Journal of Internet Computing and Services (인터넷정보학회논문지)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Review of medical imaging systems, medical imaging data problems, and XAI in the medical imaging field

  • Sun-Kuk Noh (Division of Genearl Studies, CHOSUN University)
  • Received : 2024.05.27
  • Accepted : 2024.09.26
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Currently, artificial intelligence (AI) is being applied in the medical field to collect and analyze data such as personal genetic information, medical information, and lifestyle information. In particular, in the medical imaging field, AI is being applied to the medical imaging field to analyze patients' medical image data and diagnose diseases. Deep learning (DL) of deep neural networks such as CNN and GAN have been introduced to medical image analysis and medical data augmentation to facilitate lesion detection, quantification, and classification. In this paper, we examine AI used in the medical imaging field and review related medical image data acquisition devices, medical information systems for transmitting medical image data, problems with medical image data, and the current status of explainable artificial intelligence (XAI) that has been actively applied recently. In the future, the continuous development of AI and information and communication technology (ICT) is expected to make it easier to analyze medical image data in the medical field, enabling disease diagnosis, prognosis prediction, and improvement of patients' quality of life. In the future, AI medicine is expected to evolve from the existing treatment-centered medical system to personalized healthcare through preemptive diagnosis and prevention.

Keywords

References

  1. I. Arel, D. C. Rose, and T. P. Karnowski, "Deep machine Learning - A new Frontier in Artificial Intelligence Research [Research Frontier]," IEEE Computational Intelligence Magazine, vol. 5, no. 4, pp. 13-18, 2010. https://doi.org/10.1109/MCI.2010.938364 
  2. R. Kang Hyun, "Composition of visual feature vector pattern for deep learning in image forensics," IEEE Access, vol. 8, pp. 188970-188980, 2020. https://doi.org/10.1109/ACCESS.2020.3029087 
  3. S-K Noh, "Recycled Clothing Classification System Using Intelligent IoT and Deep Learning with AlexNet," Computational Intelligence and Neuroscience, 2021. https://doi.org/10.1155/2021/5544784 
  4. Gyu-Sung Ham, Mingoo Kang, Su-Chong Joo, "A Study on Medical Information Platform Based on Big Data Processing and Edge Computing for Supporting Automatic Authentication in Emergency Situations," Journal of Internet Computing and Services (JICS), Vol. 23, No. 3, pp. 87-95, Jun. 2022. https://doi.org/10.7472/jksii.2022.23.3.87 
  5. Seonghyeon Ko, Huigyu Yang, Moonseong Kim, Hyunseung Choo, "3D Medical Image Data Augmentation for CT Image Segmentation," Journal of Internet Computing and Services (JICS), Vol. 24, No. 4, pp. 85-92, Aug. 2023. https://doi.org/10.7472/jksii.2023.24.4.85 
  6. Moonseong Kim, "Trends in Patents for Numerical Analysis-Based Financial Instruments Valuation Systems," Journal of Internet Computing and Services (JICS), Vol. 24, No. 6, pp. 41-47, Dec. 2023. https://doi.org/10.7472/jksii.2023.24.6.41 
  7. J. Ker, L. Wang, J.Rao, and T. Lim, "Deep Learning Applications in Medical Image Analysis," IEEE Access, Vol. 6, pp. 9375-9389, 2018. https://doi.org/10.1109/ACCESS.2017.2788044 
  8. AI Framework Predicts Better Patient Health Care and Reduces Cost, Casey Bennett, By INDIANA UNIVERSITY FEBRUARY, 12, 2013. https://scitechdaily.com/ai-framework-predicts-better-patienthealth-care-and-reduces-cost/ 
  9. Rav D, Wong C, Deligianni F, Berthelot M, Andreu Perez J, Lo B, et al., "Deep learning for health informatics," IEEE J Biomed Health Inform, Vol. 21, No. 1, pp. 4-21, Jan. 2017. https://doi.org/10.1109/jbhi.2016.2636665 
  10. Geert Litjens et. al., "A Survey on Deep Learning in Medical Image Analysis," Medical Image Analysis, Vol. 42, pp. 60-88, 2017. https://doi.org/10.1016/j.media.2017.07.005 
  11. Haleem A et al., "Current status and applications of Artificial Intelligence (AI) in medical field: An overview," Current Medicine Research and Practice, Vol. 9, Issue 6, pp. 231-237, 2019. https://doi.org/10.1016/j.cmrp.2019.11.005 
  12. Report: Google AI improves lung cancer diagnosis accuracy, May 21, 2019 https://www.massdevice.com/report-google-ai-improves-lung-cancer-diagnosis-accuracy/ 
  13. Scott Mayer McKinney et al., "International evaluation of an AI system for breast cancer screening," Nature 577, pp 89-94, Vol 577, January 2020. https://doi.org/10.1038/s41586-019-1799-6 
  14. Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. "Generative adversarial nets," Adv Neural Inf Process Syst., 2014. 
