Abstract
Hereditary mental illness (e.g., obsessive-compulsive disorder (OCD)) shall reduce the quality of daily life of patients. To detect OCD objectively, sparse learning is an effective method for constructing a brain functional connectivity network (BFCN) since it can remove redundant information in the data and retain valuable biological characteristics. However, the spatial relationship between adjacent or bilaterally symmetric brain regions in each subject is ignored by most existing methods. To address this limitation, a spatial similarity aware learning is proposed in this work to construct BFCNs. Specifically, a smoothing regularization term is devised to constrain the model via embracing the spatial relationship between brain regions. To further learn the informative feature and reduce feature dimension of a BFCN, we leverage a new fused deep polynomial network (FDPN) framework via stacking a multi-layer deep polynomial network (DPN) model, where a weighting scheme is used to fuse features from different output layers. FDPN can learn the high-level discriminative features of BFCN to reduce the feature dimensionality. By fusing the traditional machine learning and deep learning strategies, our proposed method can achieve promising performance to distinguish OCD and unaffected first-degree relatives (UFDRs) using the imaging data collected in the local hospital. The experimental results demonstrate that our method outperforms the state-of-the-art competing methods.
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
Voon, V., Derbyshire, K., Rück, C., et al.: Disorders of compulsivity: a common bias towards learning habits. Mol. Psychiatry 20, 1–8 (2015)
Gillan, C.M., Papmeyer, M., Morein-Zamir, S., et al.: Disruption in the balance between goal-directed behavior and habit learning in obsessive-compulsive disorder. Am. J. Psychiatry 168, 718–726 (2011)
Wu, M.S., Hamblin, R., Nadeau, J., et al.: Quality of life and burden in caregivers of youth with obsessive-compulsive disorder presenting for intensive treatment. Compr. Psychiatry 80, 46–56 (2018)
Pérez-Vigil, A., Fernández de la Cruz, L., Brander, G., et al.: Association of obsessive-compulsive disorder with objective indicators of educational attainment: a nationwide register-based sibling control study. JAMA Psychiatry 75, 47–55 (2018)
Arnold, P.D., Askland, K.D., Barlassina, C., et al.: Revealing the complex genetic architecture of obsessive–compulsive disorder using meta-analysis. Mol. Psychiatry 23, 1181–1188 (2017)
Bruin, W., Denys, D., van Wingen, G.: Diagnostic neuroimaging markers of obsessive-compulsive disorder: Initial evidence from structural and functional MRI studies. Prog. Neuropsychopharmacol. Biol. Psychiatry 91, 49–59 (2019)
Sen, B., Bernstein, G.A., Xu, T., et al.: Classification of obsessive-compulsive disorder from resting-state fMRI. In: EMBC, pp. 3606–3609. IEEE (2016)
Xing, X., Jin, L., Shi, F., et al.: Diagnosis of OCD using functional connectome and Riemann kernel PCA. In: SPIE Medical Imaging (2019). https://doi.org/10.1117/12.2512316
Wee, C.-Y., Yap, P.-T., Zhang, D., Wang, L., Shen, D.: Group-constrained sparse fMRI connectivity modeling for mild cognitive impairment identification. Brain Struct. Funct. 219(2), 641–656 (2013). https://doi.org/10.1007/s00429-013-0524-8
Du, Y., Fryer, S.L., Fu, Z., et al.: Dynamic functional connectivity impairments in early schizophrenia and clinical high-risk for psychosis. Neuroimage 180, 632–645 (2018)
Wee, C.-Y., Yang, S., Yap, P.-T., Shen, D.: Sparse temporally dynamic resting-state functional connectivity networks for early MCI identification. Brain Imaging Behav. 10(2), 342–356 (2015). https://doi.org/10.1007/s11682-015-9408-2
Kucyi, A., Davis, K.D.: Dynamic functional connectivity of the default mode network tracks daydreaming. Neuroimage 100, 471–480 (2014)
Yu, R., Han, Z., Le, A., et al.: Connectivity strength-weighted sparse group representation-based brain network construction for MCI classification. Hum. Brain Mapp. 38, 1–14 (2017)
Livni, R., Shalev-Shwartz, S., Shamir, O.: An algorithm for training polynomial networks. arXiv preprint arXiv:1304.7045 (2013)
Shi, J., Qian, Y., Wu, J., et al.: Ultrasound image based tumor classification via deep polynomial network and multiple kernel learning. Curr. Med. Imaging 14, 301–308 (2018)
Cheng, J.-Z., Ni, D., Chou, Y.-H., et al.: Computer-aided diagnosis with deep learning architecture: applications to breast lesions in US images and pulmonary nodules in CT scans. Sci. Rep. 6, 24454 (2016)
Qiao, L., Zhang, H., Kim, M., et al.: Estimating functional brain networks by incorporating a modularity prior. NeuroImage 141, 399–407 (2016)
Davey, C.E., Grayden, D.B., Egan, G.F., et al.: Filtering induces correlation in fMRI resting state data. Neuroimage 64, 728–740 (2013)
Acknowledgement
This work was supported partly by National Natural Science Foundation of China (Nos. 61871274, U1909209, 61801305, 81571758 and 31871113), Key Laboratory of Medical Image Processing of Guangdong Province (No. K217300003). Guangdong Pearl River Talents Plan (2016ZT06S220), Guangdong Basic and Applied Basic Research Foundation (No. 2019A1515111205), Shenzhen Peacock Plan (Nos. KQTD2016053112051497 and KQTD2015033016104926), and Shenzhen Key Basic Research Project (Nos. GJHZ20190822095414576, JCYJ20180507184647636, JCYJ20190808155618806, JCYJ20170818094109846, JCYJ20190808155618806, and JCYJ20190808145011259).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, P. et al. (2020). Spatial Similarity-Aware Learning and Fused Deep Polynomial Network for Detection of Obsessive-Compulsive Disorder. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12267. Springer, Cham. https://doi.org/10.1007/978-3-030-59728-3_59
Download citation
DOI: https://doi.org/10.1007/978-3-030-59728-3_59
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59727-6
Online ISBN: 978-3-030-59728-3
eBook Packages: Computer ScienceComputer Science (R0)
