{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T13:41:01Z","timestamp":1771335661800,"version":"3.50.1"},"reference-count":41,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T00:00:00Z","timestamp":1693440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Transparent Artificial Medical Intelligence (TAMI)","award":["45905"],"award-info":[{"award-number":["45905"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Sciences"],"abstract":"<jats:p>Liquid-based cytology (LBC) plays a crucial role in the effective early detection of cervical cancer, contributing to substantially decreasing mortality rates. However, the visual examination of microscopic slides is a challenging, time-consuming, and ambiguous task. Shortages of specialized staff and equipment are increasing the interest in developing artificial intelligence (AI)-powered portable solutions to support screening programs. This paper presents a novel approach based on a RetinaNet model with a ResNet50 backbone to detect the nuclei of cervical lesions on mobile-acquired microscopic images of cytology samples, stratifying the lesions according to The Bethesda System (TBS) guidelines. This work was supported by a new dataset of images from LBC samples digitalized with a portable smartphone-based microscope, encompassing nucleus annotations of 31,698 normal squamous cells and 1395 lesions. Several experiments were conducted to optimize the model\u2019s detection performance, namely hyperparameter tuning, transfer learning, detected class adjustments, and per-class score threshold optimization. The proposed nucleus-based methodology improved the best baseline reported in the literature for detecting cervical lesions on microscopic images exclusively acquired with mobile devices coupled to the \u00b5SmartScope prototype, with per-class average precision, recall, and F1 scores up to 17.6%, 22.9%, and 16.0%, respectively. Performance improvements were obtained by transferring knowledge from networks pre-trained on a smaller dataset closer to the target application domain, as well as including normal squamous nuclei as a class detected by the model. Per-class tuning of the score threshold also allowed us to obtain a model more suitable to support screening procedures, achieving F1 score improvements in most TBS classes. While further improvements are still required to use the proposed approach in a clinical context, this work reinforces the potential of using AI-powered mobile-based solutions to support cervical cancer screening. Such solutions can significantly impact screening programs worldwide, particularly in areas with limited access and restricted healthcare resources.<\/jats:p>","DOI":"10.3390\/app13179850","type":"journal-article","created":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T11:45:51Z","timestamp":1693482351000},"page":"9850","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Improving Mobile-Based Cervical Cytology Screening: A Deep Learning Nucleus-Based Approach for Lesion Detection"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7100-519X","authenticated-orcid":false,"given":"Vladyslav","family":"Mosiichuk","sequence":"first","affiliation":[{"name":"Fraunhofer Portugal AICOS, Rua Alfredo Allen 455\/461, 4200-135 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1770-4429","authenticated-orcid":false,"given":"Ana","family":"Sampaio","sequence":"additional","affiliation":[{"name":"Fraunhofer Portugal AICOS, Rua Alfredo Allen 455\/461, 4200-135 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8447-2360","authenticated-orcid":false,"given":"Paula","family":"Viana","sequence":"additional","affiliation":[{"name":"ISEP, Polytechnic of Porto, School of Engineering, Rua Dr. Ant\u00f3nio Bernardino de Almeida, 431, 4249-015 Porto, Portugal"},{"name":"INESC TEC, Campus da Faculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"}]},{"given":"Tiago","family":"Oliveira","sequence":"additional","affiliation":[{"name":"First Solutions\u2014Sistemas de Informa\u00e7\u00e3o S.A., Rua Conselheiro Costa Braga, 502F, 4450-102 Matosinhos, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8060-831X","authenticated-orcid":false,"given":"Lu\u00eds","family":"Rosado","sequence":"additional","affiliation":[{"name":"Fraunhofer Portugal AICOS, Rua Alfredo Allen 455\/461, 4200-135 Porto, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA A Cancer J. Clin."},{"key":"ref_2","unstructured":"WHO (2021, February 11). Cancer Today. Available online: https:\/\/gco.iarc.fr\/today\/fact-sheets-cancers."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"iv262","DOI":"10.1093\/annonc\/mdy160","article-title":"Cervical cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up","volume":"29","author":"Marth","year":"2018","journal-title":"Ann. Oncol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"5114","DOI":"10.3390\/ijms20205114","article-title":"A Review of Computational Methods for Cervical Cells Segmentation and Abnormality Classification","volume":"20","author":"Braga","year":"2019","journal-title":"Int. J. Mol. Sci."},{"key":"ref_5","unstructured":"Pinho, A.J., Georgieva, P., Teixeira, L.F., and S\u00e1nchez, J.A. (2022, January 4\u20136). Automated Adequacy Assessment of Cervical Cytology Samples Using Deep Learning. Proceedings of the Iberian Conference on Pattern Recognition and Image Analysis, Aveiro, Portugal."