Residual and plain convolutional neural networks for 3D brain MRI classification

By Sergey Korolev, Amir Safiullin, Mikhail Belyaev, Yulia Dodonova. IEEE International Symposium on Biomedical Imaging, 2017

446 citations recorded by the source corpus.

In the recent years there have been a number of studies that applied deep learning algorithms to neuroimaging data. Pipelines used in those studies mostly require multiple processing steps for feature extraction, although modern advancements in deep learning for image classification can provide a powerful framework for automatic feature generation and more straightforward analysis. In this paper, we show how similar performance can be achieved skipping these feature extraction steps with the residual and plain 3D convolutional neural network architectures. We demonstrate the performance of the proposed approach for classification of Alzheimer's disease versus mild cognitive impairment and normal controls on the Alzheimers Disease National Initiative (ADNI) dataset of 3D structural MRI brain scans.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Neurology

View Paper: https://www.semanticscholar.org/paper/f545c7b72f8be36afbddbf26e467d159e21682d2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Neurology

Citations in the corpus

Deep Learning Applications in Medical Image Analysis (2018, methodology): “[53] evaluated the performance of their VOXCNN and ResNet, which was based on the VGGNet [54] and Residual neural network architectures [55] respectively.”
Accurate brain age prediction with lightweight deep neural networks (2019, methodology): “…brain age prediction and modelling (Cole et al., 2017; Kawahara et al., 2017), sex classification (Arslan et al., 2018), disease prediction (Baumgartner et al., 2018; Korolev et al., 2017; Liu et al., 2018) and brain lesion segmentation (Kamnitsas et al., 2017), yet still faces several challenges.”
Group-Wise Learning for Aurora Image Classification With Multiple Representations (2019, methodology): “We further compare our GWL method with six state-ofthe-art methods on ADNI, including two deep-learning-based methods [63], [64], a voxel-level-based method [65], a regionlevel-based method [66], and two anatomical-landmark-based methods [67], [68].”
Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation (2019, methodology): “Some studies readapted two classical architectures, ResNet (He et al., 2016) and VGGNet (Simonyan and Zisserman, 2014), to fit the whole MRI (Korolev et al., 2017; Shmulev et al., 2018).”
Deep Learning for Spatio-Temporal Data Mining: A Survey (2019, methodology): “Application domains Related works Transportation [177], [187], [116], [31], [29], [6], [32], [127], [53], [112], [26], [105], [166], [82], [23], [66], [108], [126], [81], [139], [78], [128], [146], [148], [72], [98], [189], [22], [24], [99], [96], [16], [97], [85], [15], [164], [165], [95], [140], [”
Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer’s Disease Diagnosis using Structural MRI (2018, unknown): “the literature [31], [33], [34], [50], [51], [66], [68].”