Iranian Journal of Biomedical Engineering (IJBME)

به کارگیری سیستم استنتاج فازی در پیش‌پردازش جهت بهبود بخش‌بندی ضایعات سکته‌ی مغزی با استفاده از شبکه‌ی عصبی عمیق U-Net

نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 کارشناسی ارشد، گروه مهندسی پزشکی، دانشگاه صنعتی همدان، همدان، ایران

2 استادیار، گروه مهندسی پزشکی، دانشگاه صنعتی همدان، همدان، ایران

3 دانشیار، گروه مهندسی پزشکی، دانشگاه صنعتی همدان، همدان، ایران

چکیده
سکته‌ی مغزی یکی از علل مرگ و میر و عامل اصلی ایجاد ناتوانی بیماران در کشورهای توسعه یافته است. به طور معمول شناسایی ضایعات سکته‌ی مغزی به وسیله‌ی تصویربرداری مغناطیسی صورت گرفته و تحلیل آن نیازمند حضور مستمر پزشک در مرکز درمانی است. لذا پردازش هوشمند تصاویر پزشکی رویکردی موثر برای تشخیص خودکار ضایعات مغزی می‌باشد. در این مقاله یک چارچوب تلفیقی جدید بر مبنای سیستم استنتاج فازی و شبکه‌ی عصبی عمیق برای بخش‌بندی خودکار ضایعات مغزی معرفی شده است. در این راستا ابتدا به معرفی یک شبکه‌ی عمیق U-Net بهبود یافته برای تشخیص و بخش‌بندی ضایعه پرداخته شده که شامل افزایش تعداد لایه‌های بخش‌های رمزگذار و رمزگشا به همراه تغییر توابع فعال‌سازی است. سپس با به کارگیری یک سیستم استنتاج فازی مبتنی بر قواعد اگر-آن‌گاه، رویکرد پیشنهادی این مطالعه که بر مبنای پیش‌پردازش تصاویر ورودی و به کارگیری شبکه‌ی یونت بوده معرفی شده است. نتایج نشان داده که تلفیق سیستم استنتاج فازی در پیش‌پردازش با شبکه‌ی عمیق یونت توانسته است ضریب دایس را تا میزان 84/0 افزایش دهد. به علاوه بهبود کنتراست تصاویر ورودی توسط سیستم فازی نسبت به روش یکسان‌سازی هیستوگرام، باعث عمل‌کرد بسیار بهتری در تشخیص ضایعات با ابعاد کوچک شده که دلیل آن توانمندی بیش‌تر کنترل کنتراست در قواعد فازی است.

کلیدواژه‌ها

موضوعات


عنوان مقاله English

Fuzzy Inference System in Pre-Processing to Improve Stroke Lesion Segmentation using U-Net Deep Neural Network

نویسندگان English

Mohammad Mahdi Alimoradi 1
Mohammad Bagher Khodabakhshi 2
Shahriar Jamasb 3
1 M.Sc., Biomedical Engineering Department, Hamedan University of Technology, Hamedan, Iran
2 Assistant Professor, Biomedical Engineering Department, Hamedan University of Technology, Hamedan, Iran
3 Associate Professor, Biomedical Engineering Department, Hamedan University of Technology, Hamedan, Iran
چکیده English

Stroke is one of the causes of death and the main cause of disability in developed countries. Normally, identification of stroke lesions is done by magnetic imaging, and its analysis requires the continuous presence of a doctor in the treatment center. Therefore, intelligent processing of medical images will be an effective approach for automatic diagnosis of brain lesions. In this paper, a new integrated framework based on fuzzy inference system and deep neural network for automatic segmentation of brain lesions is introduced. In this regard, firstly, an improved U-Net deep network (U-Net) has been introduced for lesion detection and segmentation, which includes increasing the number of encoder and decoder layers along with changing the activation functions. Then, by using a fuzzy inference system based on if-then rules used by membership functions, the proposed approach of this study, which is based on the pre-processing of input images and the use of the unit network, has been introduced. The results showed that the integration of the fuzzy inference system in the pre-processing with the improved deep network could increase the DICE coefficient up to 0.84. In addition, improving the contrast of the input images by the fuzzy system compared to the usual pre-processing methods such as histogram equalization showed a much better performance in the detection of lesions with small dimensions, which is due to the ability to control the amount of contrast increase in the fuzzy systems compared to the usual methods.

