Research map / Label-efficient and robust learning / Self-supervised and contrastive
Scaling Self-Supervised and Cross-Modal Pretraining for Volumetric CT Transformers
Cris Claessens, Christiaan Viviers, Giacomo D'Amicantonio, Egor Bondarev, Fons van der Sommen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| SPECTRE encoder instead of Primus-M | SEoMT segmentation · KiTS23 | Dice (%): 86.13 -> 86.64 | Improved |
| SPECTRE vs strong convolutional nnU-Net ResEnc L | segmentation · KiTS23 | Dice (%): 88.06 -> 86.64 | Hurt |
| SPECTRE vs nnU-Net (plain) | segmentation · WORD | Dice (%): 83.11 -> 83.31 | No clear effect |
| SPECTRE VLA pretraining instead of CT-CLIP | text-to-image retrieval · CT-RATE val | Recall@5 (%): 2.9 -> 17.5 | Improved |
| SPECTRE vs Merlin on Findings text | text-to-image retrieval · Merlin test (N=32) | Recall@1 (%): 77.6 -> 55.5 | Hurt |
| SPECTRE vs Merlin on Impressions text | text-to-image retrieval · Merlin test (N=32) | Recall@1 (%): 38.4 -> 43.2 | Improved |
| concatenate Findings and Impressions as query | SPECTRE · Merlin test (N=32) | Recall@1 (%): 55.5 -> 66.4 | Improved |
Closest papers by meaning
- Versatile Vision-Language Model for 3D Computed Tomography (AAAI 2026 · similarity 0.88)
- Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging (NeurIPS 2025 · similarity 0.87)
- Knowledge Transfer Scaling Laws for 3D Medical Imaging (NeurIPS 2026 · similarity 0.85)
- 3DMedAgent: Unified Perception-to-Understanding for 3D Medical Analysis (ICML 2026 · similarity 0.85)
- BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays (NeurIPS 2024 · similarity 0.85)
- Revisiting MAE Pre-training for 3D Medical Image Segmentation (CVPR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
