Fine-tuning Segment Anything for Real-Time Tumor Tracking in Cine-MRI

• URL: http://arxiv.org/abs/2510.25990v1
• Date: Wed, 29 Oct 2025 21:57:12 GMT
• Title: Fine-tuning Segment Anything for Real-Time Tumor Tracking in Cine-MRI
• Authors: Valentin Boussot, Cédric Hémon, Jean-Claude Nunes, Jean-Louis Dillenseger,
• Abstract summary: We address the challenge of real-time tumor tracking in cine-MRI sequences of the thoracic and abdominal regions under strong data scarcity constraints.<n>Two complementary strategies were explored: (i) unsupervised registration with the IMPACT similarity metric and (ii) foundation model-based segmentation leveraging SAM 2.1.<n>The final model was selected based on the highest Dice Similarity Coefficient achieved on the validation set after fine-tuning.
• Score: 1.2560645967579729
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we address the TrackRAD2025 challenge of real-time tumor tracking in cine-MRI sequences of the thoracic and abdominal regions under strong data scarcity constraints. Two complementary strategies were explored: (i) unsupervised registration with the IMPACT similarity metric and (ii) foundation model-based segmentation leveraging SAM 2.1 and its recent variants through prompt-based interaction. Due to the one-second runtime constraint, the SAM-based method was ultimately selected. The final configuration used SAM2.1 b+ with mask-based prompts from the first annotated slice, fine-tuned solely on the small labeled subset from TrackRAD2025. Training was configured to minimize overfitting, using 1024x1024 patches (batch size 1), standard augmentations, and a balanced Dice + IoU loss. A low uniform learning rate (0.0001) was applied to all modules (prompt encoder, decoder, Hiera backbone) to preserve generalization while adapting to annotator-specific styles. Training lasted 300 epochs (~12h on RTX A6000, 48GB). The same inference strategy was consistently applied across all anatomical sites and MRI field strengths. Test-time augmentation was considered but ultimately discarded due to negligible performance gains. The final model was selected based on the highest Dice Similarity Coefficient achieved on the validation set after fine-tuning. On the hidden test set, the model reached a Dice score of 0.8794, ranking 6th overall in the TrackRAD2025 challenge. These results highlight the strong potential of foundation models for accurate and real-time tumor tracking in MRI-guided radiotherapy.

