Deep ICE: A Deep learning approach for MRI Intracranial Cavity Extraction

TL;DR

This paper introduces Deep ICE, a deep learning method using 3D CNNs and a novel patch strategy for automatic intracranial cavity segmentation in MRI, improving accuracy and efficiency over existing techniques.

Contribution

The paper presents a new 3D CNN-based approach with a specialized patch extraction strategy for better intracranial cavity segmentation from MRI data.

Findings

Achieved high accuracy in intracranial cavity segmentation

Reduced computational time compared to state-of-the-art methods

Effective handling of limited training data

Abstract

Automatic methods for measuring normalized regional brain volumes from MRI data are a key tool to help in the objective diagnostic and follow-up of many neurological diseases. To estimate such regional brain volumes, the intracranial cavity volume is commonly used for normalization. In this paper, we present an accurate and efficient approach to automatically segment the intracranial cavity using a volumetric 3D convolutional neural network and a new 3D patch extraction strategy specially adapted to deal with the traditional low number of training cases available in supervised segmentation and the memory limitations of modern GPUs. The proposed method is compared with recent state-of-the-art methods and the results show an excellent accuracy and improved performance in terms of computational burden.