Abstract
Traditional radiomics and deep learning have been widely employed for magnetic resonance imaging (MRI)-based glioma grading. Despite the reported promising grading performances, existing methods still have two limitations. One is that the strengths of radiomics and deep learning have not been integrated sufficiently. The other is that they cannot generalize well to different MR sequences. In this paper, we propose a human knowledge-guided and task-augmented deep learning network (HTNet) to address these issues. Particularly, radiomics handcrafted signatures are constructed to describe brain lesions and then used to guide the training of deep learning models. Furthermore, an auxiliary MRI sequence classifier is added to the original classification task to learn versatile sequence properties and thus helps the model generalize to different MR sequences without extra training cost. Extensive experiments are conducted utilizing the public dataset BraTS2020, whose results show that the proposed method has competitive capabilities in glioma grading for different MR sequences.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Cho, H.H., Lee, S.H., Kim, J., Park, H.: Classification of the glioma grading using radiomics analysis. PeerJ 6, e5982 (2018)
Gillies, R.J., Kinahan, P.E., Hricak, H.: Radiomics: images are more than pictures, they are data. Radiology 278(2), 563–577 (2016)
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)
Lambin, P., et al.: Radiomics: the bridge between medical imaging and personalized medicine. Nat. Rev. Clin. Oncol. 14(12), 749–762 (2017)
Matsui, Y., et al.: Prediction of lower-grade glioma molecular subtypes using deep learning. J. Neuro-oncol. 146(2), 321–327 (2020)
Menze, B.H., et al.: The multimodal brain tumor image segmentation benchmark (brats). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2014)
Obara, T., et al.: Adult diffuse low-grade gliomas: 35-year experience at the Nancy France neurooncology unit. Front. Oncol. 1873 (2020)
Ostrom, Q.T., Patil, N., Cioffi, G., Waite, K., Kruchko, C., Barnholtz-Sloan, J.S.: Cbtrus statistical report: primary brain and other central nervous system tumors diagnosed in the united states in 2013–2017. Neuro-oncology 22(Supplement_1), iv1–iv96 (2020)
Sultan, H.H., Salem, N.M., Al-Atabany, W.: Multi-classification of brain tumor images using deep neural network. IEEE Access 7, 69215–69225 (2019)
Vamvakas, A., et al.: Imaging biomarker analysis of advanced multiparametric MRI for glioma grading. Phys. Med. 60, 188–198 (2019)
Wu, W., et al.: Joint NCCTG and NABTC prognostic factors analysis for high-grade recurrent glioma. Neuro-oncology 12(2), 164–172 (2010)
Yang, Y., et al.: Glioma grading on conventional MR images: a deep learning study with transfer learning. Front. Neurosci. 804 (2018)
Zhao, G., et al.: Ai-powered radiomics algorithm based on slice pooling for the glioma grading. IEEE Trans. Indust. Inf. (2021)
Zhuge, Y., et al.: Automated glioma grading on conventional MRI images using deep convolutional neural networks. Med. Phys. 47(7), 3044–3053 (2020)
Acknowledgements
This research was partly supported by Scientific and Technical Innovation 2030 - “New Generation Artificial Intelligence” Project (2020AA A0104100, 2020AAA0104105), the National Natural Science Foundation of China (61871371, 81772009), Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application (2022B1212010011), the Basic Research Program of Shenzhen (JCYJ20180507182400762), Shenzhen Science and Technology Program (RCYX20210706092104034), Youth Innovation Promotion Association Program of Chinese Academy of Sciences (2019351), Collaborative Innovation Major Project of Zhengzhou (20XTZX06013, 20XTZX05015), and the Key Technologies R &D Program of Henan Province (222102210281).
Author information
Authors and Affiliations
Corresponding author
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
Wang, Y., Li, C., Lin, Y. (2022). Human Knowledge-Guided and Task-Augmented Deep Learning for Glioma Grading. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13535. Springer, Cham. https://doi.org/10.1007/978-3-031-18910-4_45
Download citation
DOI: https://doi.org/10.1007/978-3-031-18910-4_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18909-8
Online ISBN: 978-3-031-18910-4
eBook Packages: Computer ScienceComputer Science (R0)