Artificial intelligence (AI) and computer vision (CV) are beginning to impact medicine. While evidence on the clinical value of AI-based solutions for the screening and staging of colorectal cancer (CRC) is mounting, CV and AI applications to enhance the surgical treatment of CRC are still in their early stage. This manuscript introduces key AI concepts to a surgical audience, illustrates fundamental steps to develop CV for surgical applications, and provides a comprehensive overview on the state-of-the-art of AI applications for the treatment of CRC. Notably, studies show that AI can be trained to automatically recognize surgical phases and actions with high accuracy even in complex colorectal procedures such as transanal total mesorectal excision (TaTME). In addition, AI models were trained to interpret fluorescent signals and recognize correct dissection planes during total mesorectal excision (TME), suggesting CV as a potentially valuable tool for intraoperative decision-making and guidance. Finally, AI could have a role in surgical training, providing automatic surgical skills assessment in the operating room. While promising, these proofs of concept require further development, validation in multi-institutional data, and clinical studies to confirm AI as a valuable tool to enhance CRC treatment.

Pancreatic neuroendocrine tumors (PanNETs) display variable aggressive behavior. A major predictor of survival is tumor grade based on the Ki67 proliferation index. As information on transcriptomic profiles of PanNETs with different tumor grades is limited, we investigated 29 PanNETs (17 G1, 7 G2, 5 G3) for their expression profiles, mutations in 16 PanNET relevant genes and LINE-1 DNA methylation profiles. A total of 3050 genes were differentially expressed between tumors with different grades (p < 0.05): 1279 in G3 vs. G2; 2757 in G3 vs. G1; and 203 in G2 vs. G1. Mutational analysis showed 57 alterations in 11 genes, the most frequent being MEN1 (18/29), DAXX (7/29), ATRX (6/29) and MUTYH (5/29). The presence and type of mutations did not correlate with the specific expression profiles associated with different grades. LINE-1 showed significantly lower methylation in G2/G3 versus G1 tumors (p = 0.007). The expression profiles of matched primaries and metastasis (nodal, hepatic and colorectal wall) of three cases confirmed the role of Ki67 in defining specific expression profiles, which clustered according to tumor grades, independently from anatomic location or patient of origin. Such data call for future exploration of the role of Ki67 in tumor progression, given its involvement in chromosomal stability.

Aims: Between 11 to 14% of patients with locally advanced rectal cancer (LARC) have positive lateral pelvic lymph nodes (LPLN) at diagnosis, related to a worse prognosis with a 5-year survival rate between 30 to 40%. The best treatment choice for this group of patients is still a challenge. The optimal radiotherapy (RT) dose for LPLN patients has been investigated. Methods: We retrospectively collected data from LARC patients with LPLN at the primary staging MRI, treated in our center from March 2003 to December 2020. Patients underwent a neoadjuvant concomitant chemo-radiotherapy (CRT) treatment on the primary tumor (T), mesorectum, and pelvic nodes, associated with a fluoride-based chemotherapy. The total reached dose was 45 Gy at 1.8 Gy/fr on the elective sites and 55 Gy at 2.2 Gy/fr on the disease and mesorectum. Patients were divided in two groups based on whether they received a simultaneous integrated RT boost on the LPLN or not. Overall Survival (OS), Disease Free Survival (DFS), Metastasis Free Survival (MFS), and Local Control (LC) were evaluated in the whole group and then compared between the two groups. Results: A total of 176 patients were evaluated: 82 were included in the RT boost group and 94 in the non-RT boost group. The median follow-up period was 57.8 months. All the clinical endpoint (OS, DFS, MFS, LC), resulted were affected by the simultaneous integrated boost on LPLN with a survival rate of 84.7%, 79.5%, 84.1%, and 92%, respectively, in the entire population. From the comparison of the two groups, there was a statistical significance towards the RT boost group with a p < 0.006, 0.030, 0.042, 0.026, respectively. Conclusions: Concomitant radiotherapy boost on positive LPLN has shown to be beneficial on the survival outcomes (OS, DFS, MFR, and LC) in patients with LARC and LPLN. This analysis demonstrates that a higher dose of radiotherapy on positive pelvic lymph nodes led not only to a higher local control but also to a better survival rate. These results, if validated by future prospective studies, can bring a valid alternative to the surgery dissection without the important side effects and permanent disabilities observed during the years.