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"152188","DOI":"10.1109\/ACCESS.2021.3126486","article-title":"Towards the Mobile Detection of Cervical Lesions: A Region-Based Approach for the Analysis of Microscopic Images","volume":"9","author":"Sampaio","year":"2021","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/s41592-018-0261-2","article-title":"U-Net: Deep learning for cell counting, detection, and morphometry","volume":"16","author":"Falk","year":"2019","journal-title":"Nat. Methods"},{"key":"ref_8","unstructured":"Hern\u00e1ndez, C.X., Sultan, M.M., and Pande, V.S. (2018). Using Deep Learning for Segmentation and Counting within Microscopy Data. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ke, J., Jiang, Z., Liu, C., Bednarz, T., Sowmya, A., and Liang, X. (2019, January 29\u201331). Selective Detection and Segmentation of Cervical Cells. Proceedings of the ICBBT\u201919: 2019 11th International Conference on Bioinformatics and Biomedical Technology, Stockholm, Sweden.","DOI":"10.1145\/3340074.3340081"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1186\/s12859-022-05074-2","article-title":"Automatic identifying and counting blood cells in smear images by using single shot detector and Taguchi method","volume":"22","author":"Chen","year":"2022","journal-title":"BMC Bioinform."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1080\/21681163.2016.1149104","article-title":"Microscopy cell counting and detection with fully convolutional regression networks","volume":"6","author":"Xie","year":"2018","journal-title":"Comput. Methods Biomech. Biomed. Eng. Imaging Vis."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3541","DOI":"10.1038\/s41467-021-23913-3","article-title":"Hybrid AI-assistive diagnostic model permits rapid TBS classification of cervical liquid-based thin-layer cell smears","volume":"12","author":"Zhu","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Meenakshisundaram, N., and Govindaraj, D. (2023, January 5\u20137). An Automatic Method for Identification of Cervical Cancer based on Multilayer Perceptron Neural Network. Proceedings of the 2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering (ICECONF), Chennai, India.","DOI":"10.1109\/ICECONF57129.2023.10083694"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kumari, C., Padmashree, S., Bhavani, R., and Priya, R. (2022, January 16\u201317). Detection and Identification of Cervical Cancer on Elephant Herding Optimization on Convolutional Neural Network. Proceedings of the 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon), Mysuru, India.","DOI":"10.1109\/MysuruCon55714.2022.9972506"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Diniz, D., Rezende, M., Bianchi, A., Carneiro, C., Luz, E., Moreira, G., Ushizima, D., Medeiros, F., and Souza, M. (2021). A Deep Learning Ensemble Method to Assist Cytopathologists in Pap Test Image Classification. J. Imaging, 7.","DOI":"10.3390\/jimaging7070111"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1978","DOI":"10.1002\/ima.22751","article-title":"NCA -based hybrid convolutional neural network model for classification of cervical cancer on gauss-enhanced pap-smear images","volume":"32","year":"2022","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e348","DOI":"10.7717\/peerj-cs.348","article-title":"Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing","volume":"7","author":"Master","year":"2021","journal-title":"PeerJ Comput. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Xia, M., Zhang, G., Mu, C., Guan, B., and Wang, M. (2020, January 27\u201329). In Proceedings of the Cervical Cancer Cell Detection Based on Deep Convolutional Neural Network, Shenyang, China.","DOI":"10.23919\/CCC50068.2020.9188454"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3695","DOI":"10.3233\/JIFS-220173","article-title":"Detection and classification of cervical cancer images using CEENET deep learning approach","volume":"43","author":"Subarna","year":"2022","journal-title":"J. Intell. Fuzzy Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"6333","DOI":"10.3233\/JIFS-220296","article-title":"Cervical cancer classification using efficient net and fuzzy extreme learning machine","volume":"43","author":"Suphalakshmi","year":"2022","journal-title":"J. Intell. Fuzzy Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2389","DOI":"10.1007\/s00216-021-03184-z","article-title":"Recent trends in smartphone-based detection for biomedical applications: A review","volume":"413","author":"Banik","year":"2021","journal-title":"Anal. Bioanal. Chem."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1038\/s41746-020-0282-y","article-title":"Automated screening of sickle cells using a smartphone-based microscope and deep learning","volume":"3","author":"Rivenson","year":"2020","journal-title":"NPJ Digit. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.procs.2016.07.024","article-title":"Automated Detection of Malaria Parasites on Thick Blood Smears via Mobile Devices","volume":"90","author":"Rosado","year":"2016","journal-title":"Procedia Comput. Sci."