Introduction

Heterotopic pancreas (HP), also known as “ectopic pancreas”, is defined as pancreatic tissue lacking anatomic or vascular continuity with the main body of the gland [1, 2]. Although HPs can be up to 5.0 cm in size, almost 80% lesions are smaller than 3 cm [3,4,5,6]. They were often incidentally found on the upper gastrointestinal system, specifically the stomach, duodenum, and proximal jejunum in around 0.5–13.7% of corpses or 0.2–0.9% of abdominal surgeries [3, 4, 7]. In fact, the true prevalence of HP is difficult to assess as most patients are asymptomatic [8]. Invasive operations for a confirmative diagnosis as well as surgery are generally not recommended [9, 10]. But some larger lesions, or lesions in specific locations (e.g., duodenum papilla), could cause complications similar to those of the normal pancreas such as pancreatitis, pancreatic pseudocysts and even malignancy, or symptoms such as abdominal pain, bleeding and obstruction [1, 8, 11]. Additionally, malignant transformation of HP is extremely rare, and there are only sporadic case reports available in the literature [1, 12, 13].

Since HP more often manifests as a gastrointestinal submucosal lesion, it might be empirically misdiagnosed as gastrointestinal mesenchymal tumors (GIST), the true and most common submucosal tumor [14, 15]. Unlike HP, the biological behavior of GIST is complex and demonstrates varying malignant potential, including recurrences and metastasis [16,17,18]. Surgery for GISTs was more focused on the risk class rather than just the size or location of the entities [18, 19], and patients often choose regular follow-up visits or surgeries.

In terms of radiologic appearance, gastrointestinal HP and GIST have many overlap** features, and smaller lesions are harder to identify [2, 20]. Computed tomography (CT), as a non-invasive and common imaging examination method, has been emphasized for preoperative diagnosis of HP lesions and differentiation it from GIST [2, 4, 9, 11, 20,21,22,23]. Furthermore, the application of artificial intelligence, machine learning and deep learning in radiological imaging has been progressively investigated so far [24,25,20] removed the complete cystic HPs, in fact there were also 2 cases of cystic GIST in our study, and no statistical differences was found in image type between the two lesions finally. Other CT features, including ill-defined border, microlobulated appearance [30], presence of low intralesional attenuation and enhancement pattern [22, 30], were also associated with lobular architecture or dilated residual duct of HP [2, 4, 6], and were deduced by prior studies to be distinctive signs of HP. Yet they had not statistically significant difference or were just relevant predictors in our series. Due to HP likely extending to the muscularis propria or the entire wall of gastrointestinal tract [31, 35], we propose “peritumoral hypodensity line” to describe the relationship between the lesion and the peripheral gastrointestinal wall, which could reveal lesions as clear submucosal lesions or represented fat space between the extraluminal lesion and serosal layer (Fig. 2D). It was included in the RF model finally.

Duct-like structure was found to be a significant CT feature with secondary importance in the nomogram, which was referred to a central umbilication located at the mucosa of the lesion, corresponding to the rudimentary duct of the HP as seen in histologic specimens [30, 34]. T2-weighted MR images and magnetic resonance cholangiopancreatographic (MRCP) (Fig. 3B) images are best for confirming a dilated duct in HP, which is also referred to as the “ectopic duct” sign [4, 8, 11]. This sign was not included in the RF model. We infer that this sign, while unique to the ectopic pancreas, was relatively difficult to be observed. Only 7 of 48 HPs were detected this CT morphologic feature in this study, with 2 located in the lower part of stomach, 3 in the duodenum, and 2 in the jejunum or ileum, respectively. We inferred from this that the sign was easier to discern in the small intestine, similar to some previous reports [5, 30]. In addition, the trend in the age distribution of HP and GIST is consistent with most of the studies we’ve seen.

Our study has several limitations. First, the retrospective design may have introduced inherent selection bias, although our patients were enrolled from two institutions. Second, due to the long period of follow-up, different CT machines and protocols were used, which might influence the quantitative analysis. Third, due to the use of lesions LD less than 3 cm in the inclusion criterion, we excluded a great proportion of GISTs. Fourth, the size of our study population was small, especially for HP, and thus the stability of the model may be affected and the false-positive rates may increase.

Conclusion

In brief, two convenient and efficient models based on CT signs was established using nomogram and machine learning method, and could be valuable for discriminating gastrointestinal HP from GIST in clinical practice. Both models have excellent diagnostic prediction performance, although prospective studies with larger sample sizes will be required to confirm these results.