Shallow vs deep learning architectures for white matter lesion segmentation in the early stages of multiple sclerosis

@inproceedings{Rosa2018ShallowVD,
  title={Shallow vs deep learning architectures for white matter lesion segmentation in the early stages of multiple sclerosis},
  author={Francesco La Rosa and M{\'a}rio Jo{\~a}o Fartaria and Tobias Kober and Jonas Richiardi and Cristina Granziera and Jean-Philippe Thiran and Meritxell Bach Cuadra},
  booktitle={BrainLes@MICCAI},
  year={2018}
}
In this work, we present a comparison of a shallow and a deep learning architecture for the automated segmentation of white matter lesions in MR images of multiple sclerosis patients. [] Key Method Furthermore, we evaluate a prototype naive combination of the two methods, which refines the final segmentation. All methods were trained on 32 patients, and the evaluation was performed on a pure test set of 73 cases. Results show low lesion-wise false positives (30%) for the deep learning architecture, whereas…

Investigating efficient CNN architecture for multiple sclerosis lesion segmentation

The empirical study of the U-net has led to a better understanding of its architecture and guided the building of the MPU-net, a model far less parameterized than others (at least by a factor of seven), which achieves a human-level segmentation of multiple sclerosis lesions on fluid-attenuated inversion recovery images only.

Lesion Volume Quantification Using Two Convolutional Neural Networks in MRIs of Multiple Sclerosis Patients

A method for volumetric quantification of lesions on MRIs of MS patients using automatic segmentation of the brain and lesions by two CNNs achieved accurate lesion detection and segmentation with reproducibility corresponding to state-of-the-art software tools and manual segmentation.

Multiple sclerosis cortical lesion detection with deep learning at ultra‐high‐field MRI

A deep‐learning‐based framework for the automated detection and classification of MS CLs with 7’T MRI that outperforms previous state‐of‐the‐art methods for automated CL detection across scanners and protocols and may be useful to support clinical decisions at 7 T MRI.

A simple article template

An automated framework for MS lesions identification/segmentation based on three pivotal concepts to better emulate human reasoning is presented: the modeling of uncertainty; the proposal of two, separately trained, CNN, one optimized with respect to lesions themselves and the other to the environment surrounding lesions; the ensemble of the CNN output.

Ensemble CNN and Uncertainty Modeling to Improve Automatic Identification/Segmentation of Multiple Sclerosis Lesions in Magnetic Resonance Imaging

The proposed framework is trained, validated and tested on the 2016 MSSEG benchmark public data set from a single imaging modality, the FLuid-Attenuated Inversion Recovery (FLAIR), and proves that there is no sign of difference between the automated and the human raters.

Multiple Sclerosis Lesion Segmentation - A Survey of Supervised CNN-Based Methods

This survey investigates the supervised CNN-based methods for MS lesion segmentation and decouple these reviewed works into their algorithmic components and reports comparisons between their results.

Multi-Compartment Diffusion Mri, T2 Relaxometry And Myelin Water Imaging As Neuroimaging Descriptors For Anomalous Tissue Detection

The results show that the combination of multi-modal features, together with a boosting enhanced decision-tree based classifier, which combines a set of weak classifiers to form a strong classifier via a voting mechanism, is able to utilise the complementary information for the classification of abnormal tissue.

A novel segmentation framework for uveal melanoma in magnetic resonance imaging based on class activation maps

This work shows experimentally in two different MRI sequences that the weakly 2D-Unet approach outperforms previous state-of-the-art methods for tumor segmentation and that it achieves equivalent accuracy as when manual labels are used for training.

RimNet: A deep 3D multimodal MRI architecture for paramagnetic rim lesions detection in Multiple Sclerosis

  • Medicine
  • 2020
A novel convolutional neural network (CNN) architecture (RimNet) for the automated detection of paramagnetic rim lesions employing multiple MR imaging contrasts and an enhanced MRI contrast is presented.

References

SHOWING 1-10 OF 24 REFERENCES

Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach

Multiple Sclerosis Lesion Segmentation from Brain MRI via Fully Convolutional Neural Networks

A fully convolutional neural network (CNN) based method to segment white matter lesions from multi-contrast MR images for multiple sclerosis and significant improvement in segmentation quality over the competing methods is demonstrated.

Partial volume-aware assessment of multiple sclerosis lesions

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

A novel segmentation approach based on deep 3D convolutional encoder networks with shortcut connections with results showing that this method performs comparably to the top-ranked state-of-the-art methods, even when only relatively small data sets are available for training.

Segmentation of Cortical and Subcortical Multiple Sclerosis Lesions Based on Constrained Partial Volume Modeling

By using a “mixel” approach, potential partial volume effects especially affecting small lesions can be modeled, thus yielding improved lesion segmentation by using a Bayesian partial volume estimation framework that estimates the lesion concentration in each voxel.

Semi-automatic classification of lesion patterns in patients with clinically isolated syndrome

An automatic segmentation algorithm for two different contrast agents is proposed, used within a framework for early characterization of CIS patients according to lesion patterns, and more specifically according to the nature of the inflammatory patterns of these lesions.

MSSEG Challenge Proceedings: Multiple Sclerosis Lesions Segmentation Challenge Using a Data Management and Processing Infrastructure

This proceedings book gathers methodological papers of segmentation methods evaluated at the first MICCAI Challenge on Multiple Sclerosis Lesions Segmentation Challenge Using a Data Management and

Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation

This paper explores Ensembles of Multiple Models and Architectures (EMMA) for robust performance through aggregation of predictions from a wide range of methods to reduce the influence of the meta-parameters of individual models and the risk of overfitting the configuration to a particular database.