MENG-01 ENHANCING DECISION-MAKING IN SURGERY FOR A LARGE RIGHT TEMPOROCORNEAL MENINGIOMA THROUGH AN EXPLAINABLE HUMAN-AI COLLABORATION: A CASE REPORT

Abstract

Abstract Meningiomas, particularly large right temporocorneal meningiomas, present significant surgical challenges due to their proximity to critical brain structures. Optimal tumor resection while minimizing neurological deficits requires advanced decision-making strategies. This case report explores the integration of an explainable artificial intelligence (AI) system into neurosurgical workflows to enhance preoperative planning, intraoperative decision-making, and postoperative outcome prediction. A 48-year-old Arabic female presented with a one-year history of right-lateralized headaches that later generalized, accompanied by frequent episodes of transient loss of consciousness lasting 15–45 minutes. These episodes included palpitations, chest tightness, urinary incontinence, and prolonged postictal states. Neurological examination was unremarkable, with intact motor and sensory functions. Initially diagnosed with epilepsy in Algeria, she was prescribed multiple antiepileptic drugs. However, further evaluation in Belgium, including MRI and EEG, revealed a right temporal extra-axial mass (46 × 36×45 mm) suggestive of meningioma. Normal EEG findings indicated that her episodes were psychogenic non-epileptic seizures (PNES) rather than epilepsy. A multidisciplinary approach incorporating AI-assisted imaging analysis and predictive modeling was utilized to refine surgical planning. The AI system provided insights into tumor segmentation, vascular involvement, and risk assessment, enabling an optimal resection trajectory. The patient underwent a right pterional craniotomy with total tumor excision, preserving neurological function. Significant intraoperative bleeding (2L) occurred, but her postoperative course was favorable. Antiepileptic medication withdrawal was initiated, and no recurrent seizures were reported. This case underscores the utility of explainable AI in improving neurosurgical decision-making, particularly in preoperative planning and intraoperative execution. It also highlights the diagnostic complexity of seizure-like episodes in intracranial tumors, emphasizing the importance of differentiating PNES from epilepsy to prevent unnecessary long-term antiepileptic treatment. A multidisciplinary approach remains essential in optimizing patient outcomes.

Ähnliche Arbeiten