Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Trustworthy Multi-phase Liver Tumor Segmentation via Evidence-based Uncertainty (2305.05344v2)

Published 9 May 2023 in eess.IV and cs.CV

Abstract: Multi-phase liver contrast-enhanced computed tomography (CECT) images convey the complementary multi-phase information for liver tumor segmentation (LiTS), which are crucial to assist the diagnosis of liver cancer clinically. However, the performances of existing multi-phase liver tumor segmentation (MPLiTS)-based methods suffer from redundancy and weak interpretability, % of the fused result, resulting in the implicit unreliability of clinical applications. In this paper, we propose a novel trustworthy multi-phase liver tumor segmentation (TMPLiTS), which is a unified framework jointly conducting segmentation and uncertainty estimation. The trustworthy results could assist the clinicians to make a reliable diagnosis. Specifically, Dempster-Shafer Evidence Theory (DST) is introduced to parameterize the segmentation and uncertainty as evidence following Dirichlet distribution. The reliability of segmentation results among multi-phase CECT images is quantified explicitly. Meanwhile, a multi-expert mixture scheme (MEMS) is proposed to fuse the multi-phase evidences, which can guarantee the effect of fusion procedure based on theoretical analysis. Experimental results demonstrate the superiority of TMPLiTS compared with the state-of-the-art methods. Meanwhile, the robustness of TMPLiTS is verified, where the reliable performance can be guaranteed against the perturbations.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Y. Nakayama, Q. Li, S. Katsuragawa, R. Ikeda, Y. Hiai, K. Awai, S. Kusunoki, Y. Yamashita, H. Okajima, Y. Inomata et al., “Automated hepatic volumetry for living related liver transplantation at multisection ct,” Radiology, vol. 240, no. 3, pp. 743–748, 2006, DOI 10.1148/radiol.2403050850.
  2. P. Entezari, B. B. Toskich, E. Kim, S. Padia, D. Christopher, A. Sher, B. Thornburg, E. S. Hohlastos, R. Salem, J. D. Collins et al., “Promoting surgical resection through future liver remnant hypertrophy,” RadioGraphics, vol. 42, no. 7, pp. 2166–2183, 2022, DOI 10.1148/rg.220050.
  3. J. C. Spina, I. Hume, A. Pelaez, O. Peralta, M. Quadrelli, and R. Garcia Monaco, “Expected and unexpected imaging findings after 90y transarterial radioembolization for liver tumors,” Radiographics, vol. 39, no. 2, pp. 578–595, 2019, DOI 10.1148/rg.2019180095.
  4. J. Assouline, R. Cannella, G. Porrello, L. de Mestier, M. Dioguardi Burgio, L. Raynaud, O. Hentic, J. Cros, L. Tselikas, P. Ruszniewski et al., “Volumetric enhancing tumor burden at ct to predict survival outcomes in patients with neuroendocrine liver metastases after intra-arterial treatment,” Radiology: Imaging Cancer, vol. 5, no. 1, p. e220051, 2023, DOI 10.1148/rycan.220051.
  5. M. G. Linguraru, W. J. Richbourg, J. Liu, J. M. Watt, V. Pamulapati, S. Wang, and R. M. Summers, “Tumor burden analysis on computed tomography by automated liver and tumor segmentation,” IEEE Transactions on Medical Imaging, vol. 31, no. 10, pp. 1965–1976, 2012, DOI 10.1109/TMI.2012.2211887.
  6. C. Li, X. Wang, S. Eberl, M. Fulham, Y. Yin, J. Chen, and D. D. Feng, “A likelihood and local constraint level set model for liver tumor segmentation from ct volumes,” IEEE Transactions on Biomedical Engineering, vol. 60, no. 10, pp. 2967–2977, 2013, DOI 10.1109/TBME.2013.2267212.
  7. G. ming Xian, “An identification method of malignant and benign liver tumors from ultrasonography based on glcm texture features and fuzzy svm,” Expert Systems with Applications, vol. 37, no. 10, pp. 6737–6741, 2010, DOI 10.1016/j.eswa.2010.02.067.
  8. E. Begoli, T. Bhattacharya, and D. Kusnezov, “The need for uncertainty quantification in machine-assisted medical decision making,” Nature Machine Intelligence, vol. 1, no. 1, pp. 20–23, 2019, DOI 10.1038/s42256-018-0004-1.
  9. J. Zhang, Y. Xie, P. Zhang, H. Chen, Y. Xia, and C. Shen, “Light-weight hybrid convolutional network for liver tumor segmentation,” in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pp. 4271–4277.   International Joint Conferences on Artificial Intelligence Organization, 7 2019, DOI 10.24963/ijcai.2019/593.
  10. T. Lei, R. Wang, Y. Zhang, Y. Wan, C. Liu, and A. K. Nandi, “Defed-net: Deformable encoder-decoder network for liver and liver tumor segmentation,” IEEE Transactions on Radiation and Plasma Medical Sciences, vol. 6, no. 1, pp. 68–78, 2021, DOI 10.1109/TRPMS.2021.3059780.
