Background: The fecal immunochemical test (FIT) is widely implemented as a first‐line tool in organized colorectal cancer (CRC) screening programs, including Italy. Following a positive FIT, colonoscopy is recommended. Computer‐aided detection (CADe) systems have the potential to enhance adenoma detection, particularly in FIT‐positive populations where identifying advanced adenomas is critical for cancer prevention. This study evaluated the diagnostic performance of CADe‐assisted colonoscopy versus standard colonoscopy (SC) in a FIT‐based screening cohort. Methods: In this multicenter, randomized controlled trial, patients with a positive FIT result were randomized to undergo either CADe‐assisted or standard colonoscopy. The primary endpoint was the advanced adenoma detection rate (AADR). Secondary endpoints included overall adenoma detection rate (ADR), adenomas per colonoscopy (APC), and mean withdrawal time (WT). Results: Of 1077 patients enrolled, 68 were excluded due to inadequate bowel preparation, leaving 1009 patients for analysis (CADe: n = 506; SC: n = 503). AADR was comparable between the groups (21.3% vs. 20.5%, p = 0.794). However, CADe significantly improved ADR (67.6% vs. 59.8%, p = 0.012) and APC (1.82 ± 2.12 vs. 1.34 ± 1.81, p < 0.001). Mean WT was longer in the CADe group (17.10 ± 8.28 min vs. 16.13 ± 8.28 min, p = 0.016). Conclusions: In a FIT‐based organized CRC screening setting, CADe did not enhance detection of AADR with a modest increase in withdrawal time. NCT04441580.

Together with Granulicatella spp., A. defectiva was formerly classified within the group of nutritionally variant streptococci (NVS). NVS-related endocarditis has been associated with higher rates of complications, bacteriological failure, and mortality compared to other streptococci, partially due to challenges related to timely and accurate identification. PJI caused by A. defectiva are rarely reported, and standardized management strategies have not yet been established. We describe a case of a 68-year-old man with concomitant A. defectiva PJI and native mitral valve endocarditis. The patient was managed conservatively for endocarditis and subsequently underwent a two-stage arthroplasty of the infected prosthetic knee. A. defectiva was identified using MALDI-TOF mass spectrometry on both synovial fluid and blood cultures. As penicillin susceptibility data were not available, the patient was treated with vancomycin at a dose of 2 g/day, resulting in a favorable clinical response. In addition, we performed a literature review on A. defectiva and Granulicatella PJI. Despite the limited number of reported cases in the literature, the findings suggest a potential correlation between clinical outcomes and antimicrobial treatment duration. Further comprehensive studies are needed to establish standardized management strategies for A. defectiva and Granulicatella PJI.

Perioptic meningiomas pose a therapeutic challenge due to their proximity to critical visual structures. Single-fraction stereotactic radiosurgery is known to effectively control the growth of meningiomas, but this subgroup carries the risk of optic neuropathy, which is minimized with the introduction of dose hypofractionation. The Leksell Gamma Knife Icon has perfected fractionated stereotactic radiosurgery, maintaining submillimeter accuracy in each dose fraction without the need for an invasive frame. This study analyzes the feasibility, safety, and efficacy of multi-fraction Gamma Knife Icon radiosurgery for perioptic meningiomas, taking into account tumor control rates, visual preservation, and treatment-related toxicity. We conducted a retrospective analysis of 100 patients with a perioptic meningioma treated with fractionated Gamma Knife Icon radiosurgery between September 2017 and December 2022. A total of 80 Patients were female, and 20 were male; the mean age was 61.7 years (range 35–84). The most frequent anatomical locations included: cavernous sinus (35 pts), anterior clinoid (17 pts), sphenoid wing (14 pts) and olfactory groove (11 pts). The median tumor volume was 5.6 mL (range 0.12–31.7 mL). Most patients (89%) received 25 Gy in five fractions. Tumor control was achieved in 98% of cases, with a mean radiological follow-up of 41.2 months. Tumor volume did not predict radiological shrinkage (p = 0.639). Tumor shrinkage was observed more frequently in the no prior surgery group (p = 0.035). The mean clinical follow-up was 45.3 months. Among symptomatic patients (35 pts) at baseline, symptoms remained stable in 27 (77%) cases, improved in 5 (14%), and worsened in 3 (9%). No new symptoms were observed in asymptomatic patients. Overall clinical deterioration occurred in three (3%) patients—one because of tumor progression; although, without statistical evidence (p = 0.217), worsened patients had notable larger mean tumor volumes (12.6 mL vs. 6.8 mL). The dosimetric advantages of Gamma Knife technology are empowered by the biological benefits of fractionation and the convenience of non-invasive immobilization. Excellent tumor control rates and positive visual outcomes favor its routine application in properly selected patients.

Artificial intelligence (AI) has revolutionized medical image analysis. Several neural network (NN) architectures were developed and applied across the last decade, becoming essential for automated diagnosis and clinical applications. AI based on NNs has become increasingly integrated into gastroenterology, offering new opportunities for automated lesion detection and workflow optimization. Small-bowel capsule endoscopy (SBCE) has benefited substantially from these advances, addressing long-standing challenges such as time-consuming video review and variability among readers. This systematic review and meta-analysis evaluated neural network-based models for lesion detection in SBCE, assessing pooled diagnostic accuracy and the impact of AI on reading time. A total of 44 primary studies were included: 36 validation studies for accuracy and 9 clinical studies for reading time. All NN architectures demonstrated high diagnostic performance, with a pooled accuracy of 95.3% (95% CI: 94.1–96.5%). More recent architectures, including transformer-based and capsule networks, outperformed classical convolutional neural networks (CNNs). AI assistance significantly reduced SBCE reading time, with a pooled mean reduction of 84% compared to standard review. These findings highlight the strong potential of AI to enhance SBCE efficiency and diagnostic reliability.