Research Article | ![]()
Development of a Low-Cost Automated Papanicolaou Slide Stainer with Preliminary Image-Based Cellular Localization
Author(s): Keeradit Saipattalung1, Surasee Prahmkaew 2, and Pasura Aungkulanon 3
Published In : International Journal of Electrical and Electronics Research (IJEER) Volume 14, Issue 3
Publisher : FOREX Publication
Published : 30 September 2026
e-ISSN : 2347-470X
Page(s) : 852-862
Abstract
This study developed and evaluated a low-cost automated Papanicolaou slide stainer integrated with a preliminary image-processing module for localizing suspicious cellular regions. The prototype used a Raspberry Pi 4 to control three-axis stepper motors, a servo-driven slide-rack gripper, and a 5-inch touchscreen. Its aluminum-profile structure accommodated nine reagent jars and up to ten slides per cycle, although two slides per cycle were used during prototype testing. In ten experimental cycles, touchscreen start, stop, and position-selection commands achieved 100% success, while the automatic staining sequence achieved 90%. The X-axis operated successfully in all trials, whereas the Y- and Z-axes each achieved 90% success. The mean staining time was 67.04 min per cycle. The prototype’s staining quality received an overall mean score of 4.38 from expert evaluators. The image-processing workflow employed contrast enhancement, adaptive thresholding, watershed segmentation, and morphological feature extraction. Evaluation using 120 test images yielded an accuracy of 81.67%, sensitivity of 79.17%, specificity of 83.33%, precision of 76.00%, and F1-score of 77.55%. The prototype cost was approximately USD 780, substantially lower than that of an imported commercial slide stainer, and its break-even point was estimated at 76 tests, and 79 tests when maintenance costs were included. The findings support preliminary engineering and economic feasibility under the reported prototype conditions. The staining-quality score provides descriptive evidence only, and the localization metrics represent internal image-level agreement. Full-load endurance testing and external clinical validation remain necessary before routine laboratory application.
Keywords: Development, Evaluation, Low-Cost Medical Technology, Papanicolaou Staining, Image Processing, Break-Even Point.
Keeradit Saipattalung,Faculty of Industrial Technology, Phranakhon Rajabhat University, Bangkok, Thailand; Email: keeradit@pnru.ac.th
Surasee Prahmkaew, Faculty of Industrial Technology, Phranakhon Rajabhat University, Bangkok, Thailand; Email: surasee.p@pnru.ac.th
Pasura Aungkulanon, Faculty of Engineering, King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand; Email: pasura.a@eng.kmutnb.ac.th
-
[1]Golnabi, & Asadpour, A. (2007). Design and application of industrial machine vision systems. Robotics and Computer-Integrated Manufacturing, 23(6), pp. 630–637. https://doi.org/10.1016/j.rcim.2007.02.005
-
[2]Farhat & Nasiruddin M. (2022). Computer Vision based Surveillance System. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 10(10), pp. 1491–1494, https://doi.org/10.22214/ijraset.2022.41512
-
[3] Chung, W., Kim, S., Choi, M., Choi, J., Kim, H., Moon, C., & Song, J. (2009). Safe navigation of a mobile robot considering visibility of environment. IEEE Transactions on Industrial Electronics, 56(10), pp. 3941–3950. https://doi.org/10.1109/TIE.2009.2025293
-
[4] Channappa, A., Praveena, K. B., & Patrer, D. (2022). IoT-enabled smart surveillance: Adaptive image processing for security applications. World Journal of Advanced Research and Reviews, 15(3), pp. 513–525. https://doi.org/10.30574/wjarr.2022.15.3.0724
-
[5] Marković, D., Stamenković, Z., Đorđević, B., &Randić, S. (2024). Image processing for smart agriculture applications using cloud-fog computing. Sensors, 24(18), pp. 5965. https://doi.org/10.3390/s24185965
-
[6] Zhu, N., Liu, X., Liu, Z., Hu, K., Wang, Y., Tan, J., Huang, M., Zhu, Q., Ji, X., Jiang, Y., & Guo, Y. (2018). Deep learning for smart agriculture: Concepts, tools, applications, and opportunities. International Journal of Agricultural and Biological Engineering, 11(4), pp. 32–44. https://doi.org/10.25165/j.ijabe.20181104.4475
-
[7] Madasamy Raja, G., Deenadhayalan, R., Krishnamoorthy, N., &Anandamurugan, S. (2022). An image processing method for identifying plant diseases based on changes in leaf morphology. Neuro Quantology, 20(9), pp. 2792–2804. https://doi.org/10.14704/nq.2022.20.9.NQ44325
-
[8] Hu, S., Lu, R., Zhu, Y., Zhu, W., Jiang, H., & Bi, S. (2023). Application of medical image navigation technology in minimally invasive puncture robot. Sensors, 23(16), pp. 7196. https://doi.org/10.3390/s23167196
-
[9] Li, C., Zhang, G., Zhao, B., Xie, D., Du, H., Duan, X., Hu, Y., & Zhang, L. (2024). Advances of surgical robotics: image-guided classification and application. National Science Review, 11, nwae186. https://doi.org/10.1093/nsr/nwae186
-
[10] Bhole, M., Bamane, R., Jadhav, R., More, P., & Ture, R. (2021). PLC based object sorting system using image processing. International Journal of Scientific Research in Engineering and Management, 5(5), pp. 1–5.
-
[11] Farisqi, B. A., & Prahara, A. (2022). Guava fruit detection and classification using mask region-based convolutional neural network. Buletin Ilmiah Sarjana Teknik Elektro, 4(3), pp. 186–193. https://doi.org/10.12928/biste.v4i3.7412
-
[12] Lawal, O. M., & Zhao, H. (2021). YOLOFig detection model development using deep learning. IET Image Processing, 15(13), pp. 3071–3079. https://doi.org/10.1049/ipr2.12293
-
[13] Biradar, M. S., Shiparamatti, B. G., & Patil, P. M. (2021). Fabric defect detection using deep convolutional neural network. Optical Memory and Neural Networks, 30(3), 250–256. https://doi.org/10.3103/S1060992X21030024
-
[14] Biradar, M. S., Sheeparamatti, B. G., & Patil, P. M. (2018). Defect detection and classification in patterned fabric using variational mode image decomposition and neural network. Journal of Emerging Technologies and Innovative Research, 5(10), 769–774. https://www.jetir.org/papers/JETIR1810519.pdf
-
[15] Alajrami, E., Ashqar, B. A. M., Abu-Nasser, B. S., Khalil, A. J., Musleh, M. M., Barhoom, A. M., & Abu-Naser, S. S. (2019). Handwritten signature verification using deep learning. International Journal of Academic Multidisciplinary Research, 3(12), 39–44. https://www.ijeais.org/ijamr
-
[16] Sadati Salimi, S. M., Baleghi, Y., & Salehi, E. (2026). Printed circuit board quality control using image processing and modified YOLO structures. International Journal of Engineering, Transactions C: Aspects, 39(9), 2204–2212. https://doi.org/10.5829/ije.2026.39.09c.11
-
[17] Sheeba, A., Santhosh Kumar, P., Ramamoorthy, M., & Sasikala, S. (2023). Microscopic image analysis in breast cancer detection using ensemble deep learning architectures integrated with web of things. Biomedical Signal Processing and Control, 79, 104048. https://doi.org/10.1016/j.bspc.2022.104048
-
[18] Zhang, L., Lei, J., Xia, J., & Cai, A. (2022). Diagnostic value of combination of exfoliative cytology with CA125, CEA, NSE, CYFRA21-1 and CA15-3 for lung cancer. Revista Română de Medicină de Laborator, 30(4), 389–398. https://doi.org/10.2478/rrlm-2022-0037
-
[19] Koss, L. G., & Melamed, M. R. (2006). Koss' diagnostic cytology and its histopathologic bases (5th ed.). Lippincott Williams & Wilkins.
-
[20] Goel, G., Halder, A., Joshi, D., Anil, A. C., & Kapoor, N. (2020). Rapid, Economic, Acetic Acid Papanicolaou Stain (REAP): An economical, rapid, and appropriate substitute to conventional pap stain for staining cervical smears. Journal of Cytology, 37(4), 170–173. https://doi.org/10.4103/JOC.JOC_89_20
-
[21] Liao, C., Gong, Z., Fang, R., Li, L., Gao, Z., Mao, M., & Zeng, L. (2024). Design and implementation of corrosion-resistant multitasking cell stainers. PLOS ONE, 19(10), e0309334. https://doi.org/10.1371/journal.pone.0309334
-
[22] Ocampo-López-Escalera, J., Ochoa-Díaz-López, H., Sánchez-Chino, X. M., Irecta-Nájera, C. A., Tobar-Alas, S. D., & Rosete-Aguilar, M. (2025). A low-cost platform for automated cervical cytology: Addressing health and socioeconomic challenges in low-resource settings. Frontiers in Medical Technology, 7, 1531817. https://doi.org/10.3389/fmedt.2025.1531817
-
[23] Lu, Q., Liu, G., Xiao, C., Hu, C., Zhang, S., Xu, R. X., Chu, K., Xu, Q., & Smith, Z. J. (2018). A modular, open-source, slide-scanning microscope for diagnostic applications in resource-constrained settings. PLOS ONE, 13(3), e0194063. https://doi.org/10.1371/journal.pone.0194063
-
[24] Aramnet, C. (2026, March 16). Cancer statistics 2026: Lung cancer is the number one killer. Bangkok Biz News. https://www.bangkokbiznews.com/health/well-being/1225390
-
[25] Suvarna, S. K., Layton, C., & Bancroft, J. D. (2012). Bancroft's theory and practice of histological techniques (7th ed.). Churchill Livingstone Elsevier.
-
[26] Schulte, E. (1990). Standardization of the Papanicolaou stain. I. A comparison of five nuclear stains. Analytical and Quantitative Cytology and Histology, 12(3), 149–156. https://pubmed.ncbi.nlm.nih.gov/1695100/
-
[27] Bhanvadia, V. M., Santwani, P. M., & Vachhani, J. H. (2014). Analysis of diagnostic value of cytological smear method versus cell block method in body fluid cytology: Study of 150 cases. Ethiopian Journal of Health Sciences, 24(2), 125–131. http://dx.doi.org/10.4314/ejhs.v24i2.4
-
[28] Ponzetti, M., Devarapu, G. C. R., Rucci, N., Carlone, A., & Saggiomo, V. (2022). HistoEnder: A 3D printer-based histological slide autostainer that retains 3D printer functions. HardwareX, 12, e00370. https://doi.org/10.1016/j.ohx.2022.e00370
-
[29] Blank, L., & Tarquin, A. (2012). Engineering economy (7th ed.). McGraw-Hill.
-
[30] Sullivan, W. G., Wicks, E. M., & Koelling, C. P. (2012). Engineering economy (15th ed.). Pearson Education.

I. J. of Electrical & Electronics Research