CCsNeT: Automated Corpus Callosum segmentation using fully convolutional network based on U-Net

• Autorzy: Chandra Anjali , Verma Shrish , Raghuvanshi A.S. , Bodhey Narendra Kuber

Identyfikatory

DOI

10.1016/j.bbe.2021.12.008

• Języki publikacji: EN

Abstrakty

EN

Background: Corpus Callosum (CC) is the most prominent white matter bundle in the human brain that connects the left and right cerebral hemispheres. The present paper proposes a novel method for CC segmentation from 2D T1- weighted mid-sagittal brain MRI. The robust segmentation of CC in the mid-sagittal plane plays a vital role in the quantitative study of CC structural features related to various neurological disorders such as Autism, epilepsy, Alzheimer’s disease, and more. Methodology: In this perspective, the current work proposes a Fully Convolutional Network (FCN), a deep learning architecture-based U-Net model for automated CC segmentation from 2D brain MRI images referred to as CCsNeT. The architecture consists of a 35-layers deep, fully convolutional network with two paths, namely contracting and extracting, connected in a U-shape that automatically extracts spatial information. Results: This attempt uses the benchmark brain MRI database comprising ABIDE and OASIS for the experimental investigation. Compared to existing CC segmentation methodologies, the proposed CCsNeT presented improved results achieving Dice Coefficient = 96.74%, and Sensitivity = 97.01% with ABIDE dataset and were further validated against the variants of U-Net model U-Net++, MultiResU-Net, and CE-Net. Further, the performance of CCsNeT has been validated on OASIS and Real-Time Images dataset. Conclusion: Finally, the proposed CCsNeT extracts important CC characteristics such as CC area (CCA) and total brain area (TBA) to categorize the considered 2D MRI slices into control and autism spectrum disorder (ASD) groups, thereby minimizing the inter-observer and intra-observer variability.

Słowa kluczowe

EN

corpus callosum; brain segmentation; deep learning; fully convolutional network; U-Net

PL

ciało modzelowate; segmentacja mózgu; uczenie głębokie; sieć konwolucyjna; U-Net

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2022
• Tom: Vol. 42, no. 1
• Strony: 187--203
• Opis fizyczny: Bibliogr. 63 poz., rys., tab., wykr.

Twórcy

autor

Chandra Anjali

• Department of Electronics & Communication Engineering, NIT Raipur, C.G., India

autor

Verma Shrish

• Department of Electronics & Communication Engineering, NIT Raipur, C.G., India

autor

Raghuvanshi A.S.

