Convolutional Neural Network Model for Intestinal Metaplasia Recognition in Gastric Corpus Using Endoscopic Image Patches.

Gastric cancer (GC) is a significant healthcare concern, and the identification of high-risk patients is crucial. Indeed, gastric precancerous conditions present significant diagnostic challenges, particularly early intestinal metaplasia (IM) detection. This study developed a deep learning system to assist in IM detection using image patches from gastric corpus examined using virtual chromoendoscopy in a Western country. Utilizing a retrospective dataset of endoscopic images from Sant'Andrea University Hospital of Rome, collected between January 2020 and December 2023, the system extracted 200 × 200 pixel patches, classifying them with a voting scheme. The specificity and sensitivity on the patch test set were 76% and 72%, respectively. The optimization of a learnable voting scheme on a validation set achieved a specificity of 70% and sensitivity of 100% for entire images. Despite data limitations and the absence of pre-trained models, the system shows promising results for preliminary screening in gastric precancerous condition diagnostics, providing an explainable and robust Artificial Intelligence approach.

Autoimmune Gastritis and Hypochlorhydria: Known Concepts from a New Perspective.

Autoimmune atrophic gastritis is an immune-mediated disease resulting in autoimmune destruction of the specialized acid-producing gastric parietal cells. As a consequence, in autoimmune atrophic gastritis, gastric acid secretion is irreversibly impaired, and the resulting hypochlorhydria leads to the main clinical manifestations and is linked, directly or indirectly, to the long-term neoplastic complications of this disease. In the last few years, autoimmune atrophic gastritis has gained growing interest leading to the acquisition of new knowledge on different aspects of this disorder. Although reliable serological biomarkers are available and gastrointestinal endoscopy techniques have substantially evolved, the diagnosis of autoimmune atrophic gastritis is still affected by a considerable delay and relies on histopathological assessment of gastric biopsies. One of the reasons for the diagnostic delay is that the clinical presentations of autoimmune atrophic gastritis giving rise to clinical suspicion are very different, ranging from hematological to neurological-psychiatric up to gastrointestinal and less commonly to gynecological-obstetric symptoms or signs. Therefore, patients with autoimmune atrophic gastritis often seek advice from physicians of other medical specialties than gastroenterologists, thus underlining the need for increased awareness of this disease in a broad medical and scientific community.