nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation

Isensee, Fabian; Petersen, Jens; Klein, André; Zabala-Blanco, David; Jaeger, Paul F.; Kohl, Simon A. A.; Wasserthal, Jakob; Koehler, Gregor; Norajitra, Tobias; Wirkert, Sebastian J.; Maier‐Hein, Klaus H.

doi:10.48550/arxiv.1809.10486

Cited by 190 publications

(290 citation statements)

References 0 publications

Supporting

Mentioning

286

Contrasting

Order By: Relevance

“…With warm-up strategy for 80 epochs and 160 epochs respectively during training, the initial learning rate is set to 0.002 with a cosine learning rate decay schedule. The other aspects of implementation details remain consistent with [44].…”

Section: B Implementation Detailssupporting

confidence: 59%

TransBTSV2: Towards Better and More Efficient Volumetric Segmentation of Medical Images

Li¹,

Wang²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Transformer, benefiting from global (longrange) information modeling using self-attention mechanism, has been successful in natural language processing and computer vision recently. Convolutional Neural Networks, capable of capturing local features, are unable to model explicit long-distance dependencies from global feature space. However, both local and global features are crucial for dense prediction tasks, especially for 3D medical image segmentation. In this paper, we exploit Transformer in 3D CNN for 3D medical image volumetric segmentation and propose a novel network named TransBTSV2 based on the encoder-decoder structure. Different from our original TransBTS [1], the proposed TransBTSV2 is not limited to brain tumor segmentation (BTS) but focuses on general medical image segmentation, providing a strong and efficient 3D baseline for volumetric segmentation of medical images. As a hybrid CNN-Transformer architecture, TransBTSV2 can achieve accurate segmentation of medical images without any pre-training. With the proposed insight to redesign the internal structure of Transformer and the introduced Deformable Bottleneck Module, a highly efficient architecture is achieved with superior performance. Extensive experimental results on four medical image datasets (BraTS 2019, BraTS 2020, LiTS 2017 and KiTS 2019) demonstrate that TransBTSV2 achieves comparable or better results as compared to the state-of-the-art methods for the segmentation of brain tumor, liver tumor as well as kidney tumor. Code is available at https://github.com/ Wenxuan-1119/TransBTS.

show abstract

Section: B Implementation Detailssupporting

confidence: 59%

TransBTSV2: Towards Better and More Efficient Volumetric Segmentation of Medical Images

Li¹,

Wang²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In future work, we will consider a cascaded model, which addresses this practical drawback of 3D U-Net's poor segmentation results on details. Considering the outstanding performance of the nnU-Net [44] model in medical image segmentation, a 3D U-Net is first trained on down-sampled images, and the segmentation results of this U-Net are then up-sampled to the original voxel spacing and passed as additional input channels to a second 3D U-Net, which is trained on patches at full resolution. We may study and apply cascaded models to our future research.…”

Section: Discussionmentioning

confidence: 99%

Cerebrovascular Segmentation Model Based on Spatial Attention-Guided 3D Inception U-Net with Multi-Directional MIPs

Yong-wei

Kwak

2022

Applied Sciences

View full text Add to dashboard Cite

The segmentation algorithm of cerebrovascular magnetic resonance angiography (MRA) images based on deep learning plays an essential role in medical study. Traditional segmentation algorithms face poor segmentation results and poor connectivity when the cerebrovascular vessels are thinner. An improved segmentation algorithm based on deep convolutional networks is proposed in this research. The proposed segmentation network combines the original 3D U-Net with the maximum intensity projection (MIP), which was transformed from the corresponding patch of a 3D MRA image. The MRA dataset provided by Jeonbuk National University Hospital was used to evaluate the experimental results in comparison with traditional 3D cerebrovascular segmentation methods and other state–of–the–art deep learning methods. The experimental results showed that our method achieved the best test performance among the compared methods in terms of the Dice score when Inception blocks and attention modules were placed in the proposed dual-path networks.

show abstract

“…Dice score Sensitivity Precision Mean SD Mean SD Mean SD UNet [51] 0.753 0.048 0.782 0.043 0.896 0.042 nnUNet [12] 0.817 0.011 0.838 0.024 0.879 0.029 VNet [11] 0.820 0.014 0.831 0.019 0.901 0.050 SegResNet [13] In this section, we compare the performances of the ENN-UNet and RBF-UNet models with those of the baseline model, UNet [10], as well as three state-of-the-art models reviewed in Section 1: nnUNet [12], VNet [11] and SegResNet [13]. For all compared methods, the same learning set and pre-processing steps were used.…”

Section: Modelmentioning

confidence: 99%

“…UNet [10], a successful modification and extension of FCN, has become the most popular model for medical image segmentation in recent years. Driven by different tasks and datasets, many extended and optimized variants of UNet have been proposed for medical image segmentation, such as VNet [11], nnUNet [12] and SegResNet [13]. Researchers working on lymphoma segmentation take advantage of deep learning and achieve promising performance in this domain.…”

Section: Introductionmentioning

confidence: 99%

Lymphoma segmentation from 3D PET-CT images using a deep evidential network

Huang,

Ruan,

Decazes

et al. 2022

Preprint

View full text Add to dashboard Cite

An automatic evidential segmentation method based on Dempster-Shafer theory and deep learning is proposed to segment lymphomas from three-dimensional Positron Emission Tomography (PET) and Computed Tomography (CT) images. The architecture is composed of a deep feature-extraction module and an evidential layer. The feature extraction module uses an encoder-decoder framework to extract semantic feature vectors from 3D inputs. The evidential layer then uses prototypes in the feature space to compute a belief function at each voxel quantifying the uncertainty about the presence or absence of a lymphoma at this location. Two evidential layers are compared, based on different ways of using distances to prototypes for computing mass functions. The whole model is trained end-to-end by minimizing the Dice loss function. The proposed combination of deep feature extraction and evidential segmentation is shown to outperform the baseline UNet model as well as three other state-of-the-art models on a dataset of 173 patients.

show abstract

nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation

Cited by 190 publications

References 0 publications

TransBTSV2: Towards Better and More Efficient Volumetric Segmentation of Medical Images

TransBTSV2: Towards Better and More Efficient Volumetric Segmentation of Medical Images

Cerebrovascular Segmentation Model Based on Spatial Attention-Guided 3D Inception U-Net with Multi-Directional MIPs

Lymphoma segmentation from 3D PET-CT images using a deep evidential network

Contact Info

Product

Resources

About