# MRI Tumor Segmentation with Densely Connected 3D CNN

arXiv: https://arxiv.org/abs/1802.02427 · HTML: https://mlsanity.com/paper/1802.02427/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jan 2018.

## Built on by (most cited first, 16 of 16)

- [A review of deep learning-based information fusion techniques for multimodal medical image classification](https://mlsanity.com/paper/2404.15022/) (2024)
- [Medical Image Segmentation with 3D Convolutional Neural Networks: A Survey](https://mlsanity.com/paper/2108.08467/) (2021)
- [Large-Kernel Attention for 3D Medical Image Segmentation](https://mlsanity.com/paper/2207.11225/) (2022)
- [Large-Scale Extended Granger Causality for Classification of Marijuana Users From Functional MRI](https://mlsanity.com/paper/2101.01832/) (2021)
- [H-DenseFormer: An Efficient Hybrid Densely Connected Transformer for Multimodal Tumor Segmentation](https://mlsanity.com/paper/2307.01486/) (2023)
- [Large-scale Augmented Granger Causality (lsAGC) for Connectivity Analysis in Complex Systems: From Computer Simulations to Functional MRI (fMRI)](https://mlsanity.com/paper/2101.09354/) (2021)
- [Classification of Schizophrenia from Functional MRI Using Large-scale Extended Granger Causality](https://mlsanity.com/paper/2101.10471/) (2021)
- [ME-Net: Multi-Encoder Net Framework for Brain Tumor Segmentation](https://mlsanity.com/paper/2203.11213/) (2022)
- [Multi-modal Brain Tumor Segmentation via Missing Modality Synthesis and Modality-level Attention Fusion](https://mlsanity.com/paper/2203.04586/) (2022)
- [Computational Intelligence Approach to Improve the Classification Accuracy of Brain Neoplasm in MRI Data](https://mlsanity.com/paper/2101.09658/) (2021)
- [Recurrent U-net for automatic pelvic floor muscle segmentation on 3D ultrasound](https://mlsanity.com/paper/2107.13833/) (2021)
- [An End-to-End learnable Flow Regularized Model for Brain Tumor Segmentation](https://mlsanity.com/paper/2109.00622/) (2021)
- [Correlation between image quality metrics of magnetic resonance images and the neural network segmentation accuracy](https://mlsanity.com/paper/2111.01093/) (2021)
- [A Novel SLCA-UNet Architecture for Automatic MRI Brain Tumor Segmentation](https://mlsanity.com/paper/2307.08048/) (2023)
- [Hand Gesture Classification Based on Forearm Ultrasound Video Snippets Using 3D Convolutional Neural Networks](https://mlsanity.com/paper/2409.16431/) (2024)
- [MBDRes-U-Net: Multi-Scale Lightweight Brain Tumor Segmentation Network](https://mlsanity.com/paper/2411.01896/) (2024)

## Abstract (arXiv)

Glioma is one of the most common and aggressive types of primary brain tumors. The accurate segmentation of subcortical brain structures is crucial to the study of gliomas in that it helps the monitoring of the progression of gliomas and aids the evaluation of treatment outcomes. However, the large amount of required human labor makes it difficult to obtain the manually segmented Magnetic Resonance Imaging (MRI) data, limiting the use of precise quantitative measurements in the clinical practice. In this work, we try to address this problem by developing a 3D Convolutional Neural Network~(3D CNN) based model to automatically segment gliomas. The major difficulty of our segmentation model comes with the fact that the location, structure, and shape of gliomas vary significantly among different patients. In order to accurately classify each voxel, our model captures multi-scale contextual information by extracting features from two scales of receptive fields. To fully exploit the tumor structure, we propose a novel architecture that hierarchically segments different lesion regions of the necrotic and non-enhancing tumor~(NCR/NET), peritumoral edema~(ED) and GD-enhancing tumor~(ET). Additionally, we utilize densely connected convolutional blocks to further boost the performance. We train our model with a patch-wise training schema to mitigate the class imbalance problem. The proposed method is validated on the BraTS 2017 dataset and it achieves Dice scores of 0.72, 0.83 and 0.81 for the complete tumor, tumor core and enhancing tumor, respectively. These results are comparable to the reported state-of-the-art results, and our method is better than existing 3D-based methods in terms of compactness, time and space efficiency.