Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data

• URL: http://arxiv.org/abs/2510.14831v2
• Date: Sun, 02 Nov 2025 16:13:33 GMT
• Title: Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data
• Authors: Qi Chen, Xinze Zhou, Chen Liu, Hao Chen, Wenxuan Li, Zekun Jiang, Ziyan Huang, Yuxuan Zhao, Dexin Yu, Junjun He, Yefeng Zheng, Ling Shao, Alan Yuille, Zongwei Zhou,
• Abstract summary: AbdomenAtlas 2.0 is a dataset of 10,135 CT scans with a total of 15,130 tumor instances per-voxel manually annotated in six organs.<n>It achieves notable improvements over public datasets, with a +7% gain on DSC tests and +16% on out-of-distribution tests.
• Score: 62.63749675817477
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: AI for tumor segmentation is limited by the lack of large, voxel-wise annotated datasets, which are hard to create and require medical experts. In our proprietary JHH dataset of 3,000 annotated pancreatic tumor scans, we found that AI performance stopped improving after 1,500 scans. With synthetic data, we reached the same performance using only 500 real scans. This finding suggests that synthetic data can steepen data scaling laws, enabling more efficient model training than real data alone. Motivated by these lessons, we created AbdomenAtlas 2.0--a dataset of 10,135 CT scans with a total of 15,130 tumor instances per-voxel manually annotated in six organs (pancreas, liver, kidney, colon, esophagus, and uterus) and 5,893 control scans. Annotated by 23 expert radiologists, it is several orders of magnitude larger than existing public tumor datasets. While we continue expanding the dataset, the current version of AbdomenAtlas 2.0 already provides a strong foundation--based on lessons from the JHH dataset--for training AI to segment tumors in six organs. It achieves notable improvements over public datasets, with a +7% DSC gain on in-distribution tests and +16% on out-of-distribution tests.

Related papers

• Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks [59.37427210144734]
  We introduce R-Super, which trains AI to segment tumors that match descriptions in medical reports.<n>When trained on 101,654 reports, AI models achieved performance comparable to those trained on 723 masks.<n>R-Super enabled segmentation of tumors in the spleen, gallbladder, prostate, bladder, uterus, and esophagus.
  arXiv  Detail & Related papers  (2025-10-16T15:35:44Z)
• RadGPT: Constructing 3D Image-Text Tumor Datasets [13.909446077455323]
  We present AbdomenAtlas 3.0, the first public, high-quality abdominal CT dataset with detailed, expert-reviewed radiology reports.<n>All reports are paired with per-voxel masks and they describe liver, kidney and pancreatic tumors.<n>Our results show that segmentation strongly improves tumor detection in AI-made reports.
  arXiv  Detail & Related papers  (2025-01-08T18:39:10Z)
• ScaleMAI: Accelerating the Development of Trusted Datasets and AI Models [46.80682547774335]
  We propose ScaleMAI, an agent of AI-integrated data curation and annotation.<n>First, ScaleMAI creates a dataset of 25,362 CT scans, including per-voxel annotations for benign/malignant tumors and 24 anatomical structures.<n>Second, through progressive human-in-the-loop iterations, ScaleMAI provides Flagship AI Model that can approach the proficiency of expert annotators in detecting pancreatic tumors.
  arXiv  Detail & Related papers  (2025-01-06T22:12:00Z)
• Towards a Benchmark for Colorectal Cancer Segmentation in Endorectal Ultrasound Videos: Dataset and Model Development [59.74920439478643]
  In this paper, we collect and annotated the first benchmark dataset that covers diverse ERUS scenarios. Our ERUS-10K dataset comprises 77 videos and 10,000 high-resolution annotated frames. We introduce a benchmark model for colorectal cancer segmentation, named the Adaptive Sparse-context TRansformer (ASTR)
  arXiv  Detail & Related papers  (2024-08-19T15:04:42Z)
• AbdomenAtlas: A Large-Scale, Detailed-Annotated, & Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarking [16.524596737411006]
  We introduce the largest abdominal CT dataset (termed AbdomenAtlas) of 20,460 three-dimensional CT volumes from 112 hospitals across diverse populations, geographies, and facilities.<n>AbamenAtlas provides 673K high-quality masks of anatomical structures in the abdominal region annotated by a team of 10 radiologists with the help of AI algorithms.
  arXiv  Detail & Related papers  (2024-07-23T17:59:44Z)
• Quantifying uncertainty in lung cancer segmentation with foundation models applied to mixed-domain datasets [6.712251433139412]
  Medical image foundation models have shown the ability to segment organs and tumors with minimal fine-tuning.<n>These models are typically evaluated on task-specific in-distribution (ID) datasets.<n>We introduce a comprehensive set of computationally fast metrics to evaluate the performance of multiple foundation models trained with self-supervised learning (SSL)<n>SMIT produced the highest F1-score (LRAD: 0.60, 5Rater: 0.64) and lowest entropy (LRAD: 0.06, 5Rater: 0.12), indicating higher tumor detection rate and confident segmentations.
  arXiv  Detail & Related papers  (2024-03-19T19:36:48Z)
• Iterative Semi-Supervised Learning for Abdominal Organs and Tumor Segmentation [4.952008176585512]
  The FLARE23 challenge provides a large-scale dataset with both partially and fully annotated data. We propose to use the strategy of Semi-Supervised Learning (SSL) and iterative pseudo labeling to address FLARE23. Our approach achieves an average DSC score of 89.63% for organs and 46.07% for tumors on online validation leaderboard.
  arXiv  Detail & Related papers  (2023-10-02T12:45:13Z)
• Federated Learning Enables Big Data for Rare Cancer Boundary Detection [98.5549882883963]
  We present findings from the largest Federated ML study to-date, involving data from 71 healthcare institutions across 6 continents. We generate an automatic tumor boundary detector for the rare disease of glioblastoma. We demonstrate a 33% improvement over a publicly trained model to delineate the surgically targetable tumor, and 23% improvement over the tumor's entire extent.
  arXiv  Detail & Related papers  (2022-04-22T17:27:00Z)
• WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma [51.50991881342181]
  This challenge includes 10,091 patch-level annotations and over 130 million labeled pixels. First place team achieved mIoU of 0.8413 (tumor: 0.8389, stroma: 0.7931, normal: 0.8919)
  arXiv  Detail & Related papers  (2022-04-13T15:27:05Z)
• Brain tumor segmentation with self-ensembled, deeply-supervised 3D U-net neural networks: a BraTS 2020 challenge solution [56.17099252139182]
  We automate and standardize the task of brain tumor segmentation with U-net like neural networks. Two independent ensembles of models were trained, and each produced a brain tumor segmentation map. Our solution achieved a Dice of 0.79, 0.89 and 0.84, as well as Hausdorff 95% of 20.4, 6.7 and 19.5mm on the final test dataset.
  arXiv  Detail & Related papers  (2020-10-30T14:36:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.