Abstract
Accurate nodule labeling and interpretable machine learning are important for lung cancer diagnosis. To circumvent the label ambiguity issue of commonly-used unsure nodule data such as LIDC-IDRI, we constructed a sure nodule data with gold-standard clinical diagnosis. To make the traditional CNN networks interpretable, we propose herewith a novel collaborative model to improve the trustworthiness of lung cancer predictions by self-regulation, which endows the model with the ability to provide explanations in meaningful terms to a human-observer. The proposed collaborative model transfers domain knowledge from unsure data to sure data and encodes a cause-and-effect logic based on nodule segmentation and attributes. Further, we construct a regularization strategy that treats the visual saliency maps (Grad-CAM) not only as post-hoc model interpretation, but also as a rational measure for trustworthy learning in such a way that the CNN features are extracted mainly from intrinsic nodule features. Moreover, similar nodule retrieval makes a nodule diagnosis system more understandable and credible to humans-observers based on the nodule attributes. We demonstrate that the combination of the collaborative model and regularization strategy can provide the best performances on lung cancer prediction and interpretable diagnosis that can automatically: 1) classify the nodule patches; 2) analyse and explain a prediction by nodule segmentation and attributes; and 3) retrieve similar nodules for comparison and diagnosis.
H. Zhang and L. Chen—Joint first authors of this work.
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
Similar content being viewed by others
References
Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., Kim, B.: Sanity checks for saliency maps. Adv. Neural Inf. Process. Syst. 31, 1–11 (2018)
Armato, S.G., III., et al.: The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Med. Phys. 38(2), 915–931 (2011)
Armato, S.G., III., et al.: Lung image database consortium: developing a resource for the medical imaging research community. Radiology 232(3), 739–748 (2004)
Arun, N., et al.: Assessing the trustworthiness of saliency maps for localizing abnormalities in medical imaging. Radiol. Artif. Intell. 3(6), e200267 (2021)
Geirhos, R., et al.: Shortcut learning in deep neural networks. Nat. Mach. Intell. 2(11), 665–673 (2020)
Gunning, D., Stefik, M., Choi, J., Miller, T., Stumpf, S., Yang, G.Z.: XAI-explainable artificial intelligence. Sci. Robot. 4(37), 1–6 (2019)
Hansell, D.M., Bankier, A.A., MacMahon, H., McLoud, T.C., Muller, N.L., Remy, J.: Fleischner society: glossary of terms for thoracic imaging. Radiology 246(3), 697–722 (2008)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hussein, S., Cao, K., Song, Q., Bagci, U.: Risk stratification of lung nodules using 3D CNN-based multi-task learning. In: Niethammer, M., et al. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 249–260. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59050-9_20
Jacobs, C., van Ginneken, B.: Google’s lung cancer AI: a promising tool that needs further validation. Nat. Rev. Clin. Oncol. 16(9), 532–533 (2019)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kirby, J.S., et al.: LungX challenge for computerized lung nodule classification. J. Med. Imaging 3(4), 044506 (2016)
Kubota, T., Jerebko, A.K., Dewan, M., Salganicoff, M., Krishnan, A.: Segmentation of pulmonary nodules of various densities with morphological approaches and convexity models. Med. Image Anal. 15(1), 133–154 (2011)
Liu, L., Dou, Q., Chen, H., Qin, J., Heng, P.A.: Multi-task deep model with margin ranking loss for lung nodule analysis. IEEE Trans. Med. Imaging 39(3), 718–728 (2019)
McNitt-Gray, M.F., et al.: The lung image database consortium (LIDC) data collection process for nodule detection and annotation. Acad. Radiol. 14(12), 1464–1474 (2007)
Samek, W., Montavon, G., Vedaldi, A., Hansen, L.K., Müller, K.-R.: Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. LNCS (LNAI), vol. 11700. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-28954-6
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Setio, A.A.A., et al.: Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the luna16 challenge. Med. Image Anal. 42, 1–13 (2017)
Shad, R., Cunningham, J.P., Ashley, E.A., Langlotz, C.P., Hiesinger, W.: Designing clinically translatable artificial intelligence systems for high-dimensional medical imaging. Nat. Mach. Intell. 3(11), 929–935 (2021)
Shen, W., et al.: Multi-crop convolutional neural networks for lung nodule malignancy suspiciousness classification. Pattern Recogn. 61, 663–673 (2017)
Team, N.L.S.T.R.: The national lung screening trial: overview and study design. Radiology. 258(1), 243–253 (2011)
Team, N.L.S.T.R.: Reduced lung-cancer mortality with low-dose computed tomographic screening. New England J. Med. 365(5), 395–409 (2011)
Wang, Q., et al.: WGAN-based synthetic minority over-sampling technique: improving semantic fine-grained classification for lung nodules in CT images. IEEE Access 7, 18450–18463 (2019)
Wu, B., Zhou, Z., Wang, J., Wang, Y.: Joint learning for pulmonary nodule segmentation, attributes and malignancy prediction. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pp. 1109–1113. IEEE (2018)
Wu, Y., He, K.: Group normalization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01261-8_1
Xie, Y., Xia, Y., Zhang, J., Feng, D.D., Fulham, M., Cai, W.: Transferable multi-model ensemble for benign-malignant lung nodule classification on chest CT. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 656–664. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66179-7_75
Xie, Y., et al.: Knowledge-based collaborative deep learning for benign-malignant lung nodule classification on chest CT. IEEE Trans. Med. Imaging 38(4), 991–1004 (2018)
Zhang, H., et al.: Faithful learning with sure data for lung nodule diagnosis. arXiv preprint arXiv:2202.12515 (2022)
Zhang, H., et al.: Re-thinking and re-labeling LIDC-IDRI for robust pulmonary cancer prediction. arXiv preprint arXiv:2207.14238 (2022)
Zhang, H., Gu, Y., Qin, Y., Yao, F., Yang, G.Z.: Learning with sure data for nodule-level lung cancer prediction. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12266, pp. 570–578. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59725-2_55
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)
Acknowledgment
This work was partly supported by Medicine-Engineering Interdisciplinary Research Foundation of Shanghai Jiao Tong University (YG2021QN128), Shanghai Sailing Program (20YF1420800), National Nature Science Foundation of China (No.62003208), Shanghai Municipal of Science and Technology Project (Grant No. 20JC1419500), and Science and Technology Commission of Shanghai Municipality (Grant 20DZ2220400).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, H. et al. (2022). Interpretable Lung Cancer Diagnosis with Nodule Attribute Guidance and Online Model Debugging. In: Reyes, M., Henriques Abreu, P., Cardoso, J. (eds) Interpretability of Machine Intelligence in Medical Image Computing. iMIMIC 2022. Lecture Notes in Computer Science, vol 13611. Springer, Cham. https://doi.org/10.1007/978-3-031-17976-1_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-17976-1_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17975-4
Online ISBN: 978-3-031-17976-1
eBook Packages: Computer ScienceComputer Science (R0)
