Timely cancer diagnosis remains a critical challenge in resource-limited settings due to infrastructural deficits. Previous reviews have broadly examined artificial intelligence (AI) in diagnostics, but less attention has been paid to offline systems. This review provides a consolidated synthesis focused specifically on fully offline, edge-deployed systems for cancer detection. Such systems execute autonomous, on-device inference without cloud dependency, a vital capability for deployment where connectivity is unreliable. A structured search of databases and gray literature from August to December 2025 identified 450 records. After screening, evidence from 31 studies meeting the inclusion criteria was synthesized; these encompassed cervical, breast, prostate, skin, and oral cancers. The quantitative evidence confirms that edge-deployed models can maintain clinical-grade diagnostic accuracy while enabling rapid point-of-care use. Key findings indicate that through optimization techniques such as INT8 quantization, diagnostic performance in tasks such as segmentation can be preserved with a reduction of less than 3% compared to standard models, as demonstrated in adapted U-Net architectures. Concurrently, these streamlined models achieved inference speeds above 155 frames per second on embedded hardware such as the NVIDIA Jetson, enabling real-time analysis. This review establishes that the combination of robust accuracy and high-speed offline operation is technically feasible. It thereby offers an evidence-based framework for utilizing edge AI to expand access to early cancer detection in underserved populations globally.

1. Ngwa W, Addai BW, Adewole I, et al. Cancer in sub-Saharan Africa: a Lancet Oncology Commission. Lancet Oncol. 2022;23(6):e251-e312. doi: 10.1016/S1470-2045(21)00720-8

2. Wilson ML. Pathology and laboratory medicine in universal health coverage. J Lab Precis Med. 2019;4:34. doi: 10.21037/jlpm.2019.09.06

3. Byers RJ, Byers AJ, Mumba C, et al. Development of an online teaching platform to improve access to postgraduate pathology training in sub-Saharan Africa. Front Med. 2024;11:1390560. doi: 10.3389/fmed.2024.1390560

4. Fleming KA. Pathology and cancer in Africa. Ecancermedicalscience. 2019;13:945. doi: 10.3332/ecancer.2019.945

5. Mapanga W, Norris SA, Craig A, et al. Drivers of disparities in stage at diagnosis among women with breast cancer: South African breast cancers and HIV outcomes cohort. PLoS ONE. 2023;18(2):e0281916. doi: 10.1371/journal.pone.0281916

6. Naqvi A, Manglik N, Dudrey E, et al. Evaluating the performance of a low-cost mobile phone attachable microscope in cervical cytology. BMC Women’s Health. 2020;20:60. doi: 10.1186/s12905-020-00902-0

7. Choudhury D, Dolezal JM, Dyer E, et al. Developing a low-cost, open-source, locally manufactured workstation and computational pipeline for automated histopathology evaluation using deep learning. EBioMedicine. 2024;107:105276. doi: 10.1016/j.ebiom.2024.105276

8. Campanella G, Hanna MG, Geneslaw L, et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat Med. 2019;25(8):1301-1309. doi: 10.1038/s41591-019-0508-1

9. Bao H, Sun X, Zhang Y, et al. The artificial intelligence-assisted cytology diagnostic system in large-scale cervical cancer screening: a population-based cohort study of 0.7 million women. Cancer Med. 2020;9(18):6896-6906. doi: 10.1002/cam4.3296

10. Ting DSW, Cheung CY, Lim G, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA. 2017;318(22):2211-2223. doi: 10.1001/jama.2017.18152

11. Holmström, O., Linder, N., Kaingu, H., et al. Point-of-care digital cytology with artificial intelligence for cervical cancer screening in a resource-limited setting. JAMA Netw Open. 2021;4(3):e211740. doi: 10.1001/jamanetworkopen.2021.1740

12. Hijazi A, Bifulco C, Baldin P, Galon J. Digital pathology for better clinical practice. Cancers. 2024;16(9):1686. doi: 10.3390/cancers16091686

13. World Health Organization. Ethics and Governance of Artificial Intelligence for Health: WHO Guidance. World Health Organization. Available from: https://www.who. int/publications/i/item/9789240029200. [Last accessed on January 19, 2026].

