Artificial Intelligence in Neurosurgery: A State-of-the-Art Review from Past to Future

Abstract

In recent years, there has been a significant surge in discussions surrounding artificial intelligence (AI), along with a corresponding increase in its practical applications in various facets of everyday life, including the medical industry. Notably, even in the highly specialized realm of neurosurgery, AI has been utilized for differential diagnosis, pre-operative evaluation, and improving surgical precision. Many of these applications have begun to mitigate risks of intraoperative and postoperative complications and post-operative care. This article aims to present an overview of the principal published papers on the significant themes of tumor, spine, epilepsy, and vascular issues, wherein AI has been applied to assess its potential applications within neurosurgery. The method involved identifying high-cited seminal papers using PubMed and Google Scholar, conducting a comprehensive review of various study types, and summarizing machine learning applications to enhance understanding among clinicians for future utilization. Recent studies demonstrate that machine learning (ML) holds significant potential in neuro-oncological care, spine surgery, epilepsy management, and other neurosurgical applications. ML techniques have proven effective in tumor identification, surgical outcomes prediction, seizure outcome prediction, aneurysm prediction, and more, highlighting its broad impact and potential in improving patient management and outcomes in neurosurgery. This review will encompass the current state of research, as well as predictions for the future of AI within neurosurgery.

Intra-Examiner Reliability and Validity of Sagittal Cervical Spine Mensuration Methods Using Deep Convolutional Neural Networks

“…The diagnosis and treatment of spine conditions have advanced with modern technology, and this technology has enabled advances in options for care. Digital radiography, computerized mensuration programs, and precision digitization tools are necessary to aid and reduce human error from both interventions and spine alignment diagnosis [14][15][16][17]. It has previously been shown that radiography mensuration techniques using analog tools such as pencils and protractors are repeatable, reliable, and valid with multiple investigations that show good inter-and intra-examinator agreement [42][43][44][45].…”

“…Technological advances in spine pain diagnosis and treatment are necessary to reduce cost, improve outcomes, increase efficiency for the facilities and clinicians as well as reduce poor outcomes that may require additional care [11][12][13]. Technology can make the process of spine condition diagnosis more efficacious [14][15][16]. For example, previously, we presented a machine learning deep convoluted neural network (DCNN or CNN) that demonstrated that computer vision (CV) is superior to human measurement of spine displacements [17].…”

Virtual Reality and 3D Simulation in the Treatment of Pediatric Patients with Central Nervous System Tumors

“…These systems allow for the reprocessing of imaging data and for better defining, through virtual reality (VR), the relationships between pathological tissue and normal nervous structures [16]. All these data can be integrated in real time with intraoperative navigation systems, and through augmented reality the surgeon can visualize an overlap between the direct intraoperative microscopic view and previously planned 3D visual data with consequent improvement of the intraoperative orientation, and lastly increased precision during the procedure [13,14,16]. Real life and virtual morphological data can therefore be matched to functional information obtained by intraoperative mapping and monitoring, further enhancing intraoperative orientation and preservation of neurological functions [20].…”

“…In the management of the pre-surgical and surgical phases, availability of detailed anatomical and functional planning tools allows for the performance of very complex procedures, ensuring an optimal sparing of neurological function [13,14].…”

“…Modern surgical practice has been developed with an excellent containment of functional risk; nonetheless, it offers an extraordinary growth potential [10,12,14]. Development of this potential includes innovative techniques and instruments that not only provide delicate neural tissue handling, but improvement of intraoperative and perioperative patient care and refinement of patient specific approaches.…”