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Rosado, L., Costa, J.M.C.d., Elias, D., and Cardoso, J.S. (2017). Mobile-Based Analysis of Malaria-Infected Thin Blood Smears: Automated Species and Life Cycle Stage Determination. Sensors, 17.","DOI":"10.3390\/s17102167"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1337325","DOI":"10.1080\/16549716.2017.1337325","article-title":"Point-of-care mobile digital microscopy and deep learning for the detection of soil-transmitted helminths and Schistosoma haematobium","volume":"10","author":"Linder","year":"2017","journal-title":"Glob. Health Action"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"9147","DOI":"10.1021\/nn4037706","article-title":"Fluorescent Imaging of Single Nanoparticles and Viruses on a Smart Phone","volume":"7","author":"Wei","year":"2013","journal-title":"ACS Nano"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Rosado, L., Oliveira, J., Vasconcelos, M.J.M., da Costa, J.M.C., Elias, D., and Cardoso, J.S. (2017, January 21\u201323). \u03bcSmartScope: 3D-printed Smartphone Microscope with Motorized Automated Stage. Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies\u2014BIODEVICES, (BIOSTEC 2017), Porto, Portugal. INSTICC.","DOI":"10.5220\/0006155800380048"},{"key":"ref_28","first-page":"19","article-title":"\u03bcSmartScope: Towards a Fully Automated 3D-printed Smartphone Microscope with Motorized Stage","volume":"4","author":"Rosado","year":"2018","journal-title":"Commun. Comput. Inf. Sci. Book Ser."},{"key":"ref_29","first-page":"267","article-title":"\u00b5SmartScope: Towards a low-cost microscopic medical device for cervical cancer screening using additive manufacturing and optimization","volume":"236","author":"Silva","year":"2021","journal-title":"Proc. Inst. Mech. Eng. Part L J. Mater. Des. Appl."},{"key":"ref_30","unstructured":"Pereira, C., Silva, P.T., Rosado, L., Mota, L., and Martins, J. (2022, January 4\u20136). The Design Thinking Process in the Development of an Intelligent Microscopic Equipment. Proceedings of the Advances in Design and Digital Communication II, Cham, Switzerland."},{"key":"ref_31","unstructured":"Jantzen, J., Norup, J., Dounias, G., and Bjerregaard, B. (2005). Pap-smear Benchmark Data For Pattern Classification. Nat. Inspired Smart Inf. Syst. (NiSIS), 1\u20139."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Plissiti, M., Dimitrakopoulos, P., Sfikas, G., Nikou, C., Krikoni, O., and Charchanti, A. (2018, January 7\u201310). Sipakmed: A New Dataset for Feature and Image Based Classification of Normal and Pathological Cervical Cells in Pap Smear Images. Proceedings of the 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece.","DOI":"10.1109\/ICIP.2018.8451588"},{"key":"ref_33","unstructured":"Phoulady, H.A., and Mouton, P.R. (2018). A New Cervical Cytology Dataset for Nucleus Detection and Image Classification (Cervix93) and Methods for Cervical Nucleus Detection. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1261","DOI":"10.1109\/TIP.2015.2389619","article-title":"An Improved Joint Optimization of Multiple Level Set Functions for the Segmentation of Overlapping Cervical Cells","volume":"24","author":"Lu","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/JBHI.2016.2519686","article-title":"Evaluation of Three Algorithms for the Segmentation of Overlapping Cervical Cells","volume":"21","author":"Lu","year":"2016","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1038\/s41597-021-00933-8","article-title":"Cric searchable image database as a public platform for conventional pap smear cytology data","volume":"8","author":"Rezende","year":"2021","journal-title":"Nat. Sci. Data"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Nayar, R., and Wilbur, D.C. (2015). The Bethesda System for Reporting Cervical Cytology: Definitions, Criteria, and Explanatory Notes, Springer International Publishing.","DOI":"10.1007\/978-3-319-11074-5"},{"key":"ref_38","first-page":"740","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014, January 6\u201312). Microsoft coco: Common objects in context. Proceedings of the Computer Vision\u2014ECCV 2014: 13th European Conference, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_40","first-page":"233","article-title":"Relationship between cervical excisional treatment for cervical intraepithelial neoplasia and obstetrical outcome","volume":"73","author":"Monti","year":"2020","journal-title":"Minerva Obstet. Gynecol."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Giannini, A., Di Donato, V., Sopracordevole, F., Ciavattini, A., Ghelardi, A., Vizza, E., D\u2019Oria, O., Simoncini, T., Plotti, F., and Casarin, J. (2023). Outcomes of High-Grade Cervical Dysplasia with Positive Margins and HPV Persistence after Cervical Conization. Vaccines, 11.","DOI":"10.3390\/vaccines11030698"}],"container-title":["Applied Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3417\/13\/17\/9850\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:43:48Z","timestamp":1760129028000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3417\/13\/17\/9850"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,31]]},"references-count":41,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["app13179850"],"URL":"https:\/\/doi.org\/10.3390\/app13179850","relation":{},"ISSN":["2076-3417"],"issn-type":[{"value":"2076-3417","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,31]]}}}