Hypervascular gastric masses: CT findings and clinical correlates

Comparing endoscopic ultrasonography and double contrast-enhanced ultrasonography in the preoperative diagnosis of gastric stromal tumor

BACKGROUND

This study was designed to perform a comparative analysis between endoscopic ultrasonography (EUS) and double contrast-enhanced ultrasonography (DCEUS) for the preoperative diagnosis of gastric stromal tumors (GSTs).

METHODS

A retrospective study was conducted involving 139 patients with histologically confirmed GSTs. All patients preoperatively underwent DCEUS and EUS. The pathology reports were treated as the baseline and were retrospectively compared with the findings of EUS and DCEUS.

RESULTS

Of the 139 lesions, 120 and 113 were correctly identified by DCEUS and EUS, respectively, with an accuracy of 86.3% and 81.3%. The results revealed an insignificant difference between these two methods (p = 0.189).

CONCLUSIONS

DCEUS can display not only the locations, sizes, shapes, borders, internal echoes, but also show the blood perfusion patterns of GSTs. It is a highly accurate, noninvasive, and convenient method to be used at the pre-treatment stage.

Gastric adenocarcinoma: A review of the TNM classification system and ways of spreading

Gastric cancer is the fifth most common cancer in the world. The most common histologic subtype is adenocarcinoma. Gastric adenocarcinomas are staged using the American Joint Committee on Cancer's 8th TNM classification. The perigastric ligaments, mesentery, omentum, and potential spaces between the parietal and visceral peritoneal linings play are important structures for staging. The spread of disease is influenced by the location of the tumor within the stomach, as well as by the anatomy related to the ligaments and lymph vessels. CT is the imaging modality of choice for the preoperative clinical staging of gastric cancer, and it is essential for planning treatment. To be able to do an adequate imaging workup, radiologists need to know the different pathways through which gastric cancer can spread: lymphatic, subperitoneal, direct invasion, transperitoneal, hematogenous, and extramural venous invasion.

Radiology of the neuroendocrine neoplasms of the gastrointestinal tract: a comprehensive review

Neuroendocrine neoplasms (NENs) are a group of neoplasms arising from the diffuse endocrine system (DES). The gastrointestinal tract (GIT) is the most common site of NEN. The WHO classification divides NEN into three broad categories viz. well-differentiated NENs, poorly differentiated NENs, and mixed neuroendocrine-non-neuroendocrine neoplasms. All GIT NEN have the potential to synthesize and secrete various bioactive substances which may lead to various clinical syndromes. The NEN may occur anywhere in the GIT and exhibit varying clinical presentation, prognosis, and metastatic potential. Further, some tumors show association with familial syndromes like multiple endocrine neoplasia type 1 and neurofibromatosis type 1. Ultrasonography, computed tomography (CT), magnetic resonance imaging, and positron emission tomography-CT are the imaging modalities useful in the diagnosis, localization, and staging of GIT NEN. Management depends on the site, size, grade, and stage of the tumor with interventional radiology playing a significant role in some cases. This imaging review describes the role of a radiologist in the management of GIT NEN.

Gut wrenching: cases of missed gastrointestinal tumors and their mimics on computed tomography

Computed tomography (CT) of the abdomen and pelvis is one of the most common imaging studies ordered through the emergency department (ED). Because these studies are ordered for the detection of acute abnormalities and due to the relatively low incidence in patients presenting through the ED, gastrointestinal tumors are commonly missed. Moreover, many CT findings of malignant tumors overlap with benign entities, which can present a diagnostic challenge. This review article will describe the common CT findings of gastric, small bowel, colon, and appendiceal cancer as well as some of the common benign gastrointestinal conditions with similar imaging findings.

Preoperative Staging of Gastric Cancer Using Computed Tomography and Its Correlation with Histopathology with Emphasis on Multi-planar Reformations and Virtual Gastroscopy

BACKGROUND

Gastric cancer is the fifth most common cancer in the world. Preoperative staging of gastric cancer has assumed pivotal role in deciding appropriate management of gastric cancer with multi-detector computed tomography (MDCT) using hydro- and gaseous distension of stomach superseding endoscopic ultrasound in tumor (T) and nodal (N) staging. We undertook this study to evaluate the diagnostic accuracy of MDCT in the T and N staging of gastric cancer with an attempt to differentiate between early and advanced gastric carcinomas.

