{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T09:20:33Z","timestamp":1791537633760,"version":"4.3.4"},"reference-count":33,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T00:00:00Z","timestamp":1752019200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Grant-in-Aid for Scientific Research","award":["grant number 19K09293"],"award-info":[{"award-number":["grant number 19K09293"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Background\/Objectives: Circulating tumor cells (CTCs) are important biomarkers for predicting prognosis and evaluating treatment efficacy in cancer. We developed the \u201cCTC-Chip\u201d system based on microfluidics, enabling highly sensitive CTC detection and prognostic assessment in lung cancer and malignant pleural mesothelioma. However, the final identification and enumeration of CTCs require manual intervention, which is time-consuming, prone to human error, and necessitates the involvement of experienced medical professionals. Medical image recognition using machine learning can reduce workload and improve automation. However, CTCs are rare in clinical samples, limiting the training data available to construct a robust CTC image recognition system. In this study, we established a highly accurate artificial intelligence-based CTC recognition system by pre-training convolutional neural networks using images from lung cancer cell lines. Methods: We performed transfer learning of convolutional neural networks. Initially, the models were pre-trained using images obtained from lung cancer cell lines. The model\u2019s accuracy was improved by training with a limited number of clinical CTC images. Results: Transfer learning significantly improved the CTC classification accuracy to an average of 99.51%, compared to 96.96% for a model trained solely on pre-trained cell lines (p &lt; 0.05). This approach showed notable efficacy when clinical training images were limited, achieving statistically significant accuracy improvements with as few as 17 clinical CTC images (p &lt; 0.05). Conclusions: Overall, our findings demonstrate that pre-training with cancer cell lines enables rapid and highly accurate automated CTC recognition even with limited clinical data, significantly enhancing clinical applicability and potential utility across diverse cancer diagnostic workflows.<\/jats:p>","DOI":"10.3390\/cancers17142289","type":"journal-article","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T09:38:27Z","timestamp":1752140307000},"page":"2289","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Establishing a Highly Accurate Circulating Tumor Cell Image Recognition System for Human Lung Cancer by Pre-Training on Lung Cancer Cell Lines"],"prefix":"10.3390","volume":"17","author":[{"given":"Hiroki","family":"Matsumiya","sequence":"first","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenji","family":"Terabayashi","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Intellectual Systems Engineering, Faculty of Engineering, University of Toyama, Toyama 930-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusuke","family":"Kishi","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Intellectual Systems Engineering, Faculty of Engineering, University of Toyama, Toyama 930-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuki","family":"Yoshino","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Intellectual Systems Engineering, Faculty of Engineering, University of Toyama, Toyama 930-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masataka","family":"Mori","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8812-1787","authenticated-orcid":false,"given":"Masatoshi","family":"Kanayama","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rintaro","family":"Oyama","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yukiko","family":"Nemoto","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0749-8871","authenticated-orcid":false,"given":"Natsumasa","family":"Nishizawa","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yohei","family":"Honda","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taiji","family":"Kuwata","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4436-2850","authenticated-orcid":false,"given":"Masaru","family":"Takenaka","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasuhiro","family":"Chikaishi","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7142-2743","authenticated-orcid":false,"given":"Kazue","family":"Yoneda","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koji","family":"Kuroda","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takashi","family":"Ohnaga","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tohru","family":"Sasaki","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Intellectual Systems Engineering, Faculty of Engineering, University of Toyama, Toyama 