Quantitative impact of label noise on the quality of segmentation of brain tumors on MRI scans

• Autorzy: Marcinkiewicz Michał , Mrukwa Grzegorz

Identyfikatory

DOI

10.15439/2019F273

• Konferencja: Federated Conference on Computer Science and Information Systems (14 ; 01-04.09.2019 ; Leipzig, Germany)
• Języki publikacji: EN

Abstrakty

EN

Over the last few years, deep learning has proven to be a great solution to many problems, such as image or text classification. Recently, deep learning-based solutions have outperformed humans on selected benchmark datasets, yielding a promising future for scientific and real-world applications. Training of deep learning models requires vast amounts of high quality data to achieve such supreme performance. In real-world scenarios, obtaining a large, coherent, and properly labeled dataset is a challenging task. This is especially true in medical applications, where high-quality data and annotations are scarce and the number of expert annotators is limited. In this paper, we investigate the impact of corrupted ground-truth masks on the performance of a neural network for a brain tumor segmentation task. Our findings suggest that a) the performance degrades about 8% less than it could be expected from simulations, b) a neural network learns the simulated biases of annotators, c) biases can be partially mitigated by using an inversely-biased dice loss function.

Słowa kluczowe

EN

biomedical MRI; brain; image segmentation; artificial intelligence; medical image processing; neural nets; tumour

PL

rezonans magnetyczny; mózg; segmentacja obrazu; sztuczna inteligencja; przetwarzanie obrazów medycznych; sieci neuronowe; guz

• Wydawca: Polskie Towarzystwo Informatyczne
• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2019
• Tom: Vol. 18
• Strony: 61--65
• Opis fizyczny: Bibliogr. 17 poz., wz., tab., wykr., rys.

Twórcy

autor

Marcinkiewicz Michał

• Netguru, ul. Wojskowa 6, 60-792 Poznań, Poland

autor

Mrukwa Grzegorz

• Netguru, ul. Wojskowa 6, 60-792 Poznań, Poland
• Silesian University of Technology, Data Mining Group, ul. Akademicka 16, 44-100 Gliwice

Bibliografia

• 1. J. Deng, W. Dong, R. Socher, L. Li, K. Li, and L. Fei-Fei. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255, June 2009.
• 2. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. S. Bernstein, A. C. Berg, and L. Fei-Fei. Imagenet large scale visual recognition challenge. Int J Comput Vis, 115: 211, 2015.
• 3. L. Joseph, T. W. Gyorkos, and L. Coupal. Bayesian estimation of disease prevalence and the parameters of diagnostic tests in the absence of a gold standard. Am. J. Epidemiol., 141(3):263–272, Feb 1995.
• 4. I. Bross. Misclassification in 2 x 2 tables. Biometrics, 10(4):478–486, 1954.
• 5. A. A. Bankier, D. Levine, E. F. Halpern, and H. Y. Kressel. Consensus interpretation in imaging research: is there a better way? Radiology, 257(1):14–17, Oct 2010.
• 6. W. R. Mower. Evaluating bias and variability in diagnostic test reports. Ann Emerg Med, 33(1):85–91, Jan 1999.
• 7. J. G. Jarvik and R. A. Deyo. Moderate versus mediocre: the reliability of spine MR data interpretations. Radiology, 250(1):15–17, Jan 2009.
• 8. J. A. Carrino, J. D. Lurie, A. N. Tosteson, T. D. Tosteson, E. J. Carragee, J. Kaiser, M. R. Grove, E. Blood, L. H. Pearson, J. N. Weinstein, and R. Herzog. Lumbar spine: reliability of MR imaging findings. Radiology, 250(1):161–170, Jan 2009.
• 9. S. K. Warfield, K. H. Zou, and W. M. Wells. Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans Med Imaging, 23(7):903–921, Jul 2004.
• 10. X. Zhu and X. Wu. Class noise vs. attribute noise: A quantitative study. Artificial Intelligence Review, 22(3):177–210, Nov 2004.
• 11. B. H. Menze et al. The multimodal brain tumor image segmentation benchmark (BraTS). IEEE TMI, 34(10):1993–2024, Oct 2015.
• 12. S. Bakas et al. Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Scientific data, 4:1–13, 9 2017.
• 13. S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J. S. Kirby, J. B. Freymann, K. F., and C. Davatzikos. Segmenta- tion labels and radiomic features for the pre-operative scans of the TCGA-GBM collection, 2017. The Cancer Imaging Archive. https://doi.org/10.7937/K9/TCIA.2017.KLXWJJ1Q.
• 14. S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J. S. Kirby, J. B. Freymann, K. F., and C. Davatzikos. Segmenta- tion labels and radiomic features for the pre-operative scans of the TCGA-LGG collection, 2017. The Cancer Imaging Archive. https://doi.org/10.7937/K9/TCIA.2017.GJQ7R0EF.
• 15. M. Marcinkiewicz, J. Nalepa, P. R. Lorenzo, W. Dudzik, and G. Mrukwa. Automatic brain tumor segmentation using a two-stage multi-modal fcnn. In Alessandro Crimi, Spyridon Bakas, Hugo J. Kuijf, Farahani Keyvan, Mauricio Reyes, and Theo van Walsum, editors, Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, chapter 2, pages 13–24. Springer International Publishing, 2019.
• 16. O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pages 234–241, Cham, 2015. Springer International Publishing.
• 17. K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. CoRR, abs/1512.03385, 2015.

Uwagi

1. Track 1: Artificial Intelligence and Applications

2. Technical Session: 14th International Symposium Advances in Artificial Intelligence and Applications

3. Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).