METHODS

A total of 160 patients with endoscopically diagnosed and biopsy-proven gastric cancer were subjected to MDCT after adequate gaseous and hydro-distention of stomach. Multi-planar reformatted (MPR) as well as virtual gastroscopy images were also obtained. Gastric lesions were categorized into T1 to T4 stages with N staging from N0 to N3. Preoperative CT findings were correlated with histopathological findings.

RESULTS

Overall diagnostic accuracy of T staging in our study was 82.5% (132/160) with an accuracy of 75% (120/160) for N staging. The diagnostic accuracy of CT for early gastric carcinoma in our study was 93.75% with high specificity of 96% but low sensitivity of 66.7%.

CONCLUSION

MDCT using gaseous and hydro-distension of stomach is an excellent modality for near accurate preoperative T staging of gastric cancer. However, CT has a limited role in the N staging of gastric cancer. This study also suggested that the combined use of virtual gastroscopy and MPR images helps in better detection of early gastric cancers.

Computed tomographic characteristics of gastric schwannoma

Objective

This study aimed to characterize the computed tomographic (CT) features of gastric schwannoma (GS).

Methods

We retrospectively reviewed CT images of 19 cases of histologically proven GS between January 2010 and December 2015. Tumor location, size, contour, margin, growth pattern, and degree and pattern of enhancement, perigastric lymph nodes, ulceration, necrosis, and calcification were evaluated.

Results

GS was located in the gastric body (73.7%), gastric antrum (15.8%), and gastric fundus (10.5%), with a mean maximum diameter of 4.5 ± 1.8 cm. All tumors presented as oval, well-defined solid masses, with exophytic (36.8%), endoluminal (15.8%), or mixed (47.4%) growth patterns. Ulcers (57.9%) and perigastric lymph nodes (47.4%) were observed. Moderate enhancement (87.5%) was observed in the portal phase. Eighteen (94.7%) cases showed homogeneous enhancement.

Conclusions

GS typically presents as a mass in the stomach with an exophytic or mixed growth pattern, moderate homogeneous enhancement, and is prone to be accompanied by perigastric lymph node inflammatory reactive swelling. Larger GSs are more likely to be associated with ulcers.

Contrast-enhanced computed tomography may be helpful for characterizing and staging canine gastric tumors

In humans, computed tomography (CT) is a widely performed technique for the diagnosis and staging of gastric tumors. The purpose of this retrospective case series study was to describe CT findings in a group of dogs with confirmed gastric tumors. For each included dog, the following CT parameters were recorded: gastric tumor location, tumor shape, gastric involvement pattern, tumor enhancement pattern in early and late phases, presence and location of lymphadenopathy, gastric tumor attenuation values, attenuation values of enlarged lymph nodes, maximum short-axis diameter (mm) of enlarged lymph node, maximum long-axis diameter (mm) of enlarged lymph node, and short-axis diameter to long-axis diameter ratio (short axis/long axis). A total of 16 dogs met inclusion criteria and had the following final diagnoses: five lymphoma, six adenocarcinoma, three inflammatory polyps, and two leiomyoma. In the early- and delayed-phase postcontrast images, the mean CT attenuation value for lymphoma was lower than that of other gastric tumors. Lymphadenopathy was widespread in lymphomas and regional in adenocarcinomas. Lymphadenopathy was not detected in leiomyomas. Lymph node measurements in lymphoma were larger than lymph node measurements in adenocarcinoma. Although there were overlapping findings for the different types of gastric tumors, contrast-enhanced CT provided helpful information for characterizing gastric tumors based on the following criteria: early and late enhancement patterns, the site of origin of the mass lesion, and extent of local invasion and distant metastases. Lymphoma should be considered for canine gastric tumors with low mean attenuation values during early- and delayed-phase postcontrast images, and widespread, bulky, and rounded lymphadenopathy.

CT textural analysis of gastric cancer: correlations with immunohistochemical biomarkers

To investigate the ability of CT texture analysis to assess and predict the expression statuses of E-cadherin, Ki67, VEGFR2 and EGFR in gastric cancers, the enhanced CT images of 139 patients with gastric cancer were retrospectively reviewed. The region of interest was manually drawn along the margin of the lesion on the largest slice in the arterial and venous phases, which yielded a series of texture parameters. Our results showed that the standard deviation, width, entropy, entropy (H), correlation and contrast from the arterial and venous phases were significantly correlated with the E-cadherin expression level in gastric cancers (all P < 0.05). The skewness from the arterial phase and the mean and autocorrelation from the venous phase were negatively correlated with the Ki67 expression level in gastric cancers (all P < 0.05). The width, entropy and contrast from the venous phase were positively correlated with the VEGFR2 expression level in gastric cancers (all P < 0.05). No significant correlation was found between the texture features and EGFR expression level. CT texture analysis, which had areas under the receiver operating characteristic curve (AUCs) ranging from 0.612 to 0.715, holds promise in predicting E-cadherin, Ki67 and VEGFR2 expression levels in gastric cancers.

