Browsing by Author "Patel, Neal"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Image Segmentation of Operative Neuroanatomy Into Tissue Categories Using a Machine Learning Construct and Its Role in Neurosurgical Training
    (Wolters Kluwer, 2022) Witten, Andrew J.; Patel, Neal; Cohen-Gadol, Aaron; Neurological Surgery, School of Medicine
    Background: The complexity of the relationships among the structures within the brain makes efficient mastery of neuroanatomy difficult for medical students and neurosurgical residents. Therefore, there is a need to provide real-time segmentation of neuroanatomic images taken from various perspectives to assist with training. Objective: To develop the initial foundation of a neuroanatomic image segmentation algorithm using artificial intelligence for education. Methods: A pyramidal scene-parsing network with a convolutional residual neural network backbone was assessed for its ability to accurately segment neuroanatomy images. A data set of 879 images derived from The Neurosurgical Atlas was used to train, validate, and test the network. Quantitative assessment of the segmentation was performed using pixel accuracy, intersection-over-union, the Dice similarity coefficient, precision, recall, and the boundary F1 score. Results: The network was trained, and performance was assessed class wise. Compared with the ground truth annotations, the ensembled results for our artificial intelligence framework for the pyramidal scene-parsing network during testing generated a total pixel accuracy of 91.8%. Conclusion: Using the presented methods, we show that a convolutional neural network can accurately segment gross neuroanatomy images, which represents an initial foundation in artificial intelligence gross neuroanatomy that will aid future neurosurgical training. These results also suggest that our network is sufficiently robust, to an unprecedented level, for performing anatomic category recognition in a clinical setting.
  • Thumbnail Image
    Item
    Innovative Skills Development in Medical Students Through Neonatal Intubation Solutions​
    (2025-04-25) Russell III, Carl; Patel, Neal; Wilson, Damen; Johnson, Ben; Sivaprakasam, Andrew; Earl, Conner; Conlon, Steven
    Introduction/Background: Modern medical education is widely acknowledged for its rigor and fast pace. With a vast amount of information to absorb and apply, the focus often leans heavily on memorization and clinical proficiency. However, one aspect that is often underemphasized is the discovery of unmet needs and the development of innovative solutions to address these gaps. The Advancing Innovation in Medicine Student Interest Group (AIM SIG) serves as a platform for students to actively engage in identifying and addressing these needs. Study Objective/Hypothesis: The AIM SIG aims to foster innovative, collaborative solutions to systemic healthcare challenges. This year’s focus was the improvement of neonatal intubation techniques through novel equipment. Methods: In collaboration with Dr. Steven Conlon, a neonatologist at Riley Hospital for Children, AIM SIG members participated in a structured, stepwise process to explore and address gaps in neonatal intubation procedures. This process included both experiential learning and hands-on education in the engineering design process, offering medical students exposure to device development. Results: AIM SIG members conducted an extensive review of existing literature, intellectual property, and procedural data, culminating in a comprehensive needs assessment. Furthermore, members learned essential skills in “pretotyping” and 3D modeling, equipping them to generate proof-of-concept solutions aimed at improving neonatal intubation procedures. Conclusions: AIM SIG provides medical students with valuable opportunities to acquire skills in problem-solving and innovation. While translating these innovations into practice presents challenges and setbacks, the experience equips students with a versatile framework to address future problems they may encounter in their medical careers.