  11. S. Di, Y. Zhao, M. Liao, F. Zhang, and X. Li, “Td-net: A hybrid end-to-end network for automatic liver tumor segmentation from ct images,” IEEE Journal of Biomedical and Health Informatics, pp. 1–10, 2022, DOI 10.1109/JBHI.2022.3181974.
  12. F. Lyu, M. Ye, A. J. Ma, T. C.-F. Yip, G. L.-H. Wong, and P. C. Yuen, “Learning from synthetic ct images via test-time training for liver tumor segmentation,” IEEE transactions on medical imaging, vol. 41, no. 9, pp. 2510–2520, 2022, DOI 10.1109/TMI.2022.3166230.
  13. W. Zou, X. Qi, W. Zhou, M. Sun, Z. Sun, and C. Shan, “Graph flow: Cross-layer graph flow distillation for dual efficient medical image segmentation,” IEEE Transactions on Medical Imaging, 2022, DOI 10.1109/TMI.2022.3224459.
  14. N. Vogt, S. M. Brady, G. Ridgway, J. Connell, and A. I. Namburete, “Segmenting hepatocellular carcinoma in multi-phase ct,” in Medical Image Understanding and Analysis, pp. 82–92.   Springer, 2020, DOI 10.1007/978-3-030-52791-4_7.
  15. Y. Zhang, C. Peng, L. Peng, H. Huang, R. Tong, L. Lin, J. Li, Y.-W. Chen, Q. Chen, H. Hu et al., “Multi-phase liver tumor segmentation with spatial aggregation and uncertain region inpainting,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2021, pp. 68–77, 2021, DOI 10.1007/978-3-030-87193-2_7.
  16. Y. Zhang, J. Yang, J. Tian, Z. Shi, C. Zhong, Y. Zhang, and Z. He, “Modality-aware mutual learning for multi-modal medical image segmentation,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2021, pp. 589–599.   Springer, 2021, DOI 10.1007/978-3-030-87193-2_56.
  17. R. Zheng, Q. Wang, S. Lv, C. Li, C. Wang, W. Chen, and H. Wang, “Automatic liver tumor segmentation on dynamic contrast enhanced mri using 4d information: deep learning model based on 3d convolution and convolutional lstm,” IEEE Transactions on Medical Imaging, vol. 41, no. 10, pp. 2965–2976, 2022, DOI 10.1109/TMI.2022.3175461.
  18. V. Chernyak, K. J. Fowler, A. Kamaya, A. Z. Kielar, K. M. Elsayes, M. R. Bashir, Y. Kono, R. K. Do, D. G. Mitchell, A. G. Singal et al., “Liver imaging reporting and data system (li-rads) version 2018: Imaging of hepatocellular carcinoma in at-risk patients,” Radiology, vol. 289, no. 3, pp. 816–830, 2018, DOI 10.1148/radiol.2018181494.
  19. S. Kundu, “Ai in medicine must be explainable,” Nature medicine, vol. 27, no. 8, pp. 1328–1328, 2021, DOI 10.1038/s41591-021-01461-z.
  20. H. Chen, C. Gomez, C.-M. Huang, and M. Unberath, “Explainable medical imaging ai needs human-centered design: guidelines and evidence from a systematic review,” npj Digital Medicine, vol. 5, no. 1, pp. 1–15, 2022, DOI 10.1038/s41746-022-00699-2.
  21. R. Gu, G. Wang, T. Song, R. Huang, M. Aertsen, J. Deprest, S. Ourselin, T. Vercauteren, and S. Zhang, “Ca-net: Comprehensive attention convolutional neural networks for explainable medical image segmentation,” IEEE Transactions on Medical Imaging, vol. 40, no. 2, pp. 699–711, 2021, DOI 10.1109/TMI.2020.3035253.
  22. Z. Liao, Y. Xie, S. Hu, and Y. Xia, “Learning from ambiguous labels for lung nodule malignancy prediction,” IEEE Transactions on Medical Imaging, vol. 41, no. 7, pp. 1874–1884, 2022, DOI 10.1109/TMI.2022.3149344.
  23. C. Mao, L. Yao, and Y. Luo, “Imagegcn: Multi-relational image graph convolutional networks for disease identification with chest x-rays,” IEEE Transactions on Medical Imaging, vol. 41, no. 8, pp. 1990–2003, 2022, DOI 10.1109/TMI.2022.3153322.
  24. D. Major, D. Lenis, M. Wimmer, A. Berg, T. Neubauer, and K. Bühler, “On the importance of domain awareness in classifier interpretations in medical imaging,” IEEE Transactions on Medical Imaging, pp. 1–1, 2023, DOI 10.1109/TMI.2023.3247659.
