PERFORMANCE EVALUATION OF DIFFERENT DEEP LEARNING MODELS FOR CLASSIFYING ISCHEMIC, HEMORRHAGIC, AND NORMAL COMPUTED TOMOGRAPHY IMAGES: TRANSFER LEARNING APPROACHES

Abstract

A stroke is a case of damage to a brain area due to a sudden decrease or complete cessation of blood flow to the brain. The interruption or reduction of the transportation of oxygen and nutrients through the bloodstream causes damage to brain tissues. Thus, motor or sensory impairments occur in the body part controlled by the affected area of the brain. There are primarily two main types of strokes: ischemic and hemorrhagic. When a patient is suspected of having a stroke, a computed tomography scan is performed to identify any tissue damage and facilitate prompt intervention quickly. Early intervention can prevent the patient from being permanently disabled throughout their lifetime. This study classified ischemic, hemorrhage, and normal computed tomography images taken from international databases as open source with AlexNet, ResNet50, GoogleNet, InceptionV3, ShuffleNet, and SqueezeNet deep learning models using transfer learning approach. The data were divided into 80% training and 20% testing, and evaluation metrics were calculated by five-fold cross-validation. The best performance results for the three-class output were obtained with AlexNet as 0.9086±0.02 precision, 0.9097±0.02 sensitivity, 0.9091±0.02 F1 score, 0.9089±0.02 accuracy. The average area under curve values was obtained with AlexNet 0.9920±0.005 for ischemia, 0.9828±0.008 for hemorrhage, and 0.9686±0.012 for normal.

Keywords

• Computed Tomography
• Deep Learning
• Hemorrhagic Stroke
• Ischemic Stroke
• Transfer Learning

References

1. M. Şahan, S. Satar, A. F. Koç, and A. Sebe, "İskemik İnme ve Akut Faz Reaktanları," Arşiv Kaynak Tarama Dergisi, vol. 19, no. 2, pp. 85-140, 2010.
2. M. Emre, "Nöroloji Temel Kitabı," Ankara: Güneş Tıp Kitapevleri, ch. 669-792, p. 1616, 2013.
3. C. W. Tsao et al., "Heart disease and stroke statistics—2023 update: a report from the American Heart Association," Circulation, vol. 147, no. 8, pp. e93-e621, 2023.
4. R. Karthik, R. Menaka, A. Johnson, and S. Anand, "Neuroimaging and deep learning for brain stroke detection-A review of recent advancements and future prospects," Computer Methods and Programs in Biomedicine, p. 105728, 2020.
5. F. Yuce, M. Ü. Öziç, and M. Tassoker, "Detection of pulpal calcifications on bite-wing radiographs using deep learning," Clinical Oral Investigations, vol. 27, no. 6, pp. 2679-2689, 2023.
6. H. P. Chan, L. M. Hadjiiski, and R. K. Samala, "Computer‐aided diagnosis in the era of deep learning," Medical Physics, vol. 47, no. 5, pp. e218-e227, 2020.
7. H. Fujita and technology, "AI-based computer-aided diagnosis (AI-CAD): the latest review to read first," Radiological Physics, vol. 13, no. 1, pp. 6-19, 2020.
8. C. Park, C. C. Took, and J.-K. Seong, "Machine learning in biomedical engineering," Biomedical Engineering Letters, vol. 8, pp. 1-3, 2018.

