Research map / Detection and segmentation / Open-set and few-shot detection
Label-Free Liver Tumor Segmentation
Qixin Hu, Yixiong Chen, Junfei Xiao, Shuwen Sun, Jieneng Chen, Alan L. Yuille, Zongwei Zhou
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 |
|---|---|---|---|
| Train U-Net using synthetic tumors instead of manually labeled real tumors | U-Net · LiTS, 5-fold cross-validation | DSC (%): 57.51 -> 59.77 | Improved |
| Train U-Net using synthetic tumors instead of manually labeled real tumors | U-Net · LiTS, 5-fold cross-validation | NSD (%): 58.04 -> 61.29 | Improved |
| Add tiny synthetic tumors to training (ablation) | Synthetic-tumor U-Net · Shape-generation ablation, small tumors | Detection sensitivity (%): 33.4 -> 61.8 | Improved |
| Add edge blurring to tumor shapes (ablation) | Synthetic-tumor U-Net · Shape-generation ablation, all tumors | DSC (%): 43.9 -> 47.1 | Improved |
| Add elastic deformation to tumor shapes (ablation) | Synthetic-tumor U-Net · Shape-generation ablation, all tumors | DSC (%): 43.9 -> 50.3 | Improved |
| Use both elastic deformation and edge blurring (ablation) | Synthetic-tumor U-Net · Shape-generation ablation, all tumors | DSC (%): 43.9 -> 52.6 | Improved |
| Add tiny tumors to training alongside elastic deformation and edge blurring (ablation) | Synthetic-tumor U-Net · Shape-generation ablation, small tumors | Detection sensitivity (%): 33.4 -> 61.8 | Improved |
| Combine real and synthetic training data instead of using synthetic data alone (ablation) | U-Net · LiTS, 5-fold cross-validation | DSC (%): 59.81 -> 56.86 | Hurt |
Closest papers by meaning
- Towards Generalizable Tumor Synthesis (CVPR 2024 · similarity 0.90)
- Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data (ICCV 2025 · similarity 0.89)
- "Why Is There a Tumor?": Tell Me the Reason, Show Me the Evidence (ICML 2025 · similarity 0.84)
- Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation? (NeurIPS 2024 · similarity 0.83)
- CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor Segmentation (NeurIPS 2024 · similarity 0.82)
- Advancing Generalizable Tumor Segmentation with Anomaly-Aware Open-Vocabulary Attention Maps and Frozen Foundation Diffusion Models (CVPR 2025 · similarity 0.82)
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.
