Abstract
Recent advances in deep learning algorithms have led to significant benefits for solving many medical image analysis problems. Training deep learning models commonly requires large datasets with expert-labeled annotations. However, acquiring expert-labeled annotation is not only expensive but also is subjective, error-prone, and inter-/intra- observer variability introduces noise to labels. This is particularly a problem when using deep learning models for segmenting medical images due to the ambiguous anatomical boundaries. Image-based medical diagnosis tools using deep learning models trained with incorrect segmentation labels can lead to false diagnoses and treatment suggestions. Multi-rater annotations might be better suited to train deep learning models with small training sets compared to single-rater annotations. The aim of this paper was to develop and evaluate a method to generate probabilistic labels based on multi-rater annotations and anatomical knowledge of the lesion features in MRI and a method to train segmentation models using probabilistic labels using normalized active-passive loss as a “noise-tolerant loss” function. The model was evaluated by comparing it to binary ground truth for 17 knees MRI scans for clinical segmentation and detection of bone marrow lesions (BML). The proposed method successfully improved precision 14, recall 22, and Dice score 8 percent compared to a binary cross-entropy loss function. Overall, the results of this work suggest that the proposed normalized active-passive loss using soft labels successfully mitigated the effects of noisy labels.
Jacob L. Jaremko—Supported by a Canada CIFAR AI Chair.
Banafshe Felfeliyan—Supported by an Alberta Innovates Graduate Student Scholarship for Data-Enabled Innovation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bertels, J., Robben, D., Vandermeulen, D., Suetens, P.: Optimization with soft dice can lead to a volumetric bias. In: Crimi, A., Bakas, S. (eds.) BrainLes 2019. LNCS, vol. 11992, pp. 89–97. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-46640-4_9
Busby, L.P., Courtier, J.L., Glastonbury, C.M.: Bias in radiology: the how and why of misses and misinterpretations. Radiographics 38(1), 236–247 (2018)
Felfeliyan, B., Hareendranathan, A., Kuntze, G., Jaremko, J.L., Ronsky, J.L.: Improved-mask R-CNN: towards an accurate generic MSK MRI instance segmentation platform (data from the osteoarthritis initiative). Comput. Med. Imaging Graph. 97, 102056 (2022)
Ghosh, A., Kumar, H., Sastry, P.S.: Robust loss functions under label noise for deep neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)
Gros, C., Lemay, A., Cohen-Adad, J.: SoftSeg: advantages of soft versus binary training for image segmentation. Med. Image Anal. 71, 102038 (2021)
Yushkevich, P.A., et al.: User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31(3), 1116–1128 (2006)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 386–397 (2020). https://doi.org/10.1109/TPAMI.2018.2844175
Hendrycks, D., Mazeika, M., Wilson, D., Gimpel, K.: Using trusted data to train deep networks on labels corrupted by severe noise. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Ibrahim, M.S., Vahdat, A., Ranjbar, M., Macready, W.G.: Semi-supervised semantic image segmentation with self-correcting networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12715–12725 (2020)
Islam, M., Glocker, B.: Spatially varying label smoothing: capturing uncertainty from expert annotations. In: Feragen, A., Sommer, S., Schnabel, J., Nielsen, M. (eds.) IPMI 2021. LNCS, vol. 12729, pp. 677–688. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-78191-0_52
Jaremko, J.L., et al.: Validation of a knowledge transfer tool for the knee inflammation MRI scoring system for bone marrow lesions according to the OMERACT filter: data from the osteoarthritis initiative. J. Rheumatol. 44(11), 1718–1722 (2017)
Jaremko, J.L., et al.: Preliminary validation of the knee inflammation MRI scoring system (KIMRISS) for grading bone marrow lesions in osteoarthritis of the knee: data from the osteoarthritis initiative. RMD Open 3(1), e000355 (2017)
Ju, L., et al.: Improving medical images classification with label noise using dual-uncertainty estimation. IEEE Trans. Med. Imaging 41, 1533–1546 (2022)
Karimi, D., Dou, H., Warfield, S.K., Gholipour, A.: Deep learning with noisy labels: exploring techniques and remedies in medical image analysis. Med. Image Anal. 65, 101759 (2020). https://doi.org/10.1016/j.media.2020.101759
