A Two-Stage Cascade Model with Variational Autoencoders and Attention Gates for MRI Brain Tumor Segmentation

Lyu, Chenggang; Shu, Hai

doi:10.1007/978-3-030-72084-1_39

Cited by 30 publications

(20 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our experiments, we adopt the region-based training strategy, which directly optimizes these three sub-regions instead of individual labels, since its effectiveness has been widely verified in brain tumor segmentation (Isensee et al, 2020 ). For post-processing, we also adopt a frequently-used approach that the ET is replaced by the NCR/NET when its volume is less than 500 voxels to remove possible false predictions on ET (Isensee et al, 2020 ; Lyu and Shu, 2020 ; Zhang et al, 2020a ). Two popular objective metrics including the Dice score and the Hausdorff distance (%95) are used to evaluate the segmentation accuracy.…”

Section: Resultsmentioning

confidence: 99%

“…Since the TC and ET areas are included in the WT area, the segmentation result of the first stage is used to locate the input region of the second stage, which is helpful to alleviate the class imbalance issue. The sliding window-based approach introduced in Lyu and Shu ( 2020 ) is adopted to determine the input region of the second stage, namely, the window that contains the maximum number of tumor voxels is selected. In addition, considering that the peritumoral edema are mainly highlighted in T2 and Flair modalities, we only use T2 and Flair as the input source modalities in the first stage.…”

Section: The Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Brain tumor segmentation in multimodal MRI via pixel-level and feature-level image fusion

Liu

Mu²,

Cheng³

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

Brain tumor segmentation in multimodal MRI volumes is of great significance to disease diagnosis, treatment planning, survival prediction and other relevant tasks. However, most existing brain tumor segmentation methods fail to make sufficient use of multimodal information. The most common way is to simply stack the original multimodal images or their low-level features as the model input, and many methods treat each modality data with equal importance to a given segmentation target. In this paper, we introduce multimodal image fusion technique including both pixel-level fusion and feature-level fusion for brain tumor segmentation, aiming to achieve more sufficient and finer utilization of multimodal information. At the pixel level, we present a convolutional network named PIF-Net for 3D MR image fusion to enrich the input modalities of the segmentation model. The fused modalities can strengthen the association among different types of pathological information captured by multiple source modalities, leading to a modality enhancement effect. At the feature level, we design an attention-based modality selection feature fusion (MSFF) module for multimodal feature refinement to address the difference among multiple modalities for a given segmentation target. A two-stage brain tumor segmentation framework is accordingly proposed based on the above components and the popular V-Net model. Experiments are conducted on the BraTS 2019 and BraTS 2020 benchmarks. The results demonstrate that the proposed components on both pixel-level and feature-level fusion can effectively improve the segmentation accuracy of brain tumors.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: The Proposed Methodsmentioning

confidence: 99%

Brain tumor segmentation in multimodal MRI via pixel-level and feature-level image fusion

Liu

Mu²,

Cheng³

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…This method works well in whole tumor and core tumor segmentation tasks. In enhanced tumor segmentation, a tumor region segmentation model that combines a two-stage codec with regularization and attention mechanism proposed by Lyu C et al [53] works well. [27]; (e) is the structure diagram of a multi plane convolutional neural network proposed by Subhashis B et al [35]; (f) is the structure diagram of hybrid high-resolution and nonlocal feature network (h2nf net) proposed by Jia h et al [52].…”

Section: Databases Commonly Usedmentioning

confidence: 99%

Section: Databases Commonly Usedmentioning

confidence: 99%

Overview of Multi-Modal Brain Tumor MR Image Segmentation

Zhang

Yang³

et al. 2021

Healthcare

View full text Add to dashboard Cite

The precise segmentation of brain tumor images is a vital step towards accurate diagnosis and effective treatment of brain tumors. Magnetic Resonance Imaging (MRI) can generate brain images without tissue damage or skull artifacts, providing important discriminant information for clinicians in the study of brain tumors and other brain diseases. In this paper, we survey the field of brain tumor MRI images segmentation. Firstly, we present the commonly used databases. Then, we summarize multi-modal brain tumor MRI image segmentation methods, which are divided into three categories: conventional segmentation methods, segmentation methods based on classical machine learning methods, and segmentation methods based on deep learning methods. The principles, structures, advantages and disadvantages of typical algorithms in each method are summarized. Finally, we analyze the challenges, and suggest a prospect for future development trends.

show abstract

“…GANs which were generative models became popular in around 2018 found applications in brain segmentation [34][35][36][37][38]. Of late, attention modules in convolutional neural networks were found to give improved segmentation results [39][40][41][42][43][44][45]. Some recent papers focused not only on brain segmentation, but also on progression during the treatment phase and the survival prediction problem [46][47][48][49][50][51][52].…”

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of Deep Learning Models on Brain Tumor Segmentation Datasets: BraTS 2015-2020 Datasets

Aggarwal¹,

Tiwari²,

Mangipudi³

2022

RIA

View full text Add to dashboard Cite

Deep Learning neural networks have shown applicability in segmentation of brain tumor images.This research have been carried for comprehensive review of several deep learning neural networks. The datasets included in this study are standard datasets Multimodal Brain Tumor Segmentation (BraTS). This paper has summarized the performance of various deep learning neural network algorithms on BraTS datasets. Algorithms have been compared and summarized against the baseline models with specific attributes like dice score, PPV and sensitivity. It has been found that out of the different models applied on the BraTS 2015 dataset GAN in the year 2020 algorithm is showing better results on this data set. GAN architecture termed RescueNet gave the best segmentation results in terms of 0.94 dice score and 0.88 Sensitivity. This has been also observed that models used cascaded deep learning models had independent deep learning models at each stage which had no correlation among the stages which can cause class imbalance. Further it have found that the Attention models tried to solve problem of class imbalance in the brain tumor segmentation task. This work also found that existing CNN’s is having overfitting issues. For this ResNet models can add a rapid connect bounce relationship parallel to the layers of CNN to accomplish better outcomes for the brain tumor segmentation task.

show abstract

A Two-Stage Cascade Model with Variational Autoencoders and Attention Gates for MRI Brain Tumor Segmentation

Cited by 30 publications

References 17 publications

Brain tumor segmentation in multimodal MRI via pixel-level and feature-level image fusion

Brain tumor segmentation in multimodal MRI via pixel-level and feature-level image fusion

Overview of Multi-Modal Brain Tumor MR Image Segmentation

Comparative Analysis of Deep Learning Models on Brain Tumor Segmentation Datasets: BraTS 2015-2020 Datasets

Contact Info

Product

Resources

About