Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Comparison and analysis of chest X-ray-based deep learning loss function performance

흉부 X-ray 기반 딥 러닝 손실함수 성능 비교·분석

  • Seo, Jin-Beom (Department of information Security, Daejeon University) ;
  • Cho, Young-Bok (Department of information Security, Daejeon University)
  • Received : 2021.06.29
  • Accepted : 2021.07.17
  • Published : 2021.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Artificial intelligence is being applied in various industrial fields to the development of the fourth industry and the construction of high-performance computing environments. In the medical field, deep learning learning such as cancer, COVID-19, and bone age measurement was performed using medical images such as X-Ray, MRI, and PET and clinical data. In addition, ICT medical fusion technology is being researched by applying smart medical devices, IoT devices and deep learning algorithms. Among these techniques, medical image-based deep learning learning requires accurate finding of medical image biomarkers, minimal loss rate and high accuracy. Therefore, in this paper, we would like to compare and analyze the performance of the Cross-Entropy function used in the image classification algorithm of the loss function that derives the loss rate in the chest X-Ray image-based deep learning learning process.

4차 산업의 발전과 고성능의 컴퓨팅 환경 구축으로 다양한 산업분야에서 인공지능이 적용되고 있다. 의료분야에서는 X-Ray, MRI, PET 등의 의료 영상 및 임상 자료를 이용하여 암, COVID-19, 골 연령 측정 등의 딥 러닝 학습이 진행되었다. 또한 스마트 의료기기, IoT 디바이스와 딥 러닝 알고리즘을 적용하여 ICT 의료 융합 기술 등이 연구되고 있다. 이러한 기술 중 의료 영상 기반 딥 러닝 학습은 의료 영상의 바이오마커를 정확히 찾아내고, 최소한의 손실률과 높은 정확도가 필요하다. 따라서 본 논문은 흉부 X-Ray 이미지 기반 딥 러닝 학습 과정에서 손실률을 도출하는 손실 함수 중 영상분류 알고리즘에서 사용되는 Cross-Entropy 함수들의 성능을 비교·분석하고자 한다.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. 2018R1C1B5083789).

References

  1. G. Chandrika, "Study on Software Reliability and Reliability Testing," Asia-pacific Journal of Convergent Research Interchange, vol. 1, no. 1, pp. 7-20, Mar. 2015.
  2. H. M. Sim and P. Ishvi, "Analysis of an Axial T2 Weighted Brain MRI," Asia-pacific Journal of Convergent Research Interchange, vol. 3, no. 1, pp. 45-55, Mar. 2017.
  3. S. H. Lee and J. Y. Kim, "Artificial Intelligence Technology Trends Based on Medical Big Data," The Journal of The Korean Institute of Communication Sciences, vol. 37, no. 8, pp. 85-91, Aug. 2020.
  4. S. T. Kang, W. Lee, B. G. Park, and K. S. Han, "Diagnosis of Parkinson's Disease Using Two Types of Biomarkers and Characterization of Fiber Pathways," KIPS Transactions on Software and Data Engineering, vol. 3, no. 10, pp. 421-428, Oct. 2014. https://doi.org/10.3745/KTSDE.2014.3.10.421
  5. J. Y. Yun, K. T. Kim, and J. Y, Choi, "Using 3D Deep Convolutional Neural Network with MRI Biomarker patch Images for Alzheimer's Disease Diagnosis," Journal of Korea Multimedia Society, vol. 23, no. 8, pp. 940-952, Aug. 2020. https://doi.org/10.9717/KMMS.2020.23.8.940
  6. H. I. Kim and H. N. Yoon, "Classification of Medical Images Based on Mixed Attributes Relation," Journal of Digital Contents Society, vol. 21, no. 11, pp. 2033-2039, Nov. 2020. https://doi.org/10.9728/dcs.2020.21.11.2033
  7. Y. B. Cho, "Keras based CNN Model for Disease Extraction in Ultrasound Image," Journal of Digital Contents Society, vol. 19, no. 10, Oct. 2018.
  8. J. K. Aronson "Biomarkers and surrogate endpoints," British Journal of Clinical Pharmacology, vol. 59, no. 5, pp. 491-494, May. 2005. https://doi.org/10.1111/j.1365-2125.2005.02435.x
  9. S. Kyle and J. A. Tavel. "What are Biomarkers?," Current Opinion in HIV and AIDS, vol. 5, no. 6, pp. 463-466, Nov. 2011. https://doi.org/10.1097/COH.0b013e32833ed177
  10. J. H. Son, K. T. Kim, and J. Y. Choi, "Alzheimer's Disease Classification with Automated MRI Biomarker Detection Using Faster R-CNN for Alzheimer's Disease Diagnosis," Journal of Korea Multimedia Society, vol. 22, no. 10, pp. 1168-1177, Oct. 2019.
  11. X. Qi, L. G. Brown, D. J. Foran, J. Nosher, and I. Hacihaliloglu "Chest X-ray image phase features for improved diagnosis of COVID-19 using convolutional neural network," International Journal of Computer Assisted Radiology and Surgery, vol. 16, pp. 197-206, 2021. https://doi.org/10.1007/s11548-020-02305-w
  12. I. Hacihaliloglu, "Localization of bone surfaces from ultra sound data using local phase information and signal transmission maps," International workshop and challenge on computational methods and clinical applications in musculoskeletal imaging, pp. 1-11, Jan. 2017.
  13. M. Felsberg and G. Sommer, "The monogenic signal," IEEE Transactions on Signal Processing, vol. 49, no. 12, pp. 3136-3144, Dec. 2001. https://doi.org/10.1109/78.969520
  14. A. Belaid and D, Boukerroui, "α Scale spaces filters for phase based edge detection in ultrasound images," IEEE 11th International Symposium on Biomedical Imaging, pp. 1247-1250, 2014.
  15. G. Meng, Y. Wang, J. Duan, S. Xiang, and C. PAN, "Efficient Image Dehazing with Boundary Constraint and Contextual Regularization," 2013 IEEE International Conference on Computer Vision, Sydney, pp. 1247-1250, 2013.