Automatic Segmentation of MR Brain Images With a Convolutional Neural Network

By Pim Moeskops, Max A. Viergever, Adriënne M. Mendrik, L. D. Vries, Manon J. N. L. Benders, Ivana Isgum. IEEE Transactions on Medical Imaging, 2016

831 citations recorded by the source corpus.

Automatic segmentation in MR brain images is important for quantitative analysis in large-scale studies with images acquired at all ages. This paper presents a method for the automatic segmentation of MR brain images into a number of tissue classes using a convolutional neural network. To ensure that the method obtains accurate segmentation details as well as spatial consistency, the network uses multiple patch sizes and multiple convolution kernel sizes to acquire multi-scale information about each voxel. The method is not dependent on explicit features, but learns to recognise the information that is important for the classification based on training data. The method requires a single anatomical MR image only. The segmentation method is applied to five different data sets: coronal T2-weighted images of preterm infants acquired at 30 weeks postmenstrual age (PMA) and 40 weeks PMA, axial T2-weighted images of preterm infants acquired at 40 weeks PMA, axial T1-weighted images of ageing adults acquired at an average age of 70 years, and T1-weighted images of young adults acquired at an average age of 23 years. The method obtained the following average Dice coefficients over all segmented tissue classes for each data set, respectively: 0.87, 0.82, 0.84, 0.86, and 0.91. The results demonstrate that the method obtains accurate segmentations in all five sets, and hence demonstrates its robustness to differences in age and acquisition protocol.

Subfields: Computer Vision and Pattern Recognition, Pediatrics, Perinatology and Child Health

View Paper: https://www.semanticscholar.org/paper/8668404abea4588ad67787b56ef35abe2a819914

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Pediatrics, Perinatology and Child Health

Citations in the corpus

Data Augmentation Using Learned Transformations for One-Shot Medical Image Segmentation (2019, methodology): “To mitigate the need for large labeled training datasets, these methods often use data augmentation along with hand-engineered pre-processing steps and architectures [2, 40, 53, 57, 63, 65, 82].”
A Survey of Deep Learning for Scientific Discovery (2020, background): “Examples include segmenting brain MR images [156, 236], identifying key regions of cells in diﬀerent tissues [254, 217] and even studying bone structure [129].”
Deep learning in generating radiology reports: A survey (2020, positive): “In radiology, CNN is the most applicable DL algorithm for performing various tasks including medical image classification and segmentation [60].”
Learning a Variational Network for Reconstruction of Accelerated MRI Data (2017, methodology): “In medical imaging, deep learning has also been applied to areas like segmentation (7, 8), q-space image processing (9), and skull stripping (10).”
FastSurfer - A fast and accurate deep learning based neuroimaging pipeline (2019, neutral): “Most of these brain segmentation networks were trained on extracted 3D patches (de Br ^ ebisson and Montana, 2015; Wachinger et al., 2018; Mehta et al., 2017) or 2D slices (Moeskops et al., 2016; Roy et al., 2017, 2019; Jog et al., 2019).”
Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review (2017, methodology): “129] Normalisation – Tissue 2D CNN Havaei et al. 2016 [24] Outlier removal Normalisation N4ITK Connected componentanalysis Tumour 2D CNN Zhao and Jia 2016 [136] - - Tumour 2D CNN Moeskops et al. 2016 [25] Intensity scaling Bias ﬁeld correction([137]) Skull stripping (BET) - Tissue 3D FCNN Kamnitsas ”
Deep learning based brain tumor segmentation: a survey (2020, methodology): “Early research work like [89] used a 3 pathways CNN to segment brain MRI images.”
HyperDense-Net: A Hyper-Densely Connected CNN for Multi-Modal Image Segmentation (2018, background): “They achieved state-of-the-art performances in a broad range of medical image segmentation problems [36], [37], including multimodal tasks [14]–[16], [25]–[27], [29], [32], [33], [38], [39].”
Generative Adversarial Networks for Noise Reduction in Low-Dose CT (2017, background): “require CNNs with large receptive fields [41], [42], noise”
Medical image retrieval using deep convolutional neural network (2017, methodology): “In [42], multi scale CNN was applied for automatic segmentation of MR images by classifying voxel into brain tissue classes.”
VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images (2017, positive): “…(Cicek et al., 2016), parallelized long short-term memory (LSTM) (Stollenga et al., 2015), convolutional neural networks with multiple pathways (de Brebisson and Montana, 2015) or multiple patch and kernel sizes (Moeskops et al., 2016), and 2D fully convolutional networks (FCN) (Nie et al., 2016).”
State-of-the-Art Methods for Brain Tissue Segmentation: A Review (2017, methodology): “cently, convolutional neural networks (CNNs) and deep learning are gaining recognition in brain tissue segmentation [114]– [117].”
A review on deep learning in medical image analysis (2021, background): “Active learning is a valuable tool when there is little data available and collecting or labelling new data is expensive [82, 83].”
Deep Learning Applications in Medical Image Analysis (2018, methodology): “There is some overlap with Moeskops’ [76] use of input patches at different scales, and it would be interesting to see how this work in image segmentation can be advanced further.”