Enhancing Conjunctival Image-Based Anemia Classification Using Coordinate Attention on MobileNetV3-Small
DOI:
https://doi.org/10.63158/journalisi.v8i5.1796Keywords:
Anemia Classification, Conjunctival Imaging, MobileNetV3-Small, Coordinate Attention, Grad-CAM, Bootstrap BCa, Lightweight Medical ImagingAbstract
This study evaluates the integration of attention mechanisms (Efficient Channel Attention [ECA] and Coordinate Attention [CoordAtt]) into MobileNetV3-Small for preliminary conjunctival anemia screening. Using a single public dataset of 710 pediatric images from Ghana (CP-AnemiC dataset), the model was evaluated retrospectively via stratified 10-fold cross-validation (80%) and tested on a hold-out test set (20%). CoordAtt achieved the highest performance (Accuracy 78%, Sensitivity 84%, Specificity 70%, AUC 0.85), outperforming the Baseline (Accuracy 75%, Sensitivity 80%, Specificity 67%, AUC 0.80) and ECA (Accuracy 76%, Sensitivity 83%, Specificity 66%, AUC 0.81). A 95% Bootstrap BCa confidence interval test confirmed that the CoordAtt improvement over the Baseline is statistically significant for Accuracy, F1-Macro, Sensitivity, and AUC. Grad-CAM visualizations further showed more focused conjunctival localization. This improvement came with only a minimal increase in theoretical computational footprint (1.06M parameters, 0.0584 GFLOPs), keeping a lightweight profile similar to the Baseline (1.03M parameters, 0.0581 GFLOPs). These results show that CoordAtt improves classification performance without sacrificing computational efficiency, suggesting potential suitability for resource-constrained devices prior to clinical validation.
Downloads
References
[1] World Health Organization, “Global Anaemia Estimates 2025 Edition,” World Health Organization, 2025. Accessed: Oct. 12, 2025. [Online]. Available: https://www.who.int/data/gho/data/themes/topics/anaemia_in_women_and_children
[2] V. Haggenmüller et al., “Smartphone-based point-of-care anemia screening in rural Bihar in India,” Commun. Med., vol. 3, no. 1, p. 38, Mar. 2023, doi: 10.1038/s43856-023-00267-z.
[3] H. Yadav, D. Shah, S. Sayed, S. Horton, and L. F. Schroeder, “Availability of essential diagnostics in ten low-income and middle-income countries: results from national health facility surveys,” Lancet Glob. Health, vol. 9, no. 11, pp. e1553–e1560, Nov. 2021, doi: 10.1016/S2214-109X(21)00442-3.
[4] A. Al-Ganad, A. Al-Shahdhi, O. Al-Dhaifi, E. Hajeb, H. Hajeb, and A. Al-Motarreb, “Deploying medical AI in low-resource settings: a scoping review of challenges and strategies,” Front. Digit. Health, vol. 8, p. 1743634, Apr. 2026, doi: 10.3389/fdgth.2026.1743634.
[5] S. Ghosal, D. Das, V. Udutalapally, and P. N. Wasnik, “iNAP: A Hybrid Approach for NonInvasive Anemia-Polycythemia Detection in the IoMT,” ACM Trans. Comput. Healthc., vol. 3, no. 3, pp. 1–28, Jul. 2022, doi: 10.1145/3503466.
[6] Y. Chen, X. Hu, Y. Zhu, X. Liu, and B. Yi, “Real-time non-invasive hemoglobin prediction using deep learning-enabled smartphone imaging,” BMC Med. Inform. Decis. Mak., vol. 24, no. 1, p. 187, Jul. 2024, doi: 10.1186/s12911-024-02585-1.
[7] Muljono, S. A. Wulandari, H. A. Azies, M. Naufal, W. A. Prasetyanto, and F. A. Zahra, “Breaking Boundaries in Diagnosis: Non-Invasive Anemia Detection Empowered by AI,” IEEE Access, vol. 12, pp. 9292–9307, 2024, doi: 10.1109/ACCESS.2024.3353788.
[8] P. Appiahene, K. Chaturvedi, J. W. Asare, E. T. Donkoh, and M. Prasad, “CP-AnemiC: A conjunctival pallor dataset and benchmark for anemia detection in children,” Med. Nov. Technol. Devices, vol. 18, p. 100244, Jun. 2023, doi: 10.1016/j.medntd.2023.100244.
[9] A. S. Babu and S. Parthasarathy, “Computer-Vision–Based Non-Invasive Detection of Anemia from Medical Images: A Scoping Review of Artificial Intelligence with Applications in Drug Delivery and Therapeutic Monitoring,” Int. J. Drug Deliv. Technol., vol. 16, no. 2, Feb. 2026, doi: 10.25258/ijddt.16.2.23.
[10] O. Ramos-Soto, J. Ramos-Frutos, E. Perez-Zarate, D. Oliva, S. J. Mousavirad, and S. E. Balderas-Mata, “Non-invasive anemia detection from conjunctiva and sclera images using vision transformer with attention map explainability,” Sci. Rep., vol. 15, no. 1, p. 44142, Dec. 2025, doi: 10.1038/s41598-025-32343-w.
[11] E.-T. Lin et al., “Deep Learning-Based Model for Non-invasive Hemoglobin Estimation via Body Parts Images: A Retrospective Analysis and a Prospective Emergency Department Study,” J. Imaging Inform. Med., vol. 38, no. 2, pp. 775–792, Aug. 2024, doi: 10.1007/s10278-024-01209-4.
[12] J. H. Fuentes-Beingolea, F. Palomino-Quispe, J. C. Herrera-Levano, W. Vargas-Mateos, R. Florez, and A. B. Alvarez, “Illumination-Robust Conjunctival Image Preprocessing for Accurate Segmentation and Anemia Detection Using Deep Learning,” Int. J. Online Biomed. Eng. IJOE, vol. 21, no. 07, pp. 106–124, Jun. 2025, doi: 10.3991/ijoe.v21i07.54439.
[13] H.-I. Liu et al., “Lightweight Deep Learning for Resource-Constrained Environments: A Survey,” ACM Comput. Surv., vol. 56, no. 10, pp. 1–42, Oct. 2024, doi: 10.1145/3657282.
[14] J. H. Fuentes-Beingolea and F. Palomino-Quispe, “Adaptive Contrastive Learning in Vision Transformer for Non-Invasive Hemoglobin Estimation From Conjunctival Images,” IEEE Access, vol. 13, pp. 210257–210270, 2025, doi: 10.1109/ACCESS.2025.3638640.
[15] A. Howard et al., “Searching for MobileNetV3,” in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South): IEEE, Oct. 2019, pp. 1314–1324. doi: 10.1109/ICCV.2019.00140.
[16] Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, and Q. Hu, “ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA: IEEE, Jun. 2020, pp. 11531–11539. doi: 10.1109/CVPR42600.2020.01155.
[17] Q. Hou, D. Zhou, and J. Feng, “Coordinate Attention for Efficient Mobile Network Design,” in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA: IEEE, Jun. 2021, pp. 13708–13717. doi: 10.1109/CVPR46437.2021.01350.
[18] F. García Fernández, P. De Palacios, A. García-Iruela, and L. G. Esteban, “Using Bootstrapping to Determine Artificial Neural Network Confidence Intervals—Case Study of Particleboard Internal Bond Determined from Production Data,” Appl. Sci., vol. 15, no. 8, p. 4554, Apr. 2025, doi: 10.3390/app15084554.
[19] Justice Williams Asare, “CP-AnemiC (A Conjunctival Pallor) Dataset from Ghana.” Mendeley, Mar. 02, 2023. doi: 10.17632/M53VZ6B7FX.1.
[20] T. J. Bradshaw, Z. Huemann, J. Hu, and A. Rahmim, “A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging,” Radiol. Artif. Intell., vol. 5, no. 4, p. e220232, Jul. 2023, doi: 10.1148/ryai.220232.
