# 3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study

arXiv: https://arxiv.org/abs/1612.03925 · HTML: https://mlsanity.com/paper/1612.03925/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2016.

## Built on by (most cited first, 19 of 19)

- [Weakly supervised segmentation with cross-modality equivariant constraints](https://mlsanity.com/paper/2104.02488/) (2021)
- [Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization](https://mlsanity.com/paper/2209.09209/) (2022)
- [Do We Really Need Dice? The Hidden Region-Size Biases of Segmentation Losses](https://mlsanity.com/paper/2104.08717/) (2021)
- [Applications of Deep Learning Techniques for Automated Multiple Sclerosis Detection Using Magnetic Resonance Imaging: A Review](https://mlsanity.com/paper/2105.04881/) (2021)
- [Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review](https://mlsanity.com/paper/2206.11233/) (2022)
- [Learning to segment fetal brain tissue from noisy annotations](https://mlsanity.com/paper/2203.14962/) (2022)
- [Segmentation with mixed supervision: Confidence maximization helps knowledge distillation](https://mlsanity.com/paper/2109.10902/) (2021)
- [Whole Brain Segmentation with Full Volume Neural Network](https://mlsanity.com/paper/2110.15601/) (2021)
- [Harmonizing Flows: Unsupervised MR harmonization based on normalizing flows](https://mlsanity.com/paper/2301.11551/) (2023)
- [Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization](https://mlsanity.com/paper/2407.15717/) (2024)
- [DeepCERES: A Deep learning method for cerebellar lobule segmentation using ultra-high resolution multimodal MRI](https://mlsanity.com/paper/2401.12074/) (2024)
- [Deep learning-based neurodevelopmental assessment in preterm infants](https://mlsanity.com/paper/2601.11944/) (2026)
- [An MRF-UNet Product of Experts for Image Segmentation](https://mlsanity.com/paper/2104.05495/) (2021)
- [Label merge-and-split: A graph-colouring approach for memory-efficient brain parcellation](https://mlsanity.com/paper/2404.10572/) (2024)
- [Bladder segmentation based on deep learning approaches: current limitations and lessons](https://mlsanity.com/paper/2101.06498/) (2021)
- [Anisotropic mesh adaptation for region-based segmentation accounting for image spatial information](https://mlsanity.com/paper/2112.10138/) (2021)
- [Mixup-Privacy: A simple yet effective approach for privacy-preserving segmentation](https://mlsanity.com/paper/2305.13756/) (2023)
- [UESA-Net: U-Shaped Embedded Multidirectional Shrinkage Attention Network for Ultrasound Nodule Segmentation](https://mlsanity.com/paper/2509.22763/) (2025)
- [Beyond one-hot encoding? Journey into compact encoding for large multi-class segmentation](https://mlsanity.com/paper/2510.00667/) (2025)

## Abstract (arXiv)

This study investigates a 3D and fully convolutional neural network (CNN) for subcortical brain structure segmentation in MRI. 3D CNN architectures have been generally avoided due to their computational and memory requirements during inference. We address the problem via small kernels, allowing deeper architectures. We further model both local and global context by embedding intermediate-layer outputs in the final prediction, which encourages consistency between features extracted at different scales and embeds fine-grained information directly in the segmentation process. Our model is efficiently trained end-to-end on a graphics processing unit (GPU), in a single stage, exploiting the dense inference capabilities of fully CNNs. We performed comprehensive experiments over two publicly available datasets. First, we demonstrate a state-of-the-art performance on the ISBR dataset. Then, we report a em large-scale multi-site evaluation over 1112 unregistered subject datasets acquired from 17 different sites (ABIDE dataset), with ages ranging from 7 to 64 years, showing that our method is robust to various acquisition protocols, demographics and clinical factors. Our method yielded segmentations that are highly consistent with a standard atlas-based approach, while running in a fraction of the time needed by atlas-based methods and avoiding registration/normalization steps. This makes it convenient for massive multi-site neuroanatomical imaging studies. To the best of our knowledge, our work is the first to study subcortical structure segmentation on such large-scale and heterogeneous data.