Application and Progress of Deep Learning in Circulating Tumor Cell Detection
Zhu Shuai1, Liu Ming2, Yang Jianbo2, He Defeng1, Zhao Ming2*
1(College of Information Engineering,Zhejiang University of Technology, Hangzhou 310023, China) 2(Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou 310018, China)
Abstract：Circulating tumor cells (CTCs) as typical biomarkers in liquid biopsy bear great promise in early diagnosis, prognosis judgment and therapeutic monitoring of tumor. CTCs are scarce, diverse and heterogeneous in peripheral blood, and their detection tasks face multiple challenges such as low accuracy and poor specificity. Deep learning has been widely used in biomedical research and clinical applications. Efficient and accurate automated CTCs detection using deep learning models has become a new research hotspot. In thisarticle, we systematically reviewed the related research work of deep learning applied to CTCs detection in recent years. Existing method theory, key technologies, and performance analysis were described in CTCs detection process, including sample preparation, data acquisition and preprocessing, and construction of deep learning models. At last, the current challenges and future trends of deep learning in CTCs detection were discussed.
朱帅, 刘明, 阳剑波, 何德峰, 赵明. 深度学习在循环肿瘤细胞检测中的应用及进展[J]. 中国生物医学工程学报, 2025, 44(1): 101-111.
Zhu Shuai, Liu Ming, Yang Jianbo, He Defeng, Zhao Ming. Application and Progress of Deep Learning in Circulating Tumor Cell Detection. Chinese Journal of Biomedical Engineering, 2025, 44(1): 101-111.
[1] Pantel K, Speicher MR. The biology of circulating tumor cells [J]. Oncogene, 2016, 35(10): 1216-1224. [2] Alix-Panabières C, Pantel K. Clinical applications of circulating tumor cells and circulating tumor DNA as liquid biopsy [J]. Cancer Discovery, 2016, 6(5): 479-491. [3] Lin E, Cao T, Nagrath S, et al. Circulating tumor cells: diagnostic and therapeutic applications [J]. Annual Review of Biomedical Engineering, 2018, 20: 329-352. [4] Dasgupta A, Lim AR, Ghajar CM. Circulating and disseminated tumor cells: harbingers or initiators of metastasis? [J]. Molecular Oncology, 2017, 11(1): 40-61. [5] Borriello L, Coste A, Traub B, et al. Primary tumor associated macrophages activate programs of invasion and dormancy in disseminating tumor cells [J]. Nature Communications, 2022, 13(1): 626. [6] Lambert AW, Pattabiraman DR, Weinberg RA. Emerging biological principles of metastasis [J]. Cell, 2017, 168(4): 670-691. [7] He Bingsheng, Dai Chan, Lang Jidong, et al. A machine learning framework to trace tumor tissue-of-origin of 13 types of cancer based on DNA somatic mutation [J]. Biochimica Et Biophysica Acta (BBA)-Molecular Basis of Disease, 2020, 1866(11): 165916. [8] Jie Xiaoxiang, Zhang Xiaoyan, Xu Congjian. Epithelial-to-mesenchymal transition, circulating tumor cells and cancer metastasis: mechanisms and clinical applications [J]. Oncotarget, 2017, 8(46): 81558-81571. [9] Schuster E, Taftaf R, Reduzzi C, et al. Better together: circulating tumor cell clustering in metastatic cancer [J]. Trends in Cancer, 2021, 7(11): 1020-1032. [10] Qiao Yuanyuan, Li Jun, Shi Chenghe, et al. Prognostic value of circulating tumor cells in the peripheral blood of patients with esophageal squamous cell carcinoma [J]. OncoTargets and Therapy, 2017, 10: 1363-1373. [11] Ujiie D, Matsumoto T, Endo E, et al. Circulating tumor cells after neoadjuvant chemotherapy are related with recurrence in esophageal squamous cell carcinoma [J]. Esophagus, 2021, 18: 566-573. [12] Semaan A, Bernard V, Kim DU, et al. Characterization of circulating tumour cell phenotypes identifies a partial-EMT sub-population for clinical stratification of pancreatic cancer [J]. British Journal of Cancer, 2021, 124(12): 1970-1977. [13] Akashi T, Okumura T, Terabayashi K, et al. The use of an artificial intelligence algorithm for circulating tumor cell detection in patients with esophageal cancer [J]. Oncology Letters, 2023, 26(1): 1-9. [14] Vidlarova M, Rehulkova A, Stejskal P, et al. Recent advances in methods for circulating tumor cell detection [J]. International Journal of Molecular Sciences, 2023, 24(4): 3902. [15] Shen Zheyu, Wu Aiguo, Chen Xiaoyuan. Current detection technologies for circulating tumor cells [J]. Chemical Society Reviews, 2017, 46(8): 2038-2056. [16] Andree KC, van Dalum G, Terstappen LWMM. Challenges in circulating tumor cell detection by the CellSearch system [J]. Molecular Oncology, 2016, 10(3): 395-407. [17] Shimizu H, Nakayama KI. Artificial intelligence in oncology [J]. Cancer Science, 2020, 111(5): 1452-1460. [18] Elemento O, Leslie C, Lundin J, et al. Artificial intelligence in cancer research, diagnosis and therapy [J]. Nature Reviews Cancer, 2021, 21(12): 747-752. [19] Wang Shen, Zhou Yuyuan, Qin Xiaochen, et al. Label-free detection of rare circulating tumor cells by image analysis and machine learning [J]. Scientific Reports, 2020, 10(1): 12226. [20] Mostert B, Sleijfer S, Foekens JA, et al. Circulating tumor cells (CTCs): detection methods and their clinical relevance in breast cancer [J]. Cancer Treatment Reviews, 2009, 35(5): 463-474. [21] Yang Yuping, Giret TM, Cote RJ. Circulating tumor cells from enumeration to analysis: current challenges and future opportunities [J]. Cancers, 2021, 13(11): 2723. [22] Shen Cheng, Rawal S, Brown R, et al. Automatic detection of circulating tumor cells and cancer associated fibroblasts using deep learning [J]. Scientific Reports, 2023, 13(1): 5708. [23] Zeune LL, Boink YE, van Dalum G, et al. Deep learning of circulating tumour cells [J]. Nature Machine Intelligence, 2020, 2(2): 124-133. [24] Zeune L, van Dalum G, Decraene C, et al. Quantifying HER-2 expression on circulating tumor cells by ACCEPT [J]. PLoS ONE, 2017, 12(10): e0186562. [25] Stevens M, Nanou A, Terstappen LWMM, et al. StarDist image segmentation improves circulating tumor cell detection [J]. Cancers, 2022, 14(12): 2916. [26] Steyaert S, Pizurica M, Nagaraj D, et al. Multimodal data fusion for cancer biomarker discovery with deep learning [J]. Nature Machine Intelligence, 2023, 5(4): 351-362. [27] He B, Bergenstråhle L, Stenbeck L, et al. Integrating spatial gene expression and breast tumour morphology via deep learning [J]. Nature Biomedical Engineering, 2020, 4(8): 827-834. [28] Qi Ren, Zou Quan. Trends and potential of machine learning and deep learning in drug study at single-cell level [J]. Research, 2023, 6: 0050. [29] Gao Jing, Li Peng, Chen Zhikui, et al. A survey on deep learning for multimodal data fusion [J]. Neural Computation, 2020, 32(5): 829-864. [30] Ring A, Nguyen-Straeuli BD, Wicki A, et al. Biology, vulnerabilities and clinical applications of circulating tumour cells [J]. Nature Reviews Cancer, 2023, 23(2): 95-111. [31] Prangemeier T, Reich C, Koeppl H. Attention-based transformers for instance segmentation of cells in microstructures [C]// 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Seoul: IEEE, 2020: 700-707. [32] Chen Mingcan, Li Xiaolei, Xu Jingjing, et al. An innovative algorithm combining attention mechanism and feature fusion for circulating tumor cells detection [C]// 2022 16th IEEE International Conference on Signal Processing (ICSP). Beijing: IEEE, 2022: 416-419. [33] Xiao Youzi, Tian Zhiqiang, Yu Jiachen, et al. A review of object detection based on deep learning [J]. Multimedia Tools and Applications, 2020, 79: 23729-23791. [34] Luo Huilan, Chen Hongkun. Survey of object detection based on deep learning [J]. Acta Electonica Sinica, 2020, 48(6): 1230. [35] Alexander E, Leong KW, Laine AF. Automated multi-process CTC detection using deep learning [J]. arxiv.org/pdf/2109.12709v1, 2021-09-26/2024-01-02. [36] Lin TY, Goyal P, Girshick R, et al. Focal loss for dense object detection [C]// Proceedings of the IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2980-2988. [37] He Kaiming, Gkioxari G, Dollár P, et al. Mask R-CNN [C]// Proceedings of the IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2961-2969. [38] Tjoa E, Guan C. A survey on explainable artificial intelligence (XAI): toward medical XAI [J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 32(11): 4793-4813. [39] Hanif A, Zhang Xuyun, Wood S. A survey on explainable artificial intelligence techniques and challenges [C]// 2021 IEEE 25th International Enterprise Distributed Object Computing Workshop (EDOCW). Gold Coast: IEEE, 2021: 81-89. [40] Singh A, Sengupta S, Lakshminarayanan V. Explainable deep learning models in medical image analysis [J]. Journal of Imaging, 2020, 6(6): 52. [41] Zhang Zizhao, Xie Yuanpu, Xing Fuyong, et al. Mdnet: a semantically and visually interpretable medical image diagnosis network [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Venice: IEEE, 2017: 6428-6436. [42] Moen E, Bannon D, Kudo T, et al. Deep learning for cellular image analysis [J]. Nature Methods, 2019, 16(12): 1233-1246. [43] Gangadhar A, Sari-Sarraf H, Vanapalli SA. Deep learning assisted holography microscopy for in-flow enumeration of tumor cells in blood [J]. RSC Advances, 2023, 13(7): 4222-4235. [44] Guo Xiaoxu, Lin Fanghe, Yi Chuanyou, et al. Deep transfer learning enables lesion tracing of circulating tumor cells [J]. Nature Communications, 2022, 13(1): 7687. [45] Guo Zhifeng, Lin Xiaoxi, Hui Yan, et al. Circulating tumor cell identification based on deep learning [J]. Frontiers in Oncology, 2022, 12: 843879. [46] Piansaddhayanon C, Koracharkornradt C, Laosaengpha N, et al. Label-free tumor cells classification using deep learning and high-content imaging [J]. Scientific Data, 2023, 10(1): 570-584. [47] Zhuang Zhemin, Yang Zengbiao, Raj ANJ, et al. Breast ultrasound tumor image classification using image decomposition and fusion based on adaptive multi-model spatial feature fusion [J]. Computer Methods and Programs in Biomedicine, 2021, 208: 106221. [48] Le NQK, Huynh TT, Yapp EKY, et al. Identification of clathrin proteins by incorporating hyperparameter optimization in deep learning and PSSM profiles [J]. Computer Methods and Programs in Biomedicine, 2019, 177: 81-88. [49] Eulenberg P, Köhler N, Blasi T, et al. Reconstructing cell cycle and disease progression using deep learning [J]. Nature Communications, 2017, 8(1): 463. [50] Keren L, Bosse M, Marquez D, et al. A structured tumor-immune microenvironment in triple negative breast cancer revealed by multiplexed ion beam imaging [J]. Cell, 2018, 174(6): 1373-1387. [51] He Binsheng, Lu Qingqing, Lang Jidong, et al. A new method for CTC images recognition based on machine learning [J]. Frontiers in Bioengineering and Biotechnology, 2020, 8: 897. [52] Yu Haijiao, Ma Ling, Zhu Yubing, et al. Significant diagnostic value of circulating tumour cells in colorectal cancer [J]. Oncology Letters, 2020, 20(1): 317-325. [53] Moallem G, Pore AA, Gangadhar A, et al. Detection of live breast cancer cells in bright-field microscopy images containing white blood cells by image analysis and deep learning [J]. Journal of Biomedical Optics, 2022, 27(7): 076003-076003. [54] Cao Junyue, Spielmann M, Qiu Xiaojie, et al. The single-cell transcriptional landscape of mammalian organogenesis [J]. Nature, 2019, 566(7745): 496-502. [55] Alix-Panabières C, Pantel K. Challenges in circulating tumour cell research [J]. Nature Reviews Cancer, 2014, 14(9): 623-631. [56] Cao Junyue, Spielmann M, Qiu Xiaojie, et al. The single-cell transcriptional landscape of mammalian organogenesis [J]. Nature, 2019, 566(7745): 496-502. [57] Lim B, Lin Yiyun, Navin N. Advancing cancer research and medicine with single-cell genomics [J]. Cancer Cell, 2020, 37(4): 456-470. [58] Einoch-Amor R, Broza YY, Haick H. Detection of single cancer cells in blood with artificially intelligent nanoarray [J]. ACS Nano, 2021, 15(4): 7744-7755. [59] Einoch-Amor R, Zinger A, Broza YY, et al. Artificially intelligent nanoarray detects various cancers by liquid biopsy of volatile markers [J]. Advanced Healthcare Materials, 2022, 11(17): 2200356. [60] Fang Xianglin, Zeng Qiuyao, Yan Xinliang, et al. Fast discrimination of tumor and blood cells by label-free surface-enhanced Raman scattering spectra and deep learning [J]. Journal of Applied Physics, 2021, 129(12):1123103. [61] Delikoyun K, Demir AA, Tekin HC. Label-free detection of rare cancer cells using deep learning and magnetic levitation principle [C]// Label-free Biomedical Imaging and Sensing (LBIS) 2021. Bellingham: SPIE, 2021, 11655: 9-15. [62] Hashemzadeh H, Shojaeilangari S, Allahverdi A, et al. A combined microfluidic deep learning approach for lung cancer cell high throughput screening toward automatic cancer screening applications [J]. Scientific Reports, 2021, 11(1): 9804. [63] Gangadhar A, Sari-Sarraf H, Vanapalli SA. Staining-free, in-flow enumeration of tumor cells in blood using digital holographic microscopy and deep learning [J]. arxiv.org/pdf/2109.12709v1, 2021-09-26/2024-01-02. [64] Keller L, Pantel K. Unravelling tumour heterogeneity by single-cell profiling of circulating tumour cells [J]. Nature Reviews Cancer, 2019, 19(10): 553-567. [65] Ma Jun, Yang Jiani, Jin Yue, et al. Artificial intelligence based on blood biomarkers including CTCs predicts outcomes in epithelial ovarian cancer: A prospective study [J]. OncoTargets and Therapy, 2021: 3267-3280.