Background: The potential long-term survival benefits of surgical resection for synchronous liver-only metastases of pancreatic ductal adenocarcinoma (liver oligo-PDAC) remain controversial. This systematic review and meta-analysis aim to compare the current evidence on long-term survival outcomes between surgical treatment of liver oligo-PDAC and conventional systemic chemotherapy. Materials and methods: A systematic review and meta-analysis were conducted using the PubMed and Scopus databases to identify studies comparing surgery and systemic chemotherapy in terms of long-term survival in oligo-PDAC patients. The search included studies published up to October 2024. The meta-analysis was performed using the Jamovi software. Results: Eleven retrospective studies were selected for a total of 897 patients: 565(63%) underwent synchronous resection of liver metastases and the primary tumor, while 332(37%) received conventional chemotherapy. The majority of patients presented a pancreatic head tumor, and the median number of liver metastases ranged between 1 and 3 in the surgical cohort and 1 and 2 in the nonsurgical cohort. The rate of major surgical complications was 14.4% while the cumulative incidence of postoperative mortality was 2.8%. The median overall survival(OS) in the surgical group ranged from 7.6 to 18.4 months, while a lower value comprised between 6 and 9.9 months was evidenced in the nonsurgical cohort. Six studies were included in the meta-analysis for the OS evaluation, showing significantly better survival outcomes in the surgical group (OR: 0.286, 95% CI: 0.100–0.409; P < 0.0001). According to the Q-test, there was no significant heterogeneity in the true outcomes (Q = 4.063, P = 0.541, I ² = 0 %). A sensitivity analysis, conducted by excluding one study at a time, confirmed the robustness of the meta-analysis findings. Conclusions: Surgical resection of oligo-PDAC may represent a valuable treatment option with potential long-term survival benefits. However, prospective randomized trials are required to further validate these findings.

Pancreatic surgery is complex and associated with higher rates of morbidity and mortality compared to other abdominal surgeries. Over the past decade, the introduction of new technologies, such as minimally invasive approaches, improvements in multimodal treatments, advancements in anesthesia and perioperative care, and better management of complications, have collectively improved patient outcomes after pancreatic surgery. In particular, the adoption of Enhanced Recovery After Surgery (ERAS) recommendations has reduced hospital stays and improved recovery times, as well as post-operative outcomes. The aim of this narrative review is to highlight the surgeon’s perspective on the ERAS program for pancreatic surgery, with a focus on its potential advantages for perioperative functional recovery outcomes.

Purpose: Post-operative pancreatic fistula (POPF) remains the main complication after distal pancreatectomy (DP). The aim of this study is to evaluate the potential benefit of different durations of progressive stapler closure on POPF rate and severity after DP. Methods: Patients who underwent DP between 2016 and 2023 were retrospectively enrolled and divided into two groups according to the duration of the stapler closure: those who underwent a progressive compression for < 10 min and those for ≥ 10 min. Results: Among 155 DPs, 83 (53.5%) patients underwent pre-firing compression for < 10 min and 72 (46.5%) for ≥ 10 min. As a whole, 101 (65.1%) developed POPF. A lower incidence rate was found in case of ≥ 10 min compression (34–47.2%) compared to < 10 min compression (67- 80.7%) (p = 0.001). When only clinically relevant (CR) POPFs were considered, a prolonged pre-firing compression led to a lower rate (15–20.8%) than the < 10 min cohort (32–38.6%; p = 0.02). At the multivariate analysis, a compression time of at least 10 min was confirmed as a protective factor for both POPF (OR: 5.47, 95% CI: 2.16–13.87; p = 0.04) and CR-POPF (OR: 2.5, 95% CI: 1.19–5.45; p = 0.04) development. In case of a thick pancreatic gland, a prolonged pancreatic compression for at least 10 min was significantly associated to a lower rate of CR-POPF compared to < 10 min (p = 0.04). Conclusion: A prolonged pre-firing pancreatic compression for at least 10 min seems to significantly reduce the risk of CR-POPF development. Moreover, significant advantages are documented in case of a thick pancreatic gland.