Evaluating the Sensitivity of Arterial Phase CT Images for Detection of Hepatic GIST Metastases

Gastrointestinal stromal tumor (GIST) frequently metastasizes to the liver, and conventional staging computed tomography (CT) protocols use multiphasic contrast enhancement for detection of hepatic lesions. We evaluated the sensitivity of arterial phase CT imaging for hepatic GIST metastases compared with that of standard (portal venous [PV]) phase imaging. We conducted a retrospective review of patients who presented with hepatic GIST metastases identified on staging CT examinations between 2005 and 2015. Arterial and PV phase CT images were randomized and reviewed by 2 radiologists blinded to clinical history, correlative imaging, and number of controls. In total, 32 patients had hepatic metastases identified on multiphasic (arterial and PV) staging CT examinations. There was no significant difference in identification of metastases between arterial and PV phase imaging (31 vs 32, P = .32). Lesion size measurements did not significantly differ (P = .58). Arterial phase CT imaging did not significantly increase the sensitivity for hepatic GIST metastases compared with PV phase imaging alone.

Evaluation of computed tomography vascular reconstruction for the localization diagnosis of perigastric mass

BACKGROUND

The aim of this study was to evaluate the utility of computed tomography (CT) vascular reconstruction in the localization diagnosis of perigastric mass.

METHODS

Fifty-eight patients with pathologically detected perigastric mass underwent abdominal dynamic contrast-enhanced CT. CT vascular reconstructions were produced from arterial phase data using volume rendering (VR), multiplanar reconstruction (MPR), and maximal intensity projection (MIP). Image analysis was focused on the relationship between the mass, perigastric arteries, and the gastric wall. Localization diagnosis values were compared between CT vascular reconstruction and dynamic-enhanced CT images.

RESULTS

Among the 58 cases of perigastric mass, 41 cases originated from the stomach, 7 cases from the left liver lobe, 6 from the pancreas, 2 from lessor omental bursa, 1 from transverse mesocolon, and 1 from left adrenal gland. The accuracy of CT vascular reconstruction images in the localization diagnosis of perigastric mass was higher than that of dynamic-enhanced CT images (98.3% and 86.2%, respectively, P = .04). On the reference level, 35 (35/41) patients with stomach-originated masses showed the mass adjacent perigastric arteries pushed away from the stomach (arterial displacement sign), and 15 (15/17) patients with nonstomach-originated masses showed perigastric arteries between the mass and the stomach (arterial entrapment sign). The sensitivity, specificity, positive predictive value, and negative predictive value of the localization diagnosis of perigastric mass with arterial displacement sign were 85.4%, 100%, 100%, and 73.9%, respectively, and with arterial entrapment sign, 88.2%, 100%, 100%, and 95.3%, respectively.

CONCLUSION

CT vascular reconstruction can clearly depict the relationship between perigastric mass and adjacent perigastric arteries, which may help us more accurately differentiate between stomach-originated and nonstomach-originated masses compared with original dynamic-enhanced CT images.

Preoperative CT texture analysis of gastric cancer: correlations with postoperative TNM staging

AIM

To explore the role of computed tomography (CT) texture analysis in predicting pathologic stage of gastric cancers.

MATERIALS AND METHODS

Preoperative enhanced CT images of 153 patients (112 men, 41 women) with gastric cancers were reviewed retrospectively. Regions of interest (ROIs) were manually drawn along the margin of the lesion on the section where it appeared largest on the arterial and venous CT images, which yielded texture parameters, including mean, maximum frequency, mode, skewness, kurtosis, and entropy. Correlations between texture parameters and pathological stage were analysed with Spearman's correlation test. The diagnostic performance of CT texture parameters in differentiating different stages was evaluated using receiver operating characteristic (ROC) analysis.

