Identification of Cerebral Small Vessel Disease Using Multiple Instance Learning
Cerebral small vessel disease (SVD) is a common cause of ageing-associated physical and cognitive impairment. Identifying SVD is important for both clinical and research purposes but is usually dependent on radiologists’ evaluation of brain scans. Computer tomography (CT) is the most widely used brain imaging technique but for SVD it shows a low signal-to-noise ratio, and consequently poor inter-rater reliability. We therefore propose a novel framework based on multiple instance learning (MIL) to distinguish between absent/mild SVD and moderate/severe SVD. Intensity patches are extracted from regions with high probability of containing lesions. These are then used as instances in MIL for the identification of SVD. A large baseline CT dataset, consisting of 590 CT scans, was used for evaluation. We achieved approximately 75% accuracy in classifying two different types of SVD, which is high for this challenging problem. Our results outperform those obtained by either standard machine learning methods or current clinical practice.
KeywordsRandom Forest Recombinant Tissue Plasminogen Activator Computer Tomography Image Computer Tomography Scan Multiple Instance Learning
Unable to display preview. Download preview PDF.
- 1.Akbas, E., Ghanem, B., Ahuja, N.: MIS-Boost: Multiple instance selection boosting. arXiv preprint:1109.2388 (2011)Google Scholar
- 3.Chawla, M., Sharma, S., Sivaswamy, J., Kishore, L.: A method for automatic detection and classification of stroke from brain CT images. In: Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3581–3584. IEEE (2009)Google Scholar
- 4.Conijn, M.M.A., Kloppenborg, R.P., Algra, A., Mali, W.P.T.M., Kappelle, L.J., Vincken, K.L., Van Der Graaf, Y., Geerlings, M.I.: Cerebral small vessel disease and risk of death, ischemic stroke, and cardiac complications in patients with atherosclerotic disease: The second manifestations of arterial disease-magnetic resonance (SMART-MR) study. Stroke 42, 3105–3109 (2011)CrossRefGoogle Scholar
- 5.Dalca, A.V., et al.: Segmentation of cerebrovascular pathologies in stroke patients with spatial and shape priors. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part II. LNCS, vol. 8674, pp. 773–780. Springer, Heidelberg (2014)Google Scholar
- 8.Fazekas, F., Chawluk, J.B., Alavi, A., Hurtig, H.I., Zimmerman, R.A.: MR signal abnormalities at 1.5 T in Alzheimer’s dementia and normal aging. American Journal of Neuroradiology 8(3), 421–426 (1987)Google Scholar
- 13.Ramírez, J., Górriz, J., Segovia, F., Chaves, R., Salas-Gonzalez, D., López, M., Álvarez, I., Padilla, P.: Computer aided diagnosis system for the Alzheimer’s disease based on partial least squares and random forest SPECT image classification. Neuroscience Letters 472(2), 99–103 (2010)CrossRefGoogle Scholar
- 19.Wintermark, M., Albers, G.W., Alexandrov, A.V., Alger, J.R., Bammer, R., Baron, J.C., Davis, S., Demaerschalk, B.M., Derdeyn, C.P., Donnan, G.A., et al.: Acute stroke imaging research roadmap. American Journal of Neuroradiology 29(5), e23–e30 (2008)Google Scholar
- 20.Zhang, Q., Goldman, S.: EM-DD: An improved multiple-instance learning technique. In: Advances in Neural Information Processing Systems, pp. 1073–1080 (2001)Google Scholar
- 21.Zhou, Z.H.: Multi-instance learning: a survey. Tech. rep., National Laboratory for Novel Software Technology, Nanjing (2004)Google Scholar