Discussion on Using RNN Model to Optimize the Accuracy and Efficiency of Medical Image Recognition

Minkang Zhang

doi:10.71222/9vshb795

Authors

Minkang Zhang Clinical Diagnostics Group (CDG) Software Team, Bio-Rad Laboratories, Hercules, CA, 94547, USA Author

DOI:

https://doi.org/10.71222/9vshb795

Keywords:

medical image recognition, precision, efficiency

Abstract

With the continuous development of artificial intelligence technology, especially represented by deep learning, recurrent neural networks have made revolutionary breakthroughs in medical image recognition. This paper first introduces the concept of RNN pattern and its application in medical image recognition. By analyzing various applications of RNN in medical image classification, we explore how to improve the accuracy and computational efficiency of medical image recognition by optimizing the RNN model. Specifically, the gating mechanism, convolutional neural network (CNN) construction, lightweight technology and other optimization strategies, multi-modal learning and attention mechanism input are discussed. Finally, the prospects and challenges of the RNN model in medical image recognition are summarized, and the future research directions in this field are also discussed.

References

1. K. R. Singh and S. Dash, “Detection of arrhythmia from ECG signal using bat algorithm-based deep neural network,” in Proc. Int. Conf. Adv. Comput. Intell. Eng., Singapore: Springer Nature Singapore, 2022. doi: 10.1007/978-981-99-5015-7_8.

2. X.-L. Wang, W.-X. Xie, and L.-Q. Li, “Structure identification of recursive TSK particle filtering via type-2 intuitionistic fuzzy decision,” Int. J. Fuzzy Syst., vol. 23, no. 5, pp. 1294–1312, 2021, doi: 10.1007/s40815-020-01021-6.

3. T. Gao, L. Huang, S. Gao and K. Wang, "SSA: A Uniformly Recursive Bidirection-Sequence Systolic Sorter Array," IEEE Trans. Parallel Distrib. Syst., vol. 35, no. 10, pp. 1721-1734, 2024, doi: 10.1109/TPDS.2024.3434332.

4. M. Cobbinah and A. Alnaggar, “An attention encoder-decoder RNN model with teacher forcing for predicting consumer price index,” J. Data Inf. Manag., vol. 6, no. 1, pp. 65–83, 2024, doi: 10.1007/s42488-024-00114-3.

5. R. K. Behera et al., “Co-LSTM: Convolutional LSTM model for sentiment analysis in social big data,” Inf. Process. Manage., vol. 58, no. 1, p. 102435, 2021, doi: 10.1016/j.ipm.2020.102435.