Kats, E., Goldberger, J., Greenspan, H.: Soft labeling by distilling anatomical knowledge for improved MS lesion segmentation. In: 2019 IEEE 16th International Symposium on Biomedical Imaging, ISBI 2019, pp. 1563–1566. IEEE (2019)
Kats, E., Goldberger, J., Greenspan, H.: A soft STAPLE algorithm combined with anatomical knowledge. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11766, pp. 510–517. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32248-9_57
Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7482–7491 (2018)
Kim, T., Ko, J., Choi, J., Yun, S.Y., et al.: Fine samples for learning with noisy labels. In: Advances in Neural Information Processing Systems, vol. 34 (2021)
Li, H., Wei, D., Cao, S., Ma, K., Wang, L., Zheng, Y.: Superpixel-guided label softening for medical image segmentation. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12264, pp. 227–237. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59719-1_23
Liu, S., Zhu, Z., Qu, Q., You, C.: Robust training under label noise by over-parameterization. arXiv preprint arXiv:2202.14026 (2022)
Lukasik, M., Bhojanapalli, S., Menon, A., Kumar, S.: Does label smoothing mitigate label noise? In: International Conference on Machine Learning, pp. 6448–6458. PMLR (2020)
Ma, X., Huang, H., Wang, Y., Romano, S., Erfani, S., Bailey, J.: Normalized loss functions for deep learning with noisy labels. In: International Conference on Machine Learning, pp. 6543–6553. PMLR (2020)
Müller, R., Kornblith, S., Hinton, G.E.: When does label smoothing help? In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Patrini, G., Rozza, A., Krishna Menon, A., Nock, R., Qu, L.: Making deep neural networks robust to label noise: a loss correction approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1944–1952 (2017)
Pedoia, V., Norman, B., Mehany, S.N., Bucknor, M.D., Link, T.M., Majumdar, S.: 3D convolutional neural networks for detection and severity staging of meniscus and PFJ cartilage morphological degenerative changes in osteoarthritis and anterior cruciate ligament subjects. J. Magn. Reson. Imaging 49(2), 400–410 (2019)
Silva, J.L., Oliveira, A.L.: Using soft labels to model uncertainty in medical image segmentation. arXiv preprint arXiv:2109.12622 (2021)
Song, H., Kim, M., Park, D., Shin, Y., Lee, J.G.: Learning from noisy labels with deep neural networks: A survey. IEEE Trans. Neural Netw. Learn. Syst. (2022)
To, M.N.N., et al.: Coarse label refinement for improving prostate cancer detection in ultrasound imaging. Int. J. Comput. Assist. Radiol. Surg. 17, 841–847 (2022)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)
Vega, R., et al.: Sample efficient learning of image-based diagnostic classifiers using probabilistic labels. arXiv preprint arXiv:2102.06164 (2021)
Wang, D.B., Wen, Y., Pan, L., Zhang, M.L.: Learning from noisy labels with complementary loss functions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 10111–10119 (2021)
Wang, Y., Ma, X., Chen, Z., Luo, Y., Yi, J., Bailey, J.: Symmetric cross entropy for robust learning with noisy labels. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 322–330 (2019)
Xue, Y., Hauskrecht, M.: Efficient learning of classification models from soft-label information by binning and ranking. In: The 30th International Flairs Conference (2017)
Yi, R., Huang, Y., Guan, Q., Pu, M., Zhang, R.: Learning from pixel-level label noise: a new perspective for semi-supervised semantic segmentation. IEEE Trans. Image Process. 31, 623–635 (2021)
Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning (still) requires rethinking generalization. Commun. ACM 64(3), 107–115 (2021)
Acknowledgment
Academic time for JJ, is made available by Medical Imaging Consultants (MIC), Edmonton, Canada. We thank the members of the OMERACT MRI in Arthritis Working Group for their participation and support in this project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Springer Nature Switzerland AG
About this paper
Cite this paper
Felfeliyan, B. et al. (2023). Weakly Supervised Medical Image Segmentation with Soft Labels and Noise Robust Loss. In: Rousseau, JJ., Kapralos, B. (eds) Pattern Recognition, Computer Vision, and Image Processing. ICPR 2022 International Workshops and Challenges. ICPR 2022. Lecture Notes in Computer Science, vol 13644. Springer, Cham. https://doi.org/10.1007/978-3-031-37742-6_47
Download citation
DOI: https://doi.org/10.1007/978-3-031-37742-6_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-37741-9
Online ISBN: 978-3-031-37742-6
eBook Packages: Computer ScienceComputer Science (R0)