  15. Zhao Z, Zhang Z, Chen T, Singh S, Zhang H., "Image augmentations for GAN training," ArXiv Preprint, arXiv:2006.02595, 2020. https://arxiv.org/abs/2006.02595 
  16. Gyubin Lee, Yebin Yoon, Sojin Ham, Hyun-Jin Bae, Wonsang You, "A CaseStudy on an Educational Model of Medical AI Using Chest X-ray Synthetized by GAN," Proceedings of the Korea Information Processing Society Conference, Vol. 28, No. 2, pp. 887-890, 2021. https://doi.org/10.3745/PKIPS.y2021m11a.887 
  17. Andr'es Anaya-Isaza, Leonel Mera-Jimenez, Martha Zequera-Diaz, "An overview of deep learning in medical imaging," Informatics in Medicine Unlocked, Vol. 26 2021. https://doi.org/10.1016/j.imu.2021.100723 
  18. Andreas S. Panayides, "AI in Medical Imaging Informatics: Current Challengesand Future Directions," IEEE J Biomed Health Inform, Vol. 24, No. 7, pp. 1837-1857, July 2020. https://doi.org/10.1109/JBHI.2020.2991043 
  19. Radfoed A., et al, "Unsupervised representation learning with deep convolutional generative adversarial networks," arXiv:1511.06434, 2015. https://doi.org/10.48550/arXiv.1511.06434 
  20. Nripendra Kumar Singh, Khalid Raza, "Medical Image Generation Using Generative Adversarial Networks: A Review," Health Informatics: A Computational Perspective in Healthcare, Studies in Computational Intelligence, Vol. 932, pp. 77-96, January 2021. https://doi.org/10.1007/978-981-15-9735-0_5 
  21. Yoon Sup Choi, "How Artificial Intelligence Will Revolutionize Healthcare: (2) IBM Watson's Ideals and Reality Challenges," AI, Big Data, Digital Healthcare, Precision Medicine, 13 June 2017.| https://www.yoonsupchoi.com/2017/06/13/ai-medicine-2/ 
  22. V.K. Bairagi1 A.M. Sapkal, "Automated region-based hybrid compression for digital imaging and communications in medicine magnetic resonance imaging images for telemedicine applications," IET Sci. Meas. Technol., Vol. 6, Iss. 4, pp. 247-253, 2012. https://doi.org/10.1049/iet-smt.2011.0152 
  23. Park, S. Y., A summary of medical image analysis, 2020. https://www.insilicogen.com/blog/358 
  24. Bahar Mansoori, Karen K. Erhard, Jeffrey L. Sunshine, "Picture Archiving and Communication System (PACS) Implementation, Integration & Benefits in an Integrated Health System," Academic Radiology, Volume 19, Issue 2, pp. 229-235, February 2012. https://doi.org/10.1016/j.acra.2011.11.009 
  25. Yoo Se Jong, Han Seong Soo, Mi-Hyang Jeon, Han Man Seok, "A Study on the Development Direction of Medical Image Information System Using Big Data and AI," KIPS Trans. Comp. and Comm. Sys., Vol.11, No.9 pp.317-322, 2022. https://doi.org/10.3745/KTCCS.2022.11.9.317 
  26. Razzak MI, Naz S, Zaib A., "Deep learning for medical image processing: Overview, challenges and the future," Classification in BioApps, Vol. 26, pp. 323-350, 2018. https://doi.org/10.1007/978-3-319-65981-7_12 
  27. Malone IB, Cash D, Ridgway GR, MacManus DG, Ourselin S, Fox NC, et al., "MIRIAD-Public release of a multiple time point Alzheimer's MR imaging dataset," NeuroImage, Vol. 70, pp. 33-36, 2013. https://doi.org/10.1016/j.neuroimage.2012.12.044 
  28. Moreira IC, Amaral I, Domingues I, Cardoso A, Cardoso MJ, Cardoso JS. "Inbreast: Toward a full-field digital mammographic database," Academic Radiology, Vol. 19, Issue 2, pp. 236-48, 2012. https://doi.org/10.1016/j.acra.2011.09.014 
  29. Datasets, https://paperswithcode.com/datasets?mod=medical 
  30. Laila El Jiani, Sanaa El Filali, El Habib Benlahmer, "Overcome medical image data scarcity by data augmentation techniques: A review," 2022 International Conference on Microelectronics (ICM), pp. 21-24, December 2022. https://doi.org/10.1109/ICM56065.2022.10005544 
  31. A. Adadi and M. Berrada, "Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)," IEEE Access, Vol. 6, pp. 52138-52160, 2018. https://doi.org/10.1109/ACCESS.2018.2870052 
  32. Defense Advanced Research Projects Agency, DARPA "Explainable Artificial Intelligence (XAI)," DARPA presentation, DARPA, Retrieved 17 July 2017. 