14. Bera K, Schalper KA, Rimm DL, Velcheti V, Madabhushi A. Artificial intelligence in digital pathology—new tools for diagnosis and precision oncology. Nat Rev Clin Oncol. 2019;16(11):703-715. doi: 10.1038/s41571-019-0252-y

15. Fleming KA, Horton S, Wilson ML, et al. The Lancet Commission on diagnostics: transforming access to diagnostics. Lancet. 2021;398(10315):1997-2050. doi: 10.1016/S0140-6736(21)00673-5

16. Paez A. Gray literature: an important resource in systematic reviews. J Evid Based Med. 2017;10(3):233-240. doi: 10.1111/jebm.12266

17. Grames EM, Stillman AN, Tingley MW, Elphick CS. An automated approach to identifying search terms for systematic reviews using keyword co-occurrence networks. Methods Ecol Evol. 2019;10(9):1645-1654. doi: 10.1111/2041-210X.13268

18. Page MJ, McKenzie JE, Bossuyt PM, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;372:n71. doi: 10.1136/bmj.n71

19. Ciecierski-Holmes T, Singh R, Axt M, et al. Artificial intelligence for strengthening healthcare systems in low-and middle-income countries: a systematic scoping review. NPJ Digit Med. 2022;5:162. doi: 10.1038/s41746-022-00700-y

20. Banbury C, Reddi VJ, Lam M, et al. Benchmarking tiny machine learning on microcontrollers. arXiv. Preprint posted online 2003. doi: 10.48550/arXiv.2003.04821

21. Wofk D, Ma F, Yang TJ, Karaman S, Sze V. FastDepth: Fast monocular depth estimation on embedded systems. In: 2019 International Conference on Robotics and Automation (ICRA), 2019:6101-6108. doi: 10.1109/ICRA.2019.8794182

22. Farhadipour A. Lung and colon cancer detection with convolutional neural networks and adaptive histogram equalization. Iran J Comput Sci. 2024;7(3):381-395. doi: 10.1007/s42044-023-00161-w

23. Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115-118. doi: 10.1038/nature21056

24. Haenssle HA, Fink C, Toberer F, et al. Man against machine reloaded: performance of a market-approved convolutional neural network in classifying a broad spectrum of skin lesions in comparison with 96 dermatologists working under less artificial conditions. Ann Oncol. 2020;31(1):137- 143. doi: 10.1016/j.annonc.2019.10.013

25. Kaissis GA, Makowski MR, Rückert D, Braren RF. Secure, privacy-preserving and federated machine learning in medical imaging. Nat Mach Intell. 2020;2:305-311. doi: 10.1038/s42256-020-0186-1

26. Fujisawa Y, Otomo Y, Ogata Y, et al. Deep-learning-based, computer-aided classifier developed with a small dataset of clinical images surpasses board-certified dermatologists in skin tumour diagnosis. Br J Dermatol. 2019;180(2):373-381. doi: 10.1111/bjd.16924

27. Sze V, Chen YH, Yang TJ, Emer JS. Efficient processing of deep neural networks: a tutorial and survey. Proc IEEE. 2017;105(12):2295-2329. doi: 10.1109/JPROC.2017.2761740

28. Valverde JM, Shatillo A, Tohka J. Sauron U-Net: simple automated redundancy elimination in medical image segmentation via filter pruning. Neurocomputing. 2024;594:127817. doi: 10.1016/j.neucom.2024.127817

29. Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: transformers for image recognition at scale. arXiv. Preprint posted online 2010. doi: 10.48550/arXiv.2010.11929