RESULTS

Maximum frequency in the arterial phase and mean, maximum frequency, mode in the venous phase correlated positively with T stage, N stage, and overall stage (all p<0.05) of gastric cancer. Entropy in the venous phase also correlated positively with N stage (p=0.009) and overall stage (p=0.032). Skewness in the arterial phase had the highest area under the ROC curve (AUC) of 0.822 in identifying early from advanced gastric cancers. Multivariate analysis identified four parameters, including maximum frequency, skewness, entropy in the venous phase, and differentiation degree from biopsy, for predicting lymph node metastasis of gastric cancer. The multivariate model could distinguish gastric cancers with and without lymph node metastasis with an AUC of 0.892.

CONCLUSION

Multiple CT texture parameters, especially those in the venous phase, correlated well with pathological stage and hold great potential in predicting lymph node metastasis of gastric cancers.

[A radiomics-based model for differentiation between benign and malignant gastrointestinal stromal tumors]

OBJECTIVE

To establish a model for discrimination between benign and malignant gastrointestinal stromal tumors (GIST) by analyzing the texture features extracted from computed tomography (CT) images.

METHODS

The CT datasets were collected from 110 patients with GIST (including 80 as the training cohort and 30 as the validation cohort). Feature set reduction was executed with the 0.632 + bootstrap method in the initial feature set followed by stepwise forward feature selection in the feature subset, and the classification model was generated by logistic regression.

RESULTS

The 6-texture-featurebased classification model successfully discriminated between benign and malignant GIST in both the training and validation cohorts with AUCs of 0.93 and 0.91, sensitivity of 0.88 and 0.87, specificity of 0.85 and 0.86, and accuracy of 0.87 and 0.86 in the two cohorts, respectively.

CONCLUSIONS

This classification model established by radiomics analysis is capable of discrimination between benign and malignant GIST to provide assistance in preoperative diagnosis of GIST.

Histopathologic diversity of gastric cancers: Relationship between enhancement pattern on dynamic contrast-enhanced CT and histological type

PURPOSE

To evaluate the diagnostic value of contrast-enhanced computed tomography gastrography (CE-CTG) to predict the histological type of gastric cancer.

MATERIALS AND METHODS

We analyzed 47 consecutive patients with resectable advanced gastric cancer preoperatively evaluated by multiphasic dynamic contrast-enhanced CT. Two radiologists independently reviewed the CT images and they determined the peak enhancement phase, and then measured the CT attenuation value of the gastric lesion for each phase. The histological types of gastric cancers were assigned to three groups as differentiated-type, undifferentiated-type, and mixed-type. We compared the peak enhancement phase of the three types and compared the CT attenuation values in each phase.

RESULTS

The peak enhancement was significantly different between the three types of gastric cancers for both readers (reader 1, p=0.001; reader 2, p=0.009); most of the undifferentiated types had peak enhancement in the delayed phase. The CT attenuation values of undifferentiated type were significantly higher than those of differentiated or mixed type in the delayed phase according to both readers (reader 1, p=0.002; reader 2, p=0.004).

CONCLUSION

CE-CTG could provide helpful information in diagnosing the histological type of gastric cancers preoperatively.

Improvement to ultrasonographical differential diagnosis of gastric lesions: The value of contrast enhanced sonography with gastric distention

Objective

The purpose of this retrospective study is to evaluate the diagnostic value of contrast enhanced sonography plus gastric distention sonography, the Double Contrast-enhanced Ultrasound (DCUS) in gastric lesions.

Methods

107 cases with pathology confirmed gastric lesions were retrospectively reviewed, DCUS and oral contrast agent ultrasound (US) were performed in all cases prior to operation. Perfusion parameters including arrival time (AT), peak intensity (PI), time to peak (TTP), and area under the curve (AUC) of the lesion and surrounding normal tissue were analyzed. A reader blinded to pathology results were asked to rate and compare each case with surgical or resection biopsy pathology results.

