Abstract
Brain structure segmentation in Magnetic Resonance Images (MRI) is essential to the assessment and treatment of medical disorders, especially neuropsychiatric diseases. The key to semantic segmentation is to understand the low-level visual semantics and the high-level spatial semantics of the image. Due to the complex anatomical structures, the current approaches lack the ability to effectively extract rich semantic information, resulting in the inevitable loss of details in prediction results. To address this problem, we propose a novel spatial and visual feature enhancement network (SVF-Net) to accurately segment the brain structures. The SVF-Net is designed as a multi-task learning framework, in which an auxiliary coarse segmentation task is used for spatial information acquisition, an auxiliary image reconstruction task is used for visual information preservation, and a major refined segmentation task is used for brain structure segmentation. In this algorithm, multitasking optimization is mainly based on two strategies: firstly, a spatial feature enhancement (SFE) module is introduced to extract the location and spatial relationships of objects from the coarse prediction, which are then sent to the refined segmentation model for spatial information enhancement. Secondly, a visual feature preservation (VFP) model is introduced for image reconstruction, which shares the feature extractor with the refined segmentation model, so as to retain more useful low-level visual features for the model. Extensive experiments are performed on three public brain MRI T1 scan datasets (the IBSR dataset, the MALC dataset and the LPBA dataset) to evaluate the effectiveness of the proposed algorithm. The experimental results show that the SVF-Net achieves the best performance compared with the state-of-the-art methods. In addition, the ablation experiments and the noise interference experiments demonstrate that proposed SFE and VFP module have obvious advantages in improving segmentation accuracy and resisting noise interference.
Similar content being viewed by others
References
Bernal J, Kushibar K, Cabezas M, Valverde S, Oliver A, Lladó X (2019) Quantitative analysis of patch-based fully convolutional neural networks for tissue segmentation on brain magnetic resonance imaging. IEEE Access 7:89986–90002. https://doi.org/10.1109/ACCESS.2019.2926697
Petrella JR, Edward Coleman R, Murali Doraiswamy P (2003) Neuroimaging and early diagnosis of alzheimer disease: a look to the future. Radiology 226(2):315–336. https://doi.org/10.1148/radiol.2262011600
Patenaude B, Smith SM, Kennedy DN, Jenkinson M (2011) A bayesian model of shape and appearance for subcortical brain segmentation. Neuroimage 56(3):907–922. https://doi.org/10.1016/j.neuroimage.2011.02.046
Wu G, Kim M, Sanroma G, Wang Q, Munsell BC, Shen D, Alzheimer’s Disease Neuroimaging Initiative et al (2015) Hierarchical multi-atlas label fusion with multi-scale feature representation and label-specific patch partition. NeuroImage 106:34–46. https://doi.org/10.1016/j.neuroimage.2014.11.025
van Opbroek A, van der Lijn F, de Bruijne M (2013) Automated brain-tissue segmentation by multi-feature svm classification. The MIDAS Journal. http://hdl.handle.net/10380/3443
Moeskops P, Benders Manon JNL, Chiţǎ SM, Kersbergen KJ, Groenendaal F, de Vries LS, Viergever MA, Išgum I (2015) Automatic segmentation of mr brain images of preterm infants using supervised classification. NeuroImage 118:628–641. https://doi.org/10.1016/j.neuroimage.2015.06.007
Prakash RM, Selva Kumari RS (2018) Modified expectation maximization method for automatic segmentation of mr brain images. http://hdl.handle.net/10380/3445
Bengio Y (2009) Learning deep architectures for AI Now Publishers Inc. https://doi.org/10.1561/2200000006
