mlsanityData to 7 Oct 2026

Tackling the Class Imbalance Problem of Deep Learning Based Head and Neck Organ Segmentation

arXiv 2201.01636 ↗First posted 5 Jan 2022cs.CV eess.IVcited by 6

Not on the map. Why?

Abstract (arXiv)

The segmentation of organs at risk (OAR) is a required precondition for the cancer treatment with image guided radiation therapy. The automation of the segmentation task is therefore of high clinical relevance. Deep Learning (DL) based medical image segmentation is currently the most successful approach, but suffers from the over-presence of the background class and the anatomically given organ size difference, which is most severe in the head and neck (HAN) area. To tackle the HAN area specific class imbalance problem we first optimize the patch-size of the currently best performing general purpose segmentation framework, the nnU-Net, based on the introduced class imbalance measurement, and second, introduce the class adaptive Dice loss to further compensate for the highly imbalanced setting. Both the patch-size and the loss function are parameters with direct influence on the class imbalance and their optimization leads to a 3% increase of the Dice score and 22% reduction of the 95% Hausdorff distance compared to the baseline, finally reaching 0.8±0.15 and 3.17±1.7 mm for the segmentation of seven HAN organs using a single and simple neural network. The patch-size optimization and the class adaptive Dice loss are both simply integrable in current DL based segmentation approaches and allow to increase the performance for class imbalanced segmentation tasks.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 16 of its 31 references that are in the map. First posted on arXiv 5 Jan 2022.

Builds on

16 of 31 references.

References · 16

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  3. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  4. 2017Focal Loss for Dense Object Detectioncited by 749
  5. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 614
  6. 2017Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentationcited by 109
  7. 2018Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapycited by 76
  8. 2018AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomycited by 54
  9. 2021Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentationcited by 34
  10. 2019FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Imagescited by 24
  11. 2020Organ at Risk Segmentation for Head and Neck Cancer using Stratified Learning and Neural Architecture Searchcited by 23
  12. 2017Hierarchical 3D fully convolutional networks for multi-organ segmentationcited by 19
4 more
  1. 2021FocusNetv2: Imbalanced Large and Small Organ Segmentation with Adversarial Shape Constraint for Head and Neck CT Imagescited by 17
  2. 2020Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentationcited by 16
  3. 2021A Novel Hybrid Convolutional Neural Network for Accurate Organ Segmentation in 3D Head and Neck CT Imagescited by 7
  4. 2018Segmentation of Head and Neck Organs at Risk Using CNN with Batch Dice Losscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 1; 2026: 2.

6 papers.

  1. 2023Towards more precise automatic analysis: a comprehensive survey of deep learning-based multi-organ segmentationcited by 3
  2. 2023Fully Automatic Segmentation of Gross Target Volume and Organs-at-Risk for Radiotherapy Planning of Nasopharyngeal Carcinomacited by 2
  3. 2025MOSAIC: A Multi-View 2.5D Organ Slice Selector with Cross-Attentional Reasoning for Anatomically-Aware CT Localization in Medical Organ Segmentationcited by 1
  4. 2024Alleviating Class Imbalance in Semi-supervised Multi-organ Segmentation via Balanced Subclass Regularizationcited by 0
  5. 2026EPRA U-Net: An Efficient Pyramid Residual Attention Framework for Accurate Infarct Segmentation in Diffusion-Weighted MRIcited by 0
  6. 2026Importance-Aware Feature Sparsification for Wireless Split Learningcited by 0