The Identification of Cerebral Haemorrhage Through Head CT Images and Comparison of Three Convolutional Models
Authors
Zijian Wang
Share
Annotation
With modern computers and medical advancements, we can find a better way to increase efficiency and reduce human error in the healthcare system. In computer vision, machine learning models can analyze and categorize patients' head CTs. This diagnosis process is faster and retains the accuracy of experienced healthcare professionals. In this study, we used deep learning algorithms to identify cerebral haemorrhage in CT images with different CNN (convolutional neural network) architectures — exception and inception. Cerebral haemorrhage is one of the most complex diseases to diagnose and treat in the world. By comparing the performances of simple CNN, exception model, and inception model, we can find the best model for this task.
Keywords
Authors
Zijian Wang
Share
References:
1. Reynolds, Anh H. “Convolutional Neural Networks (Cnns).” Anh H. Reynolds, 15 Oct. 2017,
https://anhreynolds.com/blogs/cnn.html.
2. IBM Cloud Education. “What Are Neural Networks?” IBM,
https://www.ibm.com/cloud/learn/neural-networks.
3. Seldon. “Transfer Learning for Machine Learning.” Seldon, 29 June 2021, https://www.seldon.io/transfer-learning#:~:text=Transfer%20learning%20means%20taking%20the,to%20solve%20a%20specific%20task.
4. Xu, Joyce. “An Intuitive Guide to Deep Network Architectures.” Medium, Towards Data Science, 15 Aug. 2017, https://towardsdatascience.com/an-intuitive-guide-to-deep-network-architectures-65fdc477db41#:~:text=Xception%20stands%20for%20%E2%80%9Cextreme%20inception,of%20Inception%20to%20an%20extreme.
5. Peixeiro, Marco. “Introduction to Convolutional Neural Networks (CNN) with Tensorflow.” Medium, Towards Data Science, 19 May 2020, https://towardsdatascience.com/introduction-to-convolutional-neural-networks-cnn-with-tensorflow-57e2f4837e18.
6. Peixeiro, Marco. “Step-by-Step Guide to Building Your Own Neural Network from Scratch.” Medium, Towards Data Science, 19 May 2020, https://towardsdatascience.com/step-by-step-guide-to-building-your-own-neural-network-from-scratch-df64b1c5ab6e.
7. Quetscher, Felizia. “A Comprehensible Explanation of the Dimensions in Cnns.” Medium, Towards Data Science, 24 June 2021, https://towardsdatascience.com/a-comprehensible-explanation-of-the-dimensions-in-cnns-841dba49df5e.
8. Zhou, Victor. “Training a Convolutional Neural Network from Scratch.” Medium, Towards Data Science, 6 June 2019, https://towardsdatascience.com/training-a-convolutional-neural-network-from-scratch-2235c2a25754.
9. Felman, Adam. “Brain Hemorrhage: Causes, Symptoms, and Treatments.” Medical News
Today, MediLexicon International, 2019,
https://www.medicalnewstoday.com/articles/317080#symptoms.
10. Zhou, Victor. “CNNs, Part 1: An Introduction to Convolutional Neural Networks.” Victor
Zhou,Victor Zhou, 22 May 2019, https://victorzhou.com/blog/intro-to-cnns-part-1/#41 implementing-pooling.
11. Kwiatkowski, Robert. “Gradient Descent Algorithm - a Deep Dive.” Medium, Towards Data
Science, 13 July 2022, https://towardsdatascience.com/gradient-descent-algorithm-a
deep-dive-cf04e8115f21.
12. “Backpropagation.” Brilliant Math & Science Wiki,
https://brilliant.org/wiki/backpropagation/.
13. Techslang. “What Is a Convolutional Neural Network? - Definition by Techslang.” Techslang, Techslang - Today\'s Most Spoken Tech Explained, 12 Nov. 2020, https://www.techslang.com/definition/what-is-a-convolutional-neural-network/.
14. PARADI, Himarka, et al. “Multi Modal Learning with Deep Neural Networks - Anits.” Multi Modal Learning with Deep Neural Networks A PROJECT REPORT, 2022, http://cse.anits.edu.in/projects/projects1920B17.pdf.
15. ost@lincoln.ac.uk, Online Services Team; “Volumetric Estimation of Cystic Macular Edema in OCT Scans.” Volumetric Estimation of Cystic Macular Edema in OCT Scans - The, 1 Jan. 1970, https://eprints.lincoln.ac.uk/id/eprint/38920//1/Volumetric_Estimation_Of_Cystic_Macular_Edema_In_OCT_Scans.pdf.
16. Zhou, Shuangxi et al. “Crack Texture Feature Identification of Fiber Reinforced Concrete
Based on Deep Learning.” Materials (Basel, Switzerland) vol. 15,11 3940. 1 Jun. 2022, doi:10.3390/ma15113940
17. Wang, Zhu. “A Rom-Accelerated Parallel-in-Time Preconditioner for Solving All-at ...” A ROM-Accelerated Parallel-in-Time Preconditioner for Solving All-at-Once Systems in Unsteady Convection-Diffusion PDEs, 2021, https://people.math.sc.edu/wangzhu/reference/Liu2021ParaDIAG_PinT_ROM_zw.pdf.
18. Géron, Aurélien. “3. Convolutional Neural Networks.” EBOOKREADING.NET, https://ebookreading.net/view/book/EB9781492037354_5.html.
19. Xia, Xiao. “CNN Architectures - Googlenet/Resnet/Vggnet.” CNN Architectures - GoogLeNet/ResNet/VGGNet, 2022, https://zhuanlan.zhihu.com/p/426100290
Other articles of the issue