Rajchl M, Baxter JS, Jonathan McLeod A, Yuan J, Qiu W u, Peters TM, White JA, Khan AR (2013) Asets: Map-based brain tissue segmentation using manifold learning and hierarchical max-flow regularization. In: Proceedings of the MICCAI Grand Challenge on MR Brain Image Segmentation (MRBrainS’13). https://doi.org/10.1016/j.patrec.2017.11.016, p 375
Pereira S, Pinto A, Oliveira J, M Mendrik A, Correia JH, Silva CA (2016) Automatic brain tissue segmentation in mr images using random forests and conditional random fields. Journal of Neuroscience Methods 270:111–123. https://doi.org/10.1016/j.jneumeth.2016.06.017
Li W, Gao Y, Shi F, Li G, Gilmore JH, Lin W, Shen D (2015) Links: Learning-based multi-source integration framework for segmentation of infant brain images. NeuroImage 108:160–172. https://doi.org/10.1016/j.neuroimage.2014.12.042
Antipov G, Berrani S-A, Ruchaud N, Dugelay J-L (2015) Learned vs. hand-crafted features for pedestrian gender recognition. In: Proceedings of the 23rd ACM international conference on multimedia, pp 1263–1266
Li X, Wei Y, Wang L, Fu S, Wang C (2021) Msgse-net: Multi-scale guided squeeze-and-excitation network for subcortical brain structure segmentation. Neurocomputing 461:228–243. https://doi.org/10.1016/j.neucom.2021.07.018
Chen H, Qi D, Yu L, Qin J, Heng P-A (2018) Voxresnet: Deep voxelwise residual networks for brain segmentation from 3d mr images. NeuroImage 170:446–455. https://doi.org/10.1016/j.neuroimage.2017.04.041
Roy AG, Conjeti S, Sheet D, Katouzian A, Navab N, Wachinger C (2017) Error corrective boosting for learning fully convolutional networks with limited data. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 231–239. https://doi.org/10.1007/978-3-319-66179-7-27
Dolz J, Gopinath K, Yuan J, Lombaert H, Desrosiers C, Ayed IB (2018) Hyperdense-net: a hyper-densely connected cnn for multi-modal image segmentation. IEEE Transactions on Medical Imaging 38(5):1116–1126. https://doi.org/10.1109/TMI.2018.2878669
Kushibar K, Valverde S, González-Villà S, Bernal J, Cabezas M, Oliver A, Lladó X (2018) Automated sub-cortical brain structure segmentation combining spatial and deep convolutional features. Medical Image Analysis 48:177–186. https://doi.org/10.1016/j.media.2018.06.006
Roy AG, Conjeti S, Navab N, Wachinger C, Alzheimer’s Disease Neuroimaging Initiative et al (2019) Quicknat: a fully convolutional network for quick and accurate segmentation of neuroanatomy. NeuroImage 186:713–727. https://doi.org/10.1016/j.neuroimage.2018.11.042
Wachinger C, Reuter M, Klein T (2018) Deepnat: Deep convolutional neural network for segmenting neuroanatomy. NeuroImage 170:434–445. https://doi.org/10.1016/j.neuroimage.2017.02.035
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234–241. https://doi.org/10.1007/978-3-319-24574-4-28
Xia H, Ma M, Li H, Song S (2021) Mc-net: multi-scale context-attention network for medical ct image segmentation. Appl Intell, 1–12. https://doi.org/10.1007/s10489-021-02506-z
Wang Z, Peng Y, Li D, Guo Y, Zhang B (2021) Mmnet: A multi-scale deep learning network for the left ventricular segmentation of cardiac mri images. Applied Intelligence. https://doi.org/10.1007/s10489-021-02720-9
Shin H-C, Roth HR, Gao M, Lu L, Xu Z, Nogues I, Yao J, Mollura D, Summers RM (2016) Deep convolutional neural networks for computer-aided detection: Cnn architectures, dataset characteristics and transfer learning. IEEE Transactions on Medical Imaging 35(5):1285–1298
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580–587
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778. https://doi.org/10.1109/CVPR.2016.90
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 25:1097–1105
Shakeri M, Tsogkas S, Ferrante E, Lippe S, Kadoury S, Paragios N, Kokkinos I (2016) Sub-cortical brain structure segmentation using f-cnn’s. In: 2016 IEEE 13Th international symposium on biomedical imaging (ISBI). IEEE, pp 269–272. https://doi.org/10.1109/ISBI.2016.7493261
Roy AG, Nav Ab N, Wachinger C (2018) Concurrent spatial and channel squeeze & excitation in fully convolutional networks. Springer, Cham. https://doi.org/10.1007/978-3-030-00928-1_48
