# Text-Driven Tumor Synthesis

arXiv: https://arxiv.org/abs/2412.18589 · HTML: https://mlsanity.com/paper/2412.18589/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 66 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 11 of 11)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [From Pixel to Cancer: Cellular Automata in Computed Tomography](https://mlsanity.com/paper/2403.06459/) (2024)
- [Boosting Dermatoscopic Lesion Segmentation via Diffusion Models with Visual and Textual Prompts](https://mlsanity.com/paper/2310.02906/) (2023)
- [Analyzing Tumors by Synthesis](https://mlsanity.com/paper/2409.06035/) (2024)
- [Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation](https://mlsanity.com/paper/2410.17918/) (2024)
- [SAM-FNet: SAM-Guided Fusion Network for Laryngo-Pharyngeal Tumor Detection](https://mlsanity.com/paper/2408.05426/) (2024)
- [SAM-Swin: SAM-Driven Dual-Swin Transformers with Adaptive Lesion Enhancement for Laryngo-Pharyngeal Tumor Detection](https://mlsanity.com/paper/2410.21813/) (2024)

## Built on by (most cited first, 13 of 13)

- [Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning](https://mlsanity.com/paper/2506.02327/) (2025)
- [PanTS: The Pancreatic Tumor Segmentation Dataset](https://mlsanity.com/paper/2507.01291/) (2025)
- [MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs](https://mlsanity.com/paper/2504.06897/) (2025)
- [Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data](https://mlsanity.com/paper/2510.14831/) (2025)
- [Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction?](https://mlsanity.com/paper/2506.02093/) (2025)
- [Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation](https://mlsanity.com/paper/2504.09601/) (2025)
- [Early and Prediagnostic Detection of Pancreatic Cancer from Computed Tomography](https://mlsanity.com/paper/2601.22134/) (2026)
- [See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement](https://mlsanity.com/paper/2512.07251/) (2025)
- [Auditing Significance, Metric Choice, and Demographic Fairness in Medical AI Challenges](https://mlsanity.com/paper/2512.19091/) (2025)
- [Foundation VAEs for 3D CT Reconstruction, Augmentation, and Generation](https://mlsanity.com/paper/2605.30893/) (2026)
- [ShapeKit](https://mlsanity.com/paper/2506.24003/) (2025)
- [Clinical Metadata Guided Limited-Angle CT Image Reconstruction](https://mlsanity.com/paper/2509.01752/) (2025)
- [Beyond Masks: The Case for Medical Image Parsing](https://mlsanity.com/paper/2605.11438/) (2026)

## Abstract (arXiv)

Tumor synthesis can generate examples that AI often misses or over-detects, improving AI performance by training on these challenging cases. However, existing synthesis methods, which are typically unconditional -- generating images from random variables -- or conditioned only by tumor shapes, lack controllability over specific tumor characteristics such as texture, heterogeneity, boundaries, and pathology type. As a result, the generated tumors may be overly similar or duplicates of existing training data, failing to effectively address AI's weaknesses. We propose a new text-driven tumor synthesis approach, termed TextoMorph, that provides textual control over tumor characteristics. This is particularly beneficial for examples that confuse the AI the most, such as early tumor detection (increasing Sensitivity by +8.5%), tumor segmentation for precise radiotherapy (increasing DSC by +6.3%), and classification between benign and malignant tumors (improving Sensitivity by +8.2%). By incorporating text mined from radiology reports into the synthesis process, we increase the variability and controllability of the synthetic tumors to target AI's failure cases more precisely. Moreover, TextoMorph uses contrastive learning across different texts and CT scans, significantly reducing dependence on scarce image-report pairs (only 141 pairs used in this study) by leveraging a large corpus of 34,035 radiology reports. Finally, we have developed rigorous tests to evaluate synthetic tumors, including Text-Driven Visual Turing Test and Radiomics Pattern Analysis, showing that our synthetic tumors is realistic and diverse in texture, heterogeneity, boundaries, and pathology.