the tumors bigger than 10 cm (50%) and intraluminal growth in all tumors smaller than 5.0 cm.…”

Section: Discussionmentioning

confidence: 97%

“…Clinical manifestations are unspecific and depend on the lesion site. Digestive hemorrhage and abdominal pain are the most frequent symptoms found (16,21,23,30,32) . Our case comprised 14 (66.7%) female patients and 7 (33.3%) male patients, with average age of 61.6 years old, presenting pain or abdominal discomfort as the most frequent symptom.…”

Section: Discussionmentioning

confidence: 99%

“…Other characteristics can still be found especially in tumors of high histological degree, such as mucosa ulceration (3%-88%), cavitation and areas of central hypodensity (20%-49%) which can correspond to cystic degeneration, hemorrhage or necrosis (9,16,23,29,32) . Presence of gas or contrast in the interior of the lesion can suggest presence of mucosa ulceration and fistula formation (18) .…”

Section: Discussionmentioning

confidence: 99%

“…Computed tomography is the most important image modality to detect and characterize the GIST, once it provides information about the size of the tumor, anatomic, growth pattern, necrosis evidence, invasion of adjacent organs, and metastasis, also allowing treatment monitoring and the assessment of the disease progression (5,32) . Some authors still describe the association among tomography variables and the high tumor degree, however these finding are conflicting and there is no consensus, which makes the prediction of the biological behavior of the tumor through image characteristics problematic (13,16,21,26,(32)(33)(34) . In recent years, the malignity potential has been classified according to the tumor site, size, and mitotic index (26) .…”

Section: Tomographic Findings Of Gastric Gastrointestinal Stromal Tummentioning

confidence: 99%

See 4 more Smart Citations

Tomographic Findings of Gastric Gastrointestinal Stromal Tumor and Correlation With the Mitotic Index

Pelandré

Djahjah

Gasparetto

et al. 2013

Arq. Gastroenterol.

View full text Add to dashboard Cite

-Context -Gastrointestinal stromal tumors are uncommon abdominal neoplasms and can affect any portion of the gastrointestinal tract. Objectives -Describe the tomographic findings of the gastrointestinal stromal tumor of gastric origin, correlating it with the mitotic index. Methods -Twenty-one patients were selected within the period of January 2000 and 2008, with histopathological and immunohistochemical diagnosis of gastric gastrointestinal stromal tumors, who presented computed tomography done before the treatment. The tomographic variables analyzed were lesion topography, dimensions, contours, morphology, pattern and intensity enhancement through venous contrast, growth pattern, invasion of adjacent organs, presence of ulceration, fistula, calcifications, infiltration of mesenteric fat, lymphadenopathy and metastasis. The mitotic index was determined through optic microscopy, counting the number of mitosis figures in 50 high power fields. Results -The tumors were located in the body (66.7%) or gastric fundus (33.3%), with dimensions varying between 4.2 and 21.2 cm (average of 10.5 cm). The growth was predominantly extraluminal (47.6%) or intra/extra luminal (28.6%). The enhancement by venous contrast was heterogeneous in 66.7%. The statistical analysis showed that irregular morphology (P = 0.027) and infiltration of mesenteric fat (P = 0.012) presented correlation with the high mitotic index. Conclusions -In the present study, most part of the tumors were located in the gastric body, with average size of 10.5 cm, presenting central hypo dense area, heterogeneous enhancement through contrast and predominantly extra luminal growth. Irregular morphology and infiltration of mesenteric fat present statistical correlation with high mitotic level. HEADINGS -Gastrointestinal stromal tumors. Spiral computed tomography. Mitotic index.

show abstract

Section: Discussionsupporting

confidence: 89%

Section: Discussionmentioning

confidence: 97%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Tomographic Findings Of Gastric Gastrointestinal Stromal Tummentioning

confidence: 99%

See 3 more Smart Citations

Tomographic Findings of Gastric Gastrointestinal Stromal Tumor and Correlation With the Mitotic Index

Pelandré

Djahjah

Gasparetto

et al. 2013

Arq. Gastroenterol.

View full text Add to dashboard Cite

show abstract

Preoperative CT‐based radiomics and deep learning model for predicting risk stratification of gastric gastrointestinal stromal tumors

Yang,

Wu,

Liu

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundGastrointestinal stromal tumors (GISTs) are clinically heterogeneous with various malignant potential in different individuals. It is crucial to explore a reliable method for preoperative risk stratification of gastric GISTs noninvasively.PurposeTo establish and evaluate a machine learning model using the combination of computed tomography (CT) morphology, radiomics, and deep learning features to predict the risk stratification of primary gastric GISTs preoperatively.MethodsThe 193 gastric GISTs lesions were randomly divided into training set, validation set, and test set in a ratio of 6:2:2. The qualitative and quantitative CT morphological features were assessed by two radiologists. The tumors were segmented manually, and then radiomic features were extracted using PyRadiomics and the deep learning features were extracted using pre‐trained Resnet50 from arterial phase and venous phase CT images, respectively. Pearson correlation analysis and recursive feature elimination were used for feature selection. Support vector machines were employed to build a classifier for predicting the risk stratification of GISTs. This study compared the performance of models using different pre‐trained convolutional neural networks (CNNs) to extract deep features for classification, as well as the performance of modeling features from single‐phase and dual‐phase images. The arterial phase, venous phase and dual‐phase machine learning models were built, respectively, and the morphological features were added to the dual‐phase machine learning model to construct a combined model. Receiver operating characteristic (ROC) curves were used to evaluate the efficacy of each model. The clinical application value of the combined model was determined through the decision curve analysis (DCA) and the net reclassification index (NRI) was analyzed.ResultsThe area under the curve (AUC) of the dual‐phase machine learning model was 0.876, which was higher than that of the arterial phase model or venous phase model (0.813, 0.838, respectively). The combined model had best predictive performance than the above models with an AUC of 0.941 (95% CI: 0.887–0.974) (p = 0.012, Delong test). DCA demonstrated that the combined model had good clinical application value with an NRI of 0.575 (95% CI: 0.357–0.891).ConclusionIn this study, we established a combined model that incorporated dual‐phase morphology, radiomics, and deep learning characteristics, which can be used to predict the preoperative risk stratification of gastric GISTs.

show abstract

Patologia gastrointestinale neoplastica

Rollandi

Biscaldi

2006

Radiologia Geriatrica

View full text Add to dashboard Cite

Gastrointestinal Stromal Tumors of the Stomach: CT Findings and Prediction of Malignancy

Cited by 102 publications

References 19 publications

Tomographic Findings of Gastric Gastrointestinal Stromal Tumor and Correlation With the Mitotic Index

Tomographic Findings of Gastric Gastrointestinal Stromal Tumor and Correlation With the Mitotic Index

Preoperative CT‐based radiomics and deep learning model for predicting risk stratification of gastric gastrointestinal stromal tumors

Patologia gastrointestinale neoplastica

Contact Info

Product

Resources

About