30. Aburass S, Dorgham O, Al Shaqsi J, et al. Vision transformers in medical imaging: a comprehensive review of advancements and applications across multiple diseases. J Digit Imaging. 2025;38:3928-3971. doi: 10.1007/s10278-025-01481-y

31. Zhou Z, Sodha V, Rahman Siddiquee MMR, et al. Models genesis: generic autodidactic models for 3D medical image analysis. Med Image Anal. 2021;67:101840. doi: 10.1016/j.media.2020.101840

32. Azizi S, Mustafa B, Ryan F, et al. Big self-supervised models advance medical image classification. arXiv. Preprint posted online 2021. doi: 10.48550/arXiv.2101.05224

33. Boerkamp C, Thomas AJ. QuantU-Net: efficient wearable medical imaging using bitwidth as a trainable parameter. arXiv. Preprint posted online 2025. doi: 10.48550/arXiv.2503.08719.

34. Nguyen SA, Phan NL, Dao VH, et al. BlazeNeo: blazing fast polyp segmentation and neoplasm detection. arXiv. Preprint posted online 2022. doi: 10.48550/arXiv.2503.08719

35. Ji M, Al-Ars Z, Hofstee P, Chang Y, Zhang B. FPQNet: fully pipelined and quantized CNN for ultra-low latency image classification on FPGAs using OpenCAPI. Electronics. 2023;12(19):4085. doi: 10.3390/electronics12194085

36. An NS, Lan PN, Hang DV, et al. BlazeNeo: blazing fast polyp segmentation and neoplasm detection. arXiv. Preprint posted online 2022. doi: 10.48550/arXiv.2203.00129

37. Ji M, Al-Ars Z, Hofstee P, Chang Y, Zhang B. FPQNet: fully pipelined and quantized CNN for ultra-low latency image classification on FPGAs using OpenCAPI. Electronics. 2023;12(19):4085. doi: 10.3390/electronics12194085

38. AskariHemmat MH, Honari S, Rouhier L, et al. U-Net fixed-point quantization for medical image segmentation. arXiv. Preprint posted online 2019. doi: 10.48550/arXiv.1908.01073

39. Tasci M, Istanbullu A, Tumen V, Kosunalp S. FPGA-QNN: quantized neural network hardware acceleration on FPGAs. Appl Sci. 2025;15(2):688.doi: 10.3390/app1502068

40. Yurdem B, Kuzlu M, Gullu MK, Catak FO, Tabassum M. Federated learning: Overview, strategies, applications, tools and future directions. Heliyon. 2024;10(19):e38137. doi: 10.1016/j.heliyon.2024.e38137

41. Sheller MJ, Edwards B, Reina GA, et al. Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Sci Rep. 2020;10(1):12598. doi: 10.1038/s41598-020-69250-1

42. Yan Y, Li X, Cui K, Sun H, Yu Z. FreeNet: An efficient frequency-domain early exiting network for dynamic inference. Knowl Based Syst. 2025;314:113155. doi: 10.1016/j.knosys.2025.113155

43. Liu Q, Tian Z, Wang N, Lin Y. DRL-based dependent task offloading with delay-energy tradeoff in medical image edge computing. Complex Intell Syst. 2024;10(3):3283-3304. doi: 10.1007/s40747-023-01322-x

44. Rivenson Y, Zhang Y, Günayd?n H, Teng D, Ozcan A. Phase recovery and holographic image reconstruction using deep learning in neural networks. Light Sci Appl. 2018;7:17141. doi: 10.1038/lsa.2017.141

45. Bian Y, Xing T, Jiao K, et al. Computational portable microscopes for point-of-care-test and tele-diagnosis. Cells. 2022;11(22):3670. doi: 10.3390/cells11223670

46. Han GR, Goncharov A, Eryilmaz M, et al. Machine learning in point-of-care testing: innovations, challenges, and opportunities. Nat Commun. 2025;16:3165. doi: 10.1038/s41467-025-58527-6

47. Zhu W, Gong C, Kulkarni N, Nguyen CD, Kang D. Smartphone-based microscopes. In: Smartphone Based Medical Diagnostics. Academic Press; 2020:159-175.

