3D U-Net Based Brain Tumor Segmentation and Survival Days Prediction

Wang, Feifan; Jiang, Runzhou; Zheng, Liqin; Meng, Chun; Biswal, Bharat B.

doi:10.1007/978-3-030-46640-4_13

Cited by 93 publications

(65 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mask R‐CNN 25 works for instance segmentation, simultaneously inferring both the location of the bounding box and segmentation mask, and the balance between the two tasks weakens the capacity for segmentation. The 3D U‐Net 26 extracts multiscale features in a 3D encoder‐decoder framework with deep residual learning. The generative adversarial network (GAN) 28 synthesizes high‐contrast images to transform the intensity distribution of brain lesions in its internal subregions.…”

Section: Resultsmentioning

confidence: 99%

Correcting and reweighting false label masks in brain tumor segmentation

Cheng

Ji²,

He³

2020

Medical Physics

View full text Add to dashboard Cite

Purpose Recently, brain tumor segmentation has made important progress. However, the quality of manual labels plays an important role in the performance, while in practice, it could vary greatly and in turn could substantially mislead the learning process and decrease the accuracy. We need to design a mechanism to combine label correction and sample reweighting to improve the effectiveness of brain tumor segmentation. Methods We propose a novel sample reweighting and label refinement method, and a novel three‐dimensional (3D) generative adversarial network (GAN) is introduced to combine these two models into an united framework. Results Extensive experiments on the BraTS19 dataset have demonstrated that our approach obtains competitive results when compared with other state‐of‐the‐art approaches when handling the false labels in brain tumor segmentation. Conclusions The 3D GAN‐based approach is an effective approach to handle false label masks by simultaneously applying label correction and sample reweighting. Our method is robust to variations in tumor shape and background clutter.

show abstract

Section: Resultsmentioning

confidence: 99%

Correcting and reweighting false label masks in brain tumor segmentation

Cheng

Ji²,

He³

2020

Medical Physics

View full text Add to dashboard Cite

show abstract

“…The encoder and decoder modules follow the original design of 3D U-Net. 5 We then added context exploitation modules in the network and initialized weights using Xavier initialization. Finally, the segmentation network is fine-tuned using the BraTS19 dataset.…”

Section: Methodsmentioning

confidence: 99%

“…We propose a cascade framework based on the 3D U‐Net structure 5 to segment brain tumor regions from multimodel MRI data, which is shown in Fig. 2.…”

Section: Methodsmentioning

confidence: 99%

“…In each subnetwork, the structure keeps the encoder‐decoder framework to obtain the semantic and fine feature volumes. The encoder captures discriminant feature volumes by using three‐dimensional (3D) CNN layers from 3D U‐net 5 . After that, the context exploitation module is carefully designed and used to strengthen the classification capability, among which dual self‐attention and space interaction learning are adopted to address the challenging issues.…”

Section: Introductionmentioning

confidence: 99%

“…Multiscale analysis plays an important role in medical image segmentation. 2D U‐Net 14 and 3D U‐Net 5 extract multiscale features in a 2D or 3D encoder‐decoder framework by employing the deep residual learning, 15 while other approaches use volume pyramid 16 or dilated convolution such as dilated FCN 17 for multiscale analysis. These approaches utilize additional information from multiple scales to infer the segmented mask.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spatial‐channel relation learning for brain tumor segmentation

Cheng

Ji²,

Ding

2020

Medical Physics

View full text Add to dashboard Cite

Purpose: Recently, research on brain tumor segmentation has made great progress. However, ambiguous patterns in magnetic resonance imaging data and linear fusion omitting semantic gaps between features in different branches remain challenging. We need to design a mechanism to fully utilize the similarity within the spatial space and channel space and the correlation between these two spaces to improve the result of volumetric segmentation. Methods: We propose a revised cascade structure network. In each subnetwork, a context exploitation module is introduced between the encoder and decoder, in which the dual attention mechanism is adopted to learn the information within the spatial space and channel space, and space interaction learning is employed to model the relation between the spatial and channel spaces. Results: Extensive experiments on the BraTS19 dataset have evaluated that our approach improves the dice coefficient (DC) by a margin of 2.1, 2.0, and 1.4 for whole tumor (WT), tumor core (TC), and enhancing tumor (ET), respectively, obtaining results competitive with the state-of-art approaches working on brain tumor segmentation. Conclusions: Context exploitation in the embedding feature spaces, including intraspace relations and interspace relations, can effectively model dependency in semantic features and alleviate the semantic gap in multimodel data. Our approach is also robust to variations in different modality.

show abstract

Artificial intelligence in tumor subregion analysis based on medical imaging: A review

Lin

Wynne

Zhou

et al. 2021

J Applied Clin Med Phys

View full text Add to dashboard Cite

Medical imaging is widely used in the diagnosis and treatment of cancer, and artificial intelligence (AI) has achieved tremendous success in medical image analysis. This paper reviews AI-based tumor subregion analysis in medical imaging. We summarize the latest AI-based methods for tumor subregion analysis and their applications. Specifically, we categorize the AI-based methods by training strategy: supervised and unsupervised. A detailed review of each category is presented, highlighting important contributions and achievements. Specific challenges and potential applications of AI in tumor subregion analysis are discussed.

show abstract

3D U-Net Based Brain Tumor Segmentation and Survival Days Prediction

Cited by 93 publications

References 19 publications

Correcting and reweighting false label masks in brain tumor segmentation

Correcting and reweighting false label masks in brain tumor segmentation

Spatial‐channel relation learning for brain tumor segmentation

Artificial intelligence in tumor subregion analysis based on medical imaging: A review

Contact Info

Product

Resources

About