In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via www.lits-challenge.com.
The Liver Tumor Segmentation Benchmark (LiTS)
P. Bilic, P. Christ, H. Li, E. Vorontsov, A. Ben-Cohen, G. Kaissis, A. Szeskin, C. Jacobs, G. Mamani, G. Chartrand, F. Lohofer, J. Holch, W. Sommer, F. Hofmann, A. Hostettler, N. Lev-Cohain, M. Drozdzal, M. Amitai, R. Vivanti, J. Sosna, I. Ezhov, A. Sekuboyina, F. Navarro, F. Kofler, J. Paetzold, S. Shit, X. Hu, J. Lipkova, M. Rempfler, M. Piraud, J. Kirschke, B. Wiestler, Z. Zhang, C. Hulsemeyer, M. Beetz, F. Ettlinger, M. Antonelli, W. Bae, M. Bellver, L. Bi, H. Chen, G. Chlebus, E. Dam, Q. Dou, C. Fu, B. Georgescu, X. Giro-i-Nieto, F. Gruen, X. Han, P. Heng, J. Hesser, J. Moltz, C. Igel, F. Isensee, P. Jager, F. Jia, K. Kaluva, M. Khened, I. Kim, J. Kim, S. Kim, S. Kohl, T. Konopczynski, A. Kori, G. Krishnamurthi, F. Li, J. Li, X. Li, J. Lowengrub, J. Ma, K. Maier-Hein, K. Maninis, H. Meine, D. Merhof, A. Pai, M. Perslev, J. Petersen, J. Pont-Tuset, J. Qi, X. Qi, O. Rippel, K. Roth, I. Sarasua, A. Schenk, Z. Shen, J. Torres, C. Wachinger, C. Wang, L. Weninger, J. Wu, D. Xu, X. Yang, S. Yu, Y. Yuan, M. Yue, L. Zhang, J. Cardoso, S. Bakas, R. Braren, V. Heinemann, C. Pal, A. Tang, S. Kadoury, L. Soler, B. van Ginneken, H. Greenspan, L. Joskowicz and B. Menze
Medical Image Analysis 2022;84:102680.