# Report Supervision

arXiv: https://arxiv.org/abs/2608.27668 · HTML: https://mlsanity.com/paper/2608.27668/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 55 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis](https://mlsanity.com/paper/2111.14791/) (2021)
- [Contrastive learning of global and local features for medical image segmentation with limited annotations](https://mlsanity.com/paper/2006.10511/) (2020)
- [Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation](https://mlsanity.com/paper/1603.06098/) (2016)
- [Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis](https://mlsanity.com/paper/1908.06912/) (2019)
- [Merlin: A Computed Tomography Vision-Language Foundation Model and Dataset](https://mlsanity.com/paper/2406.06512/) (2024)
- [CT2Rep: Automated Radiology Report Generation for 3D Medical Imaging](https://mlsanity.com/paper/2403.06801/) (2024)
- [DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks](https://mlsanity.com/paper/1605.07866/) (2016)
- [AbdomenAtlas: A Large-Scale, Detailed-Annotated, & Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarking](https://mlsanity.com/paper/2407.16697/) (2024)
- [Learning to Segment Medical Images with Scribble-Supervision Alone](https://mlsanity.com/paper/1807.04668/) (2018)
- [A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark](https://mlsanity.com/paper/2203.00131/) (2022)
- [Segment Anything in Medical Images and Videos: Benchmark and Deployment](https://mlsanity.com/paper/2408.03322/) (2024)
- [RadGPT: Constructing 3D Image-Text Tumor Datasets](https://mlsanity.com/paper/2501.04678/) (2025)
- [Learning Semantics-enriched Representation via Self-discovery, Self-classification, and Self-restoration](https://mlsanity.com/paper/2007.06959/) (2020)
- [Revisiting MAE pre-training for 3D medical image segmentation](https://mlsanity.com/paper/2410.23132/) (2024)
- [Universal and Extensible Language-Vision Models for Organ Segmentation and Tumor Detection from Abdominal Computed Tomography](https://mlsanity.com/paper/2405.18356/) (2024)
- [Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?](https://mlsanity.com/paper/2411.03670/) (2024)
- [Models Genesis](https://mlsanity.com/paper/2004.07882/) (2020)
- [Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization](https://mlsanity.com/paper/2202.00232/) (2022)
- [PanTS: The Pancreatic Tumor Segmentation Dataset](https://mlsanity.com/paper/2507.01291/) (2025)
- [Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data](https://mlsanity.com/paper/2510.14831/) (2025)
- [Annotation-efficient cancer detection with report-guided lesion annotation for deep learning-based prostate cancer detection in bpMRI](https://mlsanity.com/paper/2112.05151/) (2021)
- [Learning Segmentation from Radiology Reports](https://mlsanity.com/paper/2507.05582/) (2025)
- [Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data](https://mlsanity.com/paper/2310.15098/) (2023)
- [Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks](https://mlsanity.com/paper/2510.14803/) (2025)
- [Early and Prediagnostic Detection of Pancreatic Cancer from Computed Tomography](https://mlsanity.com/paper/2601.22134/) (2026)
- [RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology](https://mlsanity.com/paper/2605.10761/) (2026)

## Abstract (arXiv)

Segmentation models can surpass radiologists, classification models, and vision-language models in tumor detection. Importantly, segmentation models outline tumors, allowing radiologists to better verify and trust the AI output. Their main limitation is the scarcity of tumor masks: creating one 3D tumor mask takes up to 30 minutes, so most public CT datasets contain only a few hundred masks, and even the largest private datasets contain only a couple of thousand. Tumor masks are not produced in clinical routine, but radiology reports are. Public datasets contain tens of thousands of CT-Report pairs, and hospitals contain hundreds of thousands. These reports describe tumors in detail, providing large-scale, informative training data. Here, we introduce Report Supervision (R-Super), a training framework that uses reports to directly supervise and improve tumor segmentation. R-Super introduces new loss functions that teach segmentation models to segment tumors that match report descriptions of tumor count, sizes, and locations. Reports are only used for training. We evaluated R-Super on kidney and pancreatic tumor segmentation, exploring diverse training data sizes, up to 41,418 CT-Report plus 3,488 pancreatic tumor CT-Mask pairs. On external validation, R-Super increased tumor detection F1-Score and segmentation DSC by up to +15% with respect to mask-only training. It also surpassed alternative methods such as CLIP and multi-task learning. Leveraging numerous readily available reports to supplement scarce masks, R-Super strongly improves AI performance when very few training masks are available (e.g., 50), and when many masks are available (e.g., 3,488), unlocking scale in tumor segmentation.