mlsanityData to 7 Oct 2026

DALight-3D: A Lightweight 3D U-Net for Brain Tumor Segmentation from Multi-Modal MRI

arXiv 2605.04518 ↗First posted 6 May 2026cs.CV cs.LG cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

Automatic brain tumor segmentation from multi-modal MRI remains challenging because volumetric models often incur substantial computational cost. This paper presents DALight-3D, a compact 3D U-Net variant that combines depthwise separable 3D convolutions, identifier-conditioned normalization, cross-slice attention, and adaptive skip fusion. The method is evaluated on the Medical Segmentation Decathlon Task01 BrainTumour benchmark under matched optimization settings against standard 3D U-Net, Attention U-Net, Residual 3D U-Net, and V-Net baselines. In the reported 50-epoch comparison, DALight-3D achieves a mean Dice of 0.727 with 2.22M parameters, compared with 0.710 Dice and 3.20M parameters for Residual 3D U-Net. Component-wise ablations show consistent performance degradation when SepConv, identifier-conditioned normalization, CSA, or SSFB is removed. These results indicate that DALight-3D offers a favorable accuracy-efficiency trade-off within the present benchmark setting.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 34 references that are in the map. First posted on arXiv 6 May 2026.

Builds on

22 of 34 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  9. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  10. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  11. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  12. 2018Group Normalizationcited by 1,514
10 more
  1. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  2. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  3. 2019A large annotated medical image dataset for the development and evaluation of segmentation algorithmscited by 371
  4. 20183D MRI brain tumor segmentation using autoencoder regularizationcited by 324
  5. 2016Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentationcited by 263
  6. 2015Brain Tumor Segmentation with Deep Neural Networkscited by 137
  7. 2016Unsupervised domain adaptation in brain lesion segmentation with adversarial networkscited by 125
  8. 2018No New-Netcited by 61
  9. 2017Automatic Brain Tumor Segmentation using Cascaded Anisotropic Convolutional Neural Networkscited by 33
  10. 2020Brain tumor segmentation with self-ensembled, deeply-supervised 3D U-net neural networks: a BraTS 2020 challenge solutioncited by 20

Built on by

Not cited yet.