Multimodal Brain Tumor Segmentation with Normal Appearance Autoencoder

Astaraki, Mehdi; Wang, Chunliang; Carrizo, Gabriel; Toma-Daşu, Iuliana; Smedby, Örjan

doi:10.1007/978-3-030-46643-5_31

Cited by 3 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, it may incur complications like hydrocephalus, where the obstruction of Cerebrospinal fluid (CSF) flow leads to increased brain pressure. 4 In recent years, supervised Deep Learning-based methods have shown promising results in different aspects of cancer image analysis, including tumor detection, 5,6 segmentation, 7,8 classification, 9 and survival analysis. 10,11 However, the accuracy and robustness of such data-greedy methods heavily depend on the quality and quantity of the training data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Synthesis of pediatric brain tumor images with mass effect

Zhou

Smedby

et al. 2023

Medical Imaging 2023: Image Processing

Self Cite

View full text Add to dashboard Cite

In children, brain tumors are the leading cause of cancer-related death. The amount of labeled data in children is much lower than that for adult subjects. This paper proposes a new method to synthesize high-quality pathological pediatric MRI brain images from pathological adult ones. To realistically simulate the appearance of brain tumors, the proposed method considers the mass effect, i.e., the deformation induced by the tumor to the surrounding tissue. First, a probabilistic U-Net was trained to predict a deformation field that encodes the mass effect from the healthy-pathological image pair. Second, the learned deformation field was utilized to warp the healthy mask to simulate the mass effect. The tumor mask is also added to the warped mask. Finally, a label-toimage transformer, i.e., the SPADE GAN, was trained to synthesize a pathological image from the segmentation masks of gray matter, white matter, CSF and the tumor. The synthetic images were evaluated in two quantitative ways: i) three supervised segmentation pipelines were trained on datasets with and without synthetic images. Two pipelines show over 1% improvements in the Dice scores when the datasets were augmented with synthetic data. ii) The Fréchet inception distance was measured between real and synthetic image distributions. Results show that SPADE outperforms the state-of-the-art Pix2PixHD method in both T1w and T2w modalities. The source code can be accessed on https://github.com/audreyeternal/pediatric-tumor-generation.

show abstract

Section: Introductionmentioning

confidence: 99%

“…15 Other methods simulate tumors by directly pasting the tumor to the healthy image using, e.g, Poisson blending. 16 However, this approach cannot mimic the mass effect mentioned before.…”

Section: Introductionmentioning

confidence: 99%