Shifted-windows transformers for the detection of cerebral aneurysms in microsurgery

Jinfan Zhou, William Muirhead, Simon C. Williams, Danail Stoyanov, Hani J. Marcus, Evangelos B. Mazomenos

Abstract: Microsurgical Aneurysm Clipping Surgery (MACS) carries a high risk for intraoperative aneurysm rupture. Automated recognition of instances when the aneurysm is exposed in the surgical video would be a valuable reference point for neuronavigation, indicating phase transitioning and more importantly designating moments of high risk for rupture. This article introduces the MACS dataset containing 16 surgical videos with frame-level expert annotations and proposes a learning methodology for surgical scene understanding identifying video frames with the aneurysm present in the operating microscope’s field-of-view.