Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.

Computational competitions are the standard for benchmarking medical image analysis algorithms, but they typically use small curated test datasets acquired at a few centers, leaving a gap to the reality of diverse multicentric patient data. To this end, the Federated Tumor Segmentation (FeTS) Challenge represents the paradigm for real-world algorithmic performance evaluation. The FeTS challenge is a competition to benchmark (i) federated learning aggregation algorithms and (ii) state-of-the-art segmentation algorithms, across multiple international sites. Weight aggregation and client selection techniques were compared using a multicentric brain tumor dataset in realistic federated learning simulations, yielding benefits for adaptive weight aggregation, and efficiency gains through client sampling. Quantitative performance evaluation of state-of-the-art segmentation algorithms on data distributed internationally across 32 institutions yielded good generalization on average, albeit the worst-case performance revealed data-specific modes of failure. Similar multi-site setups can help validate the real-world utility of healthcare AI algorithms in the future.

A case of a multisegmental, cervicothoracolumbar epidural abscess, in an 80-year-old man, successfully decompressed by using a minimally invasive technique, is presented. To review risk factors, diagnosis, treatment, decompression techniques, and morbidity and mortality regarding spinal epidural abscess. Extended spinal epidural abscess is a rate entity. To our knowledge, this is the first report of a multilevel spinal epidural abscess, completely decompressed by limited laminectomies in combination with the use of a silicon catheter, epidurally. The clinical and radiographic features associated with spinal epidural abscess, as well as decompression technique, are presented. The 80-year-old man, with a one week history of urinary tract infection, presented with fever and low back pain, mild weakness in his legs and jaundice. He underwent bilateral limited laminectomies at T2–T3 and a right hemilaminectomy at L1–L2 and the pus was drained, under mild continuous suction, using a 2.7 mm outer and 1.3 mm inner diameter silicon catheter, inserted caudally and cranially into the epidural space, at both the laminectomy sites. The patient experienced immediate relief of the low back pain, gradual fever subsidence and full neurological recovery during the next 3 weeks. In cases of suspected acute epidural abscess, especially in elderly debilitating patients: the whole spine should be scanned by MRI to exclude the possibility of multilevel involvement and adequate pus drainage, when indicated, could be performed with the above described minimally invasive technique.

The aim of this retrospective study was twofold: (1) to show the role of multi-detector computed tomography angiography (MDCTA) in the evaluation of intracranial arterial anatomic variations; (2) to highlight their clinical importance with illustrated example cases.

We present an update of the literature concerning long-term neuropsychological outcomes following surgery for refractory temporal lobe epilepsy (TLE). A thorough search was conducted through the PubMed and Medline electronic databases for studies investigating neuropsychological function in adult patients undergoing resective TLE surgery and followed for a mean/median > five years period. Two independent reviewers screened citations for eligibility and assessed relevant studies for the risk of bias. We found eleven studies fulfilling the above requirements. Cognitive function remained stable through long-term follow up despite immediate post-surgery decline; a negative relation between seizure control and memory impairment has emerged and a possible role of more selective surgery procedures is highlighted.