کلیدواژه‌ها English

Stroke Lesion
Magnetic Resonance Images
Deep Learning
U-Net Network
Fuzzy Inference System
  1. Hui, X. Zhang, F. Li, X. Mei, and Y. Guo, “A Partitioning-Stacking Prediction Fusion Network Based on an Improved Attention U-Net for Stroke Lesion Segmentation,” IEEE Access, vol. 8, pp. 47419–47432, 2020, doi: 10.1109/ACCESS.2020.2977946.
  2. Winzeck et al., “Ensemble of Convolutional Neural Networks Improves Automated Segmentation of Acute Ischemic Lesions Using Multiparametric Diffusion-Weighted MRI.,” AJNR. Am. J. Neuroradiol., vol. 40, no. 6, pp. 938–945, Jun. 2019, doi: 10.3174/ajnr.A6077.
  3. Khezrpour, H. Seyedarabi, S. N. Razavi, and M. Farhoudi, “Automatic segmentation of the brain stroke lesions from MR flair scans using improved U-Net framework,” Biomed. Signal Process. Control, vol. 78, p. 103978, 2022, doi: https://doi.org/10.1016/j.bspc.2022.103978.
  4. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation.,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 12, pp. 2481–2495, Dec. 2017, doi: 10.1109/TPAMI.2016.2644615.
  5. Shin, R. Agyeman, M. Rafiq, M. C. Chang, and G. S. Choi, “Automated segmentation of chronic stroke lesion using efficient U-Net architecture,” Biocybern. Biomed. Eng., vol. 42, no. 1, pp. 285–294, 2022, doi: https://doi.org/10.1016/j.bbe.2022.01.002.
  6. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2980–2988, doi: 10.1109/ICCV.2017.322.
  7. Stier, N. Vincent, D. Liebeskind, and F. Scalzo, “Deep Learning of Tissue Fate Features in Acute Ischemic Stroke.,” Proceedings. (IEEE. Int. Conf. Bioinformatics Biomed)., vol. 2015, pp. 1316–1321, Nov. 2015, doi: 10.1109/BIBM.2015.7359869.
  8. Karthik, U. Gupta, A. Jha, R. Rajalakshmi, and R. Menaka, “A deep supervised approach for ischemic lesion segmentation from multimodal MRI using Fully Convolutional Network,” Appl. Soft Comput., vol. 84, p. 105685, 2019, doi: https://doi.org/10.1016/j.asoc.2019.105685.
  9. Zhang, S. Xu, L. Tan, H. Wang, and J. Meng, “Stroke Lesion Detection and Analysis in MRI Images Based on Deep Learning,” J. Healthc. Eng., vol. 2021, p. 5524769, 2021, doi: 10.1155/2021/5524769.
  10. Tomita, S. Jiang, M. E. Maeder, and S. Hassanpour, “Automatic post-stroke lesion segmentation on MR images using 3D residual convolutional neural network,” NeuroImage Clin., vol. 27, p. 102276, 2020, doi: https://doi.org/10.1016/j.nicl.2020.102276.
  11. Brosch, L. Y. W. Tang, Y. Yoo, D. K. B. Li, A. Traboulsee, and R. Tam, “Deep 3D Convolutional Encoder Networks With Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation.,” IEEE Trans. Med. Imaging, vol. 35, no. 5, pp. 1229–1239, May 2016, doi: 10.1109/TMI.2016.2528821.
  12. Zhang et al., “Ischemic Stroke Lesion Segmentation Using Multi-Plane Information Fusion,” IEEE Access, vol. 8, pp. 45715–45725, 2020, doi: 10.1109/ACCESS.2020.2977415.
  13. Liu, L. Kurgan, F.-X. Wu, and J. Wang, “Attention convolutional neural network for accurate segmentation and quantification of lesions in ischemic stroke disease,” Med. Image Anal., vol. 65, p. 101791, 2020, doi: https://doi.org/10.1016/j.media.2020.101791.
