Abstract
Gliomas, the most prevalent primary brain tumors, require precise segmentation for diagnosis and treatment planning. However, this task poses significant challenges, particularly in the African population, where limited access to high-quality imaging data hampers algorithm performance. In this study, we propose a new approach combining the Segment Anything Model (SAM) and a voting network for multi-modal glioma segmentation. By fine-tuning SAM with bounding box-guided prompts (SAMBA), we adapt the model to the complexities of African datasets. Our ensemble strategy, utilizing multiple modalities and views, produces a robust consensus segmentation, addressing the intratumoral heterogeneity. This study was conducted on the Brain Tumor Segmentation (BraTS) Africa (BraTS-Africa) dataset, which provides a valuable resource for addressing challenges specific to resource-limited settings and facilitating the development of effective and more generalizable segmentation algorithms. To illustrate our approach’s potential, our experiments on the BraTS-Africa dataset yielded compelling results, with SAMBA attaining a Dice coefficient of 86.6% for binary segmentation and 60.4% for multi-class segmentation. Although the low quality of the scans currently presents difficulties, SAMBA has the potential to facilitate more generalizable segmentations for real world clinical problems with future applications to other types of brain lesions.
M. Barakat and N. Magdy—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aldape, K., Brindle, K.M., Chesler, L., Chopra, R., et al.: Challenges to curing primary brain tumours. Nat. Rev. Clin. Oncol. 16(8), 509–520 (2019)
Anazodo, U.C., Ng, J.J., Ehiogu, B., Obungoloch, J., Fatade, A., et al.: A framework for advancing sustainable magnetic resonance imaging access in Africa. NMR Biomed. 36(3), e4846 (2023)
Zhang, D., Confidence, R., Anazodo, U.: Stroke lesion segmentation from low quality and few-shot mris via similarity-weighted self-ensembling framework. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention – MICCAI 2022. MICCAI 2022. Lecture Notes in Computer Science, vol. 13435. Springer, Cham (2022)
Cahall, D.E., et al.: Inception Modules Enhance Brain Tumor Segmentation (2019). https://doi.org/10.3389/FNCOM.2019.00044
Kanmounye, U.S., Karekezi, C., Nyalundja, A.D., Awad, A.K., et al.: Adult brain tumors in Sub-Saharan Africa: a scoping review. Neuro Oncol. 24(10), 1799–1806 (2022)
Adewole, M., Rudie, J.D., Gbadamosi, A., et al.: The Brain Tumor Segmentation (BraTS) Challenge 2023: Glioma Segmentation in Sub-Saharan Africa Patient Population (BraTS-Africa). arXiv preprint arXiv:2305.19369 (2023)
Baid, U., Ghodasara, S., Mohan, S., Bilello, M., Calabrese, E., et al.: The RSNA-ASNR-MICCAI- BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv preprint arXiv:2107.02314 (2021)
Menze, B.H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2014)
Zeineldin, R.A., Karar, M.E., Burgert, O., Mathis-Ullrich, F.: Multimodal CNN networks for brain tumor segmentation in MRI: a BraTS 2022 challenge solution. arXiv preprint arXiv:2212.09310 (2022)
Isensee, F., Jäger, P.F., Full, P.M., Vollmuth, P., Maier-Hein, K.H.: nnU-Net for brain tumor segmentation. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 6th International Workshop, BrainLes 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4, 2020, Revised Selected Papers, Part II 6 2021, pp. 118–132. Springer, Cham (2020)
Gong, Q., et al.: DeepScan: Exploiting deep learning for malicious account detection in location-based social networks. IEEE Commun. Mag. 56(11), 21–27 (2018)
Hatamizadeh, A., Nath, V., Tang, Y., Yang, D., Roth, H.R., Xu, D.: Swin unetr: swin transformers for semantic segmentation of brain tumors in MRI images. In: International MICCAI Brain- lesion Workshop 2021 Sep 27, pp. 272–284. Springer, Cham (2021)
Henry, T., et al.: Brain tumor segmentation with self-ensembled, deeply-supervised 3D U-net neural networks: a BraTS 2020 challenge solution. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 6th International Workshop, BrainLes 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4, 2020, Revised Selected Papers, Part I 6 2021, pp. 327–339. Springer, Cham (2020)
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., et al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)
Ma, J., Wang, B.: Segment anything in medical images. arXiv preprint arXiv:2304.12306 (2023)
Liu, Y., Zhang, J., She, Z., Kheradmand, A., Armand, M.: SAMM (segment any medical model): A 3D Slicer integration to SAM. arXiv preprint arXiv:2304.05622 (2023)
Terven, J., Cordova-Esparza, D.: A comprehensive review of YOLO: From YOLOv1 to YOLOv8 and beyond. arXiv preprint arXiv:2304.00501 (2023)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5–9, 2015, Proceedings, Part III 18 2015, pp. 234–241. Springer, Cham (2015)
Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)
Acknowledgment
The authors would like to thank the all the faculty and instructors of the Sprint AI Training for African Medical Imaging Knowledge Translation (SPARK) Academy 2023 summer school on deep learning in medical imaging for providing insightful background knowledge that informed the research presented here. The authors thank Linshan Liu for administrative assistance in supporting SPARK and acknowledge the computational infrastructure support from the Digital Research Alliance of Canada (The Alliance) and the knowledge translation support from the McGill University Doctoral Internship Program through student exchange program for the SPARK Academy. The authors are grateful to McMedHacks for providing foundational information on python programming for medical image analysis as part of the 2023 SPARK Academy program. This research was funded by the Lacuna Fund for Health and Equity (PI: Udunna Anazodo, grant number 0508-S-001) and National Science and Engineering Research Council of Canada (NSERC) Discovery Launch Supplement (PI: Udunna Anazodo, grant number DGECR-2022-00136).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Barakat, M. et al. (2024). Towards SAMBA: Segment Anything Model for Brain Tumor Segmentation in Sub-Saharan African Populations. In: Baid, U., et al. Brain Tumor Segmentation, and Cross-Modality Domain Adaptation for Medical Image Segmentation. crossMoDA BraTS 2023 2023. Lecture Notes in Computer Science, vol 14669. Springer, Cham. https://doi.org/10.1007/978-3-031-76163-8_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-76163-8_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-76162-1
Online ISBN: 978-3-031-76163-8
eBook Packages: Computer ScienceComputer Science (R0)