MSTT-199: MRI Dataset for Musculoskeletal Soft Tissue Tumor Segmentation
Abstract: Accurate musculoskeletal soft tissue tumor segmentation is vital for assessing tumor size, location, diagnosis, and response to treatment, thereby influencing patient outcomes. However, segmentation of these tumors requires clinical expertise, and an automated segmentation model would save valuable time for both clinician and patient. Training an automatic model requires a large dataset of annotated images. In this work, we describe the collection of an MR imaging dataset of 199 musculoskeletal soft tissue tumors from 199 patients. We trained segmentation models on this dataset and then benchmarked them on a publicly available dataset. Our model achieved the state-of-the-art dice score of 0.79 out of the box without any fine tuning, which shows the diversity and utility of our curated dataset. We analyzed the model predictions and found that its performance suffered on fibrous and vascular tumors due to their diverse anatomical location, size, and intensity heterogeneity. The code and models are available in the following github repository, https://github.com/Reasat/mstt
- Enzinger and Weiss’s soft tissue tumors E-book (Elsevier Health Sciences, 2013).
- Soft tissue sarcomas. \JournalTitleCA: a cancer journal for clinicians 54, 94–109 (2004).
- Lawrenz, J. M. et al. Can radiomics and machine learning predict diagnosis in musculoskeletal myxoid soft tissue tumors? \JournalTitleJournal of the American College of Surgeons 235, S61–S62 (2022).
- Cui, C. et al. Multi-modality classification between myxofibrosarcoma and myxoma using radiomics and machine learning models. In Medical Imaging 2022: Computer-Aided Diagnosis, vol. 12033, 782–788 (SPIE, 2022).
- Fields, B. K. et al. Whole-tumor 3d volumetric mri-based radiomics approach for distinguishing between benign and malignant soft tissue tumors. \JournalTitleEuropean radiology 31, 8522–8535 (2021).
- Lee, S. et al. Ensemble learning-based radiomics with multi-sequence magnetic resonance imaging for benign and malignant soft tissue tumor differentiation. \JournalTitlePlos one 18, e0286417 (2023).
- Dionisio, F. C. F. et al. Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times. \JournalTitleRadiologia Brasileira 54, 155–164 (2021).
- Blackledge, M. D. et al. Supervised machine-learning enables segmentation and evaluation of heterogeneous post-treatment changes in multi-parametric mri of soft-tissue sarcoma. \JournalTitleFrontiers in oncology 9, 941 (2019).
- Bi, L. et al. Hybrid cnn-transformer network for interactive learning of challenging musculoskeletal images. \JournalTitleComputer Methods and Programs in Biomedicine 243, 107875 (2024).
- Neubauer, T. et al. Soft tissue sarcoma co-segmentation in combined mri and pet/ct data. In Multimodal Learning for Clinical Decision Support and Clinical Image-Based Procedures: 10th International Workshop, ML-CDS 2020, and 9th International Workshop, CLIP 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4–8, 2020, Proceedings 9, 97–105 (Springer, 2020).
- Efnet: evidence fusion network for tumor segmentation from pet-ct volumes. \JournalTitlePhysics in Medicine & Biology 66, 205005 (2021).
- A radiomics model from joint fdg-pet and mri texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities. \JournalTitlePhysics in Medicine & Biology 60, 5471 (2015).
- Label Studio: Data labeling software (2020-2022). Open source software available from https://github.com/heartexlabs/label-studio.
- Avants, B. B. et al. A reproducible evaluation of ants similarity metric performance in brain image registration. \JournalTitleNeuroimage 54, 2033–2044 (2011).
- Fedorov, A. et al. 3d slicer as an image computing platform for the quantitative imaging network. \JournalTitleMagnetic resonance imaging 30, 1323–1341 (2012).
- Label studio: Data labeling software. \JournalTitleOpen source software available from https://github. com/heartexlabs/label-studio 2022 (2020).
- Morrison, B. A. Soft tissue sarcomas of the extremities. In Baylor University Medical Center Proceedings, vol. 16, 285–290 (Taylor & Francis, 2003).
- 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, 234–241 (Springer, 2015).
- Fukushima, K. Visual feature extraction by a multilayered network of analog threshold elements. \JournalTitleIEEE Transactions on Systems Science and Cybernetics 5, 322–333 (1969).
- Kirillov, A. et al. Segment anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 4015–4026 (2023).
- Ma, J. et al. Segment anything in medical images. \JournalTitleNature Communications 15, 654 (2024).
- Dosovitskiy, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. \JournalTitlearXiv preprint arXiv:2010.11929 (2020).
- Vaswani, A. et al. Attention is all you need. \JournalTitleAdvances in neural information processing systems 30 (2017).
- Clark, K. et al. The cancer imaging archive (tcia): maintaining and operating a public information repository. \JournalTitleJournal of digital imaging 26, 1045–1057 (2013).
- Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1492–1500 (2017).
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.