Deep 3D Convolutional Encoder Networks With Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation

By Tom Brosch, Lisa Tang, Youngjin Yoo, David K. B. Li, Anthony Traboulsee, Roger C. Tam. IEEE Transactions on Medical Imaging, 2016

457 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/0d21449cba8735032af2f6dfc46e18641e6fa3d3

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 Media Technology

Citations in the corpus

Deep Learning Applications in Medical Image Analysis (2018, background): “[81] also exploited the analysis of multi-scale architecture, in segmenting MRI brain lesions of multiple sclerosis.”
The Importance of Skip Connections in Biomedical Image Segmentation (2016, methodology): “While CNNs are typically realized by a contracting path built from convolutional, pooling and fully connected layers, FCN adds an expanding path built with deconvolutional or unpooling layers.”
Deep learning based brain tumor segmentation: a survey (2020, methodology): “[28] used fully convolutional networks with skip connections to segment multiple sclerosis lesions.”
Deep Learning in Medical Imaging: General Overview (2017, methodology): “To predict segmentations of the same resolution as the input images, Brosch et al. (50, 51) recently proposed the use of a 3-layer convolutional encoder network for multiple sclerosis lesion segmentation.”
Volumetric ConvNets with Mixed Residual Connections for Automated Prostate Segmentation from 3D MR Images (2017, background): “Some studies started to employ 3D CNN to cope with detection and segmentation problems in medical volumetric data (Li et al. 2014; Brosch et al. 2016; Kamnitsas et al. 2016; Chen et al. 2016a).”
Semi-supervised Learning for Network-Based Cardiac MR Image Segmentation (2017, background): “1 Related Works Many works have proposed using FCN for medical image segmentation [3,4,12].”
Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation (2018, unknown): “equencesisakeycomponentforclinicalassessment ofdiseasestageandprognosis,aswellasforevaluatingtheeﬃcacyoftreatments duringclinicaltrials.EarlyDLapproacheshaveshownsuccessinthesegmentationoflargelesions[2],andrecentworkhasshownhowusingatissue-prioror lesion-priorcanimprovedetectionformediumandsmallles”
Deep ensemble learning of sparse regression models for brain disease diagnosis (2017, methodology): “To this end, it has also been considered as one of the major tools in brain imaging data analysis (Li et al., 2014b; Plis et al., 2014; Suk et al., 2015a, 2016b; Pereira et al., 2016; Brosch et al., 2016; Dou et al., 2016) by achieving promising performances.”
Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions (2017, methodology): “[31] presented a 3D semantic-wise CNN to segment MS lesions from MRI.”
Guest Editorial Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique (2016, unknown): “[21].”
Deep Learning in Medical Image Analysis (2017, background): “Because of the structural characteristic of images (i.e., the structural or configural information among neighboring pixels or voxels is another important source of information), convolutional neural networks have gained great interest in medical image analysis (33, 45, 32, 46, 22, 44, 31).”
Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review (2017, methodology): “[21] applied a six degree-of-freedom intra-subject registration using one of the 3 mm scans as the target image to align the different modalities.”
Evaluation of a deep learning approach for the segmentation of brain tissues and white matter hyperintensities of presumed vascular origin in MRI (2017, unknown): “Brosch et al. (2016) presented a method using a convolutional and a deconvolutional pathway with skip-connections to allow multi-scale feature integration.”
3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes (2017, methodology): “For example, 9×9×5 convolutions are used in [2].”
A survey on deep learning in medical image analysis (2017, methodology): “Some papers combat this by adapting the loss function: Brosch et al. (2016) deﬁned it to be a weighted combination of the sensitivity and the speciﬁcity, with a larger weight for the speciﬁcity to make it less sensitive to the data imbalance.”