1294. Computer Vision for Cerebrospinal Fluid Valve Detection
Authors: Ghaith Habboub, MD; Ghaith Habboub, MD; David Piraino, MD; Stephen Jones, MD; Violette Recinos, MD (Cleveland, OH)
Computer vision has significantly progressed over the last few years following the massive success of deep neural network in image classification. Radiology has been an exciting field for utilizing computer vision. While efforts are mainly focused towards broader problems, such as cancer detection, less work has been done on more routine and narrower targets.
Hydrocephalus surgical management is one of the most common procedures performed by neurosurgeons. Recognizing the type and setting of cerebrospinal fluid valves can be a demanding task due to the increasing number of patients and the variety of valve types.
The goal of this project is to create a computer vision classifier built into a smart phone app and/or embedded into the medical imaging reading system. The algorithm would detect the type and setting of a cerebrospinal fluid valve and auto-populate it into the radiology report.
We have images on ~ 6500 shunt series. Of these we used only 1.5% of the data and we are in the process of obtaining the rest for analysis. We created a multi-layer convolutional neural network utilizing Tensorflow/Keras, written in Python. We converted the model into an iOS app using CoreML, written in Swift.
Model accuracy was 60% despite utilizing 1.5% of the data. The iOS application can detect images in real time and provide probabilities utilizing the camera embedded in the smart phone.
This is the first cerebrospinal fluid valve detection classifier. We were able to achieve acceptable accuracy and we expect to significantly improve it after training the model with the rest of the data. This can decrease the workload for both the radiologists and neurosurgeons.