Related papers

• Why Registration Quality Matters: Enhancing sCT Synthesis with IMPACT-Based Registration [1.2560645967579729]
  Our model is a 2.5D U-Net++ with a ResNet-34 encoder, trained jointly across anatomical regions and fine-tuned per region.<n>On the local test sets, IMPACT-based registration achieved more accurate and anatomically consistent alignments than mutual-information-based registration.
  arXiv  Detail & Related papers  (2025-10-24T11:40:21Z)
• EMA-SAM: Exponential Moving-average for SAM-based PTMC Segmentation [1.7674345486888503]
  EMA-SAM is a lightweight extension of SAM-2 that incorporates a confidence-weighted exponential moving average pointer into the memory bank.<n>On our PTMC-RFA dataset (124 minutes, 13 patients), EMA-SAM improves emphmaxDice from 0.82 to 0.86 and emphmaxIoU from 0.72 to 0.76, while reducing false positives by 29%.
  arXiv  Detail & Related papers  (2025-10-21T01:30:27Z)
• Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Framework [47.035885218675126]
  Computational pathology (CPath) digitizes pathology slides into whole slide images (WSIs)<n>WSIs possess extremely long sequence lengths (up to 200K), significant length variations (from 200 to 200K), and limited supervision.<n>We propose a pack-based MIL framework to address these challenges.
  arXiv  Detail & Related papers  (2025-09-25T09:05:40Z)
• U-Mamba2-SSL for Semi-Supervised Tooth and Pulp Segmentation in CBCT [44.3806898357896]
  We propose U-Mamba2-SSL, a novel semi-supervised learning framework that builds on the U-Mamba2 model and employs a multi-stage training strategy.<n>U-Mamba2-SSL achieved an average score of 0.789 and a DSC of 0.917 on the hidden test set, achieving first place in Task 1 of the STSR 2025 challenge.
  arXiv  Detail & Related papers  (2025-09-24T14:19:33Z)
• ReCoSeg++:Extended Residual-Guided Cross-Modal Diffusion for Brain Tumor Segmentation [0.9374652839580183]
  We propose a semi-supervised, two-stage framework that extends the ReCoSeg approach to the larger and more heterogeneous BraTS 2021 dataset.<n>In the first stage, a residual-guided denoising diffusion probabilistic model (DDPM) performs cross-modal synthesis by reconstructing the T1ce modality from FLAIR, T1, and T2 scans.<n>In the second stage, a lightweight U-Net takes as input the concatenation of residual maps, computed as the difference between real T1ce and synthesized T1ce, with T1, T2, and FLAIR modalities to improve whole tumor segmentation
  arXiv  Detail & Related papers  (2025-08-01T20:24:31Z)
• SAM2-Aug: Prior knowledge-based Augmentation for Target Volume Auto-Segmentation in Adaptive Radiation Therapy Using Segment Anything Model 2 [6.833468826526835]
  Segment Anything Model 2 (SAM2) shows promise for prompt-based segmentation but struggles with tumor accuracy.<n>We propose prior knowledge-based augmentation strategies to enhance SAM2 for adaptive radiation therapy (ART)<n>SAM2-Aug was fine-tuned and tested on the One-Seq-Liver dataset (115 MRIs from 31 liver cancer patients)
  arXiv  Detail & Related papers  (2025-07-25T13:59:10Z)
• Improving the U-Net Configuration for Automated Delineation of Head and Neck Cancer on MRI [0.0]
  Tumor volume segmentation on MRI is a challenging and time-consuming process.<n>This work presents an approach to automated delineation of head and neck tumors on MRI scans.<n>The focus of this research was to propose improvements to the configuration commonly used in medical segmentation tasks.
  arXiv  Detail & Related papers  (2025-01-09T10:22:35Z)
• SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models [76.43625653814911]
  Diffusion models have gained popularity for accelerated MRI reconstruction due to their high sample quality. They can effectively serve as rich data priors while incorporating the forward model flexibly at inference time. We introduce SURE-based MRI Reconstruction with Diffusion models (SMRD) to enhance robustness during testing.
  arXiv  Detail & Related papers  (2023-10-03T05:05:35Z)
• Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion [56.38386580040991]
  Consistency Trajectory Model (CTM) is a generalization of Consistency Models (CM) CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance. Unlike CM, CTM's access to the score function can streamline the adoption of established controllable/conditional generation methods.
  arXiv  Detail & Related papers  (2023-10-01T05:07:17Z)
• Brain tumor segmentation with self-ensembled, deeply-supervised 3D U-net neural networks: a BraTS 2020 challenge solution [56.17099252139182]
  We automate and standardize the task of brain tumor segmentation with U-net like neural networks. Two independent ensembles of models were trained, and each produced a brain tumor segmentation map. Our solution achieved a Dice of 0.79, 0.89 and 0.84, as well as Hausdorff 95% of 20.4, 6.7 and 19.5mm on the final test dataset.
  arXiv  Detail & Related papers  (2020-10-30T14:36:10Z)
• REST: Robust and Efficient Neural Networks for Sleep Monitoring in the Wild [62.36144064259933]
  We propose REST, a new method that simultaneously tackles both issues via adversarial training and controlling the Lipschitz constant of the neural network. We demonstrate that REST produces highly-robust and efficient models that substantially outperform the original full-sized models in the presence of noise. By deploying these models to an Android application on a smartphone, we quantitatively observe that REST allows models to achieve up to 17x energy reduction and 9x faster inference.
  arXiv  Detail & Related papers  (2020-01-29T17:23:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.