Research map / Probabilistic and scientific modeling / Molecules and proteins
Knowledge-based in silico models and dataset for the comparative evaluation of mammography AI for a range of breast characteristics, lesion conspicuities and doses
Elena Sizikova, Niloufar Saharkhiz, Diksha Sharma, Miguel Lago, Berkman Sahiner, Jana Gut Delfino, Aldo Badano
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 |
|---|---|---|---|
| increase mass size from 5 mm to 9 mm | efficientnet_b0 mass detector · M-SYNTH mass detection | AUC | Improved |
| increase mass density from 1.0 to 1.1 times glandular | efficientnet_b0 mass detector · M-SYNTH mass detection | AUC | Improved |
| train on smaller masses or lower densities rather than all | efficientnet_b0 mass detector · M-SYNTH mass detection | AUC | Mixed |
| test on a different breast density than train | efficientnet_b0 mass detector · M-SYNTH mass detection | AUC | Hurt |
| vary relative radiation dose from 20% to 100% | efficientnet_b0 mass detector · M-SYNTH mass detection | AUC | No clear effect |
| train on real INBreast images instead of M-SYNTH | efficientnet_b0 mass detector · M-SYNTH test set | AUC | Hurt |
| swap architecture to vit_small_patch16_224 or vgg_16 | mass detector · M-SYNTH mass detection | AUC | No clear effect |
| train on all mass sizes instead of 7 mm only | efficientnet_b0 mass detector · M-SYNTH 5 mm masses | AUC | Improved |
| increase mass size from 5.0 to 9.0 mm in fatty breast | mass insertion · insertion time | time (min): 7.152661 -> 7.337922 | Hurt |
| move from dense to fatty breast | mass insertion and imaging · imaging time | time (min): 2.842028 -> 13.463809 | Hurt |
Closest papers by meaning
- Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding (ICLR 2025 · similarity 0.84)
- Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation? (NeurIPS 2024 · similarity 0.84)
- MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models (ICLR 2025 · similarity 0.84)
- Towards Generalizable Tumor Synthesis (CVPR 2024 · similarity 0.84)
- A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis (NeurIPS 2024 · similarity 0.84)
- "Why Is There a Tumor?": Tell Me the Reason, Show Me the Evidence (ICML 2025 · similarity 0.83)
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.
