mlsanityData to 7 Oct 2026

CTForensics: A Comprehensive Dataset and Method for AI-Generated CT Image Detection

arXiv 2603.01878 ↗First posted 2 Mar 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent advances in generative AI have made synthetic Computed Tomography (CT) images increasingly realistic, enabling promising applications in medical data augmentation while raising serious concerns about clinical safety and data trustworthiness. Detecting AI-generated CT images remains challenging for two key reasons: existing benchmarks cover only limited generation sources, and many detectors are adapted from natural-image forensics without explicitly modeling CT-specific imaging properties. In this paper, we introduce CTForensics, a dataset for detecting AI-generated CT images. CTForensics contains 75,990 2D CT images, including a dedicated test benchmark of 29,990 balanced authentic and generated samples from ten representative CT generative models spanning GAN-based and diffusion-based paradigms. We further propose the Enhanced Spatial-Frequency CT Forgery Detector (ESF-CTFD), a CT-oriented CNN framework built around a Wavelet-Enhanced Central Stem, Multi-Scale Spatial Aggregation, and a Frequency-Aware Prediction Block. The Wavelet-Enhanced Central Stem enhances local intensity correlations and high-frequency residuals, Multi-Scale Spatial Aggregation aligns anatomical features across resolutions with lightweight residual units, and the Frequency-Aware Prediction Block models global spectral artifacts. Extensive experiments on CTForensics show that ESF-CTFD achieves 96.01% mAcc and 99.96% mAP, outperforming existing methods and maintaining strong robustness under realistic perturbations with only a 0.99% average drop. Codes will be available at https://github.com/liyih/CTForensics.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

29 of 40 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  5. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  6. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  7. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 483
  8. 2024Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomographycited by 192
  9. 2020Searching Central Difference Convolutional Networks for Face Anti-Spoofingcited by 173
  10. 2021Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detectioncited by 133
  11. 2024Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspectivecited by 88
  12. 2024Wavelet Convolutions for Large Receptive Fieldscited by 74
17 more
  1. 2022Conversion Between CT and MRI Images Using Diffusion and Score-Matching Modelscited by 69
  2. 2024Anatomically-Controllable Medical Image Generation with Segmentation-Guided Diffusion Modelscited by 69
  3. 2023GenerateCT: Text-Conditional Generation of 3D Chest CT Volumescited by 64
  4. 2020Hierarchical Amortized Training for Memory-efficient High Resolution 3D GANcited by 60
  5. 2023MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Imagescited by 41
  6. 2019CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learningcited by 31
  7. 2024Generative Enhancement for 3D Medical Imagescited by 14
  8. 2025CWNet: Causal Wavelet Network for Low-Light Image Enhancementcited by 10
  9. 2025FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependenciescited by 9
  10. 2025TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced Efficiencycited by 8
  11. 2025Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learningcited by 8
  12. 2025Lung-DDPM: Semantic Layout-guided Diffusion Models for Thoracic CT Image Synthesiscited by 7
  13. 2025From Alignment to Synthesis: Contrastive Volumetric Grounding for Text-to-CT Generationcited by 6
  14. 2025Toward Medical Deepfake Detection: A Comprehensive Dataset and Novel Methodcited by 6
  15. 2021Machine Learning based Medical Image Deepfake Detection: A Comparative Studycited by 5
  16. 2024Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakescited by 5
  17. 2025Lung-DDPM+: Efficient Thoracic CT Image Synthesis using Diffusion Probabilistic Modelcited by 4

Built on by

Not cited yet.