Automated volumetric analysis of the inner ear fluid space from hydrops magnetic resonance imaging using 3D neural networks.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
22 Oct 2024
22 Oct 2024
Historique:
received:
13
10
2023
accepted:
09
10
2024
medline:
22
10
2024
pubmed:
22
10
2024
entrez:
21
10
2024
Statut:
epublish
Résumé
Due to the development of magnetic resonance (MR) imaging processing technology, image-based identification of endolymphatic hydrops (EH) has played an important role in understanding inner ear illnesses, such as Meniere's disease or fluctuating sensorineural hearing loss. We segmented the inner ear, consisting of the cochlea, vestibule, and semicircular canals, using a 3D-based deep neural network model for accurate and automated EH volume ratio calculations. We built a dataset of MR cisternography (MRC) and HYDROPS-Mi2 stacks labeled with the segmentation of the perilymph fluid space and endolymph fluid space of the inner ear to devise a 3D segmentation deep neural network model. End-to-end learning was used to segment the perilymph fluid and the endolymph fluid spaces simultaneously using aligned pair data of the MRC and HYDROPS-Mi2 stacks. Consequently, the segmentation performance of the total fluid space and endolymph fluid space had Dice similarity coefficients of 0.9574 and 0.9186, respectively. In addition, the EH volume ratio calculated by experienced otologists and the EH volume ratio value predicted by the proposed deep learning model showed high agreement according to the interclass correlation coefficient (ICC) and Bland-Altman plot analysis.
Identifiants
pubmed: 39433848
doi: 10.1038/s41598-024-76035-3
pii: 10.1038/s41598-024-76035-3
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
24798Subventions
Organisme : Korea Government (MIST)
ID : National Reserch Foundation of Korea
Organisme : Korea Government (MIST)
ID : National Reserch Foundation of Korea
Informations de copyright
© 2024. The Author(s).
Références
Hallpike, C. S. & Cairns, H. W. B. Observations of the pathology of Menie`re’s syndrome. Proc. R Soc. Med. 31, 1317–1336 (1938).
pubmed: 19991672
pmcid: 2076781
Yamakawa, K. U¨ ber die pathologische Vera¨nderung beieinem M_enie`re-Kranken. Proceedings of 42nd Annual Meeting Oto-Rhino-Laryngol Soc Japan. J. Otolaryngol. Soc. Jpn. 4, 2310–2. (1938).
Kimura, R. S. & Schuknecht, H. F. Membranous hydrops in the inner ear of the guinea pig after obliteration of the endolymphatic sac. Pract. Otorhinolaryngol. 27, 343–354 (1965).
Kimura, R. S. Experimental blockage of the endolymphatic duct and sac and its effect on the inner ear of the guinea pig. Ann. Otol Rhinol Laryngol. 76, 664–687 (1967).
doi: 10.1177/000348946707600311
pubmed: 6046009
Kimura, R. S. Experimental pathogenesis of hydrops. Arch. Otorhinolaryngol. 212, 263–275 (1976).
doi: 10.1007/BF00453674
pubmed: 990078
Kiang, N. Y. S. An auditory physiologist’s view of Ménière’s syndrome. In Second International Symposium on Ménière’s disease (ed. Nadol, J. B. Jr)13–24. (Kugler & Ghedini, Amsterdam 1989).
Schuknecht, H. F. Pathology of the Ear. 2nd edn. (Lea & Febiger, Philadelphia, 1993).
Merchant, S. N., Rauch, S. D. & Nadol, J. B. Meniere’s disease. Eur. Arch. Otorhinolaryngol. 252, 63–75 (1995).
doi: 10.1007/BF00168023
pubmed: 7598874
Nadol, J. B. Jr Pathogenesis of Meniere’s syndrome. In Ménière’s Disease, (ed. Harris, J. P.) 73–79 (The Hague, The Netherlands: Kugler, 1999).
Nakashima, T. et al. Grading of endolymphatic hydrops using magnetic resonance imaging. Acta Otolaryngol. 129 (sup560), 5–8 (2009).
doi: 10.1080/00016480902729827
Vaidyanathan, A. et al. Deep learning for the fully automated segmentation of the inner ear on MRI. Sci. Rep. 11 (1), 1–14 (2021).
doi: 10.1038/s41598-021-82289-y
Hussain, R., Lalande, A., Girum, K. B., Guigou, C., Grayeli, B. & A Automatic segmentation of inner ear on CT-scan using auto-context convolutional neural network. Sci. Rep. 11 (1), 1–10 (2021).
doi: 10.1038/s41598-021-83955-x
Zhu, S., Gao, W., Zhang, Y., Zheng, J., Liu, Z. & Yuan, G. 3D automatic MRI level set segmentation of inner ear based on statistical shape models prior. In 2017 10th International Congress on Image and Signal Processing, Biomedical Engineering and Informatics (CISP-BMEI) 1–6 (IEEE, 2017).
