Hybrid Convolutional Neural Network Method for Robust Brain Stroke Diagnosis and Segmentation

Year 2022, Volume: 10 Issue: 4, 410 - 418, 19.10.2022

Sercan Yalçın

https://doi.org/10.17694/bajece.1129233

Cited By: 1

Abstract

Artificial intelligence with deep learning methods have been employed by a majority of researchers in medical image classification and segmentation applications for many years. In this study, hybrid convolutional neural network (CNN) model has been proposed for diagnosing of brain stroke from the dataset consisting of the computed tomography (CT) brain images. The model inspired from C-Net consists of multiple concatenation layers of the networks, and prevents the concatenation of convolutional feature maps to evince the mapping process. The structures of the convolutional index and residual shortcuts of the INet model are also integrated into the proposed CNN model. In output layer of the model, it is split into two classes as whether there is a stroke or not in a brain image, and then the region of the stroke in the image is segmented. Tremendous analyzes have been conducted in terms of many benchmarks using Python programming. The proposed method shows better performances rather than some other current CNN-based methods by 99.54% accuracy and 99.1% Matthews correlation coefficient (MCC) in the diagnosis of brain stroke. The proposed method can alleviate the work of most medical staffs and facilitate the process of the patient’s remedy.

Keywords

Artificial intelligence, deep learning, convolutional neural networks, brain stroke diagnosis

References

• S. Park, et al. “Annotated normal CT data of the abdomen for deep learning: Challenges and strategies for implementation”, Diagnostic and Interventional Imaging, 101(1), 2020, pp.35-44.
• H. Huang, et al. “UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation”, Electrical Engineering and Systems Science Image and Video Processing,2020, https://doi.org/10.48550/arXiv.2004.08790.
• N. Dey, V. Rajinikanth, “Automated detection of ischemic stroke with brain MRI using machine learning and deep learning features”, Magnetic Resonance Imaging, Recording, Reconstruction and Assessment Primers in Biomedical Imaging Devices and Systems, 2022, pp.147-174.
• A. Gautam, B. Raman, “Towards effective classification of brain hemorrhagic and ischemic stroke using CNN”, Biomedical Signal Processing and Control, 63(102178), 2021.
• B.R. Gaidhani, R. Rajamenakshi, S. Sonavane, “Brain Stroke Detection Using Convolutional Neural Network and Deep Learning Models”, 2019 2nd International Conference on Intelligent Communication and Computational Techniques (ICCT), Jaipur, Sep 28-29, 2019, pp. 242-249.
• C.M. Lo, P.H. Hung, D.T. Lin, “Rapid Assessment of Acute Ischemic Stroke by Computed Tomography Using Deep Convolutional Neural Networks”, Journal of Digital Imaging, 34, 2021, pp. 637–646.
• N. Tomitaa, S. Jiangb, M.E. Maederc, S. Hassanpour, “Automatic post-stroke lesion segmentation on MR images using 3D residual convolutional neural network”, NeuroImage: Clinical, 27, 2020,102276.
• V. Badrinarayanan, A. Kendall, R. Cipolla, “Segnet: A deep convolutional encoder-decoder architecture for image segmentation”, IEEE transactions on pattern analysis and machine intelligence, 39(12), 2017, pp.2481-2495.
• O. Ronneberger, P. Fischer, T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation”, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, 2015, pp.234-241.
• L. Liu, S. Chen, F. Zhang, F.X. Wu, Y. Pan, J. Wang, “Deep convolutional neural network for automatically segmenting acute ischemic stroke lesion in multi-modality MRI”, Neural Computing and Applications, 32, 2020, pp.6545–6558.
• Z. Zhang, Q. Liu, Y. Wang, “Road extraction by deep residual UNet,’’ IEEE Geosci. Remote Sens. Lett., 15(5), pp. 749–753, May 2018.
• W. Weng, X. Zhu, “INet: Convolutional Networks for Biomedical Image Segmentation”, IEEE Access, 9, 2021, pp.16591-16603.
• M. Khened, V. A. Kollerathu, G. Krishnamurthi, “Fully convolutional multi-scale residual DenseNets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers”, Med. Image Anal., 51, pp. 21–45, Jan. 2019.
• G.S. Saragih, et al. “Ischemic Stroke Classification using Random Forests Based on Feature Extraction of Convolutional Neural Networks”, International Journal on Advanced Science Engineering Information Technology, 10(5), 2020, pp.2177-2182.
• H Barzekar, Z. Yu, “C-Net: A reliable convolutional neural network for biomedical image classification”, Expert Systems With Applications, 187, 2022, 116003.
• M. Rahimzadeh, A. Attar, “A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2”, Informatics in Medicine Unlocked, 19, 2020, 100360.
• L.-C. Chen, G. Papandreou, F. Schroff, H. Adam, “Rethinking atrous convolution for semantic image segmentation”, arXiv:1706.05587. [Online]. 2017, Available: http://arxiv.org/abs/1706.05587.
• K.S. A. Kumara, A.Y. Prasad, J. Metan, “A hybrid deep CNN-Cov-19-Res-Net Transfer learning architype for an enhanced Brain tumor Detection and Classification scheme in medical image processing”, Biomedical Signal Processing and Control, 76, 2022, 103631.
• F. Chollet, et al. Keras. https://github.com/fchollet/keras, 2015.
• M. Abadi, et al. “Tensorflow: A system for large-scale machine learning”, In 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16), 2016, pp. 265–283.