Top

Insights into Imaging

Published in:

Open Access 01-12-2023 | Glioma | Original Article

An active learning approach to train a deep learning algorithm for tumor segmentation from brain MR images

Authors: Andrew S. Boehringer, Amirhossein Sanaat, Hossein Arabi, Habib Zaidi

Published in: Insights into Imaging | Issue 1/2023

Abstract

Purpose

This study focuses on assessing the performance of active learning techniques to train a brain MRI glioma segmentation model.

Methods

The publicly available training dataset provided for the 2021 RSNA-ASNR-MICCAI Brain Tumor Segmentation (BraTS) Challenge was used in this study, consisting of 1251 multi-institutional, multi-parametric MR images. Post-contrast T1, T2, and T2 FLAIR images as well as ground truth manual segmentation were used as input for the model. The data were split into a training set of 1151 cases and testing set of 100 cases, with the testing set remaining constant throughout. Deep convolutional neural network segmentation models were trained using the NiftyNet platform. To test the viability of active learning in training a segmentation model, an initial reference model was trained using all 1151 training cases followed by two additional models using only 575 cases and 100 cases. The resulting predicted segmentations of these two additional models on the remaining training cases were then addended to the training dataset for additional training.

Results

It was demonstrated that an active learning approach for manual segmentation can lead to comparable model performance for segmentation of brain gliomas (0.906 reference Dice score vs 0.868 active learning Dice score) while only requiring manual annotation for 28.6% of the data.

Conclusion

The active learning approach when applied to model training can drastically reduce the time and labor spent on preparation of ground truth training data.

Critical relevance statement

Active learning concepts were applied to a deep learning-assisted segmentation of brain gliomas from MR images to assess their viability in reducing the required amount of manually annotated ground truth data in model training.

Key points

• This study focuses on assessing the performance of active learning techniques to train a brain MRI glioma segmentation model.

• The active learning approach for manual segmentation can lead to comparable model performance for segmentation of brain gliomas.

• Active learning when applied to model training can drastically reduce the time and labor spent on preparation of ground truth training data.

Graphical Abstract

Available only for authorised users

Arabi H, AkhavanAllaf A, Sanaat A, Shiri I, Zaidi H (2021) The promise of artificial intelligence and deep learning in PET and SPECT imaging. Phys Med 83:122–137. https://doi.org/10.1016/j.ejmp.2021.03.008CrossRefPubMed

Menze BH et al (2015) The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Trans Med Imaging 34(10):1993–2024. https://doi.org/10.1109/TMI.2014.2377694CrossRefPubMed

Odland A et al (2015) Volumetric glioma quantification: comparison of manual and semi-automatic tumor segmentation for the quantification of tumor growth. Acta Radiol 56(11):1396–1403. https://doi.org/10.1177/0284185114554822CrossRefPubMed

Kaus MR, Warfield SK, Nabavi A, Black PM, Jolesz FA, Kikinis R (2001) Automated segmentation of MR images of brain tumors. Radiology 218(2):586–591. https://doi.org/10.1148/radiology.218.2.r01fe44586CrossRefPubMed

Savjani RR, Lauria M, Bose S, Deng J, Yuan Y, Andrearczyk V (2022) Automated Tumor Segmentation in Radiotherapy. Semin Radiat Oncol 32:319–329. https://doi.org/10.1016/j.semradonc.2022.06.002.

Fu Y, Lei Y, Wang T, Curran WJ, Liu T, Yang X (2021) A review of deep learning based methods for medical image multi-organ segmentation. Phys Med 85:107–122. https://doi.org/10.1016/j.ejmp.2021.05.003.

Seo H et al (2020) Machine learning techniques for biomedical image segmentation: An overview of technical aspects and introduction to state-of-art applications. Med Phys 47(5):e148–e167. https://doi.org/10.1002/mp.13649CrossRefPubMed

Zhang D et al (2020) Exploring task structure for brain tumor segmentation from multimodality MR images. IEEE Trans Image Process 29:9032–9043. https://doi.org/10.1109/TIP.2020.3023609CrossRef

Zhang D, Huang G, Zhang Q, Han J, Han J, Yu Y (2021) Cross-modality deep feature learning for brain tumor segmentation. Pattern Recognit 110:107562. https://doi.org/10.1016/j.patcog.2020.107562.

10.

Sanaat A, Shiri I, Ferdowsi S, Arabi H, Zaidi H (2022) Robust-Deep: A Method for Increasing Brain Imaging Datasets to Improve Deep Learning Models’ Performance and Robustness. J Digit Imaging 35(3):469–481. https://doi.org/10.1007/s10278-021-00536-0CrossRefPubMedPubMedCentral

11.

Tran NT, Tran VH, Nguyen NB, Nguyen TK, Cheung NM (2021) On Data Augmentation for GAN Training. IEEE Trans Image Process 30:1882–1897. https://doi.org/10.1109/tip.2021.3049346CrossRefPubMed

12.

Sayin B, Krivosheev E, Yang J, Passerini A, Casati F (2021) A review and experimental analysis of active learning over crowdsourced data. Artif Intell Rev 54(7):5283–5305. https://doi.org/10.1007/s10462-021-10021-3. (2021/10/01 2021)CrossRef

13.

Cohn DA, Ghahramani Z, Jordan MI (1996) Active Learning with Statistical Models. Journal of Artificial Intelligence Research 4:129–145CrossRef

14.

Angluin D (1988) Queries and Concept Learning. Mach Learn 2:319–342CrossRef

15.

Baum EB (1991) Neural net algorithms that learn in polynomial time from examples and queries. IEEE Trans Neural Netw 2(1):5–19. https://doi.org/10.1109/72.80287CrossRefPubMed

16.

