Near Real-time Hippocampus Segmentation Using Patch-based Canonical Neural Network
This work addresses the need for fast and accurate medical image segmentation, particularly for hippocampus analysis in conditions like Alzheimer's disease, representing a strong specific gain in this domain.
The paper tackled hippocampus segmentation from brain MR images by proposing a patch-based deep learning framework, achieving a median Dice score of 90.98% with near real-time performance under 1 second.
Over the past decades, state-of-the-art medical image segmentation has heavily rested on signal processing paradigms, most notably registration-based label propagation and pair-wise patch comparison, which are generally slow despite a high segmentation accuracy. In recent years, deep learning has revolutionalized computer vision with many practices outperforming prior art, in particular the convolutional neural network (CNN) studies on image classification. Deep CNN has also started being applied to medical image segmentation lately, but generally involves long training and demanding memory requirements, achieving limited success. We propose a patch-based deep learning framework based on a revisit to the classic neural network model with substantial modernization, including the use of Rectified Linear Unit (ReLU) activation, dropout layers, 2.5D tri-planar patch multi-pathway settings. In a test application to hippocampus segmentation using 100 brain MR images from the ADNI database, our approach significantly outperformed prior art in terms of both segmentation accuracy and speed: scoring a median Dice score up to 90.98% on a near real-time performance (<1s).