9. C. M. Dourado Jr, S. P. P. da Silva, R. V. M. da Nobrega, A. C. d. S. Barros, P. P. Reboucas Filho, and V. H. C. J. C. N. de Albuquerque, "Deep learning IoT system for online stroke detection in skull computed tomography images," Computer Networks, vol. 152, pp. 25-39, 2019.
10. T. D. Phong et al., "Brain hemorrhage diagnosis by using deep learning," in Proceedings of the 2017 International Conference on Machine Learning and Soft Computing, 2017, pp. 34-39.
11. C.-L. Chin et al., "An automated early ischemic stroke detection system using CNN deep learning algorithm," in 2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST), Taiwan, 2017: IEEE, pp. 368-372.
12. D. R. Pereira, P. P. Reboucas Filho, G. H. de Rosa, J. P. Papa, and V. H. C. de Albuquerque, "Stroke lesion detection using convolutional neural networks," in 2018 International Joint Conference on Neural Networks (IJCNN), 2018: IEEE, pp. 1-6.
13. A. Majumdar, L. Brattain, B. Telfer, C. Farris, and J. Scalera, "Detecting intracranial hemorrhage with deep learning," in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2018: IEEE, pp. 583-587.
14. A. Gautam and B. Raman, "Towards effective classification of brain hemorrhagic and ischemic stroke using CNN," Biomedical Signal Processing Control, vol. 63, p. 102178, 2021.
15. J. Pan, G. Wu, J. Yu, D. Geng, J. Zhang, and Y. Wang, "Detecting the Early Infarct Core on Non-Contrast CT Images with a Deep Learning Residual Network," Journal of Stroke Cerebrovascular Diseases, vol. 30, no. 6, p. 105752, 2021.
16. C.-M. Lo, P.-H. Hung, and D.-T. Lin, "Rapid Assessment of Acute Ischemic Stroke by Computed Tomography Using Deep Convolutional Neural Networks," Journal of Digital Imaging, pp. 1-10, 2021.
17. Y. Watanabe et al., "Improvement of the diagnostic accuracy for intracranial haemorrhage using deep learning–based computer-assisted detection," Neuroradiology, vol. 63, no. 5, pp. 713-720, 2021.
18. K. L. Gia et al., "A Computer-Aided Detection to Intracranial Hemorrhage by Using Deep Learning: A Case Study," presented at the Green Technology and Sustainable Development 2020, Da Nang Eyaleti, Vietnam, 2020.
19. A. M. Dawud, K. Yurtkan, and H. Oztoprak, "Application of deep learning in neuroradiology: Brain haemorrhage classification using transfer learning," Computational Intelligence Neuroscience, vol. 2019, 2019.
20. S.-M. Jung and T.-K. Whangbo, "A Deep Learning System for Diagnosing Ischemic Stroke by Applying Adaptive Transfer Learning," Journal of Internet Technology, vol. 21, no. 7, pp. 1957-1968, 2020.
21. O. Öman, T. Mäkelä, E. Salli, S. Savolainen, and M. Kangasniemi, "3D convolutional neural networks applied to CT angiography in the detection of acute ischemic stroke," European Radiology Experimental, vol. 3, no. 1, pp. 1-11, 2019.
22. Y. Shinohara, N. Takahashi, Y. Lee, T. Ohmura, and T. Kinoshita, "Development of a deep learning model to identify hyperdense MCA sign in patients with acute ischemic stroke," Japanese Journal of Radiology, vol. 38, no. 2, pp. 112-117, 2020.
23. A. Neethi, S. Niyas, S. K. Kannath, J. Mathew, A. M. Anzar, and J. Rajan, "Stroke classification from computed tomography scans using 3d convolutional neural network," Biomedical Signal Processing and Control, vol. 76, p. 103720, 2022.
24. O. Ozaltin, O. Coskun, O. Yeniay, and A. Subasi, "A Deep Learning Approach for Detecting Stroke from Brain CT Images Using OzNet," Bioengineering, vol. 9, no. 12, p. 783, 2022.
25. S. Korra, R. Mamidi, N. R. Soora, K. V. Kumar, and N. C. S. Kumar, "Intracranial hemorrhage subtype classification using learned fully connected separable convolutional network," Concurrency and Computation: Practice and Experience, vol. 34, no. 24, p. e7218, 2022.
26. A. A. M. Suberi, W. N. W. Zakaria, R. Tomari, A. Nazari, M. N. H. Mohd, and N. F. N. Fuad, "Deep transfer learning application for automated ischemic classification in posterior fossa CT images," International Journal of Advanced Computer Science and Applications, vol. 10, no. 8, 2019.
27. B. A. Mohammed et al., "Multi-method diagnosis of CT images for rapid detection of intracranial hemorrhages based on deep and hybrid learning," Electronics, vol. 11, no. 15, p. 2460, 2022.
28. T. H. Gençtürk, F. K. Gülağiz, and K. İsmail, "Derin Öğrenme Yöntemleri Kullanılarak BT Taramalarında Beyin Kanaması Teşhisinin Karşılaştırmalı Bir Analizi," Journal of Intelligent Systems: Theory and Applications, vol. 6, no. 1, pp. 75-84, 2023.
