An analysis of decipherable red blood cell abnormality detection under federated environment leveraging XAI incorporated deep learning.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
27 Oct 2024
27 Oct 2024
Historique:
received:
08
05
2024
accepted:
14
10
2024
medline:
28
10
2024
pubmed:
28
10
2024
entrez:
28
10
2024
Statut:
epublish
Résumé
In recent times, automated detection of diseases from pathological images leveraging Machine Learning (ML) models has become fairly common, where the ML models learn detecting the disease by identifying biomarkers from the images. However, such an approach requires the models to be trained on a vast amount of data, and healthcare organizations often tend to limit access due to privacy concerns. Consequently, collecting data for traditional centralized training becomes challenging. These privacy concerns can be handled by Federation Learning (FL), which builds an unbiased global model from local models trained with client data while maintaining the confidentiality of local data. Using FL, this study solves the problem of centralized data collection by detecting deformations in images of Red Blood Cells (RBC) in a decentralized way. To achieve this, RBC data is used to train multiple Deep Learning (DL) models, and among the various DL models, the most efficient one is considered to be used as the global model inside the FL framework. The FL framework works by copying the global model's weight to the client's local models and then training the local models in client-specific devices to average the weights of the local model back to the global model. In the averaging process, direct averaging is performed and alongside, weighted averaging is also done to weigh the individual local model's contribution according to their performance, keeping the FL framework immune to the effects of bad clients and attacks. In the process, the data of the client remains confidential during training, while the global model learns necessary information. The results of the experiments indicate that there is no significant difference in the performance of the FL method and the best-performing DL model, as the best-performing DL model reaches an accuracy of 96% and the FL environment reaches 94%-95%. This study shows that the FL technique, in comparison to the classic DL methodology, can accomplish confidentiality secured RBC deformation classification from RBC images without substantially diminishing the accuracy of the categorization. Finally, the overall validity of the classification results has been verified by employing GradCam driven Explainable AI techniques.
Identifiants
pubmed: 39463436
doi: 10.1038/s41598-024-76359-0
pii: 10.1038/s41598-024-76359-0
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
25664Subventions
Organisme : Princess Nourah bint Abdulrahman University Researchers Supporting Project number (PNURSP2024R506), Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.
ID : PNURSP2024R506
Informations de copyright
© 2024. The Author(s).
Références
Rodgers, G. P. & Young, N. S. The Bethesda Handbook of Clinical Hematology (Lippincott Williams & Wilkins, 2013).
Bain, B. J. Diagnosis from the blood smear. N. Engl. J. Med. 353, 498–507 (2005).
doi: 10.1056/NEJMra043442
pubmed: 16079373
Dacie, J. V. Dacie and Lewis Practical Haematology (Elsevier Health Sciences, 2006).
Siniosoglou, I. et al. Federated intrusion detection in NG-IOT healthcare systems: An adversarial approach. In ICC 2021-IEEE International Conference on Communications. 1–6 (IEEE, 2021).
Yang, W., Zhang, Y., Ye, K., Li, L. & Xu, C.-Z. FFD: A federated learning based method for credit card fraud detection. In Big Data—BigData 2019: 8th International Congress, Held as Part of the Services Conference Federation, SCF 2019, San Diego, CA, USA, June 25–30, 2019, Proceedings 8. 18–32 (Springer, 2019).
Guan, H., Yap, P.-T., Bozoki, A. & Liu, M. Federated learning for medical image analysis: A survey. Pattern Recognit. 110424 (2024).
Litjens, G. et al. A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017).
doi: 10.1016/j.media.2017.07.005
pubmed: 28778026
Varghese, N. Machine learning techniques for the classification of blood cells and prediction of diseases. Int. J. Comput. Sci. Eng. 9, 66–75 (2020).
Ko, E. et al. Early red blood cell abnormalities as a clinical variable in sepsis diagnosis. Clin. Hemorheol. Microcirc. 70, 355–363 (2018).
doi: 10.3233/CH-180430
pubmed: 30320561
Lippi, G. & Plebani, M. Recent developments and innovations in red blood cells diagnostics. J. Lab. Precis. Med. 3 (2018).
Tomari, R., Zakaria, W. N. W., Jamil, M. M. A., Nor, F. M. & Fuad, N. F. N. Computer aided system for red blood cell classification in blood smear image. Proc. Comput. Sci. 42, 206–213 (2014).
doi: 10.1016/j.procs.2014.11.053
Qiu, W. et al. Multi-label detection and classification of red blood cells in microscopic images. In 2020 IEEE International Conference on Big Data (Big Data). 4257–4263 (IEEE, 2020).
Xu, M. et al. A deep convolutional neural network for classification of red blood cells in sickle cell anemia. PLoS Comput. Biol. 13, e1005746 (2017).
doi: 10.1371/journal.pcbi.1005746
pubmed: 29049291
pmcid: 5654260
Reza, M. T., Dipto, S. M., Parvez, M. Z., Barua, P. D. & Chakraborty, S. A power efficient solution to determine red blood cell deformation type using binarized densenet. In International Conference on Advances in Computing Research. 246–256 (Springer, 2023).
Aliyu, H. A., Razak, M. A. A., Sudirman, R. & Ramli, N. A deep learning Alexnet model for classification of red blood cells in sickle cell anemia. Int. J. Artif. Intell. 9, 221–228 (2020).
Alzubaidi, L., Fadhel, M. A., Al-Shamma, O., Zhang, J. & Duan, Y. Deep learning models for classification of red blood cells in microscopy images to aid in sickle cell anemia diagnosis. Electronics 9, 427 (2020).
doi: 10.3390/electronics9030427
Khalil, A. J. & Abu-Naser, S. S. Diagnosis of blood cells using deep learning. Int. J. Acad. Eng. Res. (IJAER) 6, 69–84 (2022).
Tyas, D. A., Ratnaningsih, T., Harjoko, A. & Hartati, S. Erythrocyte (red blood cell) dataset in thalassemia case. Data Brief 41, 107886 (2022).
doi: 10.1016/j.dib.2022.107886
pubmed: 35242901
pmcid: 8857444
Landis-Piwowar, K., Landis, J. & Keila, P. Clinical Laboratory Hematology . 3rd ed. 154–177 (New Jersey Pearson, 2015).
Manchanda, N. Anemias: Red Blood Morphology and Approach to Diagnosis. 284–296 (Saunders, 2015).
Bosman, G. J. Disturbed red blood cell structure and function: An exploration of the role of red blood cells in neurodegeneration. Front. Med. 5, 198 (2018).
doi: 10.3389/fmed.2018.00198
Andolfo, I., Russo, R., Gambale, A. & Iolascon, A. Hereditary stomatocytosis: An underdiagnosed condition. Am. J. Hematol. 93, 107–121 (2018).
doi: 10.1002/ajh.24929
pubmed: 28971506
Parab, M. A. & Mehendale, N. D. Red blood cell classification using image processing and CNN. SN Comput. Sci. 2, 70 (2021).
doi: 10.1007/s42979-021-00458-2
Dinh, N. H., Cheanh Beaupha, S. M. & Tran, L. T. A. The validity of reticulocyte hemoglobin content and percentage of hypochromic red blood cells for screening iron-deficiency anemia among patients with end-stage renal disease: A retrospective analysis. BMC Nephrol. 21, 1–7 (2020).
Abadi, M. et al. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016).
GitHub—keras-team/keras: Deep learning for humans—github.com. https://github.com/keras-team/keras . Accessed 01 Feb 2024.
Deng, J. et al. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition. 248–255 (IEEE, 2009).
Aledhari, M., Razzak, R., Parizi, R. M. & Saeed, F. Federated learning: A survey on enabling technologies, protocols, and applications. IEEE Access 8, 140699–140725 (2020).
doi: 10.1109/ACCESS.2020.3013541
pubmed: 32999795
pmcid: 7523633
Zhang, W. et al. Blockchain-based federated learning for device failure detection in industrial IOT. IEEE Internet Things J. 8, 5926–5937 (2020).
doi: 10.1109/JIOT.2020.3032544
Sarma, K. V. et al. Federated learning improves site performance in multicenter deep learning without data sharing. J. Am. Med. Inform. Assoc. 28, 1259–1264 (2021).
doi: 10.1093/jamia/ocaa341
pubmed: 33537772
pmcid: 8200268
Zhang, W. et al. Dynamic-fusion-based federated learning for covid-19 detection. IEEE Internet Things J. 8, 15884–15891 (2021).
doi: 10.1109/JIOT.2021.3056185
pubmed: 35663640
Aich, S. et al. Protecting personal healthcare record using blockchain & federated learning technologies. In 2022 24th International Conference on Advanced Communication Technology (ICACT). 109–112 (IEEE, 2022).
Stripelis, D., Ambite, J. L., Lam, P. & Thompson, P. Scaling neuroscience research using federated learning. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI). 1191–1195 (IEEE, 2021).
Duan, Q. et al. Combining federated learning and edge computing toward ubiquitous intelligence in 6g network: Challenges, recent advances, and future directions. In IEEE Communications Surveys & Tutorials (2023).
Zhou, F., Hu, S., Du, X., Wan, X. & Wu, J. A lightweight neural network model for disease risk prediction in edge intelligent computing architecture. Future Internet 16, 75 (2024).
doi: 10.3390/fi16030075
Selvaraju, R. R. et al. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision. 618–626 (2017).
Tyas, D. A., Hartati, S., Harjoko, A. & Ratnaningsih, T. Morphological, texture, and color feature analysis for erythrocyte classification in thalassemia cases. IEEE Access 8, 69849–69860 (2020).
doi: 10.1109/ACCESS.2020.2983155