# Can Foundation Models Really Segment Tumors? A Benchmarking Odyssey in Lung CT Imaging

arXiv: https://arxiv.org/abs/2505.01239 · HTML: https://mlsanity.com/paper/2505.01239/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 2 May 2025.

## Builds on (most cited first, 15 of 15)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Medical SAM 2: Segment medical images as video via Segment Anything Model 2](https://mlsanity.com/paper/2408.00874/) (2024)
- [Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practice](https://mlsanity.com/paper/1911.01685/) (2019)
- [Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentation](https://mlsanity.com/paper/2304.12637/) (2023)
- [TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation](https://mlsanity.com/paper/2208.00713/) (2022)
- [Segment Anything in Medical Images and Videos: Benchmark and Deployment](https://mlsanity.com/paper/2408.03322/) (2024)
- [On Efficient Variants of Segment Anything Model: A Survey](https://mlsanity.com/paper/2410.04960/) (2024)
- [RadioPathomics: Multimodal Learning in Non-Small Cell Lung Cancer for Adaptive Radiotherapy](https://mlsanity.com/paper/2204.12423/) (2022)
- [Deep Learning for Human Locomotion Analysis in Lower-Limb Exoskeletons: A Comparative Study](https://mlsanity.com/paper/2503.16904/) (2025)

## Built on by (most cited first, 5 of 5)

- [Context-Gated Cross-Modal Perception with Visual Mamba for PET-CT Lung Tumor Segmentation](https://mlsanity.com/paper/2510.27508/) (2025)
- [Probabilistic NDVI Forecasting from Sparse Satellite Time Series and Weather Covariates](https://mlsanity.com/paper/2602.17683/) (2026)
- [Longitudinal NSCLC Treatment Progression via Multimodal Generative Models](https://mlsanity.com/paper/2603.06147/) (2026)
- [Exploring Prompt Alignment with Clinical Factors in Zero-Shot Segmentation VLMs for NSCLC Tumor Segmentation](https://mlsanity.com/paper/2605.01266/) (2026)
- [NoduleFlow: Automatic 3D Lung Nodule Detection and Segmentation](https://mlsanity.com/paper/2610.16548/) (2026)

## Abstract (arXiv)

Accurate lung tumor segmentation is crucial for improving diagnosis, treatment planning, and patient outcomes in oncology. However, the complexity of tumor morphology, size, and location poses significant challenges for automated segmentation. This study presents a comprehensive benchmarking analysis of deep learning-based segmentation models, comparing traditional architectures such as U-Net and DeepLabV3, self-configuring models like nnUNet, and foundation models like MedSAM, and MedSAM~2. Evaluating performance across two lung tumor segmentation datasets, we assess segmentation accuracy and computational efficiency under various learning paradigms, including few-shot learning and fine-tuning. The results reveal that while traditional models struggle with tumor delineation, foundation models, particularly MedSAM~2, outperform them in both accuracy and computational efficiency. These findings underscore the potential of foundation models for lung tumor segmentation, highlighting their applicability in improving clinical workflows and patient outcomes.