Corpus ID: 237491786

Team NeuroPoly: Description of the Pipelines for the MICCAI 2021 MS New Lesions Segmentation Challenge

@article{Macar2021TeamND,
  title={Team NeuroPoly: Description of the Pipelines for the MICCAI 2021 MS New Lesions Segmentation Challenge},
  author={U. Macar and Enamundram Naga Karthik and Charley Gros and Andr'eanne Lemay and Julien Cohen-Adad},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.05409}
}
This paper gives a detailed description of the pipelines used for the challenge including the data preprocessing steps applied. Our pipelines have sufficient overlap in terms of the architecture and the parameters used, hence are all described within this paper. Our code for this work can be found at: https://github.com/ivadomed/ms-challenge-2021 
1 Citations
Multiple Sclerosis Lesions Identification/Segmentation in Magnetic Resonance Imaging using Ensemble CNN and Uncertainty Classification
TLDR
An automated framework based on three pivotal concepts to better emulate human reasoning is presented, which proves that there is no significant difference between the automated and the human raters. Expand

References

SHOWING 1-10 OF 23 REFERENCES
Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis
TLDR
A refinement for finer grained parsing of SDI results in situations where the number of objects is unknown is presented, showing the wealth of information that can be learned from refined analysis of medical image segmentations. Expand
Attention U-Net: Learning Where to Look for the Pancreas
TLDR
A novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes is proposed to eliminate the necessity of using explicit external tissue/organ localisation modules of cascaded convolutional neural networks (CNNs). Expand
ivadomed: A Medical Imaging Deep Learning Toolbox
TLDR
ivadomed is an open-source Python package for designing, end-to-end training, and evaluating deep learning models applied to medical imaging data that features cutting-edge architectures, such as FiLM and HeMis, as well as various uncertainty estimation methods (aleatoric and epistemic). Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
Longitudinal multiple sclerosis lesion segmentation: Resource and challenge
TLDR
A quantitative evaluation comparing the consistency of the two raters as well as exploring the performance of the eleven submitted results in addition to three other lesion segmentation algorithms are presented. Expand
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
TLDR
This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once. Expand
Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation
TLDR
A 3D MS lesion segmentation CNN is developed, augmented to provide four different voxel-based uncertainty measures based on Monte Carlo (MC) dropout, and empirical evidence suggests that uncertainty measures consistently allow us to choose superior operating points compared only using the network’s sigmoid output as a probability. Expand
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
TLDR
It is argued that Transformers can serve as strong encoders for medical image segmentation tasks, with the combination of U-Net to enhance finer details by recovering localized spatial information. Expand
A Probabilistic U-Net for Segmentation of Ambiguous Images
TLDR
A generative segmentation model based on a combination of a U-Net with a conditional variational autoencoder that is capable of efficiently producing an unlimited number of plausible hypotheses and reproduces the possible segmentation variants as well as the frequencies with which they occur significantly better than published approaches. Expand
Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks
TLDR
A fully‐automatic framework — robust to variability in both image parameters and clinical condition — for segmentation of the spinal cord and intramedullary MS lesions from conventional MRI data of MS and non‐MS cases is developed. Expand
...
1
2
3
...