Intracranial Hemorrhage Detection Using Neural Network Based Methods With Federated Learning

TL;DR

This paper presents a neural network method for detecting and classifying intracranial hemorrhages from CT scans, achieving over 92% accuracy, and explores federated learning to enhance privacy-preserving model training.

Contribution

It introduces a time-distributed convolutional neural network for hemorrhage detection and proposes federated learning extensions for privacy-aware model deployment.

Findings

Achieved over 92% accuracy in hemorrhage detection

Demonstrated the effectiveness of time-distributed CNN architecture

Proposed federated learning for privacy-preserving medical imaging

Abstract

Intracranial hemorrhage, bleeding that occurs inside the cranium, is a serious health problem requiring rapid and often intensive medical treatment. Such a condition is traditionally diagnosed by highly-trained specialists analyzing computed tomography (CT) scan of the patient and identifying the location and type of hemorrhage if one exists. We propose a neural network approach to find and classify the condition based upon the CT scan. The model architecture implements a time distributed convolutional network. We observed accuracy above 92% from such an architecture, provided enough data. We propose further extensions to our approach involving the deployment of federated learning. This would be helpful in pooling learned parameters without violating the inherent privacy of the data involved.