In febrile infants younger than 30 days, lumbar puncture (LP) is a procedure routinely performed to evaluate for meningitis. LPs are mainly performed in the emergency setting by clinicians and trainees. However, novice success rates are historically poor with over 60% failure rates that can lead to diagnostic uncertainty, prolonged pain, and unnecessary resource utilization. Reduction of unsuccessful and traumatic LPs in infants can improve diagnostic ability and reduce patient harm. Ultrasound performed at the point-of-care has the potential to increase LP success rates through improved visualization of the anatomy, however it is dependent on the skill of the operator to interpret findings accurately thereby limiting it’s efficacy in the population of providers that most needs it.

The main purpose of this project is to use a pre-existing ultrasound database of ultrasound spinal anatomy videos to develop an artificially intelligent algorithm that can identify the important anatomic structures for planning an infant lumbar puncture procedure.

The specific aim is to annotate spinal anatomy in a corpus of ultrasound data to train a deep learning algorithm and test accuracy of algorithmic feature recognition against expert labels in a hold-out set.

To fulfill this aim, the team will need to achieve the following tasks:

  1. Upload ultrasound video data to annotation platform
  2. Facilitate expert annotation of imaging data
  3. Use machine learning to develop intelligent algorithm for automated feature recognition
  4. Test algorithm accuracy against expert gold standard Pre-existing video ultrasound data consists of 80 six-second clips visualizing infant spinal anatomy in long axis and short axis views.

Our desired end goal is a functional algorithm that can identify key features on spinal anatomy on ultrasound at a threshold of >95% accuracy.

This is an UNPAID research project.

Faculty Advisor

  • Professor: David Kessler
  • Center/Lab: Emergency Medicine
  • Location: Presbyterian Building- PB-2-135D,
  • The goal of the Emergency Medicine office of innovation is to help foster collaboration among departments, disciplines, academia, and industry in order to design, optimize, and implement programs that improve care delivery and quality.

Project Timeline

  • Earliest starting date: 4/1/2023
  • End date: 9/30/2023
  • Number of hours per week of research expected during Spring-Summer 2023: ~10

Candidate requirements

  • Skill sets: fluency in machine learning techniques needed to accomplish the task
  • Student eligibility: freshman, sophomore, junior, senior, master’s
  • International students on F1 or J1 visa: eligible
  • Academic Credit Possible: No