Results

From the 107 gastric lesions, 75 were malignant gastric lesions (33 gastric cancers,42 gastrointestinal stromal tumors (GISTs)) and 32 were benign gastric lesions (11 inflammatory masses and 21 polypoid adenomas). Compared with US, DCUS achieved higher value in sensitivity (90.6% vs. 70.6%), specificity (75% vs. 62.5%), positive predictive value (89.5% vs. 81.5%), negative predictive value (77.4% vs. 47.6%), and overall accuracy (85.9% vs. 68.2%). When US was tested against DCUS, the increase in correct diagnoses value was significant (P = .01). Furthermore, gastric cancer had faster AT, higher PI and AUC than normal tissue (P<0.05); GIST and Inflammatory mass had higher PI than normal tissue (P<0.05); gastric cancer and GIST had faster AT than polypoid adenoma (P<0.05), Inflammatory mass showed higher PI than other 3 lesions and gastric cancer had higher PI than polypoid adenoma and GIST (P<0.05); gastric cancer and inflammatory mass had larger AUC than polypoid adenoma and GIST (P<0.05). Conclusion DCUS improved diagnostic performance compared with US. The combination of different CEUS enhancement characteristics with quantitative perfusion parameters may provide a promising tool to help differentiate gastric cancer and GIST from benign lesions.

Usefulness of conventional and low-dose hydro-CT in the diagnosis of gastric tumors in comparison to endoscopy

PURPOSE

The aim of this retrospective study was to evaluate the usefulness of hydro-CT in the diagnosis of gastric tumors in comparison to endoscopy.

MATERIAL AND METHODS

The study involved 40 patients with a diagnosis of gastric tumor established by histopathology who underwent endoscopy and conventional or low-dose hydro-CT. Hydro-CT images were retrospectively analyzed based on the consensus of two radiologists who were blinded to the endoscopy findings. The diagnostic accuracy of hydro-CT and endoscopy for the diagnosis of gastric tumors was evaluated using the results of the histopathological examination as the reference standard.

RESULTS

Histopathology confirmed the presence of gastric cancer in 28 patients (70%), while gastrointestinal stromal tumors (GISTs) were recognized in the remaining 12 cases (30%). Correct diagnoses of the type of gastric tumor in hydro-CT were obtained in 37 patients (92.5%). This was not significantly different from the 85% accuracy of endoscopy. Further analysis showed that the correctness of GIST diagnosis in endoscopy and hydro-CT also did not differ significantly (91.7% and 100% respectively). The percentage of correctly diagnosed malignant lesions in hydro-CT was lower than for GISTs at 89.29%, while in endoscopy it was insignificantly lower (82.14%). The diagnostic accuracy of conventional and low-dose hydro-CT in the diagnosis of gastric tumors (95% and 90% respectively) was not significantly different.

CONCLUSIONS

Conventional and low-dose hydro-CT may be a valuable non-invasive diagnostic method in the diagnosis of gastric tumors for patients who have contraindications to endoscopy or who are unable to undergo gastric biopsy.

Application of CT texture analysis in predicting histopathological characteristics of gastric cancers

OBJECTIVES

To explore the application of computed tomography (CT) texture analysis in predicting histopathological features of gastric cancers.

METHODS

Preoperative contrast-enhanced CT images and postoperative histopathological features of 107 patients (82 men, 25 women) with gastric cancers were retrospectively reviewed. CT texture analysis generated: (1) mean attenuation, (2) standard deviation, (3) max frequency, (4) mode, (5) minimum attenuation, (6) maximum attenuation, (7) the fifth, 10th, 25th, 50th, 75th and 90th percentiles, and (8) entropy. Correlations between CT texture parameters and histopathological features were analysed.

RESULTS

Mean attenuation, maximum attenuation, all percentiles and mode derived from portal venous CT images correlated significantly with differentiation degree and Lauren classification of gastric cancers (r, -0.231 ~ -0.324, 0.228 ~ 0.321, respectively). Standard deviation and entropy derived from arterial CT images also correlated significantly with Lauren classification of gastric cancers (r = -0.265, -0.222, respectively). In arterial phase analysis, standard deviation and entropy were significantly lower in gastric cancers with than those without vascular invasion; however, minimum attenuation was significantly higher in gastric cancers with than those without vascular invasion.

CONCLUSION

CT texture analysis held great potential in predicting differentiation degree, Lauren classification and vascular invasion status of gastric cancers.

KEY POINTS

• CT texture analysis is noninvasive and effective for gastric cancer. • Portal venous CT images correlated significantly with differentiation degree and Lauren classification. • Standard deviation, entropy and minimum attenuation in arterial phase reflect vascular invasion.

