Generalized Wasserstein Dice Loss, Test-time Augmentation, and Transformers for the BraTS 2021 challenge

• URL: http://arxiv.org/abs/2112.13054v1
• Date: Fri, 24 Dec 2021 13:01:44 GMT
• Title: Generalized Wasserstein Dice Loss, Test-time Augmentation, and Transformers for the BraTS 2021 challenge
• Authors: Lucas Fidon, Suprosanna Shit, Ivan Ezhov, Johannes C. Paetzold, S\'ebastien Ourselin, Tom Vercauteren
• Abstract summary: Brain tumor segmentation is a challenging task in medical image computation. In this paper, we explore strategies to increase model robustness without increasing inference time. Our ensemble of seven 3D U-Nets with test-time augmentation produces an average dice score of 89.4% and an average Hausdorff 95% distance of 10.0 mm.
• Score: 3.3180658085204513
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Brain tumor segmentation from multiple Magnetic Resonance Imaging (MRI) modalities is a challenging task in medical image computation. The main challenges lie in the generalizability to a variety of scanners and imaging protocols. In this paper, we explore strategies to increase model robustness without increasing inference time. Towards this aim, we explore finding a robust ensemble from models trained using different losses, optimizers, and train-validation data split. Importantly, we explore the inclusion of a transformer in the bottleneck of the U-Net architecture. While we find transformer in the bottleneck performs slightly worse than the baseline U-Net in average, the generalized Wasserstein Dice loss consistently produces superior results. Further, we adopt an efficient test time augmentation strategy for faster and robust inference. Our final ensemble of seven 3D U-Nets with test-time augmentation produces an average dice score of 89.4% and an average Hausdorff 95% distance of 10.0 mm when evaluated on the BraTS 2021 testing dataset. Our code and trained models are publicly available at https://github.com/LucasFidon/TRABIT_BraTS2021.

Related papers

• SMaRt: Improving GANs with Score Matching Regularity [94.81046452865583]
  Generative adversarial networks (GANs) usually struggle in learning from highly diverse data, whose underlying manifold is complex. We show that score matching serves as a promising solution to this issue thanks to its capability of persistently pushing the generated data points towards the real data manifold. We propose to improve the optimization of GANs with score matching regularity (SMaRt)
  arXiv  Detail & Related papers  (2023-11-30T03:05:14Z)
• Image-level supervision and self-training for transformer-based cross-modality tumor segmentation [2.29206349318258]
  We propose a new semi-supervised training strategy called MoDATTS. MoDATTS is designed for accurate cross-modality 3D tumor segmentation on unpaired bi-modal datasets. We report that 99% and 100% of this maximum performance can be attained if 20% and 50% of the target data is annotated.
  arXiv  Detail & Related papers  (2023-09-17T11:50:12Z)
• Deep Learning Framework for Real-time Fetal Brain Segmentation in MRI [15.530500862944818]
  We analyze the speed-accuracy performance of a variety of deep neural network models. We devised a symbolically small convolutional neural network that combines spatial details at high resolution with context features extracted at lower resolutions. We trained our model as well as eight alternative, state-of-the-art networks with manually-labeled fetal brain MRI slices.
  arXiv  Detail & Related papers  (2022-05-02T20:43:14Z)
• Optimized U-Net for Brain Tumor Segmentation [62.997667081978825]
  We propose an optimized U-Net architecture for a brain mboxtumor segmentation task in the BraTS21 Challenge. Our solution was the winner of the challenge validation phase, with the normalized statistical ranking score of 0.267 and mean Dice score of 0.8855.
  arXiv  Detail & Related papers  (2021-10-07T11:44:09Z)
• The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers [8.424405898986118]
  We report improvements on five popular datasets: SCAN, CFQ, PCFG, COGS, and Mathematics. Our models improve accuracy from 50% to 85% on the PCFG productivity split, and from 35% to 81% on COGS. This calls for proper generalization validation sets for developing neural networks that generalize systematically.
  arXiv  Detail & Related papers  (2021-08-26T17:26:56Z)
• Evolving Deep Convolutional Neural Network by Hybrid Sine-Cosine and Extreme Learning Machine for Real-time COVID19 Diagnosis from X-Ray Images [0.5249805590164902]
  Deep Convolutional Networks (CNNs) can be considered as applicable tools to diagnose COVID19 positive cases. This paper proposes using the Extreme Learning Machine (ELM) instead of the last fully connected layer to address this deficiency. The proposed approach outperforms comparative benchmarks with a final accuracy of 98.83% on the COVID-Xray-5k dataset.
  arXiv  Detail & Related papers  (2021-05-14T19:40:16Z)
• Generalized Wasserstein Dice Score, Distributionally Robust Deep Learning, and Ranger for brain tumor segmentation: BraTS 2020 challenge [4.787559241352888]
  Training a deep neural network is an optimization problem with four main ingredients: the design of the deep neural network, the per-sample loss function, the population loss function, and the architectures. We experimented with adopting the opposite approach, focusing only on the design of the deep neural network. With an ensemble of three deep neural networks trained with various optimization procedures, we achieved promising results on the validation of the BraTS 2020 challenge.
  arXiv  Detail & Related papers  (2020-11-03T10:50:48Z)
• Brain tumor segmentation with self-ensembled, deeply-supervised 3D U-net neural networks: a BraTS 2020 challenge solution [56.17099252139182]
  We automate and standardize the task of brain tumor segmentation with U-net like neural networks. Two independent ensembles of models were trained, and each produced a brain tumor segmentation map. Our solution achieved a Dice of 0.79, 0.89 and 0.84, as well as Hausdorff 95% of 20.4, 6.7 and 19.5mm on the final test dataset.
  arXiv  Detail & Related papers  (2020-10-30T14:36:10Z)
• Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection [91.43066633305662]
  The main purpose of RGB-D salient object detection (SOD) is how to better integrate and utilize cross-modal fusion information. In this paper, we explore these issues from a new perspective. We implement a kind of more flexible and efficient multi-scale cross-modal feature processing.
  arXiv  Detail & Related papers  (2020-07-13T07:59:55Z)
• Contextual-Bandit Anomaly Detection for IoT Data in Distributed Hierarchical Edge Computing [65.78881372074983]
  IoT devices can hardly afford complex deep neural networks (DNN) models, and offloading anomaly detection tasks to the cloud incurs long delay. We propose and build a demo for an adaptive anomaly detection approach for distributed hierarchical edge computing (HEC) systems. We show that our proposed approach significantly reduces detection delay without sacrificing accuracy, as compared to offloading detection tasks to the cloud.
  arXiv  Detail & Related papers  (2020-04-15T06:13:33Z)
• Diversity inducing Information Bottleneck in Model Ensembles [73.80615604822435]
  In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. We explicitly optimize a diversity inducing adversarial loss for learning latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data. Compared to the most competitive baselines, we show significant improvements in classification accuracy, under a shift in the data distribution.
  arXiv  Detail & Related papers  (2020-03-10T03:10:41Z)

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.