• Department of Electronics & Communication Engineering, NIT Raipur, C.G., India

autor

Bodhey Narendra Kuber

• Department of Radiodiagnosis, AIIMS Raipur, C.G., India

Bibliografia

• [1] Fitsiori A, Nguyen D, Karentzos A, Delavelle J, Vargas MI. The corpus callosum: White matter or terra incognita. Br J Radiol 2011;84(997):5–18.
• [2] Chandra A, Verma S, Raghuvanshi AS, Londhe ND, Bodhey NK, Subham K, et al. 3rd IEEE Int Conf Electr Comput Commun Technol ICECCT 2019;2019:2019.
• [3] Ardekani BA, Ikuta T, Bachman A, Szeszko PR. Multi-Atlas Corpus Callosum Segmentation with Adaptive Atlas Selection. Ismrm 2012;20:2564.
• [4] Aboitiz F, Scheibel AB, Fisher RS, Zaidel E. Fiber composition of the human corpus callosum. Brain Res 1992;598(1-2):143–53.
• [5] Ye HT, Ji JF, Liu W, Li G, Xun Z. Annals of clinical case reports reduction of the corpus callosum in first-episode, drug naive schizophrenia patients is worsened in the absence of depression symptoms: evidence for depression-type. Ann Clin Case Rep 2019;4:4–5.
• [6] Samartzis L, Dima D, Fusar-Poli P, Kyriakopoulos M. White matter alterations in early stages of schizophrenia: A systematic review of diffusion tensor imaging studies. J Neuroimaging 2014;24(2):101–10.
• [7] Unterberger I, Bauer R, Walser G, Bauer G. Corpus callosum and epilepsies. Seizure Eur J Epilepsy 2016;37:55–60.
• [8] Lacerda ALT, Brambilla P, Sassi RB, Nicoletti MA, Mallinger AG, Frank E, et al. Journal of anatomical MRI study of corpus callosum in unipolar depression. J Psychiatr Res 2005;39 (4):347–54.
• [9] Katti G, Ara SA, Shireen A. Magnetic Resonance Imaging (MRI) – A Review. Int. J. Dent. Clin. 2011;3(1):65–70.
• [10] Li Y, Wang H, Ahmed N, Mandal M. Automated corpus callosum segmentation in midsagittal brain MR images. IJIVP 2017;8(1):1554–65.
• [11] G. V. Bhalerao and N. Sampathila, ‘‘K-means clustering approach for segmentation of corpus callosum from brain magnetic resonance images,” Proc. Int. Conf. Circuits, Commun. Control Comput. I4C 2014, no. November, pp. 434–437, 2014.
• [12] Seixas FL, De Souza AS, Dos Santos AASMD, Muchaluat Saade DC. Automated segmentation of the corpus callosum midsagittal surface area. Proc. SIBGRAPI 2007–20th Brazilian Symp Comput Graph Image Process 2007:287–93.
• [13] A. Jlassi, K. ElBedoui, W. Barhoumi, and C. Maktouf, ‘‘Unsupervised method based on probabilistic neural network for the segmentation of corpus callosum in MRI Scans,” VISIGRAPP 2019 - Proc. 14th Int. Jt. Conf. Comput. Vision, Imaging Comput. Graph. Theory Appl., vol. 4, no. Visigrapp, pp. 545–552, 2019.
• [14] Srinivasan K, Nanditha NM. An intelligent skull stripping algorithm for mri image sequences using mathematical morphology. Biomed Res 2018;29(16):3201–6.
• [15] Kalavathi P, Prasath VBS. Methods on Skull Stripping of MRI Head Scan Images—a Review. J Digit Imaging 2016;29 (3):365–79.
• [16] Al-Tamimi MSH, Sulong G. Tumor brain detection through MR images: A review of literature. J Theor Appl Inf Technol 2014;62(2):387–403.
• [17] Cover GS, Herrera WG, Bento MP, Appenzeller S, Rittner L. Computational methods for corpus callosum segmentation on MRI: A systematic literature review. Comput Methods Programs Biomed 2018;154:25–35.
• [18] Q. He, Y. Duan, J. Miles, and N. Takahashi, ‘‘A context-sensitive active contour for 2D corpus callosum segmentation,” Int J Biomed Imaging, vol 2007, no. Cc, 2007.
• [19] J. K. Mogali, N. Nallapareddy, C. S. Seelamantula, and M. Unser, ‘‘A shape-template based two-stage corpus callosum segmentation technique for sagittal plane T1-weighted brain magnetic resonance images,” 2013 IEEE Int. Conf. Image Process. ICIP 2013 - Proc., pp. 1177–1181, 2013.
• [20] ddin Al Shidaifat A, Choi H-K. Implementation of 2D Snake Model-based Segmentation on Corpus Callosum. J. Korea Multimed. Soc. 2014;17(12):1412–7.
