MOIS-SAM2: Exemplar-based Segment Anything Model 2 for multilesion interactive segmentation of neurofibromas in whole-body MRI
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915702712041472 |
|---|---|
| author | Kolokolnikov, Georgii Schmalhofer, Marie-Lena Goetz, Sophie Well, Lennart Farschtschi, Said Mautner, Victor-Felix Ristow, Inka Werner, Rene |
| author_facet | Kolokolnikov, Georgii Schmalhofer, Marie-Lena Goetz, Sophie Well, Lennart Farschtschi, Said Mautner, Victor-Felix Ristow, Inka Werner, Rene |
| contents | Background and Objectives: Neurofibromatosis type 1 is a genetic disorder characterized by the development of numerous neurofibromas (NFs) throughout the body. Whole-body MRI (WB-MRI) is the clinical standard for detection and longitudinal surveillance of NF tumor growth. Existing interactive segmentation methods fail to combine high lesion-wise precision with scalability to hundreds of lesions. This study proposes a novel interactive segmentation model tailored to this challenge.
Methods: We introduce MOIS-SAM2, a multi-object interactive segmentation model that extends the state-of-the-art, transformer-based, promptable Segment Anything Model 2 (SAM2) with exemplar-based semantic propagation. MOIS-SAM2 was trained and evaluated on 119 WB-MRI scans from 84 NF1 patients acquired using T2-weighted fat-suppressed sequences. The dataset was split at the patient level into a training set and four test sets (one in-domain and three reflecting different domain shift scenarios, e.g., MRI field strength variation, low tumor burden, differences in clinical site and scanner vendor).
Results: On the in-domain test set, MOIS-SAM2 achieved a scan-wise DSC of 0.60 against expert manual annotations, outperforming baseline 3D nnU-Net (DSC: 0.54) and SAM2 (DSC: 0.35). Performance of the proposed model was maintained under MRI field strength shift (DSC: 0.53) and scanner vendor variation (DSC: 0.50), and improved in low tumor burden cases (DSC: 0.61). Lesion detection F1 scores ranged from 0.62 to 0.78 across test sets. Preliminary inter-reader variability analysis showed model-to-expert agreement (DSC: 0.62-0.68), comparable to inter-expert agreement (DSC: 0.57-0.69).
Conclusions: The proposed MOIS-SAM2 enables efficient and scalable interactive segmentation of NFs in WB-MRI with minimal user input and strong generalization, supporting integration into clinical workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19277 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MOIS-SAM2: Exemplar-based Segment Anything Model 2 for multilesion interactive segmentation of neurofibromas in whole-body MRI Kolokolnikov, Georgii Schmalhofer, Marie-Lena Goetz, Sophie Well, Lennart Farschtschi, Said Mautner, Victor-Felix Ristow, Inka Werner, Rene Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Background and Objectives: Neurofibromatosis type 1 is a genetic disorder characterized by the development of numerous neurofibromas (NFs) throughout the body. Whole-body MRI (WB-MRI) is the clinical standard for detection and longitudinal surveillance of NF tumor growth. Existing interactive segmentation methods fail to combine high lesion-wise precision with scalability to hundreds of lesions. This study proposes a novel interactive segmentation model tailored to this challenge. Methods: We introduce MOIS-SAM2, a multi-object interactive segmentation model that extends the state-of-the-art, transformer-based, promptable Segment Anything Model 2 (SAM2) with exemplar-based semantic propagation. MOIS-SAM2 was trained and evaluated on 119 WB-MRI scans from 84 NF1 patients acquired using T2-weighted fat-suppressed sequences. The dataset was split at the patient level into a training set and four test sets (one in-domain and three reflecting different domain shift scenarios, e.g., MRI field strength variation, low tumor burden, differences in clinical site and scanner vendor). Results: On the in-domain test set, MOIS-SAM2 achieved a scan-wise DSC of 0.60 against expert manual annotations, outperforming baseline 3D nnU-Net (DSC: 0.54) and SAM2 (DSC: 0.35). Performance of the proposed model was maintained under MRI field strength shift (DSC: 0.53) and scanner vendor variation (DSC: 0.50), and improved in low tumor burden cases (DSC: 0.61). Lesion detection F1 scores ranged from 0.62 to 0.78 across test sets. Preliminary inter-reader variability analysis showed model-to-expert agreement (DSC: 0.62-0.68), comparable to inter-expert agreement (DSC: 0.57-0.69). Conclusions: The proposed MOIS-SAM2 enables efficient and scalable interactive segmentation of NFs in WB-MRI with minimal user input and strong generalization, supporting integration into clinical workflows. |
| title | MOIS-SAM2: Exemplar-based Segment Anything Model 2 for multilesion interactive segmentation of neurofibromas in whole-body MRI |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2509.19277 |