Prediction of Ischemic Stroke in MRI Images based on Machine Learning: A Systematic Review
DOI:
https://doi.org/10.62051/qtf5k466Keywords:
Ischemic Stroke; deep learning; MRI.Abstract
Ischemic stroke is a dangerous disease that endangers human health and is one of the important causes of disability and death. Early detection and prediction of ischemic stroke are essential for timely intervention and prevention of serious consequences. Fortunately, deep learning-based medical image research has made great progress, which can assist doctors in diagnosing conditions. This paper analyzes the overall effectiveness of existing machine learning (ML) methods in predicting final infarction from baseline imaging. First, this paper searched 11 relevant studies and analyzed the impact of these methods on patients with acute ischemic stroke (AIS). Then, the performance, effect and characteristics of the model are analyzed. Although these methods are generally good at predicting infarction, they show great potential. Based on machine learning methods, reliance on abundant data is essential for effective learning. Insufficient data can lead to significant errors in model predictions. Therefore, future research should focus on collecting ample clinical data for model training to enhance both accuracy and robustness.
Downloads
References
Brinjikji, W., Duffy, S., Burrows, A., Hacke, W., Liebeskind, D., Majoie, C. B. L. M., Dippel, D. W. J., Siddiqui, A. H., Khatri, P., Baxter, B., Nogueira, R., Gounis, M., Jovin, T., & Kallmes, D. F. Correlation of imaging and histopathology of thrombi in acute ischemic stroke with etiology and outcome: a systematic review. Journal of neurointerventional surgery, 2017, 9(6), 529–534.
Maegerlein, C., Friedrich, B., Berndt, M., Lucia, K. E., Schirmer, L., Poppert, H., Zimmer, C., Pelisek, J., Boeckh-Behrens, T., & Kaesmacher, J. Impact of histological thrombus composition on preinterventional thrombus migration in patients with acute occlusions of the middle cerebral artery. Interventional neuroradiology : journal of peritherapeutic neuroradiology, surgical procedures and related neurosciences, 2018, 24(1), 70–75.
Simons, N., Mitchell, P., Dowling, R., Gonzales, M., & Yan, B. Thrombus composition in acute ischemic stroke: a histopathological study of thrombus extracted by endovascular retrieval. Journal of neuroradiology = Journal de neuroradiologie, 2015, 42(2), 86–92.
Seymour, C. W., Kennedy, J. N., Wang, S., Chang, C. H., Elliott, C. F., Xu, Z., Berry, S., Clermont, G., Cooper, G., Gomez, H., Huang, D. T., Kellum, J. A., Mi, Q., Opal, S. M., Talisa, V., van der Poll, T., Visweswaran, S., Vodovotz, Y., Weiss, J. C., Yealy, D. M., … Angus, D. C. Derivation, Validation, and Potential Treatment Implications of Novel Clinical Phenotypes for Sepsis, 2019, 321(20), 2003–2017.
Debs N, Decroocq M, Cho T H, et al. Evaluation of the realism of an MRI simulator for stroke lesion prediction using convolutional neural network, Simulation and Synthesis in Medical Imaging: 4th International Workshop, SASHIMI 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 13, 2019, Proceedings 4. Springer International Publishing, 2019: 151-160.
Zhou, J., Lee, S., Liu, Y., Chan, J. S. K., Li, G., Wong, W. T., Jeevaratnam, K., Cheng, S. H., Liu, T., Tse, G., & Zhang, Q. Predicting Stroke and Mortality in Mitral Regurgitation: A Machine Learning Approach. Current problems in cardiology, 2023, 48(2), 101464.
Kumar, S., Marchina, S., Massaro, J., Feng, W., Lahoti, S., Selim, M., & Herzig, S. J. ACDD4 score: A simple tool for assessing risk of pneumonia after stroke. Journal of the neurological sciences, 2017, 372, 399–402.
Heo, T., Kim, Y.S., Choi, J.M., Jeong, Y.S., Seo, S.Y., Lee, J.H., Jeon, J.P., & Kim, C. Prediction of Stroke Outcome Using Natural Language Processing-Based Machine Learning of Radiology Report of Brain MRI. Journal of Personalized Medicine, 2020, 10.
Li, M., Lang, M., Deng, F., Chang, K., Buch, K.A., Rincon, S., Mehan, W.A., Leslie-Mazwi, T.M., & Kalpathy-Cramer, J. Analysis of Stroke Detection during the COVID-19 Pandemic Using Natural Language Processing of Radiology Reports. American Journal of Neuroradiology, 2020, 42, 429 - 434.
Ong, C.J., Orfanoudaki, A., Zhang, R., Caprasse, F.P., Hutch, M.R., Ma, L., Fard, D., Balogun, O., Miller, M.I., Minnig, M.A., Saglam, H., Prescott, B., Greer, D.M., Smirnakis, S.M., & Bertsimas, D. Machine learning and natural language processing methods to identify ischemic stroke, acuity and location from radiology reports. PLoS ONE, 2020, 15.
Kim, C., Zhu, V.J., Obeid, J.S., & Lenert, L. Natural language processing and machine learning algorithm to identify brain MRI reports with acute ischemic stroke. PLoS ONE, 2019, 14.
Garg, R., Oh, E., Naidech, A.M., Kording, K.P., & Prabhakaran, S. Automating Ischemic Stroke Subtype Classification Using Machine Learning and Natural Language Processing. Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association, 2019, 28(7), 2045-2051.
Downloads
Published
Conference Proceedings Volume
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.