# A Prior Knowledge Based Tumor and Tumoral Subregion Segmentation Tool for Pediatric Brain Tumors

arXiv: https://arxiv.org/abs/2109.14775 · HTML: https://mlsanity.com/paper/2109.14775/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 9 references that are in the map.
- First posted on arXiv 30 Sep 2021.

## Builds on (most cited first, 4 of 4)

- [3D MRI brain tumor segmentation using autoencoder regularization](https://mlsanity.com/paper/1810.11654/) (2018)
- [Automatic Brain Tumor Segmentation using Cascaded Anisotropic Convolutional Neural Networks](https://mlsanity.com/paper/1709.00382/) (2017)
- [DeepNeuro: an open-source deep learning toolbox for neuroimaging](https://mlsanity.com/paper/1808.04589/) (2018)
- [Sequential 3D U-Nets for Biologically-Informed Brain Tumor Segmentation](https://mlsanity.com/paper/1709.02967/) (2017)

## Built on by (most cited first, 1 of 1)

- [Enhancing efficiency in paediatric brain tumour segmentation using a pathologically diverse single-center clinical dataset](https://mlsanity.com/paper/2507.22152/) (2025)

## Abstract (arXiv)

In the past few years, deep learning (DL) models have drawn great attention and shown superior performance on brain tumor and subregion segmentation tasks. However, the success is limited to segmentation of adult gliomas, where sufficient data have been collected, manually labeled, and published for training DL models. It is still challenging to segment pediatric tumors, because the appearances are different from adult gliomas. Hence, directly applying a pretained DL model on pediatric data usually generates unacceptable results. Because pediatric data is very limited, both labeled and unlabeled, we present a brain tumor segmentation model that is based on knowledge rather than learning from data. We also provide segmentation of more subregions for super heterogeneous tumor like atypical teratoid rhabdoid tumor (ATRT). Our proposed approach showed superior performance on both whole tumor and subregion segmentation tasks to DL based models on our pediatric data when training data is not available for transfer learning.