29. A. Hakim et al. "Ischemic Stroke Lesion Segmentation." Available: http://www.isles challenge.org/ [Accessed: May 7, 2020].
30. RSNA. "Intracranial Hemorrhage Detection." Radiological Society of North America. Available: https://www.kaggle.com/c/rsna-intracranial-hemorrhage-detection/rules [Accessed: Oct. 30, 2020 ].
31. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," Advances in neural information processing systems, vol. 25, pp. 1097-1105, 2012.
32. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770-778.
33. C. Szegedy et al., "Going deeper with convolutions," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1-9.
34. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the inception architecture for computer vision," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2818-2826.
35. X. Zhang, X. Zhou, M. Lin, and J. Sun, "Shufflenet: An extremely efficient convolutional neural network for mobile devices," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6848-6856.
36. F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size," arXiv preprint arXiv:1602.07360, 2016.
37. C. W. Cereda et al., "A benchmarking tool to evaluate computer tomography perfusion infarct core predictions against a DWI standard," Journal of Cerebral Blood Flow & Metabolism, vol. 36, no. 10, pp. 1780-1789, 2016.
38. Neuroimaging Informatics Tools and Resources Clearinghouse. "MRIcro." McCausland Brain Imaging Center. Available: https://www.nitrc.org/projects/mricro/ [Accessed: Oct. 20, 2020].
39. M. Altıntaş, "Classification of Stroke with Different Deep Learning Models in Computerized Tomography Images," Master's Thesis, Department of Biomedical Engineering, Graduate School of Natural and Applied Sciences, Necmettin Erbakan University, Türkiye, 2021.
40. Z. N. K. Swati et al., "Brain tumor classification for MR images using transfer learning and fine-tuning," Computerized Medical Imaging and Graphics, vol. 75, pp. 34-46, 2019.
41. M. Soltanpour, R. Greiner, P. Boulanger, and B. Buck, "Ischemic Stroke Lesion Prediction in CT Perfusion Scans Using Multiple Parallel U-Nets Following by a Pixel-Level Classifier," in 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE), 2019: IEEE, pp. 957-963.
42. S. Yalçın and H. Vural, "Brain stroke classification and segmentation using encoder-decoder based deep convolutional neural networks," Computers in Biology and Medicine, vol. 149, p. 105941, 2022.
43. I. Guerrón, N. Peréz, D. Benítez, F. Grijalva, D. Riofrío, and M. Baldeon-Calisto, "Extending the U-Net Architecture for Strokes Segmentation on CT Scan Images," in 2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS), 2023: IEEE, pp. 1-7.
44. S. Yalcin, "Hybrid Convolutional Neural Network Method for Robust Brain Stroke Diagnosis and Segmentation," Balkan Journal of Electrical and Computer Engineering, vol. 10, no. 4, pp. 410-418, 2022.
45. Z. Liu, C. Cao, S. Ding, Z. Liu, T. Han, and S. J. I. A. Liu, "Towards clinical diagnosis: Automated stroke lesion segmentation on multi-spectral MR image using convolutional neural network," IEEE Access, vol. 6, pp. 57006-57016, 2018.
46. L. Chen, P. Bentley, and D. Rueckert, "Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks," NeuroImage: Clinical, vol. 15, pp. 633-643, 2017.
47. A. Clèrigues et al., "Acute and sub-acute stroke lesion segmentation from multimodal MRI," Computer Methods and Programs in Biomedicine, vol. 194, p. 105521, 2020.
48. J. Hong, H. Cheng, Y.-D. Zhang, and J. Liu, "Detecting cerebral microbleeds with transfer learning," Machine Vision Applications, vol. 30, no. 7, pp. 1123-1133, 2019.
49. Y. Yu et al., "Use of deep learning to predict final ischemic stroke lesions from initial magnetic resonance imaging," JAMA Network Open, vol. 3, no. 3, pp. e200772-e200772, 2020.
50. L. Zhang et al., "Ischemic Stroke Lesion Segmentation Using Multi-Plane Information Fusion," IEEE Access, vol. 8, pp. 45715-45725, 2020.
51. R. Zhang et al., "Automatic segmentation of acute ischemic stroke from DWI using 3-D fully convolutional DenseNets," IEEE Transactions on Medical Imaging, vol. 37, no. 9, pp. 2149-2160, 2018.
52. C. U. Perez Malla, M. d. C. Valdes Hernandez, M. F. Rachmadi, and T. Komura, "Evaluation of enhanced learning techniques for segmenting ischaemic stroke lesions in brain magnetic resonance perfusion images using a convolutional neural network scheme," Frontiers in Neuroinformatics, vol. 13, p. 33, 2019.