Extending nn-UNet for Brain Tumor Segmentation

Luu, Huan Minh; Park, Sung-Hong

doi:10.1007/978-3-031-09002-8_16

Cited by 70 publications

(67 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, for small tumors located on the vertex, we experienced that complex venous structures draining to the superior sagittal sinus or missing out on MR cut made prominent error in the U‐Net models; however, the application of nnU‐Net drastically reduced these errors. Although the efficacy of nnU‐Net, which scored the highest in the Multimodal Brain Tumor Segmentation (BraTS) Challenge 2021, is well known, its applicability for meningioma has yet to be published 33 …”

Section: Discussionmentioning

confidence: 99%

Fully Automated MRI Segmentation and Volumetric Measurement of Intracranial Meningioma Using Deep Learning

Kang

Witanto²,

Pratama³

et al. 2022

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Accurate and rapid measurement of the MRI volume of meningiomas is essential in clinical practice to determine the growth rate of the tumor. Imperfect automation and disappointing performance for small meningiomas of previous automated volumetric tools limit their use in routine clinical practice. Purpose To develop and validate a computational model for fully automated meningioma segmentation and volume measurement on contrast‐enhanced MRI scans using deep learning. Study Type Retrospective. Population A total of 659 intracranial meningioma patients (median age, 59.0 years; interquartile range: 53.0–66.0 years) including 554 women and 105 men. Field Strength/Sequence The 1.0 T, 1.5 T, and 3.0 T; three‐dimensional, T1‐weighted gradient‐echo imaging with contrast enhancement. Assessment The tumors were manually segmented by two neurosurgeons, H.K. and C.‐K.P., with 10 and 26 years of clinical experience, respectively, for use as the ground truth. Deep learning models based on U‐Net and nnU‐Net were trained using 459 subjects and tested for 100 patients from a single institution (internal validation set [IVS]) and 100 patients from other 24 institutions (external validation set [EVS]), respectively. The performance of each model was evaluated with the Sørensen‐Dice similarity coefficient (DSC) compared with the ground truth. Statistical Tests According to the normality of the data distribution verified by the Shapiro–Wilk test, variables with three or more categories were compared by the Kruskal–Wallis test with Dunn's post hoc analysis. Results A two‐dimensional (2D) nnU‐Net showed the highest median DSCs of 0.922 and 0.893 for the IVS and EVS, respectively. The nnU‐Nets achieved superior performance in meningioma segmentation than the U‐Nets. The DSCs of the 2D nnU‐Net for small meningiomas less than 1 cm3 were 0.769 and 0.780 with the IVS and EVS, respectively. Data Conclusion A fully automated and accurate volumetric measurement tool for meningioma with clinically applicable performance for small meningioma using nnU‐Net was developed. Evidence Level 3 Technical Efficacy Stage 2

show abstract

Section: Discussionmentioning

confidence: 99%

Fully Automated MRI Segmentation and Volumetric Measurement of Intracranial Meningioma Using Deep Learning

Kang

Witanto²,

Pratama³

et al. 2022

Magnetic Resonance Imaging

View full text Add to dashboard Cite

show abstract

“…Since 2014, deep learning algorithms have been extensively researched for tumor segmentation in the BraTS challenge [9,[30][31][32][33][34][35][36][37][38][39]. Myronenko [32] won the BraTS 2018 competition by training an asymmetrical U-Net with a broader encoder and an additional variational decoder branch that provided further regularization.…”

Section: Tumor Segmentationmentioning

confidence: 99%

“…To find the optimal architecture and learning strategy, extensive ablation studies were conducted to test: U-Net depth, number of convolutional channels, decoder attention, residual connections, losses, and post-processing strategy. Similarly, [38] developed a novel brain tumor segmentation method by improving nnU-Net, including using a larger network, replacing batch normalization with group normalization, and using axial attention in the decoder. In addition, [39] proposed a trusted brain tumor segmentation network, which could generate robust segmentation results and reliable uncertainty estimates, modeled using subjective logic theory.…”

