The 2019 World Health Organization (WHO) classification of gastrointestinal tumors defines well‑differentiated grade 3 neuroendocrine tumors, the mixed neuroendocrine‑non‑neuroendocrine tumors (MiNENs) and classifies goblet cell carcinoid as goblet cell adenocarcinoma. The expression of somatostatin receptors (SSTRs) is the foundation for somatostatin analogue therapy. At present, there are only a few studies that have analyzed the immunohistochemical reactivity of SSTRs in gastrointestinal neuroendocrine neoplasms (NENs). The aim of the present study was to evaluate the immunohistochemical expression of SSTR2 and SSTR5 in gastrointestinal NENs and goblet cell adenocarcinomas and the correlation of these markers with clinical and morphological factors. The study included 67 patients with NENs and 4 patients with adenocarcinoma ex‑goblet cell carcinoid diagnosed between January 2008 and December 2018. Tumors were reclassified according to the 2019 WHO classification. Immunohistochemical staining for chromogranin A, synaptophysin, Ki‑67, p53, SSTR2, and SSTR5 were performed in all the cases. The results showed that, G1 and G2 neuroendocrine tumors were more common SSTR2‑positive in comparison with G3 carcinomas (P<0.0001). In addition, 33.3% of neuroendocrine carcinomas and 2 cases of low‑grade adenocarcinoma ex‑goblet cell carcinoid were SSTR2‑positive. Neuroendocrine carcinomas had significantly lower SSTR2 and SSTR5 expression compared with well‑differentiated neuroendocrine tumors (P=0.0130; P=0.0437, respectively). The SSTR2 expression in the early tumor stages was 100%, more often than in advanced stages (55.6%; P=0.0011). The results demonstrated the decrease in SSTR2 expression with increasing malignancy and tumor stage. The SSTR2‑positive expression in neuroendocrine carcinomas and adenocarcinoma ex‑goblet cell carcinoid provides evidence for the benefits of somatostatin analog treatment associated with surgery and chemotherapy.

In the gastroenterology field, the impact of artificial intelligence was investigated for the purposes of diagnostics, risk stratification of patients, improvement in quality of endoscopic procedures and early detection of neoplastic diseases, implementation of the best treatment strategy, and optimization of patient prognosis. Computer-assisted diagnostic systems to evaluate upper endoscopy images have recently emerged as a supporting tool in endoscopy due to the risks of misdiagnosis related to standard endoscopy and different expertise levels of endoscopists, time-consuming procedures, lack of availability of advanced procedures, increasing workloads, and development of endoscopic mass screening programs. Recent research has tended toward computerized, automatic, and real-time detection of lesions, which are approaches that offer utility in daily practice. Despite promising results, certain studies might overexaggerate the diagnostic accuracy of artificial systems, and several limitations remain to be overcome in the future. Therefore, additional multicenter randomized trials and the development of existent database platforms are needed to certify clinical implementation. This paper presents an overview of the literature and the current knowledge of the usefulness of different types of machine learning systems in the assessment of premalignant and malignant esophageal lesions via conventional and advanced endoscopic procedures. This study makes a presentation of the artificial intelligence terminology and refers also to the most prominent recent research on computer-assisted diagnosis of neoplasia on Barrett’s esophagus and early esophageal squamous cell carcinoma, and prediction of invasion depth in esophageal neoplasms. Furthermore, this review highlights the main directions of future doctor–computer collaborations in which machines are expected to improve the quality of medical action and routine clinical workflow, thus reducing the burden on physicians.

Background and Objectives: This study aimed to assess the clinical-pathological profile of patients with invasive cutaneous melanomas and to identify the parameters with a prognostic role in the lymph nodal spread of this malignant tumor. Materials and Methods: We performed a retrospective study on patients with invasive cutaneous melanomas who underwent surgery in the “Pius Brînzeu” County Clinical Emergency Hospital from Timișoara, Romania, and were evaluated for the status of loco-regional lymph nodes. We selected and analyzed some parameters searching for their relationship with lymph node metastases. Results: We identified 79 patients with invasive cutaneous melanomas (29 men and 50 women, mean age 59.36 years). A percentage of 58.3% of melanomas had Breslow tumor thickness >2 mm; 69.6% of melanomas showed a Clark level IV–V. Tumor ulceration was present in 59.5% of melanomas. A mitotic rate of ≥5 mitoses/mm² was observed in 48.1% of melanomas. Tumor-infiltrating lymphocytes (TILs), non-brisk, were present in 59.5% of cases and 22.8% of patients had satellite/in-transit metastasis (SINTM). Tumor regression was identified in 44.3% of cases. Lymph nodes metastases were found in 43.1% of patients. Statistical analysis showed that lymph node metastases were more frequent in melanomas with Breslow thickness >2 mm (p = 0.0002), high Clark level (p = 0.0026), mitotic rate >5 mitoses/mm² (p = 0.0044), ulceration (p = 0.0107), lymphovascular invasion (p = 0.0182), SINTM (p = 0.0302), and non-brisk TILs (p = 0.0302). Conclusions: The Breslow thickness >2 mm, high Clark level, high mitotic rate and ulceration are the most important prognostic factors for lymph nodal spread in cutaneous melanomas. However, some melanomas without these clinical-pathological features can have an unexpected, aggressive evolution, which entails the necessity of close and prolonged clinical follow-up of patients, including those with lesions considered without risk.