48. Dwork C, Roth A. The algorithmic foundations of differential privacy. Found Trends Theor Comput Sci. 2014;9(3–4):211-407. doi: 10.1561/0400000042

49. Gilad-Bachrach R, Dowlin N, Laine K, et al. CryptoNets: Applying neural networks to encrypted data with high throughput and accuracy. Proceedings of Machine Learning Research. 2016. Available from: https://proceedings.mlr. press/v48/gilad-bachrach16.html [last accessed on].

50. Nebeker C, Torous J, Bartlett Ellis RJ. Building the case for actionable ethics in digital health research supported by artificial intelligence. BMC Med. 2019;17:137. doi: 10.1186/s12916-019-1377-7

51. Shepherd C, Markantonakis K. Trusted Execution Environments. Springer; 2024. doi: 10.1007/978-3-031-55561-9

52. Liu X, Glocker B, McCradden MM, et al. The medical algorithmic audit. Lancet Digit. Health. 2022;4(5):e384-e397. doi: 10.1016/S2589-7500(22)00003-6

53. Allahqoli L, Laganà AS, Mazidimoradi A, et al. Diagnosis of cervical cancer and pre-cancerous lesions by artificial intelligence: a systematic review. Diagnostics. 2022;12(11):2771. doi: 10.3390/diagnostics12112771

54. Dwork C, Roth A. The algorithmic foundations of differential privacy. Found Trends Theor Comput Sci. 2014;9(3-4):211-407. doi: 10.1561/0400000042

55. Mertz M, Toskovich K, Shields G, Attema G, Dumond J, Cameron E. Exploring trust factors in AI-healthcare integration: a rapid review. Front Artif Intell. 2025;8:1658510. doi: 10.3389/frai.2025.1658510

56. Linder N, Nyirenda D, Mårtensson A, et al. AI supported diagnostic innovations for impact in global women’s health. BMJ. 2025;391:e086009. doi: 10.1136/bmj-2025-086009

57. Valles-Coral MA, Pinedo L, Rodríguez C, et al. Application of artificial intelligence in cervical cytology: a systematic review of deep learning models, datasets, and reported metrics. Front Big Data. 2026;8:1678863. doi: 10.3389/fdata.2025.1678863

58. Tschandl, P., Rinner, C., Apalla, Z., et al. Human-computer collaboration for skin cancer recognition. Nat Med. 2020;26(8):1229-1234. doi: 10.1038/s41591-020-0942-0

59. Liu L, Liu J, Su Q, Chu Y, Xia H, Xu R. Performance of artificial intelligence for diagnosing cervical intraepithelial neoplasia and cervical cancer: a systematic review and meta-analysis. EclinicalMedicine. 2024;80:102992. doi: 10.1016/j.eclinm.2024.102992

60. Witkowski, A. M., Burshtein, J., Christopher, M., et al. Clinical utility of a digital dermoscopy image-based artificial intelligence device in the diagnosis and management of skin cancer by dermatologists. Cancers. 2024;16(21):3592. doi: 10.3390/cancers16213592

61. Breslauer, D. N., Maamari, R. N., Switz, N. A., Lam, W. A., Fletcher, D. A. Mobile phone based clinical microscopy for global health applications. PLoS ONE. 2009;4(7):e6320. doi: 10.1371/journal.pone.0006320

62. Kabukye, J. K., Namugga, J., Mpamani, C. J., et al. Implementing smartphone-based telemedicine for cervical cancer screening in Uganda: qualitative study of stakeholders’ perceptions. J Med Internet Res. 2023;25:e45132. doi: 10.2196/45132

63. Bai, J., Li, N., Ye, H., et al. AI-assisted cervical cytology precancerous screening for high-risk population in resource-limited regions using a compact microscope. Nat Commun. 2025;16:7429. doi: 10.1038/s41467-025-62589-x