Section: Tumor Segmentationmentioning

confidence: 99%

Large-Kernel Attention for 3D Medical Image Segmentation

Nan

Ser

et al. 2023

Cogn Comput

View full text Add to dashboard Cite

Automated segmentation of multiple organs and tumors from 3D medical images such as magnetic resonance imaging (MRI) and computed tomography (CT) scans using deep learning methods can aid in diagnosing and treating cancer. However, organs often overlap and are complexly connected, characterized by extensive anatomical variation and low contrast. In addition, the diversity of tumor shape, location, and appearance, coupled with the dominance of background voxels, makes accurate 3D medical image segmentation difficult. In this paper, a novel 3D large-kernel (LK) attention module is proposed to address these problems to achieve accurate multi-organ segmentation and tumor segmentation. The advantages of biologically inspired self-attention and convolution are combined in the proposed LK attention module, including local contextual information, long-range dependencies, and channel adaptation. The module also decomposes the LK convolution to optimize the computational cost and can be easily incorporated into CNNs such as U-Net. Comprehensive ablation experiments demonstrated the feasibility of convolutional decomposition and explored the most efficient and effective network design. Among them, the best Mid-type 3D LK attention-based U-Net network was evaluated on CT-ORG and BraTS 2020 datasets, achieving state-of-the-art segmentation performance when compared to avant-garde CNN and Transformer-based methods for medical image segmentation. The performance improvement due to the proposed 3D LK attention module was statistically validated.

show abstract

“…Due to the excellent performance of the U-Net architecture [ 33 ] for medical image segmentation, lots of the CNN-based [ 34 , 35 ] and almost all recently proposed Transformer-based medical image segmentation methods [ 8 , 9 , 10 , 12 , 36 , 37 , 38 ] adopted U-Net-like architectures to capture the global and local contextual information for each pixel. Futrega et al [ 34 ] carried out extensive ablation studies on several tricks to improve the performance of the U-Net architecture.…”

Section: Related Workmentioning

confidence: 99%

“…By combining the selected effective tricks, their optimized U-Net architecture took third place in the test phase of the BraTS 2021 [ 15 , 16 , 17 , 18 , 19 ] segmentation competition. Luu et al [ 35 ] experimented with several modifications of the nn-UNet [ 39 ], and the modified nn-UNet won first place in the test phase of the BraTS 2021 segmentation competition. UNETR [ 8 ] uses ViT as the encoder and converts the features from four different stages of ViT to build hierarchical feature maps, which are fed into the decoder to generate the segmentation mask.…”

Section: Related Workmentioning

confidence: 99%

High-Resolution Swin Transformer for Automatic Medical Image Segmentation

Chen

Ren

Guo

et al. 2023

Sensors

View full text Add to dashboard Cite

The resolution of feature maps is a critical factor for accurate medical image segmentation. Most of the existing Transformer-based networks for medical image segmentation adopt a U-Net-like architecture, which contains an encoder that converts the high-resolution input image into low-resolution feature maps using a sequence of Transformer blocks and a decoder that gradually generates high-resolution representations from low-resolution feature maps. However, the procedure of recovering high-resolution representations from low-resolution representations may harm the spatial precision of the generated segmentation masks. Unlike previous studies, in this study, we utilized the high-resolution network (HRNet) design style by replacing the convolutional layers with Transformer blocks, continuously exchanging feature map information with different resolutions generated by the Transformer blocks. The proposed Transformer-based network is named the high-resolution Swin Transformer network (HRSTNet). Extensive experiments demonstrated that the HRSTNet can achieve performance comparable with that of the state-of-the-art Transformer-based U-Net-like architecture on the 2021 Brain Tumor Segmentation dataset, the Medical Segmentation Decathlon’s liver dataset, and the BTCV multi-organ segmentation dataset.

show abstract

Extending nn-UNet for Brain Tumor Segmentation

Cited by 70 publications

References 22 publications

Fully Automated MRI Segmentation and Volumetric Measurement of Intracranial Meningioma Using Deep Learning

Fully Automated MRI Segmentation and Volumetric Measurement of Intracranial Meningioma Using Deep Learning

Large-Kernel Attention for 3D Medical Image Segmentation

High-Resolution Swin Transformer for Automatic Medical Image Segmentation

Contact Info

Product

Resources

About