mlsanityData to 7 Oct 2026

Anatomy-Decomposed Chest Computed Tomography (CT) Projections as Scalable Supervision for Bone Suppression in Chest Radiographs

arXiv 2609.24937 ↗First posted 21 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Bone overlap can obscure abnormalities in chest radiographs, while scarce paired training data limit supervised bone suppression. We address this challenge with a digitally reconstructed radiograph (DRR) framework that converts chest computed tomography (CT) into paired supervision for component suppression. A novel bone segmentation algorithm enables CT decomposition into bone, non-lung soft-tissue, and lung components, which are projected separately. Their weighted combination yields synthetic radiographs with pixel-registered component images that sum exactly to the full DRR. Models trained on these data suppress bone or lung components by predicting the target component and recovering the remainder by subtraction, transferring to real radiographs without real paired training data. As an extension, their outputs on real radiographs provide target domains for unpaired, component-wise DRR translation, reducing the appearance gap while retaining anatomical details. Across multiple public datasets, downstream detection experiments demonstrate the utility of bone suppression, with gains concentrated on abnormalities with substantial bone overlap. Compared with open-source DRR engines applied to the same CTs, our unmodified DRRs achieve comparable realism and preservation of label-relevant anatomy, while translated DRRs achieve the best Fr'echet inception distance (FID), lung-field sharpness, and agreement with source-CT anatomy among the evaluated methods. Models and inference code: https://huggingface.co/qureaiorg/bone-suppression ; Translated projections: https://huggingface.co/datasets/qureaiorg/ct2xr-projections.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 72 references that are in the map. First posted on arXiv 21 Sep 2026.

Builds on

31 of 72 references.

References · 31

  1. 2016Pyramid Scene Parsing Networkcited by 2,472
  2. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  3. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  4. 2018Demystifying MMD GANscited by 1,268
  5. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  6. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  7. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  8. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  9. 2022MedCLIP: Contrastive Learning from Unpaired Medical Images and Textcited by 564
  10. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  11. 2020VinDr-CXR: An open dataset of chest X-rays with radiologist's annotationscited by 236
  12. 2024Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomographycited by 192
19 more
  1. 2019U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translationcited by 186
  2. 2021TorchXRayVision: A library of chest X-ray datasets and modelscited by 131
  3. 2018Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mappingcited by 113
  4. 2017One-Sided Unsupervised Domain Mappingcited by 91
  5. 2021Dual Contrastive Learning for Unsupervised Image-to-Image Translationcited by 65
  6. 2023Large-Vocabulary Segmentation for Medical Images with Text Promptscited by 60
  7. 2018DeepDRR -- A Catalyst for Machine Learning in Fluoroscopy-guided Procedurescited by 55
  8. 2022QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translationcited by 39
  9. 2022Fast Auto-Differentiable Digitally Reconstructed Radiographs for Solving Inverse Problems in Intraoperative Imagingcited by 37
  10. 2021A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentationcited by 33
  11. 2023Accurate Fine-Grained Segmentation of Human Anatomy in Radiographs via Volumetric Pseudo-Labelingcited by 24
  12. 2024DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Renderingcited by 22
  13. 2020Generalizing Spatial Transformers to Projective Geometry with Applications to 2D/3D Registrationcited by 21
  14. 2025MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable Autoencoderscited by 20
  15. 2021Chest X-Ray Bone Suppression for Improving Classification of Tuberculosis-Consistent Findingscited by 13
  16. 2022Image Synthesis with Disentangled Attributes for Chest X-Ray Nodule Augmentation and Detectioncited by 11
  17. 2024Nodule detection and generation on chest X-rays: NODE21 Challengecited by 7
  18. 2020Bone Structures Extraction and Enhancement in Chest Radiographs via CNN Trained on Synthetic Datacited by 5
  19. 2021A bone suppression model ensemble to improve COVID-19 detection in chest X-rayscited by 2

Built on by

Not cited yet.