Search

This article analyses the literature regarding the value of computer-assisted systems in esogastroduodenoscopy-quality monitoring and the assessment of gastric lesions. Current data show promising results in upper-endoscopy quality control and a satisfactory detection accuracy of gastric premalignant and malignant lesions, similar or even exceeding that of experienced endoscopists. Moreover, artificial systems enable the decision for the best treatment strategies in gastric-cancer patient care, namely endoscopic vs surgical resection according to tumor depth. In so doing, unnecessary surgical interventions would be avoided whilst providing a better quality of life and prognosis for these patients. All these performance data have been revealed by numerous studies using different artificial intelligence (AI) algorithms in addition to white-light endoscopy or novel endoscopic techniques that are available in expert endoscopy centers. It is expected that ongoing clinical trials involving AI and the embedding of computer-assisted diagnosis systems into endoscopic devices will enable real-life implementation of AI endoscopic systems in the near future and at the same time will help to overcome the current limits of the computer-assisted systems leading to an improvement in performance. These benefits should lead to better diagnostic and treatment strategies for gastric-cancer patients. Furthermore, the incorporation of AI algorithms in endoscopic tools along with the development of large electronic databases containing endoscopic images might help in upper-endoscopy assistance and could be used for telemedicine purposes and second opinion for difficult cases.

Despite a decrease in gastric cancer incidence, the development of novel biologic agents and combined therapeutic strategies, the prognosis of gastric cancer remains poor. Recently, the introduction of modern immunotherapy, especially using immune checkpoint inhibitors, led to an improved prognosis in many cancers. The use of immunotherapy was also associated with manageable adverse event profiles and promising results in the treatment of patients with gastric cancer, especially in heavily pretreated patients. These data have led to an accelerated approval of some checkpoint inhibitors in this setting. Understanding the complex relationship between the host immune microenvironment and tumor and the immune escape phenomenon leading to cancer occurrence and progression will subsequently lead to the identification of prognostic immune markers. Furthermore, this understanding will result in the discovery of both new mechanisms for blocking tumor immunosuppressive signals and pathways to stimulate the local immune response by targeting and modulating different subsets of immune cells. Due to the molecular heterogeneity of gastric cancers associated with different clinico-biologic parameters, immune markers expression and prognosis, novel immunotherapy algorithms should be personalized and addressed to selected subsets of gastric tumors, which have been proven to elicit the best clinical responses. Future perspectives in the treatment of gastric cancer include tailored dual immunotherapies or a combination of immunotherapy with other targeted agents with synergistic antitumor effects.

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.

Malignant vascular tumors of the liver include rare primary hepatic mesenchymal tumors developed in the background of a normal liver parenchyma. Most of them are detected incidentally by the increased use of performing imaging techniques. Their diagnosis is challenging, involving clinical and imaging criteria, with final confirmation by histology and immunohistochemistry. Surgery represents the mainstay of treatment. Liver transplantation (LT) has improved substantially the prognosis of hepatic epithelioid hemangioendothelioma (HEHE), with 5-year patient survival rates of up to 81%, based on the European Liver Intestine Transplantation Association-European Liver Transplant Registry study. Unfortunately, the results of surgery and LT are dismal in cases of hepatic angiosarcoma (HAS). Due to the disappointing results of very short survival periods of approximately 6-7 mo after LT, because of tumor recurrence and rapid progression of the disease, HAS is considered an absolute contraindication to LT. Recurrences after surgical resection are high in cases of HEHE and invariably present in cases of HAS. The discovery of reliable prognostic markers and the elaboration of prognostic scores following LT are needed to provide the best therapeutic choice for each patient. Studies on a few patients have demonstrated the stabilization of the disease in a proportion of patients with hepatic vascular tumors using novel targeted antiangiogenic agents, cytokines or immunotherapy. These new approaches, alone or in combination with other therapeutic modalities, such as surgery and classical chemotherapy, need further investigation to assess their role in prolonging patient survival. Personalized therapeutic algorithms according to the histopathological features, behavior, molecular biology and genetics of the tumors should be elaborated in the near future for the management of patients diagnosed with primary malignant vascular tumors of the liver.