  14. K. Cornelio, M. A. Del Castillo, and P. Naval, U-ISLES: Ischemic Stroke Lesion Segmentation Using TensorFlow U-Net. 2020.
  15. Pinto, J. Amorim, A. Hakim, V. Alves, M. Reyes, and C. A. Silva, “Prediction of Stroke Lesion at 90-Day Follow-Up by Fusing Raw DSC-MRI With Parametric Maps Using Deep Learning,” IEEE Access, vol. 9, pp. 26260–26270, 2021, doi: 10.1109/ACCESS.2021.3058297.
  16. -L. Liao et al., “Implementation and outcome of thrombolysis with alteplase 3 to 4.5 h after acute stroke in Chinese patients.,” CNS Neurosci. Ther., vol. 19, no. 1, pp. 43–47, Jan. 2013, doi: 10.1111/cns.12031.
  17. B. Khodabakhshi, N. Eslamyeh, S. Z. Sadredini, and M. Ghamari, “Cuffless blood pressure estimation using chaotic features of photoplethysmograms and parallel convolutional neural network.,” Comput. Methods Programs Biomed., vol. 226, p. 107131, Nov. 2022, doi: 10.1016/j.cmpb.2022.107131.
  18. Sathish, R. Rajan, A. Vupputuri, N. Ghosh, and D. Sheet, “Adversarially Trained Convolutional Neural Networks for Semantic Segmentation of Ischaemic Stroke Lesion using Multisequence Magnetic Resonance Imaging.,” Annu. Int. Conf. IEEE Eng. Med. Biol.  Soc. IEEE Eng. Med. Biol. Soc. Annu. Int. Conf., vol. 2019, pp. 1010–1013, Jul. 2019, doi: 10.1109/EMBC.2019.8857527.
  19. Kooi et al., “Large scale deep learning for computer aided detection of mammographic lesions.,” Med. Image Anal., vol. 35, pp. 303–312, Jan. 2017, doi: 10.1016/j.media.2016.07.007.
  20. Kirichev, T. Slavov, and G. Momcheva, “Fuzzy U-Net Neural Network Design for Image Segmentation BT - Contemporary Methods in Bioinformatics and Biomedicine and Their Applications,” 2022, pp. 177–184.
  21. Joshi and S. Kumar, Image contrast enhancement using fuzzy logic. 2018.
  22. Ni, J. Wu, J. Tong, Z. Chen, and J. Zhao, “GC-Net: Global context network for medical image segmentation.,” Comput. Methods Programs Biomed., vol. 190, p. 105121, Jul. 2020, doi: 10.1016/j.cmpb.2019.105121.
  23. B. Khodabakhshi, M. H. Moradi, Z. M. Sanat, and P. Jafari Moghadam Fard, “Lung sound decomposition using recurrent fuzzy wavelet network,” J. Intell. Fuzzy Syst., vol. 33, pp. 2497–2508, 2017, doi: 10.3233/JIFS-17684.
  24. Salami, M. B. Khodabakhshi, and M. H. Moradi, “Fuzzy transfer learning approach for analysing imagery BCI tasks,” in 2017 Artificial Intelligence and Signal Processing Conference (AISP), 2017, pp. 300–305, doi: 10.1109/AISP.2017.8324101.
  25. C. Sullivan et al., “Metrology Standards for Quantitative Imaging Biomarkers.,” Radiology, vol. 277, no. 3, pp. 813–825, Dec. 2015, doi: 10.1148/radiol.2015142202.
  26. Karthik, R. Menaka, M. Hariharan, and D. Won, “Ischemic Lesion Segmentation using Ensemble of Multi-Scale Region Aligned CNN,” Comput. Methods Programs Biomed., vol. 200, p. 105831, 2021, doi: https://doi.org/10.1016/j.cmpb.2020.105831.
  27. Chen, P. Bentley, and D. Rueckert, “Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks,” NeuroImage Clin., vol. 15, pp. 633–643, 2017, doi: https://doi.org/10.1016/j.nicl.2017.06.016.
دوره 17، شماره 1
بهار 1402
صفحه 83-95

  • تاریخ دریافت 13 مرداد 1402
  • تاریخ بازنگری 18 آبان 1402
  • تاریخ پذیرش 18 آبان 1402