mlsanityData to 14 Oct 2026

Pseudo-Label Guided Multi-Contrast Generalization for Non-Contrast Organ-Aware Segmentation

arXiv 2205.05898 ↗First posted 12 May 2022eess.IV cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Non-contrast computed tomography (NCCT) is commonly acquired for lung cancer screening, assessment of general abdominal pain or suspected renal stones, trauma evaluation, and many other indications. However, the absence of contrast limits distinguishing organ in-between boundaries. In this paper, we propose a novel unsupervised approach that leverages pairwise contrast-enhanced CT (CECT) context to compute non-contrast segmentation without ground-truth label. Unlike generative adversarial approaches, we compute the pairwise morphological context with CECT to provide teacher guidance instead of generating fake anatomical context. Additionally, we further augment the intensity correlations in 'organ-specific' settings and increase the sensitivity to organ-aware boundary. We validate our approach on multi-organ segmentation with paired non-contrast & contrast-enhanced CT scans using five-fold cross-validation. Full external validations are performed on an independent non-contrast cohort for aorta segmentation. Compared with current abdominal organs segmentation state-of-the-art in fully supervised setting, our proposed pipeline achieves a significantly higher Dice by 3.98% (internal multi-organ annotated), and 8.00% (external aorta annotated) for abdominal organs segmentation. The code and pretrained models are publicly available at https://github.com/MASILab/ContrastMix.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 39 references that are in the map. First posted on arXiv 12 May 2022.

Builds on

23 of 39 references.

References · 23

  1. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  2. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  3. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 959
  4. 2013Domain Generalization via Invariant Feature Representationcited by 623
  5. 2018nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentationcited by 291
  6. 2020Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentationcited by 134
  7. 2016Unsupervised domain adaptation in brain lesion segmentation with adversarial networkscited by 125
  8. 2020Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domainscited by 124
  9. 2020Unpaired Multi-modal Segmentation via Knowledge Distillationcited by 81
  10. 2019Disentangled Representation Learning in Cardiac Image Analysiscited by 69
  11. 2018SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truthcited by 68
  12. 2018Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Losscited by 61
11 more
  1. 20193D Whole Brain Segmentation using Spatially Localized Atlas Network Tilescited by 50
  2. 2019Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effectscited by 43
  3. 2018An application of cascaded 3D fully convolutional networks for medical image segmentationcited by 34
  4. 2018Multi-Scale Coarse-to-Fine Segmentation for Screening Pancreatic Ductal Adenocarcinomacited by 24
  5. 2018A multi-scale pyramid of 3D fully convolutional networks for abdominal multi-organ segmentationcited by 17
  6. 2021Unsupervised Domain Adaptation for Small Bowel Segmentation using Disentangled Representationcited by 11
  7. 2016Spatial Aggregation of Holistically-Nested Networks for Automated Pancreas Segmentationcited by 10
  8. 2020RAP-Net: Coarse-to-Fine Multi-Organ Segmentation with Single Random Anatomical Priorcited by 8
  9. 2019Semi-Supervised Multi-Organ Segmentation through Quality Assurance Supervisioncited by 6
  10. 2020A Deep learning Approach to Generate Contrast-Enhanced Computerised Tomography Angiography without the Use of Intravenous Contrast Agentscited by 3
  11. 2021Semantic-Aware Contrastive Learning for Multi-object Medical Image Segmentationcited by 3

Built on by

Not cited yet.