  33. D.E. Lee, C.S. Park, J.-W. Kang, M.W. Kim, "A review of Explainable AI Techniques in Medical Imaging," Journal of Biomedical Engineering Research, Vol. 43, Issue 4, pp. 259-270, 2022. http://dx.doi.org/10.9718/JBER.2022.43.4.259 
  34. M. T. Ribeiro, S. Singh, and C. Guestrin, "'Why Should I Trust You?': Explaining the Predictions of Any Classifier," Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 1135-1144, 2016. https://doi.org/10.1145/2939672.2939778 
  35. P. F. Felzenszwalb and D. P. Huttenlocher, "Efficient GraphBased Image Segmentation," International Journal of Computer Vision, Vol. 59, pp. 67-181, 2004. https://doi.org/10.1023/B:VISI.0000022288.19776.77 
  36. A Saha, EJ Bristy, MR Islam, R Afzal, SA Ridita, "LIME-based Explainable AI Models for Predicting Disease from Patient's Symptoms," 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), July 2023. https://doi.org/10.1109/ICCCNT56998.2023.10307223 
  37. S. Lundberg and S.-I. Lee, "A Unified Approach to Interpreting Model Predictions," Advances in neural information processing systems 30 (NIPS 2017), 2017. 
  38. S. Bach, A. Binder, G. Montavon, F. Klauschen, K.-R.Muller, and W. Samek, "On Pixel-Wise Explanations for Non Linear Classifier Decisions by Layer-Wise Relevance Propagation," PLOS ONE, 10(7), e0130140, 2015. https://doi.org/10.1371/journal.pone.0130140 
  39. B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, "Learning Deep Features for Discriminative Localization," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 2921-2929, 2016. 
  40. R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D.Parikh, and D. Batra, "Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization," Proceedings of the IEEE international conference on computer vision (ICCV), pp. 618-626, 2017. 
  41. D. Smilkov, N. Thorat, B. Kim, F. Viegas, and M. Wattenberg, "Smooth Grad: removing noise by adding noise," arXiv preprint arXiv:1706.03825, 2017. 
  42. Md. Sarwar Kamal, Aden Northcote, Linkon Chowdhury, Ruben Gonzalez Crespo, Nilanjan Dey, "Enrique Herrera-Viedma, Alzheimer's Patient Analysis Using Image and Gene Expression Data and Explainable-AI to Present Associa ted Genes," IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 70, pp. 1-7, 2021. https://doi.org/10.1109/TIM.2021.3107056 
  43. Sannidhi Rao, Shikha Mehta, Shreya Kulkarni, Harshal Dalvi, Neha Katre, Meera Narvekar, "A Study of LIME and SHAP Model Explainers for Autonomous Disease Predictions," 2022 IEEE Bombay Section Signature Conference (IBSSC), pp. 1-6, 2022. https://doi.org/10.1109/IBSSC56953.2022.10037324 
  44. I. Palatnik de Sousa, M. Maria Bernardes Rebuzzi Vellasco and E. Costa da Silva, "Local Interpretable Model-Agnostic Explanations for Classification of Lymph Node Metastases," Sensors (Basel), 19(13), 2969, 2019. https://doi.org/10.3390/s19132969 
  45. S. Knapic, A. Malhi, R. Saluja, and K. Framling, "Explainable Artificial Intelligence for Human Decision Support System in the Medical Domain," Machine Learning and Knowledge Extraction, 3(3), 740-770, 2021. https://doi.org/10.3390/make3030037 
  46. B. H. M. van der Velden, M. A. A. Ragusi, M. H. A. Janse,C. E. Loo, and K. G. A. Gilhuijs, "Interpretable deep learning regression for breast density estimation on MRI," SPIE Medical Imaging, Vol. 11314, 2020. https://doi.org/10.1117/12.2549003 
