Recent Outcomes and Challenges of Artificial Intelligence, Machine Learning, and Deep Learning in Neurosurgery

Awuah, Wireko Andrew; Adebusoye, Favour Tope; Wellington, Jack; David, Lian; Salam, Abdus; Weng Yee, Amanda Leong; Lansiaux, Edouard; Yarlagadda, Rohan; Garg, Tulika; Abdul-Rahman, Toufik; Kalmanovich, Jacob; Miteu, Goshen David; Kundu, Mrinmoy; Mykolaivna, Nikitina Iryna

doi:10.1016/j.wnsx.2024.100301

Cited by 11 publications

(2 citation statements)

References 77 publications

(107 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI-driven imaging overlays helped improve the percentages of gross total resections [ 31 ]. In neurosurgery, AR-related guidance systems allow surgeons to achieve more complete resection of intraparenchymal neoplasms [ 32 ]. In orthopedics, ARIO guidance has helped reduce intraoperative time and improve outcomes [ 33 ].…”

Section: Reviewmentioning

confidence: 99%

The Future of Artificial Intelligence in Surgery

Hamilton

2024

Cureus

View full text Add to dashboard Cite

Until recently, innovations in surgery were largely represented by extensions or augmentations of the surgeon’s perception. This includes advancements such as the operating microscope, tumor fluorescence, intraoperative ultrasound, and minimally invasive surgical instrumentation. However, introducing artificial intelligence (AI) into the surgical disciplines represents a transformational event. Not only does AI contribute substantively to enhancing a surgeon’s perception with such methodologies as three-dimensional anatomic overlays with augmented reality, AI-improved visualization for tumor resection, and AI-formatted endoscopic and robotic surgery guidance. What truly makes AI so different is that it also provides ways to augment the surgeon’s cognition. By analyzing enormous databases, AI can offer new insights that can transform the operative environment in several ways. It can enable preoperative risk assessment and allow a better selection of candidates for procedures such as organ transplantation. AI can also increase the efficiency and throughput of operating rooms and staff and coordinate the utilization of critical resources such as intensive care unit beds and ventilators. Furthermore, AI is revolutionizing intraoperative guidance, improving the detection of cancers, permitting endovascular navigation, and ensuring the reduction in collateral damage to adjacent tissues during surgery (e.g., identification of parathyroid glands during thyroidectomy). AI is also transforming how we evaluate and assess surgical proficiency and trainees in postgraduate programs. It offers the potential for multiple, serial evaluations, using various scoring systems while remaining free from the biases that can plague human supervisors. The future of AI-driven surgery holds promising trends, including the globalization of surgical education, the miniaturization of instrumentation, and the increasing success of autonomous surgical robots. These advancements raise the prospect of deploying fully autonomous surgical robots in the near future into challenging environments such as the battlefield, disaster areas, and even extraplanetary exploration. In light of these transformative developments, it is clear that the future of surgery will belong to those who can most readily embrace and harness the power of AI.

show abstract

Section: Reviewmentioning

confidence: 99%

The Future of Artificial Intelligence in Surgery

Hamilton

2024

Cureus

View full text Add to dashboard Cite

show abstract

“…While their review outlines current techniques, they suggest future research explore hybrid models combining deep learning with other methodologies to maximize effectiveness. Awuah et al [39] highlights AI's potential to enhance patient outcomes in neurosurgery by aiding neurosurgeons in diagnostics, prognostics, and surgical decision-making. AI, including machine learning and deep learning, has advanced significantly, reducing complications, improving surgical planning, and overall benefiting patient care in neurosurgery.…”

Section: Introductionmentioning

confidence: 99%

Enhancing EfficientNetv2 with global and efficient channel attention mechanisms for accurate MRI-Based brain tumor classification

Pacal,

Celik,

Bayram

et al. 2024

Cluster Comput

View full text Add to dashboard Cite

The early and accurate diagnosis of brain tumors is critical for effective treatment planning, with Magnetic Resonance Imaging (MRI) serving as a key tool in the non-invasive examination of such conditions. Despite the advancements in Computer-Aided Diagnosis (CADx) systems powered by deep learning, the challenge of accurately classifying brain tumors from MRI scans persists due to the high variability of tumor appearances and the subtlety of early-stage manifestations. This work introduces a novel adaptation of the EfficientNetv2 architecture, enhanced with Global Attention Mechanism (GAM) and Efficient Channel Attention (ECA), aimed at overcoming these hurdles. This enhancement not only amplifies the model’s ability to focus on salient features within complex MRI images but also significantly improves the classification accuracy of brain tumors. Our approach distinguishes itself by meticulously integrating attention mechanisms that systematically enhance feature extraction, thereby achieving superior performance in detecting a broad spectrum of brain tumors. Demonstrated through extensive experiments on a large public dataset, our model achieves an exceptional high-test accuracy of 99.76%, setting a new benchmark in MRI-based brain tumor classification. Moreover, the incorporation of Grad-CAM visualization techniques sheds light on the model’s decision-making process, offering transparent and interpretable insights that are invaluable for clinical assessment. By addressing the limitations inherent in previous models, this study not only advances the field of medical imaging analysis but also highlights the pivotal role of attention mechanisms in enhancing the interpretability and accuracy of deep learning models for brain tumor diagnosis. This research sets the stage for advanced CADx systems, enhancing patient care and treatment outcomes.

show abstract