  25. M. Sensoy, L. Kaplan, and M. Kandemir, “Evidential deep learning to quantify classification uncertainty,” Advances in neural information processing systems, vol. 31, 2018. [Online]. Available: https://dl.acm.org/doi/abs/10.5555/3327144.3327239
  26. F. Ouhmich, V. Agnus, V. Noblet, F. Heitz, and P. Pessaux, “Liver tissue segmentation in multiphase ct scans using cascaded convolutional neural networks,” International journal of computer assisted radiology and surgery, vol. 14, pp. 1275–1284, 2019, DOI 10.1007/s11548-019-01989z.
  27. C. Sun, S. Guo, H. Zhang, J. Li, M. Chen, S. Ma, L. Jin, X. Liu, X. Li, and X. Qian, “Automatic segmentation of liver tumors from multiphase contrast-enhanced ct images based on fcns,” Artificial intelligence in medicine, vol. 83, pp. 58–66, 2017, DOI 10.1016/j.artmed.2017.03.008.
  28. A. Raju, C.-T. Cheng, Y. Huo, J. Cai, J. Huang, J. Xiao, L. Lu, C. Liao, and A. P. Harrison, “Co-heterogeneous and adaptive segmentation from multi-source and multi-phase ct imaging data: A study on pathological liver and lesion segmentation,” in Computer Vision–ECCV 2020, pp. 448–465.   Springer, 2020, DOI 10.1007/978-3-030-58592-1_27.
  29. Y. Dong, X. Li, J. Dezert, R. Zhou, C. Zhu, L. Wei, and S. S. Ge, “Evidential reasoning with hesitant fuzzy belief structures for human activity recognition,” IEEE Transactions on Fuzzy Systems, vol. 29, no. 12, pp. 3607–3619, 2021, DOI 10.1109/TFUZZ.2021.3079495.
  30. Y. Dong, X. Li, J. Dezert, R. Zhou, C. Zhu, L. Cao, M. O. Khyam, and S. S. Ge, “Multi-source weighted domain adaptation with evidential reasoning for activity recognition,” IEEE Transactions on Industrial Informatics, pp. 1–12, 2022, DOI 10.1109/TII.2022.3182780.
  31. T. Nair, D. Precup, D. L. Arnold, and T. Arbel, “Exploring uncertainty measures in deep networks for multiple sclerosis lesion detection and segmentation,” Medical Image Analysis, vol. 59, p. 101557, 2020, DOI 10.1016/j.media.2019.101557.
  32. S. Kohl, B. Romera-Paredes, C. Meyer, J. De Fauw, J. R. Ledsam, K. Maier-Hein, S. Eslami, D. Jimenez Rezende, and O. Ronneberger, “A probabilistic u-net for segmentation of ambiguous images,” Advances in Neural Information Processing Systems, vol. 31, 2018. [Online]. Available: https://dl.acm.org/doi/10.5555/3327757.3327800
  33. B. Lakshminarayanan, A. Pritzel, and C. Blundell, “Simple and scalable predictive uncertainty estimation using deep ensembles,” in Advances in Neural Information Processing Systems, vol. 30.   Curran Associates, Inc., 2017. [Online]. Available: https://dl.acm.org/doi/10.5555/3295222.3295387
  34. K. Zou, X. Yuan, X. Shen, M. Wang, and H. Fu, “Tbrats: Trusted brain tumor segmentation,” in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2022, pp. 503–513.   Springer, 2022, DOI 10.1007/978-3-031-16452-1_48.
  35. Z. Han, C. Zhang, H. Fu, and J. T. Zhou, “Trusted multi-view classification with dynamic evidential fusion,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 2, pp. 2551–2566, 2023, DOI 10.1109/TPAMI.2022.3171983.
  36. S. Klein, M. Staring, K. Murphy, M. A. Viergever, and J. P. W. Pluim, “elastix: A toolbox for intensity-based medical image registration,” IEEE Transactions on Medical Imaging, vol. 29, no. 1, pp. 196–205, 2010, DOI 10.1109/TMI.2009.2035616.
  37. A. Jungo and M. Reyes, “Assessing reliability and challenges of uncertainty estimations for medical image segmentation,” in Medical Image Computing and Computer Assisted Intervention – MICCAI 2019, pp. 48–56.   Springer, 2019, DOI 10.1007/978-3-030-32245-8_6.
  38. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pp. 234–241.   Springer, 2015, DOI 10.1007/978-3-319-24574-4_28.
  39. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in ICLR (Poster), 2015. [Online]. Available: http://arxiv.org/abs/1412.6980
  40. D. Mathieu, N. Vasile, C. Dibie, and P. Grenier, “Portal cavernoma: dynamic ct features and transient differences in hepatic attenuation,” Radiology, vol. 154, no. 3, pp. 743–748, 1985, DOI 10.1148/radiology.154.3.3881794.
  41. J. H. Lim, D. Choi, S. H. Kim, S. J. Lee, W. J. Lee, H. K. Lim, and S. Kim, “Detection of hepatocellular carcinoma: value of adding delayed phase imaging to dual-phase helical ct,” American Journal of Roentgenology, vol. 179, no. 1, pp. 67–73, 2002, DOI 10.2214/ajr.179.1.1790067.
Citations (24)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now