A Multi-path Decoder Network for Brain Tumor Segmentation
Autor: | Anna M. Barrett, Yunzhe Xue, Usman Roshan, Fadi G. Farhat, Jeffrey R. Binder, William W. Graves, Olga Boukrina, Meiyan Xie |
---|---|
Rok vydání: | 2020 |
Předmět: |
Modality (human–computer interaction)
Computer science business.industry Brain tumor Pattern recognition Image segmentation medicine.disease Convolutional neural network 030218 nuclear medicine & medical imaging Image (mathematics) 03 medical and health sciences Identification (information) 0302 clinical medicine medicine State (computer science) Artificial intelligence business Encoder 030217 neurology & neurosurgery Block (data storage) |
Zdroj: | Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries ISBN: 9783030466428 BrainLes@MICCAI (2) |
Popis: | The identification of brain tumor type, shape, and size from MRI images plays an important role in glioma diagnosis and treatment. Manually identifying the tumor is time expensive and prone to error. And while information from different image modalities may help in principle, using these modalities for manual tumor segmentation may be even more time consuming. Convolutional U-Net architectures with encoders and decoders are state of the art in automated methods for image segmentation. Often only a single encoder and decoder is used, where different modalities and regions of the tumor share the same model parameters. This may lead to incorrect segmentations. We propose a convolutional U-Net that has separate, independent encoders for each image modality. The outputs from each encoder are concatenated and given to separate fusion and decoder blocks for each region of the tumor. The features from each decoder block are then calibrated in a final feature fusion block, after which the model gives it final predictions. Our network is an end-to-end model that simplifies training and reproducibility. On the BraTS 2019 validation dataset our model achieves average Dice values of 0.75, 0.90, and 0.83 for the enhancing tumor, whole tumor, and tumor core subregions respectively. |
Databáze: | OpenAIRE |
Externí odkaz: |