  47. F. Arcadu, F. Benmansour, A. Maunz, J. Willis, Z. Haskova,and M. Prunotto, "Deep learning algorithm predicts diabetic retinopathy progression in individual patients," npj Digit. Med., 2019. https://doi.org/10.1038/s41746-019-0172-3 
  48. IFRA SHAHEEN, NADEEM JAVAID, NABIL ALRAJEH, YOUSRA ASIM1, SHERAZ ASLAM, "Hi-Le and HiTCLe: Ensemble Learning Approaches for Early Diabetes Detection Using Deep Learning and Explainable Artificial Intelligence," IEEE Access, Vol. 12, pp. 66516-66538, May, 2024. https://doi.org/10.1109/ACCESS.2024.3398198 
  49. K. Young, G. Booth, B. Simpson, R. Dutton, and S. Shrapnel, "Deep Neural Network or Dermatologist?," Interpretability of Machine Intelligence in Medical Image Computing and Multimodal Learning for Clinical Decision Support (ML-CDS 2019, IMIMIC 2019), vol. 11797, 48-55, 2019. https://doi.org/10.1007/978-3-030-33850-3_6 
  50. H. Choi, Y. K. Kim, E. J. Yoon, J.-Y. Lee, and D. S. Lee, "Cognitive signature of brain FDG PET based on deep learning: domain transfer from Alzheimer's disease to Parkinson's disease," Eur J Nucl Med Mol Imaging, Vol. 47, pp. 403-412, 2020. https://doi.org/10.1007/s00259-019-04538-7 
  51. Z. Lin et al., "Multi-task learning for quality assessment of fetal head ultrasound images," Medical Image Analysis, Vol. 58, 101548, 2019. https://doi.org/10.1016/j.media.2019.101548 
  52. A. H. Ornek and M. Ceylan, "Explainable Artificial Intelligence (XAI): Classification of Medical Thermal Images of Neonates Using Class Activation Maps," Traitement du Signal, 38(5), pp.1271-1279, 2021. https://doi.org/10.18280/ts.380502 
  53. Z. Yang, L. Zhao, S. Wu, and C. Y.-C. Chen, "Lung Lesion Localization of COVID-19 From Chest CT Image: A Novel Weakly Supervised Learning Method," IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 6, pp. 1864-1872, 2021. https://doi.org/10.1109/JBHI.2021.3067465 
  54. M. U. Alam, J. R. Baldvinsson and Y. Wang, "Exploring LRP and Grad-CAM visualization to interpret multi-label-multi-class pathology prediction using chest radiography," 2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS), pp. 258-263, July, 2022. https://doi.org/10.1109/CBMS55023.2022.00052 
  55. Md. Rezaul Karim, Till Dohmen, Michael Cochez, Oya Beyan, Dietrich Rebholz-Schuhmann, Stefan Decker, "DeepCOVIDExplainer: Explainable COVID-19 Diagnosis from Chest X-ray Images," 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1034-1037, December 2020. https://doi.org/10.1109/BIBM49941.2020.9313304 
  56. M. Bohle, F. Eitel, M. Weygandt, and K. Ritter, "Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification," Front. Aging Neurosci., vol. 11, 2019. https://doi.org/10.3389/fnagi.2019.00194 
  57. I. Grigorescu, L. Cordero-Grande, A. David Edwards, J. V. Hajnal, M. Modat, and M. Deprez, "Investigating Image Registration Impact on Preterm Birth Classification: An Interpretable Deep Learning Approach," Smart Ultrasound Imaging and Perinatal, Preterm and Paediatric Image Analysis (PIPPI 2019, SUSI 2019), vol. 11798, pp. 104-112, 2019. https://doi.org/10.1007/978-3-030-32875-7_12 
  58. S. Dang and S. Chaudhury, "Novel relative relevance score for estimating brain connectivity from fMRI data using an explainable neural network approach," Journal of Neuroscience Methods, vol. 326, 1DKS08371, 2019. https://doi.org/10.1016/j.jneumeth.2019.108371