Milletari F, Ahmadi S-A, Kroll C, Plate A, Rozanski V, Maiostre J, Levin J, Dietrich O, Ertl-Wagner B, Bötzel K. et al (2017) Hough-cnn: deep learning for segmentation of deep brain regions in mri and ultrasound. Comput Vis Image Underst 164:92–102. https://doi.org/10.1016/j.cviu.2017.04.002
Roy AG, Conjeti S, Navab N, Wachinger C, Alzheimer’s Disease Neuroimaging Initiative et al (2019) Bayesian quicknat: model uncertainty in deep whole-brain segmentation for structure-wise quality control. NeuroImage 195:11–22. https://doi.org/10.1016/j.neuroimage.2019.03.042
Zhou Z, Siddiquee MRM, Tajbakhsh N, Liang J (2018) Unet++: A nested u-net architecture for medical image segmentation. In: Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, pp 3–11. https://doi.org/10.1007/978-3-030-00889-5-1
Huang H, Lin L, Tong R, Hu H, Wu J (2020) Unet 3+: A full-scale connected unet for medical image segmentation. https://doi.org/10.1109/ICASSP40776.2020.9053405
Oktay O, Schlemper J, Le Folgoc L, Lee M, Heinrich M, Misawa K, Mori K, McDonagh S, Hammerla NY, Kainz B et al (2018) Attention u-net: Learning where to look for the pancreas. arXiv:1804.03999
Gu Z, Cheng J, Fu H, Zhou K, Hao H, Zhao Y, Zhang T, Gao S, Liu J (2019) Ce-net: Context encoder network for 2d medical image segmentation. IEEE Trans Med Imaging 38(10):2281–2292. https://doi.org/10.1109/TMI.2019.2903562
Wang J, Sun K, Cheng T, Jiang B, Xiao B (2021) Deep high-resolution representation learning for visual recognition. IEEE Trans Pattern Anal Mach Intell 43(10):3349–3364. https://doi.org/10.1109/TPAMI.2020.2983686
Liu X, He P, Chen W, Gao J (2019) Multi-task deep neural networks for natural language understanding. arXiv:1901.11504
Kendall A, Gal Y, Cipolla R (2018) Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7482–7491. https://doi.org/10.1109/CVPR.2018.00781
Kingma DP, Ba J Adam:, A method for stochastic optimization. arXiv:1412.6980
Worth AJ (1996) The internet brain segmentation repository (ibsr). http://www.cma.mgh.harvard.edu/ibsr
Landman BA, Warfield S (2012) Miccai: 2012 Grand challenge and workshop on multi-atlas labeling. In: Proc. international conference on medical image computing and computer assisted intervention, MICCAI, vol 2012. http://www.incf.org/community/events/miccai
Shattuck DW, Mirza M, Adisetiyo V, Hojatkashani C, Salamon G, Narr KL, Poldrack RA, Bilder RM, Toga AW (2008) Construction of a 3d probabilistic atlas of human cortical structures. NeuroImage 39(3):1064–1080. https://doi.org/10.1016/j.neuroimage.2007.09.031
Marcus DS, Wang TH, Parker J, Csernansky JG, Morris JC, Buckner RL (2007) Open access series of imaging studies (oasis): cross-sectional mri data in young, middle aged, nondemented, and demented older adults. Journal of Cognitive Neuroscience 19(9):1498–1507. https://doi.org/10.1162/jocn.2007.19.9.1498
Yang H, Sun J, Li H, Wang L, Xu Z (2018) Neural multi-atlas label fusion: Application to cardiac mr images. Medical Image Analysis 49:60–75. https://doi.org/10.1016/j.media.2018.07.009
Zhang C, Lin G, Liu F, Yao R, Shen C (2019) Canet: Class-agnostic segmentation networks with iterative refinement and attentive few-shot learning 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). arXiv:1903.02351v1
Acknowledgements
This work is supported by National Nature Science Foundation of China (grant No.61871106 and No.61370152), Key R & D projects of Liaoning Province, China (grant No. 2020JH2/10100029), and the Open Project Program Foundation of the Key Laboratory of Opto-Electronics Information Processing, Chinese Academy of Sciences (OEIP-O-202002).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Hu, Q., Wei, Y., Li, X. et al. SVF-Net: spatial and visual feature enhancement network for brain structure segmentation. Appl Intell 53, 4180–4200 (2023). https://doi.org/10.1007/s10489-022-03706-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03706-x