# Synthetic Tumors Make AI Segment Tumors Better

arXiv: https://arxiv.org/abs/2210.14845 · HTML: https://mlsanity.com/paper/2210.14845/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 26 Oct 2022.

## Builds on (most cited first, 13 of 13)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images](https://mlsanity.com/paper/2201.01266/) (2022)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis](https://mlsanity.com/paper/2111.14791/) (2021)
- [CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation](https://mlsanity.com/paper/2001.06535/) (2020)
- [Label-Free Segmentation of COVID-19 Lesions in Lung CT](https://mlsanity.com/paper/2009.06456/) (2020)
- [Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detection](https://mlsanity.com/paper/1906.04962/) (2019)
- [Free-form tumor synthesis in computed tomography images via richer generative adversarial network](https://mlsanity.com/paper/2104.09701/) (2021)
- [METGAN: Generative Tumour Inpainting and Modality Synthesis in Light Sheet Microscopy](https://mlsanity.com/paper/2104.10993/) (2021)

## Built on by (most cited first, 14 of 14)

- [MAISI: Medical AI for Synthetic Imaging](https://mlsanity.com/paper/2409.11169/) (2024)
- [Towards Generalizable Tumor Synthesis](https://mlsanity.com/paper/2402.19470/) (2024)
- [AbdomenAtlas: A Large-Scale, Detailed-Annotated, & Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarking](https://mlsanity.com/paper/2407.16697/) (2024)
- [Label-Free Liver Tumor Segmentation](https://mlsanity.com/paper/2303.14869/) (2023)
- [AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks](https://mlsanity.com/paper/2305.09666/) (2023)
- [From Pixel to Cancer: Cellular Automata in Computed Tomography](https://mlsanity.com/paper/2403.06459/) (2024)
- [Early Detection and Localization of Pancreatic Cancer by Label-Free Tumor Synthesis](https://mlsanity.com/paper/2308.03008/) (2023)
- [Boosting Dermatoscopic Lesion Segmentation via Diffusion Models with Visual and Textual Prompts](https://mlsanity.com/paper/2310.02906/) (2023)
- [Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data](https://mlsanity.com/paper/2510.14831/) (2025)
- [Analyzing Tumors by Synthesis](https://mlsanity.com/paper/2409.06035/) (2024)
- [Synthetic Data as Validation](https://mlsanity.com/paper/2310.16052/) (2023)
- [Expectation-Maximization as the Engine of Scalable Medical Intelligence](https://mlsanity.com/paper/2501.03410/) (2025)
- [See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement](https://mlsanity.com/paper/2512.07251/) (2025)
- [3D-LLDM: Label-Guided 3D Latent Diffusion Model for Improving High-Resolution Synthetic MR Imaging in Hepatic Structure Segmentation](https://mlsanity.com/paper/2603.23845/) (2026)

## Abstract (arXiv)

We develop a novel strategy to generate synthetic tumors. Unlike existing works, the tumors generated by our strategy have two intriguing advantages: (1) realistic in shape and texture, which even medical professionals can confuse with real tumors; (2) effective for AI model training, which can perform liver tumor segmentation similarly to a model trained on real tumors - this result is unprecedented because no existing work, using synthetic tumors only, has thus far reached a similar or even close performance to the model trained on real tumors. This result also implies that manual efforts for developing per-voxel annotation of tumors (which took years to create) can be considerably reduced for training AI models in the future. Moreover, our synthetic tumors have the potential to improve the success rate of small tumor detection by automatically generating enormous examples of small (or tiny) synthetic tumors.