[21] S. Prusty, S. Patnaik, and S. K. Dash, “SKCV: Stratified K-fold cross-validation on ML classifiers for predicting cervical cancer,” Front. Nanotechnol., vol. 4, p. 972421, Aug. 2022, doi: 10.3389/fnano.2022.972421.
[22] E. Goceri, “Medical image data augmentation: techniques, comparisons and interpretations,” Artif. Intell. Rev., vol. 56, no. 11, pp. 12561–12605, Nov. 2023, doi: 10.1007/s10462-023-10453-z.
[23] L. Cui et al., “Towards Reliable Healthcare Imaging: A Multifaceted Approach in Class Imbalance Handling for Medical Image Segmentation,” Interdiscip. Sci. Comput. Life Sci., vol. 17, no. 3, pp. 614–633, Sep. 2025, doi: 10.1007/s12539-025-00726-2.
[24] S. H. Park and K. Han, “Methodologic Guide for Evaluating Clinical Performance and Effect of Artificial Intelligence Technology for Medical Diagnosis and Prediction,” Radiology, vol. 286, no. 3, pp. 800–809, Mar. 2018, doi: 10.1148/radiol.2017171920.
[25] G. S. Collins et al., “TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods,” BMJ, vol. 385, p. e078378, Apr. 2024, doi: 10.1136/bmj-2023-078378.
[26] X. Chen et al., “Recent advances and clinical applications of deep learning in medical image analysis,” Med. Image Anal., vol. 79, p. 102444, Jul. 2022, doi: 10.1016/j.media.2022.102444.
[27] B. H. M. Van Der Velden, H. J. Kuijf, K. G. A. Gilhuijs, and M. A. Viergever, “Explainable artificial intelligence (XAI) in deep learning-based medical image analysis,” Med. Image Anal., vol. 79, p. 102470, Jul. 2022, doi: 10.1016/j.media.2022.102470.
[28] 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,” in 2017 IEEE International Conference on Computer Vision (ICCV), Venice: IEEE, Oct. 2017, pp. 618–626. doi: 10.1109/ICCV.2017.74.
[29] K. Borys et al., “Explainable AI in medical imaging: An overview for clinical practitioners – Beyond saliency-based XAI approaches,” Eur. J. Radiol., vol. 162, p. 110786, May 2023, doi: 10.1016/j.ejrad.2023.110786.
[30] H. Chen, C. Gomez, C.-M. Huang, and M. Unberath, “Explainable medical imaging AI needs human-centered design: guidelines and evidence from a systematic review,” Npj Digit. Med., vol. 5, no. 1, p. 156, Oct. 2022, doi: 10.1038/s41746-022-00699-2.
[31] W. Du, “When +1% is Not Enough: A Paired Bootstrap Protocol for Evaluating Small Improvements,” in Advances in Knowledge Discovery and Data Mining, vol. 16597, R. C.-W. Wong, H. Tong, H. Lu, J. Kwok, F. Salim, Y. Song, and M. L. Yiu, Eds., in Lecture Notes in Computer Science, vol. 16597. , Singapore: Springer Nature Singapore, 2026, pp. 519–531. doi: 10.1007/978-981-92-1300-9_41.
[32] T. C. Hesterberg, “What Teachers Should Know About the Bootstrap: Resampling in the Undergraduate Statistics Curriculum,” Am. Stat., vol. 69, no. 4, pp. 371–386, Oct. 2015, doi: 10.1080/00031305.2015.1089789.
[33] J. Carpenter and J. Bithell, “Bootstrap confidence intervals: when, which, what? A practical guide for medical statisticians,” Stat. Med., vol. 19, no. 9, pp. 1141–1164, May 2000, doi: 10.1002/(SICI)1097-0258(20000515)19:9<1141::AID-SIM479>3.0.CO;2-F.
[34] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA: IEEE, Jun. 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Author's Declaration
- The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
- The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
- If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
- The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights
