Abstract
Generating pixel or voxel-wise annotations of radiological images to train deep learning-based segmentation models is a time consuming and expensive job involving precious time and effort of radiologists. Other challenges include obtaining diverse annotated training data that covers the entire spectrum of potential situations. In this paper, we propose an Active Learning (AL) based segmentation strategy involving a human annotator or “Oracle" to annotate interactively. The deep learning-based segmentation model learns in parallel by training in iterations with the annotated samples. A publicly available MRI dataset of brain tumors (Glioma) is used for the experimental studies. The efficiency of the proposed AL-based segmentation model is demonstrated in terms of annotation time requirement compared with the conventional Passive Learning (PL) based strategies. Experimentally it is also demonstrated that the proposed AL-based segmentation strategy achieves comparable or enhanced segmentation performance with much fewer annotations through quantitative and qualitative evaluations of the segmentation results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bakas, S., et al.: Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci. Data 4(1), 1–13 (2017)
Banerjee, S., Dhara, A.K., Wikström, J., Strand, R.: Segmentation of intracranial aneurysm remnant in MRA using dual-attention atrous net. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 9265–9272. IEEE (2021)
Banerjee, S., Mitra, S.: Novel volumetric sub-region segmentation in brain tumors. Front. Comput. Neurosci. 14, 3 (2020)
Banerjee, S., Mitra, S., Shankar, B.U.: Automated 3D segmentation of brain tumor using visual saliency. Inf. Sci. 424, 337–353 (2018)
Banerjee, S., Nysjö, F., Toumpanakis, D., Dhara, A.K., Wikström, J., Strand, R.: AI-based solution for improving neuroradiology workflow for cerebrovascular structure monitoring. Research Square (2023)
Banerjee, S., Strand, R.: Lifelong learning with dynamic convolutions for glioma: segmentation from multi-modal MRI. In: SPIE Medical Imaging 2023 (2023)
Banerjee, S., Toumpanakis, D., Dhara, A.K., Wikström, J., Strand, R.: Topology-aware learning for volumetric cerebrovascular segmentation. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), pp. 1–4. IEEE (2022)
Belharbi, S., Ben Ayed, I., McCaffrey, L., Granger, E.: Deep active learning for joint classification & segmentation with weak annotator. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 3338–3347 (2021)
Budd, S., Robinson, E.C., Kainz, B.: A survey on active learning and human-in-the-loop deep learning for medical image analysis. Med. Image Anal. 71, 102062 (2021)
Fedorov, A., et al.: 3D Slicer as an image computing platform for the quantitative imaging network. Magn. Reson. Imaging 30(9), 1323–1341 (2012)
Kamnitsas, K., et al.: Deepmedic for brain tumor segmentation. In: International Workshop on Brain Lesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (2016)
Kaur, G., Rana, P.S., Arora, V.: State-of-the-art techniques using pre-operative brain MRI scans for survival prediction of glioblastoma multiforme patients and future research directions. Clin. Transl. Imaging, 1–35 (2022)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kumar, S.K.: On weight initialization in deep neural networks. arXiv preprint arXiv:1704.08863 (2017)
Malpani, R., Petty, C.W., Bhatt, N., Staib, L.H., Chapiro, J.: Use of artificial intelligence in nononcologic interventional radiology: current state and future directions. Digest. Disease Interv. 5(04), 331–337 (2021)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Settles, B.: Active learning (2012)
Shukla, G., et al.: Advanced magnetic resonance imaging in glioblastoma: a review. Chin. Clin. Oncol. 6(4), 40 (2017)
Moliterno Günel, J., Piepmeier, J.M., Baehring, J.M. (eds.): Springer, Cham (2017). https://doi.org/10.1007/978-3-319-49864-5
Wu, X., Chen, C., Zhong, M., Wang, J., Shi, J.: Covid-AL: the diagnosis of Covid-19 with deep active learning. Med. Image Anal. 68, 101913 (2021)
Zhou, Z., Shin, J.Y., Gurudu, S.R., Gotway, M.B., Liang, J.: Active, continual fine tuning of convolutional neural networks for reducing annotation efforts. Med. Image Anal. 71, 101997 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Banerjee, S., Strand, R. (2023). Deep Active Learning for Glioblastoma Quantification. In: Gade, R., Felsberg, M., Kämäräinen, JK. (eds) Image Analysis. SCIA 2023. Lecture Notes in Computer Science, vol 13885. Springer, Cham. https://doi.org/10.1007/978-3-031-31435-3_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-31435-3_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31434-6
Online ISBN: 978-3-031-31435-3
eBook Packages: Computer ScienceComputer Science (R0)