64. Baller SP, Jindal A, Chadha M, Gerndt M. DeepEdgeBench: benchmarking deep neural networks on edge devices. 2021 IEEE International Conference on Cloud Engineering (IC2E), 2021:20-30. doi: 10.1109/IC2E52221.2021.00016

65. Kadar Mohamed Jabarullah MA, Chakka SN, Kanungo S. Edge-cloud hybrid architecture for distributed AI applications. 2025 International Conference on Computing Technologies & Data Communication (ICCTDC), 2025:1-5. doi: 10.1109/ICCTDC64446.2025.11158770

66. Shen M, Zou Z, Bao H, et al. Cost-effectiveness of artificial intelligence-assisted liquid-based cytology testing for cervical cancer screening in China. Lancet Reg Health West Pac. 2023;34:100726. doi: 10.1016/j.lanwpc.2023.100726

67. Vayena E, Blasimme A, Cohen IG. Machine learning in medicine: addressing ethical challenges. PLoS Med. 2018;15(11):e1002689. doi: 10.1371/journal.pmed.1002689

68. Pham T. Ethical and legal considerations in healthcare AI: innovation and policy for safe and fair use. R Soc Open Sci. 2025;12(5):241873. doi: 10.1098/rsos.241873

69. Wang T, Guo J, Zhang B, Yang G, Li D. Deploying AI on edge: advancement and challenges in edge intelligence. Mathematics. 2025;13(11):1878. doi: 10.3390/math13111878

70. Zhang ZM. Ethics and governance of trustworthy medical artificial intelligence. BMC Med Inform Decis Mak. 2023;23(1):7. doi: 10.1186/s12911-023-02103-9

71. López DM, Rico-Olarte C, Blobel B, Hullin C. Challenges and solutions for transforming health ecosystems in low-and middle-income countries through artificial intelligence. Front Med. 2022;9:958097. doi: 10.3389/fmed.2022.958097

72. Mittelstadt BD, Floridi L, et al. The ethics of algorithms: mapping the debate. Big Data Soc. 2016;3(2):1-21. doi: 10.1177/2053951716679679

73. Marey A, Ambrozaite O, Afifi A, et al. A perspective on AI implementation in medical imaging in LMICs: challenges, priorities, and strategies. Eur Radiol. 2025;35(5):2985-2995. doi: 10.1007/s00330-025-12031-z

74. Yang J, Dung NT, Thach PN, et al. Generalizability assessment of AI models across hospitals in a low-middle and high income country. Nat Commun. 2024;15:8270. doi: 10.1038/s41467-024-52618-6

75. Ienca M, Vayena E. On the responsible use of digital data to tackle the COVID-19 pandemic. Nat Med. 2020;26(8):1183- 1185. doi: 10.1038/s41591-020-0832-5

76. Mehta MC. AI & healthcare in low- and middle-income countries. ITU-T Workshop Presentation. Available from: https://www.itu.int/en/ITU-T/Workshops-and- Seminars/20181114/Documents/Mehul%20C%20Mehta_ Presentation.pdf [Last accessed on November 30, 2026].

77. Ankolekar A, Boie S, Abdollahyan M, et al. Advancing breast, lung and prostate cancer research with federated learning: a systematic review. npj Digit Med. 2025;8:314. doi: 10.1038/s41746-025-01591-5

78. Ali Z, Waqar M, Kim A. Federated learning in public health: a systematic review of decentralized, equitable, and secure disease prevention approaches. Healthcare. 2025;13(21):2760. doi: 10.3390/healthcare13212760

79. Li T, Wandella A, Gomer R, Al-Mafazy MH. Operationalizing health data governance for AI innovation in low-resource government health systems: a practical implementation perspective from Zanzibar. Data Policy. 2024;6:e63. doi: 10.1017/dap.2024.65