Gastric heterotopic pancreas masquerading as a stromal tumor: A case report

An ensemble machine learning model assists in the diagnosis of gastric ectopic pancreas and gastric stromal tumors

OBJECTIVE

To develop an ensemble machine learning (eML) model using multiphase computed tomography (MPCT) for distinguishing between gastric ectopic pancreas (GEP) and gastric stromal tumors (GIST) in lesions < 3 cm.

METHODS

In this study, we retrospectively collected MPCT images from 138 patients between April 2017 and June 2023 across two centers. Cohort 1 comprised 94 patients divided into a training cohort and an internal validation cohort, while the 44 patients from Cohort 2 constituted the external validation cohort. Deep learning (DL) models were constructed based on the lesion region, and radiomics features were extracted to develop radiomics models, which were later integrated into the fusion model. Model performance was assessed through the analysis of the area under the receiver operating characteristic curve (AUROC). The diagnostic efficacy of the optimal model was compared with that of a radiologist. Additionally, the radiologist with the assistance of the eML model provides a secondary diagnosis, to assess the potential clinical value of the model.

RESULTS

After evaluation using an external validation cohort, the radiomics model demonstrated the highest performance in the venous phase, achieving AUROC of 0.87. The DL model showed optimal performance in the non-contrast phase, with AUROC of 0.81. The eML achieved the best performance across all models, with AUROC of 0.90. The use of eML-assisted analysis resulted in a significant improvement in the junior radiologist's accuracy, rising from 0.77 to 0.93 (p < 0.05). However, the senior radiologist's accuracy, while improving from 0.86 to 0.95, did not exhibit a statistically significant difference.

CONCLUSION

eML model based on MPCT can effectively distinguish between GEPs and GISTs < 3 cm.

CRITICAL RELEVANCE STATEMENT

The multiphase CT-based fusion model, incorporating radiomics and DL technology, proves effective in distinguishing between GEP and gastric stromal tumors, serving as a valuable tool to enhance diagnoses and offering references for clinical decision-making.

KEY POINTS

No studies yet differentiated these tumors via radiomics or DL. Radiomics and DL methodologies unveil potentially distinct phenotypes within lesions. Quantitative analysis on CT for GIST and ectopic pancreas. Ensemble learning aids accurate diagnoses, assisting treatment decisions.

Benign Tumors and Tumorlike Lesions of the Pancreas

The pancreas is a complex organ that may give rise to large number of neoplasms and non-neoplastic lesions. This article focuses on benign neoplasms, such as serous neoplasms, and tumorlike (pseudotumoral) lesions that may be mistaken for neoplasm not only by clinicians and radiologists, but also by pathologists. The family of pancreatic pseudotumors, by a loosely defined conception of that term, includes a variety of lesions including heterotopia, hamartoma, and lipomatous pseudohypertrophy. Autoimmune pancreatitis and paraduodenal ("groove") pancreatitis may also lead to pseudotumor formation. Knowledge of these entities will help in making an accurate diagnosis.

Present status and perspectives of endosonography 2017 in gastroenterology

Endoscopic ultrasound has become an essential tool in modern gastroenterology and abdominal surgery. Compared with all other endoscopic methods, it has the most potential for innovation and its future looks bright. Thus, we compiled this summary of established and novel applications of endoscopic ultrasound methods to inform the reader about what is already possible and where future developments will lead in improving patient care further. This review is structured in four parts. The first section reports on developments in diagnostic endoscopic ultrasound, the second looks at semi-invasive endoscopic ultrasound, and the third discusses advances in therapeutic endoscopic ultrasound. An overview on the future prospects of endoscopic ultrasound methods concludes this article.

Gastric Heterotopic Pancreas: Computed Tomography With Clinicopathologic Correlation

Asymptomatic heterotopic pancreas (HP) is benign and can be monitored long term without further intervention. Heterotopic pancreas is sometimes surgically resected because it can be difficult to distinguish HP from neoplastic submucosal masses such as gastrointestinal stromal tumors. Although it is not very common, HP should be considered in the differential diagnosis when diagnosing extramucosal gastric masses to avoid unnecessary intervention. We review gastric HP with pathologic correlation to help with diagnosing HP on computed tomography.