The Universal Lesion Segmentation '23 Challenge

Clinical Relevancy

In recent years, there has been a notable increase in the number of CT exams conducted annually, leading to heightened workloads for radiologists. This trend is expected to continue, particularly with the projected 47% rise in global cancer cases by 2040 compared to 2020. Oncological radiology is poised to bear a significant portion of this increased workload, given that cancer patients often undergo multiple imaging procedures over time to monitor disease progression.

Assessing disease progression and treatment response in longitudinal CT scans typically involves manual measurements of lesions according to the Response Evaluation Criteria In Solid Tumors (RECIST) guidelines. However, this process can be time-consuming, as it requires measuring a limited number of "target lesions" across various organs or structures.

The ULS23 Challenge

To alleviate the time burden associated with lesion annotation, automatic segmentation models have emerged. These models can extract information with minimal guidance from radiologists, such as a single-click inside the lesion or through bounding box predictions. Additionally, segmenting lesion volumes in 3D offers valuable insights for calculating more informative lesion characteristics. Registration algorithms further facilitate time savings by propagating segmented lesions during follow-up exams.

Despite significant advancements in AI-based segmentation models for specific tumor types, there remains a need for versatile and robust models capable of quickly segmenting diverse lesion types in the thorax-abdomen region. To address this gap, the Universal Lesion Segmentation (ULS) Challenge has been launched. By providing well-curated and varied datasets, including fully annotated 3D training data and a diverse multi-center test set, this challenge aims to serve as a benchmark for ULS models. Additionally, baseline ULS models are made publicly available to facilitate research and development in this area.</font>

Partners and Organizers

Organizers: Max de Grauw, Bram van Ginneken & Alessa Hering of the Diagnostic Image Analysis Group

Partners: Mathai Tejas, Pritam Mukherjee & Ronald Summers of the National Institutes of Health

Annotation team: dr. Ernst Scholten, dr. ir. Ewoud Smit, Pit van Halbeek, Suze Loomans, Romy van den Akker, Pieter Drijver, Noortje van Kempen, Eva Boldrini, Temke Kohlbrandt

References

1. Boland, G. W., Guimaraes, A. S., & Mueller, P. R. (2009). The radiologist’s conundrum: benefits and costs of increasing CT capacity and utilization. European radiology, 19, 9-11.
2. McDonald, R. J., Schwartz, K. M., Eckel, L. J., et al. (2015). The effects of changes in utilization and technological advancements of cross-sectional imaging on radiologist workload. Academic radiology, 22(9), 1191-1198.
3. Sung, H., Ferlay, J., Siegel, R. L., et al. (2021). Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians, 71(3), 209-249.
4. Eisenhauer, E. A., Therasse, P., Bogaerts, J., et al. (2009). New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). European journal of cancer, 45(2), 228-247.
5. Hering, A., Peisen, F., Amaral, T., et al. (2021, August). Whole-body soft-tissue lesion tracking and segmentation in longitudinal CT imaging studies. In Medical Imaging with Deep Learning (pp. 312-326). PMLR.
6. Cai, J., Tang, Y., Lu, L., et al.(2018). Accurate weakly-supervised deep lesion segmentation using large-scale clinical annotations: Slice-propagated 3d mask generation from 2d recist. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part IV 11 (pp. 396-404). Springer International Publishing.
7. Tang, Y., Yan, K., Xiao, J., et al. (2020). One click lesion RECIST measurement and segmentation on CT scans. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part IV 23 (pp. 573-583). Springer International Publishing.
8. Tang, Y., Yan, K., Cai, J., et al. (2021). Lesion segmentation and RECIST diameter prediction via click-driven attention and dual-path connection. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part II 24 (pp. 341-351). Springer International Publishing.
9. Yan, K., Wang, X., Lu, L., et al. (2018). DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. Journal of medical imaging, 5(3), 036501-036501.