Ahmadi, S. A., Raiser, T. M., Rühl, R. M., Flanagin, V. L. & Zu Eulenburg, P. IE-Map: a novel in-vivo atlas and template of the human inner ear. Sci. Rep. 11 (1), 1–16 (2021).
doi: 10.1038/s41598-021-82716-0
Kirsch, V., Nejatbakhshesfahani, F., Ahmadi, S. A., Dieterich, M. & Ertl-Wagner, B. A probabilistic atlas of the human inner ear’s bony labyrinth enables reliable atlas-based segmentation of the total fluid space. J. Neurol. 266 (1), 52–61 (2019).
doi: 10.1007/s00415-019-09488-6
pubmed: 31422454
Powell, K. A. et al. Atlas-based segmentation of temporal bone anatomy. Int. J. Comput. Assist. Radiol. Surg. 12 (11), 1937–1944 (2017).
doi: 10.1007/s11548-017-1658-6
pubmed: 28852952
pmcid: 5676303
Meng, J., Li, S., Zhang, F., Li, Q. & Qin, Z. Cochlear size and shape variability and implications in cochlear implantation surgery. Otol. Neurotol. 37(9), 1307–1313 (2016).
doi: 10.1097/MAO.0000000000001189
pubmed: 27579839
Kendi, T. K., Arikan, O. K. & Koc, C. Volume of components of labyrinth: magnetic resonance imaging study. OtolNeurotol. 26 (4), 778–781 (2005).
Wang, R. et al. Medical image segmentation using deep learning: a survey. IET Image Proc. 16 (5), 1243–1267 (2022).
doi: 10.1049/ipr2.12419
Niyas, S., Pawan, S. J., Kumar, M. A. & Rajan, J. Medical image segmentation with 3D convolutional neural networks: a survey. Neurocomputing. 493, 397–413 (2022).
doi: 10.1016/j.neucom.2022.04.065
Shen, D., Wu, G. & Suk, H. I. Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221 (2017).
doi: 10.1146/annurev-bioeng-071516-044442
pubmed: 28301734
pmcid: 5479722
Liu, X., Song, L., Liu, S. & Zhang, Y. A review of deep-learning-based medical image segmentation methods. Sustainability. 13 (3), 1224 (2021).
doi: 10.3390/su13031224
Litjens, G. et al. A survey on deep learning in medical image analysis. Med. Image. Anal. 42, 60–88 (2017).
doi: 10.1016/j.media.2017.07.005
pubmed: 28778026
Gürkov, R. et al. MR volumetric assessment of endolymphatic hydrops. Eur. Radiol. 25 (2), 585–595 (2015).
doi: 10.1007/s00330-014-3414-4
pubmed: 25319347
Neves, C. A., Tran, E. D., Kessler, I. M. & Blevins, N. H. Fully automated preoperative segmentation of temporal bone structures from clinical CT scans. Sci. Rep. 11 (1), 1–11 (2021).
doi: 10.1038/s41598-020-80619-0
Noble, J. H., Labadie, R. F., Majdani, O. & Dawant, B. M. Automatic segmentation of intracochlear anatomy in conventional CT. IEEE Trans. Biomed. Eng. 58 (9), 2625–2632 (2011).
doi: 10.1109/TBME.2011.2160262
pubmed: 21708495
pmcid: 3804019
Iyaniwura, J. E., Elfarnawany, M., Ladak, H. M. & Agrawal, S. K. An automated A-value measurement tool for accurate cochlear duct length estimation. J. Otolaryngology-Head Neck Surg. 47 (1), 1–8 (2018).
doi: 10.1186/s40463-018-0253-3
Liu, T., Xu, Y., An, Y. & Ge, H. Intelligent segmentation algorithm for diagnosis of Meniere’s disease in the inner auditory canal using MRI images with three-dimensional level set. Contrast Media Mol. Imaging 2021 (2021).
Heutink, F., Koch, V., Verbist, B., van der Woude, W. J., Mylanus, E., Huinck, W.,... & Caballo, M. Multi-scale deep learning framework for cochlea localization, segmentation and analysis on clinical ultra-high-resolution CT images. Comput. Methods Programs Biomed. 191, 105387 (2020).
Elfarnawany, M. et al. Micro-CT versus synchrotron radiation phase contrast imaging of human cochlea. J. Microsc. 265 (3), 349–357 (2017).
doi: 10.1111/jmi.12507
pubmed: 27935035
Franz, D., Hofer, M., Pfeifle, M., Pirlich, M., Stamminger, M. & Wittenberg, T. Wizard-based segmentation for cochlear implant planning. In Bildverarbeitung für die Medizin 2014 258–263 (Springer, Berlin, Heidelberg, 2014).