930-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fumihiro","family":"Tanaka","sequence":"additional","affiliation":[{"name":"Second Department of Surgery, School of Medicine, University of Occupational and Environmental Health, Kitakyushu 807-8555, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1186\/s13073-020-00728-3","article-title":"Tracking cancer progression: From circulating tumor cells to metastasis","volume":"12","author":"Aceto","year":"2020","journal-title":"Genome Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1186\/s12943-021-01392-w","article-title":"Using single-cell sequencing technology to detect circulating tumor cells in solid tumors","volume":"20","author":"Xu","year":"2021","journal-title":"Mol. Cancer"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"877","DOI":"10.21037\/tlcr-22-712","article-title":"Significance of circulating tumor cells in lung cancer: A narrative review","volume":"12","author":"Hamilton","year":"2023","journal-title":"Transl. Lung Cancer Res."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, X., Bai, L., Kong, L., and Guo, Z. (2024). Advances in circulating tumor cells for early detection, prognosis and metastasis reduction in lung cancer. Front. Oncol., 14.","DOI":"10.3389\/fonc.2024.1411731"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4943","DOI":"10.2147\/OTT.S249063","article-title":"HMGA1 regulates the stem cell-like properties of circulating tumor cells from GIST patients via Wnt\/\u03b2-catenin pathway","volume":"13","author":"Chen","year":"2020","journal-title":"Onco Targets Ther."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1530\/ERC-21-0179","article-title":"Whole-genome sequencing of single circulating tumor cells from neuroendocrine neoplasms","volume":"28","author":"Childs","year":"2021","journal-title":"Endocr. Relat. Cancer"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wang, C., Luo, Q., Huang, W., Zhang, C., Liao, H., Chen, K., and Pan, M. (2021). Correlation between circulating tumor cell DNA genomic alterations and mesenchymal CTCs or CTC-associated white blood cell clusters in hepatocellular carcinoma. Front. Oncol., 11.","DOI":"10.3389\/fonc.2021.686365"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Laprovitera, N., Salamon, I., Gelsomino, F., Porcellini, E., Riefolo, M., Garonzi, M., Tononi, P., Valente, S., Sabbioni, S., and Fontana, F. (2021). Genetic characterization of cancer of unknown primary using liquid biopsy approaches. Front. Cell Dev. Biol., 9.","DOI":"10.3389\/fcell.2021.666156"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cappelletti, V., Verzoni, E., Ratta, R., Vismara, M., Silvestri, M., Montone, R., Miodini, P., Reduzzi, C., Claps, M., and Sepe, P. (2020). Analysis of single circulating tumor cells in renal cell carcinoma reveals phenotypic heterogeneity and genomic alterations related to progression. Int. J. Mol. Sci., 21.","DOI":"10.3390\/ijms21041475"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"6897","DOI":"10.1158\/1078-0432.CCR-04-0378","article-title":"Tumor cells circulate in the peripheral blood of all major carcinomas but not in healthy subjects or patients with nonmalignant diseases","volume":"10","author":"Allard","year":"2004","journal-title":"Clin. Cancer Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"920","DOI":"10.1158\/1078-0432.CCR-06-1695","article-title":"Detection of circulating tumor cells in peripheral blood of patients with metastatic breast cancer: A validation study of the CellSearch System","volume":"13","author":"Riethdort","year":"2007","journal-title":"Clin. Cancer Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"6980","DOI":"10.1158\/1078-0432.CCR-09-1095","article-title":"Circulating tumor cell as a diagnostic marker in primary lung cancer","volume":"15","author":"Tanaka","year":"2009","journal-title":"Clin. Cancer Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1007\/s10544-013-9775-7","article-title":"Polymeric microfluidic devices exhibiting sufficient capture of cancer cell line for isolation of circulating tumor cells","volume":"15","author":"Ohnaga","year":"2013","journal-title":"Biomed. Microdevices"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"77","DOI":"10.3892\/or.2016.5235","article-title":"EpCAM-independent capture of circulating tumor cells with a \u2018universal CTC-chip\u2019","volume":"37","author":"Chikaishi","year":"2017","journal-title":"Oncol. Rep."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1111\/cas.15255","article-title":"Prognostic impact of circulating tumor cells detected with the microfluidic \u201cuniversal CTC-chip\u201d for primary lung cancer","volume":"113","author":"Kanayama","year":"2022","journal-title":"Cancer Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1007\/s12154-013-0094-5","article-title":"Fluorescent labeling and modification of proteins","volume":"6","author":"Toseland","year":"2013","journal-title":"J. Chem. Biol."