1. MMC
  2. All Volumes and Issues
  3. Volume 11, Number 3, 2024
  4. Enhancing the vision graph model by elevating the precision diagnostics with attention and convolutions in medical imaging

Enhancing the vision graph model by elevating the precision diagnostics with attention and convolutions in medical imaging

MMC.
2024;
Volume 11, Number 3
: pp. 773–784
https://doi.org/10.23939/mmc2024.03.773
Received: January 20, 2024
Revised: August 16, 2024
Accepted: August 17, 2024

Khaider Y., Rahhali D., En Nahnahi N.  Enhancing the vision graph model by elevating the precision diagnostics with attention and convolutions in medical imaging.  Mathematical Modeling and Computing. Vol. 11, No. 3, pp. 773–784 (2024)

Authors:
  1. Y. Khaider
  2. D. Rahhali
  3. N. En Nahnahi
1
Sidi Mohamed Ben Abdellah University, Faculty of Sciences Dhar EL Mehraz, LISAC Laboratory, Fez
2
Sidi Mohamed Ben Abdellah University, Faculty of Sciences Dhar EL Mehraz, LISAC Laboratory, Fez
3
LISAC Laboratory, Faculty of Sciences Dhar El Mahraz, Sidi Mohamed Ben Abdellah University

The COVID-19 showed us that rapid and accurate diagnostics is a necessity.  Therefore, researchers began to implement deep learning models that can help the doctors to reach faster and reliable results, but there are more development to be done.  In our research paper, we introduced an innovative approach to enhance the Vision Graph model's accuracy for better results.  Our method exploits the strength of the ConvMixer architecture and Attention mechanism.  We start by utilizing Depthwise convolution and Pointwise convolution to capture spatial information in detail while reducing computational complexity of the model.  Additionally, we added a hybrid attention module in which we combine the Convolution-based attention with Self-attention to boost the model's patterns identifying ability. We tested these enhancements on the COVID radiology dataset and demonstrated that our approach can help models be more accurate in their results.

deep learning
medical imaging
attention
CBAM
CNN
vision GNN
  1. Pawar D. D., Patil W. D., Raut D. K.  Fractional-order mathematical model for analysing impact of quarantine on transmission of COVID-19 in India.  Mathematical Modeling and Computing.  8 (2), 253–266 (2021).
  2. Yavorska O., Bun R.  Spatial analysis of COVID-19 spread in Europe using "center of gravity" concept.  Mathematical Modeling and Computing.  9 (1), 130–142 (2022).
  3. Khoroshchuk D., Liubinskyi B. B.  Machine learning in lung lesion detection caused by certain diseases.  Mathematical Modeling and Computing.  10 (4), 1084–1092 (2023).
  4. Wang L., Lin Z. Q., Wong A.  COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images.  Scientific Reports.  10, 19549 (2020).
  5. Rajpurkar P., Irvin J., Zhu K., Yang B., Mehta H., Duan T., Ding D., Bagul A., Ball R. L., Langlotz C., Shpanskaya K., Lungren M. P., Ng A. Y.  CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning.  Preprint arXiv:1711.05225 (2017).
  6. Wynants L., Van Calster B., Collins G. S., Riley D. K., Heinze G., Schuit E., Bonten M. M. J., Damen J. A. A., Debray T. P. A., De Vos M., Dhiman P., Haller M. C.  Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal.  The BMJ.  369, m1328 (2020).
  7. Dosovitskiy A, Beyer L., Kolesnikov A., Weissenborn D., Zhai X., Unterthiner T., Dehghani M., Minderer M., Heigold G., Gelly S., Uszkoreit J., Houlsby N.  An Image is Worth $16\times16$ Words: Transformers for Image Recognition at Scale.  International Conference on Learning Representations.  1–21 (2021).
  8. Han K., Wang Y., Guo J., Tang Y., Wu E.  Vision GNN: an image is worth graph of nodes.  NIPS'22: Proceedings of the 36th International Conference on Neural Information Processing System.  603 (2022).
  9. Trockman A., Kolter J. Z.  Patches Are All You Need?  Proceedings of the International Conference on Learning Representations (ICLR). (2022).
  10. Goldman S. A., Wong H. T.  Neural Networks for Graph Recognition.  Proceedings of the International Conference on Neural Networks (ICNN).  (1996).
  11. Kipf T. N., Wellin M.  Semi-Supervised Classification with Graph Convolutional Networks.  Proceedings of the International Conference on Learning Representations (ICLR). (2017).
  12. Veličkovié P., Cucurull G., Casano A., Romero A., Liò P., Bengio Y.  Graph Attention Networks.  Proceedings of the International Conference on Learning Representations (ICLR). (2018).
  13. Hamilton W. L., Ying R., Leskovec J.  Inductive Representation Learning on Large Graphs.  Advances in Neural Information Processing Systems (NeurIPS). (2017).
  14. Xu K., Hu W., Leskovec J., Jegelka S.  How Powerful are Graph Neural Networks?  The Seventh International Conference on Learning Representations (ICLR). (2019).
  15. Wang Y., Sun Y., Liu Z., Sarma S. E., Bronstein M. M., Solomon J. M.  Dynamic Graph CNN for Learning on Point Clouds.  ACM Transactions on Graphics.  38 (5), 146 (2019).
  16. Zhang T., Liu Y., Chen X., Huang X., Zhu F., Zheng X.  GPS: A Policy-driven Sampling Approach for Graph Representation Learning.  Preprint arXiv:2112.14482 (2021).
  17. Yu B., Yin H., Zhu Z.  Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting.  Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. 3634–3640 (2018).
  18. Zeng H., Zhou H., Srivastava A., Kannan R., Prasanna V.  GraphSAINT: Graph Sampling Based Inductive Learning Method.  International Conference on Learning Representations. (2020).
  19. Yun S., Jeong M., Kim R., Kang J., Kim H. J.  Graph Transformer Networks.  Advances in Neural Information Processing Systems (NeurIPS). (2019).
  20. Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A. N., Kaiser L., Polosukhin I.  Attention Is All You Need.  Advances in Neural Information Processing Systems (NeurIPS). (2017).
  21. Klambauer G., Unterthiner T., Mayr A., Hochreiter S.  Self-Normalizing Neural Networks.  Advances in Neural Information Processing Systems (NeurIPS). (2017).
  22. Tanno R., Arulkumaran K., Alexander D. C., Criminisi A., Nori A.  Adaptive Neural Trees.  Proceedings of the 36th International Conference on Machine Learning.  97, 6166–6175 (2019).
  23. Woo S., Park J., Lee J. Y., Kweon I. S.  CBAM: Convolutional Block Attention Module.  Computer Vision – ECCV 2018.  3–19 (2018).
  24. https://blog.paperspace.com/attention-mechanisms-in-computer-vision-cbam/.
  25. https://www.kaggle.com/tawsifurrahman/covid19-radiography-database.
  26. Kumar S., Mallik A.  COVID-19 Detection from Chest X-rays Using Trained Output Based Transfer Learning Approach.  Neural Processing Letters.  55, 2405–2428 (2022).