Microsurgical treatment of posterior inferior cerebellar aneurysms based on angioarchitecture supplemented by high-resolution vessel wall MRI:a case series report

Background Surgical treatment of posterior inferior cerebellar artery(PICA)aneurysms is challenging because many are nonsaccular and atherosclerotic.We report our tailored approach to PICA aneurysms,which is based on angioarchitecture supplemented by high-resolution vessel wall MRI(HR-VW MRI)findings.Methods From March 2010 to September 2020,27 patients with 29 PICA aneurysms underwent surgical treatment in our institution.Since October 2016,HR-VW MRI has been used for aneurysmal wall assessment.Clinical characteristics,radiological data and surgical outcomes were analysed.Results Nineteen proximal PICA aneurysms(vertebral artery(VA),P1,P2 and P3)were treated using the far-lateral approach.Ten distal PICA aneurysms(P4,P5)were treated using the suboccipital midline approach.Direct clipping or clip reconstruction was achieved in 19 aneurysms.Ten were trapped in conjunction with extracranial-intracranial or intracranial-intracranial bypass,including three occipital artery-PICA reimplantations,three PICA-VA reimplantations,two PICA-PICA side-to side anastomoses,one PICA-PICA reimplantation and one PICA-PICA reanastomosis.All aneurysms were eventually completely obliterated and all bypasses remained patent.At the last follow-up,26 patients(96.2%)achieved a good outcome(modified Rankin Scale score<3).Eight patients underwent HR-VW MRI.Among these,the six aneurysms with focal wall enhancement required bypass and the two with negative enhancement were successfully clipped.Conclusion PICA aneurysms have a higher frequency of complex features such as large or giant size and fusiform or dissecting morphology.Favourable outcomes were achieved with individualised microsurgical strategies based on angioarchitecture.HR-VW MRI may be used as a promising technique to predict aneurysmal atherosclerosis.

Training time minimization for federated edge learning with optimized gradient quantization and bandwidth allocation

Training a machine learning model with federated edge learning(FEEL)is typically time consuming due to the constrained computation power of edge devices and the limited wireless resources in edge networks.In this study,the training time minimization problem is investigated in a quantized FEEL system,where heterogeneous edge devices send quantized gradients to the edge server via orthogonal channels.In particular,a stochastic quantization scheme is adopted for compression of uploaded gradients,which can reduce the burden of per-round communication but may come at the cost of increasing the number of communication rounds.The training time is modeled by taking into account the communication time,computation time,and the number of communication rounds.Based on the proposed training time model,the intrinsic trade-off between the number of communication rounds and per-round latency is characterized.Specifically,we analyze the convergence behavior of the quantized FEEL in terms of the optimality gap.Furthermore,a joint data-and-model-driven fitting method is proposed to obtain the exact optimality gap,based on which the closed-form expressions for the number of communication rounds and the total training time are obtained.Constrained by the total bandwidth,the training time minimization problem is formulated as a joint quantization level and bandwidth allocation optimization problem.To this end,an algorithm based on alternating optimization is proposed,which alternatively solves the subproblem of quantization optimization through successive convex approximation and the subproblem of bandwidth allocation by bisection search.With different learning tasks and models,the validation of our analysis and the near-optimal performance of the proposed optimization algorithm are demonstrated by the simulation results.