Naganawa, S. et al. MR imaging of endolymphatic hydrops: utility of iHYDROPS-Mi2 combined with deep learning reconstruction denoising. Magn. Reson. Med. Sci. 20 (3), 272–279 (2021).
doi: 10.2463/mrms.mp.2020-0082
pubmed: 32830173
Cho, Y. S., Cho, K., Park, C. J., Chung, M. J., Kim, J. H., Kim, K.,... & Chung, W. H. Automated measurement of hydrops ratio from MRI in patients with Ménière’s disease using CNN-based segmentation. Sci. Rep. 10 (1), 1–10 (2020)
Park, C. J., Cho, Y. S., Chung, M. J., Kim, Y. K., Kim, H. J., Kim, K.,... & Cho, B. H. A Fully automated analytic system for measuring endolymphatic hydrops ratios in patients With Ménière Disease via Magnetic Resonance Imaging: deep learning model development study. J. Med. Internet Res. 23 (9), e29678 (2021).
Iida, T., Teranishi, M., Yoshida, T., Otake, H., Sone, M., Kato, M.,... & Nakashima, T. Magnetic resonance imaging of the inner ear after both intratympanic and intravenous gadolinium injections. Acta Oto-Laryngol. 133 (5), 434–438 (2013).
Ronneberger, O., Fischer, P. & Brox, T. U-net: convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention 234–241 (Springer, Cham, 2015).
Nogovitsyn, N., Souza, R., Muller, M., Srajer, A., Hassel, S., Arnott, S. R.,... & MacQueen, G. M. Testing a deep convolutional neural network for automated hippocampus segmentation in a longitudinal sample of healthy participants. NeuroImage 197, 589–597 (2019).
Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T. & Ronneberger, O. 3D U-Net: learning dense volumetric segmentation from sparse annotation. In International Conference on Medical Image Computing and Computer-Assisted Intervention 424–432 (Springer, Cham, 2016).
Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. ICLR 2019 (2017).
Abraham, N. & Khan, N. M. A novel focal tversky loss function with improved attention u-net for lesion segmentation. In 2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019) pp. 683–687 (IEEE, 2019).
Lin, T. Y., Goyal, P., Girshick, R., He, K. & Dollár, P. Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42, 2980–2991 (2018).
Salehi, S. S. M., Erdogmus, D. & Gholipour, A. Tversky loss function for image segmentation using 3D fully convolutional deep networks. In International Workshop on Machine Learning in Medical Imaging 379–387 (Springer, Cham, 2017).
Naganawa, S., Yamazaki, M., Kawai, H., Bokura, K., Sone, M. & Nakashima, T. Imaging of endolymphatic and perilymphatic fluid after intravenous administration of single-dose gadodiamide. Magn. Reson. Med. Sci. 11, 145–150 (2012).
Szklo, M. & Nieto, F. J. Epidemiology: Beyond the Basics (Jones & Bartlett, 2014).
Bland, J. M. & Altman, D. Statistical methods for assessing agreement between two methods of clinical measurement. Lancet. 327 (8476), 307–310 (1986).
doi: 10.1016/S0140-6736(86)90837-8
Hu, J., Shen, L. & Sun, G. Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 7132–7141 (2018).
Oktay, O. et al. Attention U-net: learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 (2018).
Nodirov, J., Abdusalomov, A. B. & Whangbo, T. K. Attention 3D U-Net with multiple skip connections for segmentation of brain tumor images. Sensors. 22 (17), 6501 (2022).
doi: 10.3390/s22176501
pubmed: 36080958
pmcid: 9460422
Futrega, M., Milesi, A., Marcinkiewicz, M. & Ribalta, P.. Optimized U-Net for brain tumor segmentation. In International MICCAI Brainlesion Workshop 15–29 (Springer International Publishing, Cham, 2021).
Hatamizadeh, A. et al. Swin unetr: swin transformers for semantic segmentation of brain tumors in mri images. In International MICCAI Brainlesion Workshop 272–284 (Springer International Publishing, Cham, 2021).
Gao, Y. et al. A data-scalable transformer for medical image segmentation: architecture, model efficiency, and benchmark. arXiv preprint arXiv:2203.00131. (2022).
Amit, T., Shaharbany, T., Nachmani, E. & Wolf, L. Segdiff: Image segmentation with diffusion probabilistic models. arXiv preprint arXiv:2112.00390. (2021).
Wu, J., Fu, R., Fang, H., Zhang, Y. & Xu, Y. Medsegdiff-v2: Diffusion based medical image segmentation with transformer. arXiv preprint arXiv:2301.11798. (2023).