• [21] Adamson C, Beare R, Walterfang M, Seal M. Software Pipeline for Midsagittal Corpus Callosum Thickness Profile Processing: Automated Segmentation, Manual Editor, Thickness Profile Generator, Group-Wise Statistical Comparison and Results Display. Neuroinformatics 2014;12 (4):595–614.
• [22] P. Damayanti, D. Yuniasri, R. Sarno, A. Fajar, and D. Rahmawati, ‘‘Corpus callosum segmentation from brain MRI images based on level set method,” Proc. - 2020 Int. Semin. Appl. Technol. Inf. Commun. IT Challenges Sustain. Scalability, Secur. Age Digit. Disruption, iSemantic 2020, pp. 155–160, 2020.
• [23] Rajan S, Brettschneider J, Collingwood JF. Regional segmentation strategy for DTI analysis of human corpus callosum indicates motor function deficit in mild cognitive impairment. J Neurosci Methods 2020;345 108870.
• [24] Freitas P, Rittner L, Appenzeller S, Lotufo R. Watershed-based segmentation of the midsagittal section of the corpus callosum in diffusion MRI. Proc - 24th SIBGRAPI Conf Graph Patterns Images 2011:274–80.
• [25] Herron TJ, Kang X, Woods DL. Automated measurement of the human corpus callosum using MRI. Front Neuroinform 2012;6(August):1–15.
• [26] Rittner L, Campbell JSW, Freitas PF, Appenzeller S, Bruce Pike G, Lotufo RA. Analysis of scalar maps for the segmentation of the corpus callosum in diffusion tensor fields. J Math Imaging Vis 2013;45(3):214–26.
• [27] Ciecholewski M, Spodnik JH. Semi-automatic corpus callosum segmentation and 3D visualization using active contour methods. Symmetry (Basel) 2018;10(11):1–25.
• [28] Lynn JD et al. Microstructure of Human Corpus Callosum across the Lifespan: Regional Variations in Axon Caliber, Density, and Myelin Content. Cereb Cortex 2021;31 (2):1032–45.
• [29] Bilgen I, Guvercin G, Rekik I. Machine learning methods for brain network classification: Application to autism diagnosis using cortical morphological networks. J Neurosci Methods 2020;343 108799.
• [30] Fischl B. FreeSurfer. Neuroimage 2012;62(2):774–81.
• [31] J. Xu, F. Liang, and L. Gu, ‘‘Bayesian co-segmentation of multiple MR images,” Proc. - 2009 IEEE Int. Symp. Biomed. Imaging From Nano to Macro, ISBI 2009, vol. 3, pp. 53–56, 2009.
• [32] El-Baz A, Elnakib A, Casanova MF, Gimel’farb G, Switala AE, Jordan D, et al. Accurate automated detection of autism related corpus callosum abnormalities. J Med Syst 2011;35 (5):929–39.
• [33] G. Park, K. Kwak, S. W. Seo, and J. M. Lee, ‘‘Automatic segmentation of corpus callosum in midsagittal based on Bayesian inference consisting of sparse representation error and multi-atlas voting,” Front. Neurosci., vol. 12, no. SEP, 2018.
• [34] W. G. Herrera, M. Pereira, M. Bento, A. T. Lapa, S. Appenzeller, and L. Rittner, ‘‘A framework for quality control of corpus callosum segmentation in large-scale studies,” J. Neurosci. Methods, vol. 334, no. September 2019, p. 108593, 2020.
• [35] Karsch K, He Q, Duan Y. A fast, semi-automatic brain structure segmentation algorithm for magnetic resonance imaging. 2009 IEEE Int Conf Bioinforma Biomed BIBM 2009;2009:297–302.
• [36] Gass T, Sze´kely G, Goksel O. Simultaneous segmentation and multiresolution nonrigid atlas registration. IEEE Trans Image Process 2014;23(7):2931–43.
• [37] Jac Fredo AR, Kavitha G, Ramakrishnan S. Automated segmentation and analysis of corpus callosum in autistic MR brain images using fuzzy-c-means-based level set method. J Med Biol Eng 2015;35(3):331–7.
• [38] Jang SH, Kim OL, Kim SH, Do Lee H, Calabrò RS. Differences in corpus callosum injury between cerebral concussion and diffuse axonal injury. Med. (United States) 2019;98(41):16–8.
• [39] Tetsuka S. Reversible lesion in the splenium of the corpus callosum. Brain Behav 2019;9(11):1–10.
• [40] Berman S, Filo S, Mezer AA. Modeling conduction delays in the corpus callosum using MRI-measured g-ratio. NeuroImage 2019;195:128–39.
• [41] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 2015;9351:234–41.
