Geometric Convolutional Neural Network for Analyzing Surface-Based Neuroimaging Data

한글 요약

대뇌피질은 보통 곡면 형태의 메쉬(mesh)로 표현되는데, 일반적인 합성곱 신경망(CNN)은 2차원 이미지에 맞춰져 있어 이런 표면 자료에 곧바로 적용하기 어렵습니다. 이 연구는 표면 위의 자료를 다층 메쉬 구조에서 샘플링하고 재배열하여 기존 CNN 도구로 학습할 수 있게 하는 기하학적 CNN(gCNN)을 제안했습니다. 인간 커넥톰 프로젝트의 대뇌피질 두께 지도로 성별을 분류하는 과제에서 gCNN은 서포트 벡터 머신이나 지도를 평면에 투영한 뒤 사용한 2차원 CNN보다 유의하게 높은 정확도를 보였고, 학습된 국소 특징이 위치에 무관하게 다른 과제에 재사용될 수 있다는 점도 확인되었습니다. 이 방법은 뇌 표면 기반 자료에 딥러닝을 적용할 길을 열어 기초 연구와 임상 응용 모두에 활용될 수 있습니다.

In machine learning, one of the most popular deep learning methods is the convolutional neural network (CNN), which utilizes shared local filters and hierarchical information processing analogous to the brain's visual system. Despite its popularity in recognizing two-dimensional (2D) images, the conventional CNN is not directly applicable to semi-regular geometric mesh surfaces, on which the cerebral cortex is often represented. In order to apply the CNN to surface-based brain research, we propose a geometric CNN (gCNN) that deals with data representation on a mesh surface and renders pattern recognition in a multi-shell mesh structure. To make it compatible with the conventional CNN toolbox, the gCNN includes data sampling over the surface, and a data reshaping method for the convolution and pooling layers. We evaluated the performance of the gCNN in sex classification using cortical thickness maps of both hemispheres from the Human Connectome Project (HCP). The classification accuracy of the gCNN was significantly higher than those of a support vector machine (SVM) and a 2D CNN for thickness maps generated by a map projection. The gCNN also demonstrated position invariance of local features, which rendered reuse of its pre-trained model for applications other than that for which the model was trained without significant distortion in the final outcome. The superior performance of the gCNN is attributable to CNN properties stemming from its brain-like architecture, and its surface-based representation of cortical information. The gCNN provides much-needed access to surface-based machine learning, which can be used in both scientific investigations and clinical applications.