Non-destructive detection of ovary regions in live female mud crabs by machine-learning assisted multispectral imaging
,
and
*
Article Sidebar
Full Text: 
PDF
Main Article Content
Abstract
Ovarian fullness of female mud crabs (Scylla paramamosain) is key determinant of market value but is still assessed subjectively by hand. Spectrometry offers an objective alternative, and our previous studies under in vitro and semi-in vivo conditions demonstrated the potential of spectrometric features for discrimination of crab tissues (meat, ovary, hepatopancreas, and shell). However, it was still challenging to apply under in vivo conditions. This study aims to detect the ovary region in live mud crabs while keeping the ‘in vivo’ condition by combining a custom multispectral-imaging system and simple ML techniques. A special optical setup and a concise multispectral camera were included in the system aiming to acquire the transmission image through the intact carapace practically in the crab-farming fields. The ovary region was predicted pixel-wise and patch-wise using conventional classifiers (Logistic Regression, Random Forest, Gradient Boosting, k-NN, and SVM) and Convolutional Neural Networks (CNN), enhanced by Principal Component Analysis (PCA) for feature transformation. The patch-wise random forest model with PCA (7×7 patches) achieved superior performance, with an accuracy of 0.872 and an F1-score of 0.872, outperforming other methods. These findings mark a significant advancement in the application of multispectral imaging for automated, non-destructive quality assessment in live aquaculture specimens.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
Keenan, C. P., Davie, P. J. F., & Mann, D. L. (1998). A revision of the genus Scylla de Haan, 1833 (Crustacea: Decapoda: Brachyura: Portunidae). The Raffles Bulletin of Zoology, 46(1), 217–245.
Shelley, C., & Lovatelli, A. (2011). Mud crab aquaculture: A practical manual (FAO Fisheries and Aquaculture Technical Paper No. 567). Food and Agriculture Organization of the United Nations. http://www.fao.org/3/ba0110e/ba0110e.pdf
Bhuiyan, M. S., Shamsuzzaman, M. M., Hossain, M. M., Mitu, S. J., & Mozumder, M. M. H. (2021). Mud crab (Scylla serrata Forsskål, 1775) value chain analysis in the Khulna region of Bangladesh. Aquaculture and Fisheries, 6(3), 330–336. https://doi.org/10.1016/j.aaf.2021.01.004
C-AID Consultants. (2016). Australian industry live mud crab grading scheme (Version 3) [PDF]. Retrieved from https://www.c-aid.com.au/wp-content/uploads/Mud-Crab-Grading-Scheme-V3-2016.pdf
Wu, Q., Waiho, K., Huang, Z., Li, S., Zheng, H., Zhang, Y., Ikhwanuddin, M., Lin, F., & Ma, H. (2020). Growth performance and biochemical composition dynamics of ovary, hepatopancreas and muscle tissues at different ovarian maturation stages of female mud crab, Scylla paramamosain. Aquaculture, 515, 734560. https://doi.org/10.1016/j.aquaculture.2019.734560
Fang, K., Wu, K., Wang, J., Liu, G., Ouyang, W., Lin, G., Tian, H., Feng, M., & Wen, X. (2025). Comparative analysis of fatty acid, amino acid, and mineral of wild female mud crabs (Scylla paramamosain) from the southeast coast of China: Insights for consumer preference. Journal of Food Composition and Analysis, 145, 107808. https://doi.org/10.1016/j.jfca.2025.107808
Jiang, X., Wang, W., Liu, M., Lin, Z., & Zheng, X. (2025). Comparative analysis of morphological characteristics and nutritional quality in wild-caught and pond-reared female mud crab, Scylla paramamosain. Journal of Food Composition and Analysis, 146, 107953. https://doi.org/10.1016/j.jfca.2025.107953
Wu, Q., Shi, X., Fang, S., Xie, Z., Guan, M., Li, S., Zheng, H., Zhang, Y., Ikhwanuddin, M., & Ma, H. (2019). Different biochemical composition and nutritional value attribute to salinity and rearing period in male and female mud crab Scylla paramamosain. Aquaculture, 513, 734417. https://doi.org/10.1016/j.aquaculture.2019.734417
Amin-Safwan, A., Mardhiyyah, M. P., Izzah-Syafiah, M. A., Muhd-Farouk, H., Manan, H., Mahsol, H. H., Nadirah, M., & Ikhwanuddin, M. (2019). Dataset on reproductive status of ovary mud crab at different salinity levels. Data in Brief, 26, 104426. https://doi.org/10.1016/j.dib.2019.104426
Han, W., Liu, H., & Wang, Y. (2024). Changes of nutrient composition in the ovaries and hepatopancreas of mud crab Scylla paramamosain broodstock and their offspring performance at different salinities. Aquaculture, 585, 740704. https://doi.org/10.1016/j.aquaculture.2024.740704
Aaqillah-Amr, M. A., Hidir, A., Noordiyana, M. N., & Ikhwanuddin, M. (2018). Morphological, biochemical and histological analysis of mud crab ovary and hepatopancreas at different stages of development. Animal Reproduction Science, 195, 274–283. https://doi.org/10.1016/j.anireprosci.2018.06.005
Yu, K., Xu, H., Shi, C., Wang, C., Mu, C., Ye, Y., Chen, S., Li, R., & Wu, Q. (2025). Overwintering temperature affects lipid and fatty acid metabolism in hepatopancreas and ovary of female mud crab Scylla paramamosain. Aquaculture Reports, 40, 102563. https://doi.org/10.1016/j.aqrep.2024.102563
Vo, H. D., Tran, N. T., & Fukuzawa, M. (2025). Experimental study on spectrometric features of mud crabs for automatic internal quality grading. In Communications in Computer and Information Science (Vol. 2191, pp. 3–14). Springer. https://doi.org/10.1007/978-981-97-9616-8_1
Tran, N. T., Vo, H. D., Ngo, C. T., Nguyen, Q. H., & Fukuzawa, M. (2024). Towards automatic internal quality grading of mud crabs: A preliminary study on spectrometric analysis. In Communications in Computer and Information Science (Vol. 1950, pp. 3–14). Springer. https://doi.org/10.1007/978-981-99-7666-9_1
Wold, J. P., O’Farrell, M., Tschudi, J., & Lorentzen, G. (2024). Rapid and non-destructive quantification of meat content in the legs of live red king crab (Paralithodes camtschaticus) by near-infrared spectroscopy. LWT, 201, 116246. https://doi.org/10.1016/j.lwt.2024.116246
Moosavi-Nasab, M., Khoshnoudi-Nia, S., Azimifar, Z., & Kamyab, S. (2021). Evaluation of the total volatile basic nitrogen (TVB-N) content in fish fillets using hyperspectral imaging coupled with deep learning neural network and meta-analysis. Scientific Reports, 11(1), 84659. https://doi.org/10.1038/s41598-021-84659-y
Kong, D., Shi, Y., Sun, D., Zhou, L., Zhang, W., Qiu, R., & He, Y. (2022). Hyperspectral imaging coupled with CNN: A powerful approach for quantitative identification of feather meal and fish by-product meal adulterated in marine fishmeal. Microchemical Journal, 180, 107517. https://doi.org/10.1016/j.microc.2022.107517
Li, P., Tang, S., Chen, S., Tian, X., & Zhong, N. (2023). Hyperspectral imaging combined with convolutional neural network for accurately detecting adulteration in Atlantic salmon. Food Control, 147, 109573. https://doi.org/10.1016/j.foodcont.2022.109573
Shao, Y., Shi, Y., Wang, K., Li, F., Zhou, G., & Xuan, G. (2023). Detection of small yellow croaker freshness by hyperspectral imaging. Journal of Food Composition and Analysis, 115, 104980. https://doi.org/10.1016/j.jfca.2022.104980
Zhang, H., Zhang, S., Chen, Y., Luo, W., Huang, Y., Tao, D., Zhan, B., & Liu, X. (2020). Non-destructive determination of fat and moisture contents in salmon (Salmo salar) fillets using near-infrared hyperspectral imaging coupled with spectral and textural features. Journal of Food Composition and Analysis, 92, 103567. https://doi.org/10.1016/j.jfca.2020.103567
Ismail, A., Yim, D. G., Kim, G., & Jo, C. (2023). Hyperspectral imaging coupled with multivariate analyses for efficient prediction of chemical, biological and physical properties of seafood products. Food Engineering Reviews, 15(1), 41–55. https://doi.org/10.1007/s12393-022-09327-x