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kulkarni, M.B., Reed, M.S., Cao, X., Garc\u00eda, H.A., Ochoa, M.I., Jiang, S., Hasan, T., Doyley, M.M., and Pogue, B.W. (2025). Combined dual-channel fluorescence depth sensing of indocyanine green and protoporphyrin IX kinetics in subcutaneous murine tumors. J. Biomed. Opt., 30.","DOI":"10.1117\/1.JBO.30.S1.S13709"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1002\/cyto.a.22993","article-title":"Comparison and optimization of machine learning methods for automated classification of circulating tumor cells","volume":"89","author":"Lannin","year":"2016","journal-title":"Cytom. A."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"6703","DOI":"10.1158\/0008-5472.CAN-18-0653","article-title":"A convolutional neural network uses microscopic images to differentiate between mouse and human cell lines and their radioresistant clones","volume":"78","author":"Toratani","year":"2018","journal-title":"Cancer Res."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1038\/s42256-020-0153-x","article-title":"Deep learning of circulating tumour cells","volume":"2","author":"Zeune","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhou, Y., Qin, X., Nair, S., Huang, X., and Liu, Y. (2020). Label-free detection of rare circulating tumor cells by image analysis and machine learning. Sci. Rep., 10.","DOI":"10.1038\/s41598-020-69056-1"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102444","DOI":"10.1016\/j.media.2022.102444","article-title":"Recent advances and clinical applications of deep learning in medical image analysis","volume":"79","author":"Chen","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"He, B., Lu, Q., Lang, J., Yu, H., Peng, C., Bing, P., Li, S., Zhou, Q., Liang, Y., and Tian, G. (2020). A new method for CTC images recognition based on machine learning. Front. Bioeng. Biotechnol., 8.","DOI":"10.3389\/fbioe.2020.00897"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"377","DOI":"10.7150\/thno.5195","article-title":"Detecting circulating tumor cells: Current challenges and new trends","volume":"3","author":"Hong","year":"2013","journal-title":"Theranostics"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.canlet.2006.12.014","article-title":"Circulating tumor cells (CTC) detection: Clinical impact and future directions","volume":"253","author":"Benali","year":"2007","journal-title":"Cancer Lett."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1016\/j.ymeth.2010.01.027","article-title":"Circulating tumour cells in clinical practice: Methods of detection and possible characterization","volume":"50","author":"Sandri","year":"2010","journal-title":"Methods"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1038\/nrc3820","article-title":"Challenges in circulating tumour cell research","volume":"14","author":"Pantel","year":"2014","journal-title":"Nat. Rev. Cancer"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"320","DOI":"10.3892\/ol.2023.13906","article-title":"The use of an artificial intelligence algorithm for circulating tumor cell detection in patients with esophageal cancer","volume":"26","author":"Akashi","year":"2023","journal-title":"Oncol. Lett."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","article-title":"A threshold selection method from gray-level histograms","volume":"9","author":"Otsu","year":"1979","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Yan, Y., Chen, M., Shyu, M.L., and Chen, S.C. (2015, January 14\u201316). Deep learning for imbalanced multimedia data classification. Proceedings of the 2015 IEEE International Symposium on Multimedia, Miami, FL, USA.","DOI":"10.1109\/ISM.2015.126"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1186\/s40537-023-00727-2","article-title":"A survey on deep learning tools dealing with data scarcity: Definitions, challenges, solutions, tips, and applications","volume":"10","author":"Alzubaidi","year":"2023","journal-title":"J. Big Data."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Pullikuth, A.K., Routh, E.D., Zimmerman, K.D., Chifman, J., Chou, J.W., Soike, M.H., Jin, G., Su, J., Song, Q., and Black, M.A. (2021). Bulk and single-cell profiling of breast tumors identifies TREM-1 as a dominant immune suppressive marker associated with poor outcomes. Front. Oncol., 11.","DOI":"10.3389\/fonc.2021.734959"}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/17\/14\/2289\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:07:30Z","timestamp":1760033250000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/17\/14\/2289"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,9]]},"references-count":33,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["cancers17142289"],"URL":"https:\/\/doi.org\/10.3390\/cancers17142289","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,9]]}}}