# AI-Driven MRI-based Brain Tumour Segmentation Benchmarking

arXiv: https://arxiv.org/abs/2506.20786 · HTML: https://mlsanity.com/paper/2506.20786/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 25 Jun 2025.

## Builds on (most cited first, 20 of 20)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [Segment Anything Model for Medical Image Analysis: an Experimental Study](https://mlsanity.com/paper/2304.10517/) (2023)
- [Medical Image Segmentation Review: The success of U-Net](https://mlsanity.com/paper/2211.14830/) (2022)
- [DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation](https://mlsanity.com/paper/1707.00652/) (2017)
- [SAM-Med3D: Towards General-purpose Segmentation Models for Volumetric Medical Images](https://mlsanity.com/paper/2310.15161/) (2023)
- [nnU-Net for Brain Tumor Segmentation](https://mlsanity.com/paper/2011.00848/) (2020)
- [Why rankings of biomedical image analysis competitions should be interpreted with care](https://mlsanity.com/paper/1806.02051/) (2018)
- [The Brain Tumor Segmentation (BraTS) Challenge 2023: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs)](https://mlsanity.com/paper/2305.17033/) (2023)
- [Segment Anything in Medical Images and Videos: Benchmark and Deployment](https://mlsanity.com/paper/2408.03322/) (2024)
- [Extending nn-UNet for brain tumor segmentation](https://mlsanity.com/paper/2112.04653/) (2021)
- [How we won BraTS 2023 Adult Glioma challenge? Just faking it! Enhanced Synthetic Data Augmentation and Model Ensemble for brain tumour segmentation](https://mlsanity.com/paper/2402.17317/) (2024)
- [Multimodal CNN Networks for Brain Tumor Segmentation in MRI: A BraTS 2022 Challenge Solution](https://mlsanity.com/paper/2212.09310/) (2022)
- [Biomedical SAM 2: Segment Anything in Biomedical Images and Videos](https://mlsanity.com/paper/2408.03286/) (2024)
- [Brain tumour segmentation with incomplete imaging data](https://mlsanity.com/paper/2206.06120/) (2022)

## Abstract (arXiv)

Medical image segmentation has greatly aided medical diagnosis, with U-Net based architectures and nnU-Net providing state-of-the-art performance. There have been numerous general promptable models and medical variations introduced in recent years, but there is currently a lack of evaluation and comparison of these models across a variety of prompt qualities on a common medical dataset. This research uses Segment Anything Model (SAM), Segment Anything Model 2 (SAM 2), MedSAM, SAM-Med-3D, and nnU-Net to obtain zero-shot inference on the BraTS 2023 adult glioma and pediatrics dataset across multiple prompt qualities for both points and bounding boxes. Several of these models exhibit promising Dice scores, particularly SAM and SAM 2 achieving scores of up to 0.894 and 0.893, respectively when given extremely accurate bounding box prompts which exceeds nnU-Net's segmentation performance. However, nnU-Net remains the dominant medical image segmentation network due to the impracticality of providing highly accurate prompts to the models. The model and prompt evaluation, as well as the comparison, are extended through fine-tuning SAM, SAM 2, MedSAM, and SAM-Med-3D on the pediatrics dataset. The improvements in point prompt performance after fine-tuning are substantial and show promise for future investigation, but are unable to achieve better segmentation than bounding boxes or nnU-Net.