Large-scale generative tumor synthesis in computed tomography images for improving tumor recognition

Linshan Wu, Jiaxin Zhuang, Yanning Zhou, Sunan He, Jiabo Ma, Luyang Luo, Xi Wang, Xuefeng Ni, Xiaoling Zhong, Mingxiang Wu, Yinghua Zhao, Xiaohui Duan, Varut Vardhanabhuti, Pranav Rajpurkar, Hao ChenNature Communications 2025 · DOI

TL;DR

This paper introduces FreeTumor, a novel Generative AI framework that synthesizes realistic tumors in CT scans to overcome the critical shortage of annotated medical data. By leveraging vast amounts of unlabeled CT scans, FreeTumor significantly enhances tumor recognition models, demonstrating superior performance in segmentation and early detection, with validation from expert radiologists.

What Problem Does This Paper Address?

AI has shown immense promise in revolutionizing tumor screening and diagnosis through automated recognition. However, the development of these AI models is severely bottlenecked by the scarcity of large, high-quality, annotated medical datasets. Creating these datasets is an arduous and expensive process, requiring extensive manual labeling by highly trained radiologists. This data hunger limits the progress and widespread adoption of AI in clinical settings. The paper aims to bridge this gap by generating synthetic tumor data at scale, thereby augmenting existing datasets and improving the performance of tumor recognition models.

Methods

FreeTumor employs a two-stage Generative AI approach:

  • Stage 1: Large-Scale Generative Tumor Synthesis Training: This stage focuses on training the core synthesis model. It utilizes a Generative Adversarial Network (GAN) framework. A key innovation is the use of a segmentation-based discriminator instead of a traditional classification discriminator. This discriminator is trained on real tumor data and is tasked with distinguishing between real and synthetically generated tumors. The generator learns to produce tumors that can fool this discriminator, thereby improving the realism of the synthetic tumors. This stage also incorporates a quality control mechanism that uses the discriminator to filter out low-quality synthetic tumors, ensuring only realistic ones are used for downstream tasks.
  • Stage 2: Tumor Synthesis for Large-Scale Segmentation Training: In this stage, the trained generator is used to synthesize tumors onto healthy CT scans. These synthetic tumors are then used to augment the training datasets for segmentation models. The process is designed to be "online," meaning tumors are synthesized as needed during segmentation training, avoiding the creation of large offline synthetic datasets.

Datasets

The study leverages a massive dataset for training and evaluation:

  • Curated Dataset: A total of 161,310 publicly available CT volumes were collected from 33 different sources.
  • Annotation Rarity: Crucially, only 2.3% (3,696 volumes) of this vast dataset contained annotated tumors.
  • Tumor Types: The research focuses on five types of tumors/lesions: liver tumors, pancreas tumors, kidney tumors, lung tumors, and COVID-19 related lesions.
  • Data Split: Abdomen CT volumes (19,571) were used for liver, pancreas, and kidney tumors, while chest CT volumes (141,784) were used for lung tumors and COVID-19.

Key Insights and Ideas

  • Unlocking Unlabeled Data: The core idea is that large amounts of unlabeled medical data, which are far more abundant than labeled data, can be effectively harnessed for improving AI models through generative synthesis.
  • Segmentation as a Discriminator: Using a segmentation model as a discriminator for GANs is a novel approach for tumor synthesis. It directly optimizes for the realism of tumors in a way that is relevant to the downstream segmentation task, rather than just general image realism.
  • Quality Control is Crucial: Simply generating synthetic data isn't enough. The paper highlights the importance of a quality control mechanism to discard imperfect synthetic tumors, which could otherwise degrade model performance.
  • Radiologist Validation: The rigorous "Visual Turing Test" involving 13 board-certified radiologists provides strong evidence for the high fidelity of the synthesized tumors, a critical step for clinical trust.
  • Data Scale Matters: The study demonstrates a clear correlation between the scale of training data (augmented by synthesis) and improved segmentation performance, especially on datasets with very few annotations.

Key Results

  • Radiologist Evaluation: Expert radiologists could only distinguish between real and synthetic tumors with 51.1% sensitivity and 60.8% accuracy, indicating the high realism of FreeTumor's synthetic data.
  • Segmentation Improvement: FreeTumor, when used to augment training data, achieved an average +6.7% Dice score improvement across 12 public datasets compared to the baseline SwinUNETR model. For specific datasets with very limited annotations (e.g., IRCAD), improvements reached +16.1%.
  • Early Tumor Detection: FreeTumor led to an average +16.4% sensitivity improvement in detecting small tumors (diameter < 2cm), which is crucial for timely diagnosis and treatment.
  • Out-of-Domain Performance: FreeTumor demonstrated superior generalizability, outperforming previous methods in out-of-domain evaluation by an average of +12.3% Dice score.

Limitations and Future Work

  • Clinical Application: While promising, the authors acknowledge that further exploration of FreeTumor's application in real-world clinical practice is necessary to fully substantiate its effectiveness.
  • Tumor Types and Modalities: The current work focuses on CT scans and specific tumor types. Future work aims to extend FreeTumor to other medical imaging modalities (e.g., MRI, pathology) and a wider range of tumor types.
  • Synthetic Tumor Imperfections: Despite rigorous quality control, the authors note that synthetic tumors are not always flawless, and further improvements are possible. Case studies show some instances where radiologists could still identify distinct features of synthetic tumors.

Summary updated

Abstract

AI-driven tumor recognition unlocks new possibilities for precise tumor screening and diagnosis. However, the progress is heavily hampered by the scarcity of annotated datasets, demanding extensive efforts by radiologists. To this end, we introduce FreeTumor, a Generative AI framework to enable large-scale tumor synthesis for mitigating data scarcity. Specifically, FreeTumor effectively leverages limited labeled data and large-scale unlabeled data for training. Unleashing the power of large-scale data, FreeTumor is capable of synthesizing a large number of realistic tumors for augmenting training datasets. We curate a large-scale dataset comprising 161,310 Computed Tomography (CT) volumes for tumor synthesis and recognition, with only 2.3% containing annotated tumors. 13 board-certified radiologists are engaged to discern between synthetic and real tumors, rigorously validating the quality of synthetic tumors. Through high-quality tumor synthesis, FreeTumor showcases a notable superiority over state-of-the-art tumor recognition methods, indicating promising prospects in clinical applications.
BibTeX
@inproceedings{wu2025large,
  author = {Linshan Wu and Jiaxin Zhuang and Yanning Zhou and Sunan He and Jiabo Ma and Luyang Luo and Xi Wang and Xuefeng Ni and Xiaoling Zhong and Mingxiang Wu and Yinghua Zhao and Xiaohui Duan and Varut Vardhanabhuti and Pranav Rajpurkar and Hao Chen},
  title = {{Large-scale generative tumor synthesis in computed tomography images for improving tumor recognition}},
  booktitle = {Nature Communications},
  year = {2025},
  doi = {10.1038/s41467-025-66071-6},
}
Figure