Development of AI-Based Decision Support for Intraoperative Guidance in Neurosurgery

Comparison of contrast flow dynamics in a cerebral aneurysm using 4D angiographic reconstruction (top row) and computational fluid dynamics (CFD) simulation (bottom row). Each row shows parametric maps of key flow biomarkers—Time to Peak (TTP), Mean Transit Time (MTT), Time to Arrival (TTA), Peak Height (PH), and Area Under the Curve (AUC)—derived from simulated contrast injection. These maps represent volumetric contrast behavior and are used to inform AI models designed for intraoperative decision support. The ability to quantify and visualize contrast flow in 3D enables deeper insight into aneurysm hemodynamics, aiding safer surgical planning.

Use AI to help doctors make better decisions during brain surgery — and present your work at an international conference. 

Project description

This summer research project invites two undergraduate students to join our lab in developing artificial intelligence tools to help neurosurgeons make better decisions during surgery. Students will learn how to process and analyze real surgical imaging data, build simple machine learning models, and test their tools in a simulated surgical environment using previously collected data and patient-specific vascular models. This work supports a broader goal of using technology to improve patient safety during high-risk procedures like aneurysm treatment. The project is designed for students curious about medicine, imaging, computer science, or engineering, and offers exposure to both research and clinical translation. At the end of the project, students will write and submit a full conference manuscript and travel to present their findings at SPIE Medical Imaging 2026 in Vancouver. 

Project outcome

By the end of the project, students will:

1. Build and test a basic AI model using surgical imaging data

2. Co-author an 8–10 page SPIE Medical Imaging conference paper

3. Deliver an oral or poster presentation at SPIE 2026 in Vancouver, Canada

4. Gain hands-on experience with imaging analysis, machine learning, and clinical research translation

Project details

Timing, eligibility and other details
Length of commitment Short (less than a semester; 0-2 months) 
Start time Summer (May/June) 
In-person, remote, or hybrid? In-Person Project 
Level of collaboration Large group collaboration (4+ students) 
Benefits N/A
Who is eligible All undergraduate students who have experience with python

Core partners

  • Canon Stroke and Vascular Research Center: Hosts our imaging labs and provides access to surgical data, vascular models, and equipment.

  • Gates Vascular Institute: A state-of-the-art clinical and research facility where our simulations and testing take place.

  • SPIE Medical Imaging Conference: An international conference where students will present their final paper and engage with experts in biomedical imaging and AI. 

Project mentor

Ciprian Ionita

Assistant Professor;

Biomedical Engineering

875 Ellicott Street, 8052 Clinical Translation Research Center

Phone: (716) 400-4283

Email: cnionita@buffalo.edu

Start the project

  1. Email the project mentor using the contact information above to express your interest and get approval to work on the project. (Here are helpful tips on how to contact a project mentor.)
  2. After you receive approval from the mentor to start this project, click the button to start the digital badge. (Learn more about ELN's digital badge options.) 
Start the Digital Badge

Preparation activities

Once you begin the digital badge series, you will have access to all the necessary activities and instructions. Your mentor has indicated they would like you to also complete the specific preparation activities below. Please reference this when you get to Step 2 of the Preparation Phase. 

  • Before beginning work on this project, students must complete the following activities to build foundational knowledge and meet compliance requirements related to working with patient imaging data:

  • Complete HIPAA and IRB Compliance Training

  • Students must complete UB’s mandatory HIPAA training and CITI Program training in Human Subjects Research (Biomedical Focus).

  • Certificates of completion must be submitted to the PI prior to starting the project.

Keywords

AI, machine learning, medical imaging, neurosurgery, biomedical engineering, computational modeling, 3D imaging, surgery simulation, data science, clinical research, SPIE conference, undergraduate research, brain aneurysms, image analysis, decision support systems