Cacciarelli DK, Tyssedal, Sølve J (2022) Stream-Based Active Learning with Linear Models. Knowledge-Based Systems 254:109664. https://doi.org/10.1016/j.knosys.2022.109664.

17.

Grimova N, Macas M (2019) Query-by-Committee Framework Used for Semi-Automatic Sleep Stages Classification. MDPI Proceedings 31(80). https://doi.org/10.3390/proceedings2019031080.

18.

Ge W et al (2021) Deep active learning for Interictal Ictal Injury Continuum EEG patterns. J Neurosci Methods 351:108966. https://doi.org/10.1016/j.jneumeth.2020.108966CrossRefPubMed

19.

Bodenstedt S et al (2019) Active learning using deep Bayesian networks for surgical workflow analysis. Int J Comput Assist Radiol Surg 14(6):1079–1087. https://doi.org/10.1007/s11548-019-01963-9CrossRefPubMed

20.

De Angeli K et al (2021) Deep active learning for classifying cancer pathology reports. BMC Bioinformatics 22(1):113. https://doi.org/10.1186/s12859-021-04047-1CrossRefPubMedPubMedCentral

21.

Qian P et al (2020) mDixon-Based Synthetic CT Generation for PET Attenuation Correction on Abdomen and Pelvis Jointly Using Transfer Fuzzy Clustering and Active Learning-Based Classification. IEEE Trans Med Imaging 39(4):819–832. https://doi.org/10.1109/TMI.2019.2935916CrossRefPubMed

22.

Sourati J, Gholipour A, Dy JG, Kurugol S, Warfield SK (2018) Active Deep Learning with Fisher Information for Patch-wise Semantic Segmentation. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support 2018(11045):83–91. https://doi.org/10.1007/978-3-030-00889-5_10CrossRef

23.

Sharma D, Shanis Z, Reddy CK, Gerber S, Enquobahrie A (2019) Active learning technique for multimodal brain tumor segmentation using limited labeled images. In: Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data. Lecture Notes in Computer Science, vol 11795. Springer International Publishing, Cham, p 148–156. https://doi.org/10.1007/978-3-030-33391-1_17

24.

Hao R, Namdar K, Liu L, Khalvati F (2021) A Transfer Learning–Based Active Learning Framework for Brain Tumor Classification. Front Artif Intell 4:635766. https://doi.org/10.3389/frai.2021.635766.

25.

Baid U et al (2021) The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv e-prints, p. arXiv:2107.02314. https://doi.org/10.48550/arXiv.2107.02314

26.

Bakas S, Akbari H, Sotiras A et al (2017) Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci Data 4:170117. https://doi.org/10.1038/sdata.2017.117.

27.

Tustison NJ et al (2010) N4ITK: improved N3 bias correction. IEEE Trans Med Imaging 29(6):1310–1320. https://doi.org/10.1109/TMI.2010.2046908CrossRefPubMedPubMedCentral

28.

He K, Zhang X, Ren S, Sun J (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770–778. https://doi.org/10.1109/CVPR.2016.90.

29.

Li W, Wang G, Fidon L, Ourselin S, Cardoso MJ, Vercauteren T (2017) On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Task. International Conference on Information Processing in Medical Imaging 2017:348–360. https://doi.org/10.1007/978-3-319-59050-9_28.

30.

Gibson E et al (2018) NiftyNet: a deep-learning platform for medical imaging. Comput Methods Programs Biomed 158:113–122. https://doi.org/10.1016/j.cmpb.2018.01.025CrossRefPubMedPubMedCentral

31.

Zijdenbos AP, Dawant BM, Margolin RA, Palmer AC (1994) Morphometric analysis of white matter lesions in MR images: method and validation. IEEE Trans Med Imaging 13(4):716–724. https://doi.org/10.1109/42.363096CrossRefPubMed

32.

Madhawa K, Murata T (2020) Active Learning for Node Classification: An Evaluation. Entropy (Basel) 22. https://doi.org/10.3390/e22101164.

Title: An active learning approach to train a deep learning algorithm for tumor segmentation from brain MR images
Authors: Andrew S. Boehringer
Amirhossein Sanaat
Hossein Arabi
Habib Zaidi
Publication date: 01-12-2023
Publisher: Springer Vienna
Keywords: Glioma
Glioma
Glioma
Magnetic Resonance Imaging
Magnetic Resonance Imaging
Published in: Insights into Imaging / Issue 1/2023
Electronic ISSN: 1869-4101
DOI: https://doi.org/10.1186/s13244-023-01487-6

2024 ASCO Annual Meeting

Springer Medicine

An active learning approach to train a deep learning algorithm for tumor segmentation from brain MR images

Abstract

Purpose

Methods

Results

Conclusion

Critical relevance statement

Key points

Graphical Abstract

2024 ASCO Annual Meeting

Springer Medicine

Abstract

Purpose

Methods

Results

Conclusion

Critical relevance statement

Key points

Graphical Abstract

Please log in to get access to this content

Other articles of this Issue 1/2023

Stepwise diagnostic algorithm for high-attenuation pulmonary abnormalities on CT

CT appearances and classification of hepatic epithelioid hemangioendothelioma

QuADRANT: a study on uptake and implementation of clinical audit of medical radiological procedures in Europe—expert recommendations for improvement, endorsed by the ESR

High-resolution ultrasound and magnetic resonance imaging of ulnar nerve neuropathy in the distal Guyon tunnel

Imaging of hepatocellular carcinoma recurrence after liver transplantation

Preoperative prediction of cholangiocyte phenotype hepatocellular carcinoma on contrast-enhanced MRI and the prognostic implication after hepatectomy