Publications:
Maye-Lasserre, Tom; Li, Yitong; Jian, Bailiang; Ghahremani, Morteza; Wiestler, Benedikt; Wachinger, Christian Conference on Empirical Methods in Natural Language Processing (EMNLP) 2026, 2026. @conference{maye2026generating,Modern 3D medical vision-language models (VLMs) can generate fluent radiology-style text while exhibit critically low pathology detection and output diversity, collapsing to generic templates that under-report rare yet critical findings. We identify this failure mode as Template Collapse. This failure stems from the unique constraints of 3D medical imaging, e.g., limited data, severe label imbalance, and weak signals from volumetric encoders. Under these constraints, text-generation objectives encourage shortcut learning and fluent but weakly grounded reports. We systematically diagnose the Template Collapse through clinical fidelity, output diversity, normal-template bias, and rare-finding survival. To mitigate it, we propose CLarGen, a decoupled framework that separates what to say (clinical detection) from how to say it (language synthesis). CLarGen uses (i) a Latent Query Transformer for multi-label pathology detection, (ii) pathology-guided retrieval for clinically matched exemplars, and (iii) a medical language model to synthesize the final report from detected findings and retrieved context. Across state-of-the-art 3D CT report generation baselines, CLarGen mitigates Template Collapse and substantially improves clinical accuracy (macro-F1 0.487 vs. 0.189; CRG 0.472 vs. 0.368) while maintaining fluent reporting. Our results suggest that explicit, measurable clinical grounding is essential for template-collapse-resistant 3D CT report generation. |
Rath, Martin; Ghahremani, Morteza; Li, Yitong; Taghipour, Ashkan; Makowski, Marcus; Wachinger, Christian Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rays Conference The British Machine Vision Conference (BMVC) 2026, 2026. @conference{rath2026conditional,Computed tomography (CT) provides rich 3D anatomical detail but is often constrained by high radiation exposure, substantial costs, and limited availability. Standard chest X-rays are cost-effective and widely accessible, but provide only 2D projections with limited pathological information. Reconstructing 3D CT volumes from 2D X-rays could markedly increase diagnostic accessibility, yet existing methods rely predominantly on synthetic X-ray projections, limiting clinical generalization. We propose AXON, a multi-stage diffusion-based framework that reconstructs 3D CT volumes directly from real X-rays with substantially improved fidelity over existing approaches. AXON follows a coarse-to-fine paradigm: a Brownian Bridge diffusion model first captures global anatomical structure, and a ControlNet-guided refinement stage then enhances local intensity detail and anatomical realism. To alleviate the depth ambiguity inherent in 2D-to-3D reconstruction, AXON incorporates bi-planar X-ray views, enabling more accurate spatial reasoning and structural recovery. A dedicated super-resolution module further increases the spatial resolution of the generated volumes. Experiments on public and external datasets show that AXON consistently surpasses state-of-the-art approaches while generalizing across diverse clinical distributions. At our highest-resolution bi-planar setting, AXON achieves an 11.9% improvement in PSNR and an 11.0% increase in SSIM over the strongest baseline evaluated at that resolution. In the 1283 single-planar setting, it maintains a lead of 7.8% in PSNR on LIDC-IDRI, with larger margins on the external clinical dataset of 8.0% in PSNR and 16.9% in SSIM. |
Li, Yitong; Ghahremani, Morteza; Wally, Youssef; Wachinger, Christian DiaMond: Dementia Diagnosis with Multi-Modal Vision Transformers Using MRI and PET Conference IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025. @conference{Li2024diamond, |
Wang, Jiajun; Ghahremani, Morteza; Li, Yitong; Ommer, Björn; Wachinger., Christian Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation Conference Conference on Neural Information Processing Systems (NeurIPS), 2024. @conference{Wang2024, |
Ghahremani, Morteza; Khateri, Mohammad; Jian, Bailiang; Wiestler, Benedikt; Adeli, Ehsan; Wachinger, Christian H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration Conference 2024. @conference{ghahremani2024hvit, |
Jian, Bailiang; Pan, Jiazhen; Ghahremani, Morteza; Rueckert, Daniel; Wachinger, Christian; Wiestler, Benedikt Mamba? Catch The Hype Or Rethink What Really Helps for Image Registration Conference 2024. @conference{nokey, |
Ghahremani, Morteza; Wachinger, Christian RegBN: Batch Normalization of Multimodal Data with Regularization Conference 2023. @conference{ghahremani2023regbn, |
You must be logged in to post a comment.