Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
AmnioML: Amniotic Fluid Segmentation and Volume Prediction with Uncertainty Quantification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use the U-Net segmentation architecture | AmnioML · Fetal MRI test set | average Dice coefficient: 0.91 ± 0.06; tied for best | Helped |
| Use thresholded volume prediction (Algorithm 1) instead of standard split conformal prediction | AmnioML volume intervals · Fetal MRI test set | average interval length | Helped |
| Use thresholded volume prediction (Algorithm 1) | AmnioML volume intervals · Fetal MRI test set | empirical coverage | No clear effect |
| Add neighboring slices as motion-context features (ablation) | U-Net slice segmentation · Validation set | prediction performance | No clear effect |
| Use three input slices as motion context (ablation) | U-Net slice segmentation · Validation set | prediction performance | Helped |
| Use AmnioML to assist manual segmentation | Medical specialists · Clinical use | segmentation time speedup: 20.7 times | Helped |
Closest papers by meaning
- FETAL-GAUGE: A BENCHMARK FOR ASSESSING VISION-LANGUAGE MODELS IN FETAL ULTRASOUND (ICLR 2026 · similarity 0.85)
- F$^2$-Assist: Multi-Phase Fetal Growth Forecast and Report Generation from Ultrasound Examination (CVPR 2026 · similarity 0.83)
- MCAT: Visual Query-Based Localization of Standard Anatomical Clips in Fetal Ultrasound Videos Using Multi-Tier Class-Aware Token Transformer (AAAI 2025 · similarity 0.82)
- Unraveling Normal Anatomy via Fluid-Driven Anomaly Randomization (CVPR 2025 · similarity 0.81)
- MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation (CVPR 2024 · similarity 0.80)
- Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline (CVPR 2025 · similarity 0.80)
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.