Development Trends and Future Prospects of Artificial Intelligence in Medical Image Processing

Cheng Luo

doi:10.62051/qc7fac76

Authors

Cheng Luo

DOI:

https://doi.org/10.62051/qc7fac76

Keywords:

AI; Medical Imaging; CNN; GAN; U-Net.

Abstract

In recent years, the momentum of the development of artificial intelligence has become increasingly strong, and the integration of artificial intelligence and various disciplines has also been applied to all aspects of human life. At the same time, in the medical industry related to human health, research on artificial intelligence + medicine has been carried out for many years. In the medical field, the processing of medical images already accounts for 80%-90% of the medical data sources, playing an extremely important role in the doctor's diagnosis and treatment plan formulation. However, a large amount of medical imaging data such as X-ray imaging, CT, MRI, etc. is handed over to doctors to manually identify disease lesions, which inevitably leads to some errors. In addition, the annual growth rate of the above medical images is roughly 30%, but the annual growth rate of radiologists is only 4%, which makes image analysis doctors face more severe analysis tasks. To address such needs, multiple models that apply deep learning technology to medical image analysis have emerged. This article will focus on analyzing the application of three deep learning models in the field of medical image analysis: convolutional neural networks (CNNs), generative adversarial networks (GANs), U-Net and its variants, and introduce their latest development status, analyze and compare their advantages and disadvantages, analyze the technical challenges that the model will encounter in practical applications, and make reasonable future prospects.

Downloads

Download data is not yet available.

References

[1] Y. Shoshan, R. Bakalo, F. Gilboa-Solomon, et al., Artificial Intelligence for Reducing Workload in Breast Cancer Screening with Digital Breast Tomosynthesis, Radiology 2022 Volume 303:1, 69-77.

[2] Q. Han, X. Qian, H. X. Xu, et al., DM-CNN: Dynamic Multi-scale Convolutional Neural Network with uncertainty quantification for medical image classification, Computers in Biology and Medicine, Volume 168, (2024)

[3] H. Ding, N. Huang, Y. Wu and X. Cui, LEGAN: Addressing Intraclass Imbalance in GAN-Based Medical Image Augmentation for Improved Imbalanced Data Classification, in IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1-14, 2024, Art no. 2517914.

[4] O. Ronneberger, P. Fischer and T. Brox, U-Net: Convolutional networks for biomedical image segmentation, Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent, pp. 234-241, 2015.

[5] D. W. Dai, C. X. Dong, Q. S. Yan, et al., I2U-Net: A dual-path U-Net with rich information interaction for medical image segmentation, Medical Image Analysis, Volume 97, (2024).

[6] H. N. Veena, K. K. Patil, P. Vanajakshi, et al. An Enhanced RNN-LSTM Model for Fundus Image Classification to Diagnose Glaucoma. SN COMPUT. SCI. 5, 514 (2024).

[7] L. Y. Fu, Y. Z. Chen, W. Ji, F. Yang, SSTrans-Net: Smart Swin Transformer Network for medical image segmentation, Biomedical Signal Processing and Control, Volume 91, (2024).

[8] S. Baba, G. X. Li, and T. Kamiya, Rigid Image Registration for Head MRI Based on 3DCNN Incorporated Global Information. In Proceedings of the 2024 9th International Conference on Biomedical Signal and Image Processing (ICBIP '24). Association for Computing Machinery, New York, NY, USA, 62–65 (2024).

[9] H. Gwon, I. Ahn, Y. Kim, et al., LDP-GAN: Generative adversarial networks with local differential privacy for patient medical records synthesis, Computers in Biology and Medicine, Volume 168, (2024)

[10] J. Chen, J. Mei, X. H. Li, et al., TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers, Medical Image Analysis, Volume 97, (2024)

[11] G. Q. Sun, Y. Z. Pan, W. K. Kong, et al, DA-TransUNet: integrating spatial and channel dual attention with transformer U-net for medical image segmentation, Frontiers in Bioengineering and Biotechnology, Volume 12 (2024)

[12] Q. Zhang, W. Qi, H. Zheng and X. Shen, CU-Net: A U-Net Architecture for Efficient Brain-Tumor Segmentation on BraTS 2019 Dataset, 2024 4th International Conference on Machine Learning and Intelligent Systems Engineering (MLISE), Zhuhai, China, 2024, pp. 255-258.

[13] P. Senapati, A. Basu, M. Deb, et al. Sharp dense U-Net: an enhanced dense U-Net architecture for nucleus segmentation. Int. J. Mach. Learn. & Cyber. 15, 2079–2094 (2024)