AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data

Qi Chen, Xinze Zhou, Chen Liu, Hao Chen, Wenxuan Li, Zekun Jiang, Ziyan Huang, Yuxuan Zhao, Dexin Yu, Junjun He, Yefeng Zheng, Ling Shao and 2 more

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 8 citations (OpenAlex)

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 changedWhereMeasuredEffect
add 3x synthetic tumors to real training scans (~435 real) (ablation)SegResNet · JHH pancreatic, out-of-distribution (PANORAMA)DSC: 36.8 -> 52.8Improved
add 3x synthetic tumors at full real scale (3159 scans) (ablation)SegResNet · JHH pancreatic, out-of-distribution (PANORAMA)DSC: 41.2 -> 53.5Improved
add synthetic tumors to 278 real scans, in-distribution (ablation)SegResNet · JHH pancreatic, in-distributionDSC: 52.7 -> 58.1Improved
add synthetic tumors at 3159 real scans, in-distribution (ablation)SegResNet · JHH pancreatic, in-distributionDSC: 59.7 -> 59.3No clear effect
scale real scans from 1500 to 3159SegResNet · JHH pancreatic, in-distributionDSC: 59.3 -> 59.7No clear effect
scale real scans from 1500 to 3159SegResNet · JHH pancreatic, out-of-distribution (PANORAMA)DSC: 38.4 -> 41.2Improved
train ResEncM on Cancerverse instead of public datasetsResEncM · Cancerverse val, pancreatic tumorDSC: 57.0 -> 65.8Improved
train ResEncM on Cancerverse instead of public datasetsResEncM · 3D-IRCADb liver tumor (external)DSC: 67.1 -> 81.1Improved
train on Cancerverse, colon tumor NSDResEncM · Cancerverse val, colon tumorNSD: 48.7 -> 47.6Hurt
train on Cancerverse, liver tumor sensitivityResEncM · Cancerverse val, liver tumorsensitivity: 89.1 -> 83.7Hurt
train ResEncM on Cancerverse instead of public datasetsResEncM · MSD Task07 Pancreas (test)DSC: 62.3 -> 67.2Improved
train ResEncM on Cancerverse instead of public datasetsResEncM · Kipa kidney tumor (external)DSC: 76.4 -> 83.6Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy