Education, Science, Technology, Innovation and Life
Open Access
Sign In

Lung Disease Diagnosis based on Transfer Learning

Download as PDF

DOI: 10.23977/jaip.2022.050113 | Downloads: 24 | Views: 693

Author(s)

Wanle Chi 1,2, Yun Huoy Choo 2, Ong Sing Goh 2, Gong Dafeng 1,2

Affiliation(s)

1 College of artificial intelligence, Wenzhou Polytechnic, Wenzhou, Zhejiang 325035, China
2 Faculty of Information and Communication Technology, Universiti Teknikal Malaysia Melaka (UTeM), Malacca 76100, Malaysia

Corresponding Author

Wanle Chi

ABSTRACT

The diagnosis of lung nodules is an important indicator of clinical indications of malignant lung diseases such as lung cancer. Traditionally, doctors read CT lung nodule image to judge the lung disease. The difficulty of doctors' judgement leads to missed diagnosis and misdiagnosis. Through the cooperation of human intelligence and artificial intelligence, computer aided diagnosis can improve the medical imaging clinical diagnosis, improve diagnosis efficiency and accuracy.The objective of paper is to develop a computer-aided diagnostic predictor for lung disease. This paper proposes using cheap and many malignancy labels to transfer learn to expensive and few pathological diagnosis. The paper proposes a partially soft parameter sharing method. In the LIDC datasets, the result of experiment shows that the algorithm of paper is more accurate than other approaches.

KEYWORDS

Lung Disease Diagnosis, LIDC; Lung Image, Transfer Learning, Multi-Tasking Learning, Soft Parameter Sharing

CITE THIS PAPER

Wanle Chi, Yun Huoy Choo, Ong Sing Goh and Gong Dafeng, Lung Disease Diagnosis based on Transfer Learning. Journal of Artificial Intelligence Practice (2022) Vol. 5: 98-104. DOI: http://dx.doi.org/10.23977/jaip.2022.050113.

REFERENCES

[1] Nie S D,Li - Hong L I,Chen Z X. A CI feature - based lung nodule segmentation using three-domain mean shift clustering. International Conference on Wavelet Analysis and Pattern Recognition. IEEE,2008: 223-227.
[2]Han F, Wang H, Zhang G, et al. Texture feature analysis for computer-aided diagnosis on lung nodules .Journal of Digital Imaging, 2015, 28 (1):99-115.
[3]Zhongqi M, Haosheng Z, Haishi Y , et al. Face expression recognition based on multiple feature fusion dense residual CNN . Computer Application and Software, 2019, 36 (7): 197-201.
[4]Shuo Z, Rong Z. Research on the Handwritten Digital Recognition Algorithm Based on the Convolutional Neural Network Model. Computer Application and Software, 2019, 36 (8): 172-176.
[5]Shun Z, Yihong G, Jinjun W. The development of deep convolutional neural networks and their applications in computer vision. Journal of Computer Science, 2019, 42 (3): 453-482.
[6]Juanxiu T, Guocai L, Shanshan G, et al. Research and Challenges of Deep Learning Methods for Medical Image Analysis. Journal of Automation, 2018, 44 (3): 401-424.

Downloads: 5242
Visits: 171918

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.