The application of artificial intelligence (AI) is accelerating the paradigm shift towards patient-tailored brain tumor management, achieving optimal onco-functional balance for each individual. AI-based models can positively impact different stages of the diagnostic and therapeutic process. Although the histological investigation will remain difficult to replace, in the near future the radiomic approach will allow a complementary, repeatable and non-invasive characterization of the lesion, assisting oncologists and neurosurgeons in selecting the best therapeutic option and the correct molecular target in chemotherapy. AI-driven tools are already playing an important role in surgical planning, delimiting the extent of the lesion (segmentation) and its relationships with the brain structures, thus allowing precision brain surgery as radical as reasonably acceptable to preserve the quality of life. Finally, AI-assisted models allow the prediction of complications, recurrences and therapeutic response, suggesting the most appropriate follow-up. Looking to the future, AI-powered models promise to integrate biochemical and clinical data to stratify risk and direct patients to personalized screening protocols.

Purpose Traumatic elbow dislocation is the second most frequent joint dislocation, even though the elbow is a congruent and stable joint. Individual variability in anatomical congruence of the elbow and how it relates to simple or complex instability has rarely been studied in the literature; we hypothesized that a greater articular coverage by the humeral trochlea would be more likely to result in complex dislocation. The aim of this study is to analyze trochlear morphology in simple (SED) and complex elbow dislocation (CED), to assess whether the degree of humeroulnar joint congruence influences the incidence of coronoid fractures in elbow dislocation. The secondary goal is to evaluate the association between trochlear morphology and coronoid fracture pattern. Methods All the elbow CT scans of the hospital server were retrospectively analyzed. 62 patients were enrolled and so divided in 2 groups: SED and CED with isolated coronoid fracture. Patients who were skeletally immature, presented with other concomitant elbow fractures, or who previously underwent elbow surgery were excluded. The CT scans were performed after closed reduction and prior to further treatment. Coronoid fracture pattern was classified on CT scan according to Regan-Morrey and O’Driscoll classifications; “grade 0” was assigned to SED. Trochlear coverage was measured and expressed as three angles (anterior, posterior, and distal) and their width/depth ratios. Measurements were taken by four different readers and the assessment was repeated after 15 days. Results No statistically significant difference was found between humeral trochlear morphology of SED and CED patients. There was no association between morphometric measurements and coronoid fracture pattern. The results are strengthened by a good intra- and inter-reader reproducibility of the CT analysis protocol. Conclusions Our study is the first to evaluate the impact of trochlear morphology on elbow instability. Considering the results, other variables may have a greater impact on coronoid bone damage, such as trauma energy or ligamentous hyperlaxity: in particular, we believe that the capsuloligamentous structures of the elbow might contribute in a preponderant way to articular stability. The CT analysis protocol gave excellent results: reproducible, accurate and easy to perform. Level of evidence III.