Objectives: To assess the impact of an Artificial Intelligence (AI) limb bone fracture diagnosis software (AIS) on emergency department (ED) workflow and diagnostic accuracy. Materials and Methods: A retrospective study was conducted in two phases—without AIS (Period 1: 1 January 2020–30 June 2020) and with AIS (Period 2: 1 January 2021–30 June 2021). Results: Among 3720 patients (1780 in Period 1; 1940 in Period 2), the discrepancy rate decreased by 17% (p = 0.04) after AIS implementation. Clinically relevant discrepancies showed no significant change (−1.8%, p = 0.99). The mean length of stay in the ED was reduced by 9 min (p = 0.03), and expert consultation rates decreased by 1% (p = 0.38). Conclusions: AIS implementation reduced the overall discrepancy rate and slightly decreased ED length of stay, although its impact on clinically relevant discrepancies remains inconclusive. Key Point: After AI software deployment, the rate of radiographic discrepancies decreased by 17% (p = 0.04) but this was not clinically relevant (−2%, p = 0.99). Length of patient stay in the emergency department decreased by 5% with AI (p = 0.03). Bone fracture AI software is effective, but its effectiveness remains to be demonstrated.

Glial tumors represent the leading etiology of primary brain tumors. Their particularities lie in (i) their location in a highly functional organ that is difficult to access surgically, including for biopsy, and (ii) their rapid, anisotropic mode of extension, notably via the fiber bundles of the white matter, which further limits the possibilities of resection. The use of mathematical tools enables the development of numerical models representative of the oncotype, genotype, evolution, and therapeutic response of lesions. The significant development of digital technologies linked to high-resolution NMR exploration, coupled with the possibilities offered by AI, means that we can envisage the creation of digital twins of tumors and their host organs, thus reducing the use of physical sampling.

Background: Gliomas, including the most severe form known as glioblastomas, are primary brain tumors arising from glial cells, with significant impact on adults, particularly men aged 45 to 70. Recent advancements in the WHO (World Health Organization) classification now correlate genetic markers with glioma phenotypes, enhancing diagnostic precision and therapeutic strategies. Aims and Methods: This scoping review aims to evaluate the current state of deep learning (DL) applications in the genetic characterization of adult gliomas, addressing the potential of these technologies for a reliable virtual biopsy. Results: We reviewed 17 studies, analyzing the evolution of DL algorithms from fully convolutional networks to more advanced architectures (ResNet and DenseNet). The methods involved various validation techniques, including k-fold cross-validation and external dataset validation. Conclusions: Our findings highlight significant variability in reported performance, largely due to small, homogeneous datasets and inconsistent validation methods. Despite promising results, particularly in predicting individual genetic traits, the lack of robust external validation limits the generalizability of these models. Future efforts should focus on developing larger, more diverse datasets and integrating multidisciplinary collaboration to enhance model reliability. This review underscores the potential of DL in advancing glioma characterization, paving the way for more precise, non-invasive diagnostic tools. The development of a robust algorithm capable of predicting the somatic genetics of gliomas or glioblastomas could accelerate the diagnostic process and inform therapeutic decisions more quickly, while maintaining the same level of accuracy as the traditional diagnostic pathway, which involves invasive tumor biopsies.

Background The presence of a coincident intracranial aneurysm (CIA) on the target vessel of patients undergoing mechanical thrombectomy (MT) for acute ischemic stroke (AIS) poses challenges, as the benefits and risks of the procedure in this scenario remain unclear. This study aimed to evaluate the efficacy and safety of MT in AIS cases with a CIA on the target vessel. Methods We retrospectively analyzed data from 14 stroke centers in France and Switzerland between January 2015 and January 2023. We identified AIS cases with CIA on the target vessel treated with MT. The control population was constituted from the ETIS registry (Endovascular Treatment in Ischemic Stroke), including AIS patients treated with MT in the same centers during the same period, and were matched (1:4) on age (±1 year) and sex. The primary outcome was favorable functional status at 3 months, defined as a modified Rankin Scale (mRS) score ≤2 or equal to pre-stroke mRS. Results A total of 104 MT-treated patients with at least one CIA on the target vessel and 416 MT-treated patients without CIA were analyzed. Despite an aneurysm rupture occurring in 5.8% of cases, no significant differences were observed in favorable functional outcome at 3 months between the CIA and control groups (42.4% vs 41.0%; adjusted OR 1.20, 95% CI 0.72 to 1.97). Similarly, recanalization rates (modified Thrombolysis In Cerebral Infarction (mTICI) ≥2b at end of MT) did not differ significantly (90.0% vs 85.9%; adjusted OR 1.75, 95% CI 0.77 to 3.95). Conclusion MT is an effective option for AIS patients, even with CIA on the target vessel, but the risk of rupture underscores the need for procedural planning. Future studies should further explore size and location criteria to optimize patient selection and orientation.

Most human physiological processes follow circadian rhythms such as glucose metabolism and neuronal activity, thereby playing a major role in brain metabolism regulation. Proton Magnetic Resonance Spectroscopy (¹H-MRS) has become a valuable tool for quantification of brain metabolism in clinical settings. Nonetheless, only limited evidence of brain metabolism variation throughout the day has been found, restricted to specific brain regions or limited by a sample size. The aim of this study was to investigate time-of-day effect on brain metabolism in ¹H-MRS of different brain regions associated with circadian rhythms in healthy adults. This prospective monocentric study included 39 healthy volunteers aged between 25 and 40 years. They underwent three 3T MRI examinations the same day at 7:30, 13:30 and 17:30. Two CSI MRS sequences were acquired to study brain regions of the basal ganglia and semi-oval center. A linear mixed model was used to investigate differences between session times, sex and brain hemisphere on acquired total Choline (tCho), total N-Acetyl-Aspartate (tNAA), and Lactate (Lac). Models showed a significant decrease in tCho/tNAA in the last session of -1.60% (p = 0.017) and a lower value of tCho/tCr of -9.74% (p = 0.014) and tCho/tNAA of -7.98% (p = 0.044) for women as compared with men. In the right hemisphere a higher value of tNAA/tCr of +2.84% (p < 0.001) was found, while tCho/tNAA was lower by -1.60% (p = 0.003) compared to the left hemisphere. The metabolite ratios under investigation were not affected by circadian rhythms, except for a small decrease of tCho/tNAA at 17:30. However, sex and brain hemispheres had a significant impact on brain metabolism. While brain MRS examination for most common metabolites could be carried out at any time of day, it is still important to consider the patient's sex and the side of the brain being examined.