Approach to intensely enhancing neck nodes

Cervical node evaluation is one of the most common problems encountered by a radiologist. Here, we present a pictorial review of intensely enhancing neck nodes. While enhancement in a cervical node is a common radiologic finding on contrast-enhanced computed tomography scan, only few conditions cause intense enhancement in cervical nodes. We discuss the common causes of intensely enhancing neck nodes along with pertinent radiologic features and key differentiating points that aid radiologists in reaching a diagnosis. In addition, we discuss certain potential non-nodal mimics, which need to be excluded.

Beyond the GIST: mesenchymal tumors of the stomach

Intramural gastric masses arise in the wall of the stomach (generally within the submucosa or muscularis propria), often with intact overlying mucosa. These tumors are typically mesenchymal in origin and have overlapping radiologic appearances. A combination of features such as location, attenuation, enhancement, and growth pattern may suggest one diagnosis over another. Gastrointestinal stromal tumors (GISTs) account for the majority of intramural tumors and can vary widely in appearance, from small intraluminal lesions to exophytic masses that protrude into the peritoneal cavity, commonly with areas of hemorrhage or necrosis. A well-circumscribed mass measuring -70 to -120 HU is a lipoma. Leiomyomas usually manifest as low-attenuation masses at the gastric cardia. Homogeneous attenuation is a noteworthy characteristic of schwannomas, particularly for larger lesions that might otherwise be mistaken for GISTs. A hypervascular mass in the antrum is a common manifestation of glomus tumors. Hemangiomas are also hypervascular but often manifest in childhood. Inflammatory fibroid polyps usually arise as a polypoid mass in the antrum. Inflammatory myofibroblastic tumors are infiltrative neoplasms with a propensity for local recurrence. Plexiform fibromyxomas are rare, usually antral tumors. Carcinoid tumors are epithelial in origin, but often submucosal in location, and therefore should be distinguished from other intramural lesions. Multiple carcinoid tumors are associated with hypergastrinemia, either in the setting of chronic atrophic gastritis or Zollinger-Ellison syndrome. Sporadic solitary carcinoid tumors not associated with hypergastrinemia have a higher rate of metastasis. Histopathologic analysis, including immunohistochemistry, is usually required for diagnosis of intramural masses.

Imaging features of carcinoid tumors of the gastrointestinal tract

OBJECTIVE

Recent studies have provided a better understanding of the biologic behavior of gastrointestinal carcinoid tumors. This article focusing on imaging of gastrointestinal carcinoids will emphasize epidemiology, molecular biology, taxonomy, histopathology, and management.

CONCLUSION

Gastrointestinal carcinoids are a biologically heterogeneous group of tumors, with variable clinical presentation and biologic behavior. Imaging can play an important role in multidisciplinary identification and management of this disease.

Texture-based classification of different gastric tumors at contrast-enhanced CT

PURPOSE

To determine the feasibility of texture analysis for the classification of gastric adenocarcinoma, lymphoma, and gastrointestinal stromal tumors on contrast-enhanced hydrodynamic-MDCT images.

MATERIALS AND METHODS

The arterial phase scans of 47 patients with adenocarcinoma (AC) and a histologic tumor grade of [AC-G1, n=4, G1, n=4; AC-G2, n=7; AC-G3, n=16]; GIST, n=15; and lymphoma, n=5, and the venous phase scans of 48 patients with AC-G1, n=3; AC-G2, n=6; AC-G3, n=14; GIST, n=17; lymphoma, n=8, were retrospectively reviewed. Based on regions of interest, texture analysis was performed, and features derived from the gray-level histogram, run-length and co-occurrence matrix, absolute gradient, autoregressive model, and wavelet transform were calculated. Fisher coefficients, probability of classification error, average correlation coefficients, and mutual information coefficients were used to create combinations of texture features that were optimized for tumor differentiation. Linear discriminant analysis in combination with a k-nearest neighbor classifier was used for tumor classification.

RESULTS

On arterial-phase scans, texture-based lesion classification was highly successful in differentiating between AC and lymphoma, and GIST and lymphoma, with misclassification rates of 3.1% and 0%, respectively. On venous-phase scans, texture-based classification was slightly less successful for AC vs. lymphoma (9.7% misclassification) and GIST vs. lymphoma (8% misclassification), but enabled the differentiation between AC and GIST (10% misclassification), and between the different grades of AC (4.4% misclassification). No texture feature combination was able to adequately distinguish between all three tumor types.

CONCLUSION

Classification of different gastric tumors based on textural information may aid radiologists in establishing the correct diagnosis, at least in cases where the differential diagnosis can be narrowed down to two histological subtypes.