Towards broader generalization of deep learning methods for multiple
sclerosis lesion segmentation
- URL: http://arxiv.org/abs/2012.07950v1
- Date: Mon, 14 Dec 2020 21:33:53 GMT
- Title: Towards broader generalization of deep learning methods for multiple
sclerosis lesion segmentation
- Authors: Reda Abdellah Kamraoui, Vinh-Thong Ta, Thomas Tourdias, Boris
Mansencal, Jos\'e V Manjon, Pierrick Coup\'e
- Abstract summary: DeepLesionBrain (DLB) is a novel method robust to domain shift and performing well on unseen datasets.
DLB is based on a large ensemble of compact 3D CNNs.
It learns both generic features extracted at global image level and specific features extracted at local image level.
- Score: 0.39146761527401414
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recently, segmentation methods based on Convolutional Neural Networks (CNNs)
showed promising performance in automatic Multiple Sclerosis (MS) lesions
segmentation. These techniques have even outperformed human experts in
controlled evaluation condition. However state-of-the-art approaches trained to
perform well on highly-controlled datasets fail to generalize on clinical data
from unseen datasets. Instead of proposing another improvement of the
segmentation accuracy, we propose a novel method robust to domain shift and
performing well on unseen datasets, called DeepLesionBrain (DLB). This
generalization property results from three main contributions. First, DLB is
based on a large ensemble of compact 3D CNNs. This ensemble strategy ensures a
robust prediction despite the risk of generalization failure of some individual
networks. Second, DLB includes a new image quality data augmentation to reduce
dependency to training data specificity (e.g., acquisition protocol). Finally,
to learn a more generalizable representation of MS lesions, we propose a
hierarchical specialization learning (HSL). HSL is performed by pre-training a
generic network over the whole brain, before using its weights as
initialization to locally specialized networks. By this end, DLB learns both
generic features extracted at global image level and specific features
extracted at local image level. At the time of publishing this paper, DLB is
among the Top 3 performing published methods on ISBI Challenge while using only
half of the available modalities. DLB generalization has also been compared to
other state-of-the-art approaches, during cross-dataset experiments on
MSSEG'16, ISBI challenge, and in-house datasets. DLB improves the segmentation
performance and generalization over classical techniques, and thus proposes a
robust approach better suited for clinical practice.
Related papers
- Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud
Semantic Segmentation via Decoupling Optimization [64.36097398869774]
Semi-supervised learning (SSL) has been an active research topic for large-scale 3D scene understanding.
The existing SSL-based methods suffer from severe training bias due to class imbalance and long-tail distributions of the point cloud data.
We introduce a new decoupling optimization framework, which disentangles feature representation learning and classifier in an alternative optimization manner to shift the bias decision boundary effectively.
arXiv Detail & Related papers (2024-01-13T04:16:40Z) - Predicting Infant Brain Connectivity with Federated Multi-Trajectory
GNNs using Scarce Data [54.55126643084341]
Existing deep learning solutions suffer from three major limitations.
We introduce FedGmTE-Net++, a federated graph-based multi-trajectory evolution network.
Using the power of federation, we aggregate local learnings among diverse hospitals with limited datasets.
arXiv Detail & Related papers (2024-01-01T10:20:01Z) - Learnable Weight Initialization for Volumetric Medical Image Segmentation [66.3030435676252]
We propose a learnable weight-based hybrid medical image segmentation approach.
Our approach is easy to integrate into any hybrid model and requires no external training data.
Experiments on multi-organ and lung cancer segmentation tasks demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2023-06-15T17:55:05Z) - Robust Prototypical Few-Shot Organ Segmentation with Regularized
Neural-ODEs [10.054960979867584]
We propose Regularized Prototypical Neural Ordinary Differential Equation (R-PNODE)
R-PNODE constrains support and query features from the same classes to lie closer in the representation space.
We show that R-PNODE exhibits increased adversarial robustness for a wide array of these attacks.
arXiv Detail & Related papers (2022-08-26T03:53:04Z) - AADG: Automatic Augmentation for Domain Generalization on Retinal Image
Segmentation [1.0452185327816181]
We propose a data manipulation based domain generalization method, called Automated Augmentation for Domain Generalization (AADG)
Our AADG framework can effectively sample data augmentation policies that generate novel domains.
Our proposed AADG exhibits state-of-the-art generalization performance and outperforms existing approaches.
arXiv Detail & Related papers (2022-07-27T02:26:01Z) - Augmentation based unsupervised domain adaptation [2.304713283039168]
Deep learning models trained on small and unrepresentative data tend to outperform when deployed in data that differs from the one used for training.
Our approach takes advantage of the properties of adversarial domain adaptation and consistency training to achieve more robust adaptation.
arXiv Detail & Related papers (2022-02-23T13:06:07Z) - Self-Ensembling GAN for Cross-Domain Semantic Segmentation [107.27377745720243]
This paper proposes a self-ensembling generative adversarial network (SE-GAN) exploiting cross-domain data for semantic segmentation.
In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN.
Despite its simplicity, we find SE-GAN can significantly boost the performance of adversarial training and enhance the stability of the model.
arXiv Detail & Related papers (2021-12-15T09:50:25Z) - Quasi-Global Momentum: Accelerating Decentralized Deep Learning on
Heterogeneous Data [77.88594632644347]
Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks.
In realistic learning scenarios, the presence of heterogeneity across different clients' local datasets poses an optimization challenge.
We propose a novel momentum-based method to mitigate this decentralized training difficulty.
arXiv Detail & Related papers (2021-02-09T11:27:14Z) - Domain Generalization for Medical Imaging Classification with
Linear-Dependency Regularization [59.5104563755095]
We introduce a simple but effective approach to improve the generalization capability of deep neural networks in the field of medical imaging classification.
Motivated by the observation that the domain variability of the medical images is to some extent compact, we propose to learn a representative feature space through variational encoding.
arXiv Detail & Related papers (2020-09-27T12:30:30Z) - Quality-aware semi-supervised learning for CMR segmentation [2.9928692313705505]
One of the challenges in developing deep learning algorithms for medical image segmentation is the scarcity of training data.
We propose a novel scheme that uses QC of the downstream task to identify high quality outputs of CMR segmentation networks.
In essence, this provides quality-aware augmentation of training data in a variant of SSL for segmentation networks.
arXiv Detail & Related papers (2020-09-01T17:18:22Z) - Siloed Federated Learning for Multi-Centric Histopathology Datasets [0.17842332554022694]
This paper proposes a novel federated learning approach for deep learning architectures in the medical domain.
Local-statistic batch normalization (BN) layers are introduced, resulting in collaboratively-trained, yet center-specific models.
We benchmark the proposed method on the classification of tumorous histopathology image patches extracted from the Camelyon16 and Camelyon17 datasets.
arXiv Detail & Related papers (2020-08-17T15:49:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.