• [42] Dash M, Londhe ND, Ghosh S, Semwal A, Sonawane RS. PsLSNet: Automated psoriasis skin lesion segmentation using modified U-Net-based fully convolutional network. Biomed Signal Process Control 2019;52:226–37.
• [43] Chandra A. SegNet – based Corpus Callosum segmentation for brain Magnetic Resonance Images (MRI). 2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), 2019.
• [44] He K. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. 2015 IEEE Int Conf. Comput. Vis. 2015:1026–34.
• [45] Suárez-Paniagua V, Segura-Bedmar I. Evaluation of pooling operations in convolutional architectures for drug-drug interaction extraction. BMC Bioinf 2018;19(S8). https://doi. org/10.1186/s12859-018-2195-1.
• [46] D. Scherer, A. Müller, and S. Behnke, ‘‘Evaluation of pooling operations in convolutional architectures for object recognition,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 6354 LNCS, no. PART 3, pp. 92–101, 2010.
• [47] M. Siam, M. Gamal, M. Abdel-Razek, S. Yogamani, M. Jagersand, and H. Zhang, ‘‘A comparative study of real-time semantic segmentation for autonomous driving,” IEEE Comput Soc Conf Comput Vis Pattern Recognit Work, vol. 2018- June, no. August, pp. 700–710, 2018.
• [48] Hinton G. Dropout: A Simple Way to Prevent Neural Networks from. Overfitting 2014;15:1929–58.
• [49] Bottou L. Large-scale machine learning with stochastic gradient descent. Proc COMPSTAT 2010–19th Int Conf Comput Stat Keynote, Invit Contrib Pap 2010:177–86.
• [50] S. Ruder, ‘‘An overview of gradient descent optimization algorithms,” pp. 1–14, 2016.
• [51] M. L. di Scandalea, C. S. Perone, M. Boudreau, and J. CohenAdad, ‘‘Deep Active Learning for Axon-Myelin Segmentation on Histology Data,” pp. 1–8, 2019.
• [52] C. S. Perone, M. Boudreau, and J. Cohen-adad, ‘‘Deep Active Learning for Axon-Myelin Segmentation on Histology Data,” pp. 1–8.
• [53] F. Chollet, ‘‘Introduction to Keras,” 2018.
• [54] M. Abadi et al., ‘‘TensorFlow : A System for Large-Scale Machine Learning This paper is included in the Proceedings of the TensorFlow : A system for large-scale machine learning,” 2016.
• [55] ‘‘ABIDE corpus callosum and brain segmentation data.” [Online]. Available: https://sites.google.com/site/hpardoe/ cc_abide.
• [56] H. Sharif and R. A. Khan, ‘‘A novel framework for automatic detection of Autism: A study on Corpus Callosum and Intracranial Brain Volume,” vol. d, 2019.
• [57] Marcus DS, Wang TH, Parker J, Csernansky JG, Morris JC, Buckner RL. Open Access Series of Imaging Studies (OASIS): Cross-sectional MRI data in young, middle aged, nondemented, and demented older adults. J Cogn Neurosci 2007;19(9):1498–507.
• [58] Kucharsky Hiess R, Alter R, Sojoudi S, Ardekani BA, Kuzniecky R, Pardoe HR. Corpus Callosum Area and Brain Volume in Autism Spectrum Disorder: Quantitative Analysis of Structural MRI from the ABIDE Database. J Autism Dev Disord 2015;45(10):3107–14.
• [59] S. J. Sujit, R. E. Gabr, I. Coronado, M. Robinson, S. Datta, and P. A. Narayana, ‘‘Automated Image Quality Evaluation of Structural Brain Magnetic Resonance Images using Deep Convolutional Neural Networks,” 2018 9th Cairo Int. Biomed. Eng. Conf. CIBEC 2018 - Proc., no. December, pp. 33–36, 2019.
• [60] S. Shrivastava and A. Chandra, ‘‘Comparative Study of Deep Learning Models for Segmentation of Corpus Callosum,” in Fourth International Conference on Computing Methodologies and Communication (ICCMC 2020) IEEE Xplore Part Number: CFP20K25-ART; ISBN:978-1-7281-4889-2 Comparative, 2020, pp. 418–423.
• [61] Liu X, Song L, Liu S, Zhang Y. A review of deep-learning-based medical image segmentation methods. Sustain 2021;13 (3):1–29.
• [62] Platten M, Martola J, Fink K, Ouellette R, Piehl F, Granberg T. MRI-Based Manual versus Automated Corpus Callosum Volumetric Measurements in Multiple Sclerosis. J Neuroimaging 2020;30(2):198–204.
• [63] Henschel L, Conjeti S, Estrada S, Diers K, Fischl B, Reuter M. FastSurfer - A fast and accurate deep learning based neuroimaging pipeline. Neuroimage 2020;219 117012.