HER2 testing represents a cornerstone of the treatment algorithm in advanced gastric and gastroesophageal junction adenocarcinoma (GC), yet its evaluation remains complex due to tumor heterogeneity and methodological variability. Unlike breast cancer, HER2 expression in GC is often incomplete and heterogeneous, resulting in discordant results between biopsies, resections, and metastatic sites. Both spatial and temporal HER2 heterogeneity are key determinants of testing reproducibility, diagnostic accuracy, and treatment selection and response in GC. Optimizing sampling through multiple, well-targeted biopsies, standardizing IHC/ISH protocols, and reassessing HER2 status at progression may be crucial steps to ensure diagnostic accuracy. The recognition of HER2-low disease introduces a new pathological and clinical subgroup of GC with potential sensitivity to antibody–drug conjugates, while emerging techniques such as circulating tumor DNA analysis are increasingly applied to detect HER2 amplification and co-existing genetic alterations. Integrating molecular tools and standardized reassessment strategies can enhance HER2 testing reliability and enable more precise treatment strategies, with the potential to minimize HER2 resistance mechanisms. This review provides a practice-oriented guide on the interpretation and optimization of HER2 testing in gastric cancer, while providing insight into the underlying molecular mechanisms driving heterogeneity and resistance.
Ovarian cancer is the deadliest gynecologic malignancy worldwide, with a 5-year overall survival rate of approximately 49%. Although complete resection is associated with the most favorable prognosis following primary debulking surgery, accurately assessing tumor resectability at diagnosis remains a major clinical challenge. We propose a decision support system (DSS) designed to predict residual tumor after primary debulking surgery, based on clinical and imaging data available at diagnosis. The system was developed and validated using a retrospective cohort of 465 patients with high-grade serous ovarian cancer, collected at the European Institute of Oncology in Milan, Italy. We developed a deep learning (DL) model that combines pre-trained Vision Transformer encoders with an attention mechanism and a classification head. When evaluated on an independent test cohort of 75 cases, our best-performing model achieved an area under the curve (AUC) of 0.80 (95% CI: 0.68–0.89) and a recall of 0.86 (95% CI: 0.71–0.97), demonstrating discriminatory ability with a particularly low rate of false negatives. Clinically, the model correctly identified 24 out of 28 patients (86%) with non-resectable disease, who would not have benefited from primary debulking surgery. Notably, within this subgroup, the model accurately predicted 93% (13 out of 14) of cases in which surgery was aborted intraoperatively due to unforeseen unresectable disease. These findings suggest that the model could have potential in preventing unnecessary and inappropriate surgical interventions. The proposed DSS is a fully automated, DL–based system for predicting tumor resectability at diagnosis, without the need for manual segmentation or expert evaluation of radiological features and structured clinical parameters. This approach could facilitate and accelerate personalized treatment planning in ovarian cancer. The work is part of the project Under-XAI: understanding ovarian cancer initiation and progression through explainable AI. Project code: PNRR-MAD-2022-12376574.
8 February 2026 in International Journal of Gynecological Cancer
University students with cancer in Italy face major barriers in maintaining their academic pathways despite existing disability legislation. This brief communication combines an overview of the Italian legal and institutional context with findings from a community‐led qualitative descriptive needs‐assessment. Following a national social media call, the analysis included semi‐structured interviews with 69 eligible participants. Interviews were documented through contemporaneous written notes and analyzed manually using descriptive content analysis, combining domains from the interview guide with recurrent categories identified in open‐ended responses. Participants described administrative burdens, inconsistent recognition of cancer‐related needs, limited access to remote learning and flexible examinations, marked variability in university support, emotional distress, and social isolation. These findings provide preliminary real‐world evidence of how existing arrangements are experienced by Italian university students affected by cancer. Although specific interventions were not evaluated, the findings may inform the development and prospective assessment of more consistent academic accommodations, accessible information, individualized support, and integrated psychosocial services.