Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM67825
Volume:
10 |
10 |
Oct 2026
Pages:
1-12
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Professor in ECE SOET
Christ University
Department of Computer Science
Maharani Cluster University
Computer Science & Technology
RRIT (VTU Autonomous)
Department of Computer Science
Maharani Cluster University
Cancer care increasingly depends on the ability to find malignant cells with sub-millimetre precision and to act on them without damaging the healthy tissue around them. This paper examines how artificial intelligence (AI) and robotic systems are converging into a closed-loop clinical workflow that can be usefully described as “detect, target, and confirm.” In this model, AI operates as the cognitive layer, parsing radiological images, histopathology slides, and molecular biomarker data to localize tumours and characterize their genetic and phenotypic traits, while robotic platforms — ranging from macro-scale surgical manipulators to magnetically steered micro- and nanorobots — translate that intelligence into physical action inside a defined region of the body. We review the architecture of this loop across three stages: detection through deep-learning image analysis and multi-omic data fusion; targeting through robot-assisted surgery, image-guided biopsy, and actively steered drug carriers; and confirmation through intraoperative sensing, real-time imaging feedback, and biomarker verification that closes the control loop and lets the system adapt mid-procedure. Evidence from recent robotic-surgical studies, nanorobotic simulations, and deep-learning segmentation challenges is synthesised to illustrate the current capability and maturity of each stage. We also discuss unresolved challenges, including the generalizability of imaging models across patient populations and scanners, the difficulty of navigating soft, deformable tissue at the microscale, regulatory and safety questions, and the burden of integrating imaging, robotics, and biological data into a single decision pipeline. We conclude that although no single commercial system yet performs the entire loop autonomously, its individual components are maturing quickly enough that a genuinely closed detect-target-confirm system for localized cancer care is a realistic near-term objective rather than a speculative one.
KEYWORDS
Artificial intelligence and robotics are converging into a workflow that can reasonably be described as a detect-target-confirm loop for localized cancer care, with AI serving as the system's interpretive layer and robotics, at scales ranging from full-sized surgical arms to nanometre-scale carriers, serving as its means of physical action. The detection stage is the most mature, supported by a large and fast-growing body of deep-learning research on tumour segmentation and multimodal diagnosis. The targeting stage is maturing quickly on the surgical side, where real-patient evidence already shows measurable gains in precision and outcomes, and is progressing rapidly but still preclinically on the nanorobotic side. The confirmation stage, which is what actually closes the loop and allows adaptive correction rather than a one-shot plan, remains the least standardised of the three and is the area most likely to determine how quickly this technology moves from an assembly of promising components into a single, reliably closed-loop clinical system. None of the individual pieces reviewed here are speculative; what remains speculative is how soon, and how completely, they will be integrated.
[1] Leszczyńska A, Obuchowicz R, Strzelecki M, Seweryn M. The integration of artificial intelligence into robotic cancer surgery: a systematic review. Journal of Clinical Medicine. 2025 Sep 1;14(17):6181. https://www.mdpi.com/2077-0383/14/17/6181 [2] Najar Najafi N, Hajihassani H, Azimzadeh Irani M. The impact of artificial intelligence on cancer diagnosis and treatment: a review. Cancer informatics. 2025 Sep;24:11769351251371273. https://journals.sagepub.com/doi/full/10.1177/11769351251371273 [3] Tiwari A, Mishra S, Kuo TR. Current AI technologies in cancer diagnostics and treatment. Molecular cancer. 2025 Jun 2;24(1):159. https://link.springer.com/article/10.1186/s12943-025-02369-9 [4] Ng J, Wah K. AI-enhanced robotic hands: a breakthrough in early tumour detection and removal. Journal of Robotic Surgery. 2026 Feb 5;20(1):218. https://link.springer.com/article/10.1007/s11701-026-03159-1 [5] Wah JN. The rise of robotics and AI-assisted surgery in modern healthcare. Journal of Robotic Surgery. 2025 Jun 20;19(1):311. https://link.springer.com/article/10.1007/s11701-025-02485-0 [6] Kavousinejad S. Simulation of nanorobots with artificial intelligence and reinforcement learning for advanced cancer cell detection and tracking. arXiv preprint arXiv:2411.02345. 2024 Nov 4. https://arxiv.org/abs/2411.02345 [7] Das KP. Nanoparticles and convergence of artificial intelligence for targeted drug delivery for cancer therapy: Current progress and challenges. Frontiers in Medical Technology. 2023 Jan 6;4:1067144. http://frontiersin.org/journals/medical-technology/articles/10.3389/fmedt.2022.1067144/full [8] Anto M, Mukherjee K, Mukherjee K. Nano bio-robots: a new frontier in targeted therapeutic delivery. Frontiers in Robotics and AI. 2025 Nov 6;12:1639445. https://www.frontiersin.org/journals/robotics-and-ai/articles/10.3389/frobt.2025.1639445/full [9] Leong WY. Biohybrid micro-robots for targeted drug delivery in cancer therapy. Engineering Proceedings. 2025 Dec 24;120(1):4. https://www.mdpi.com/2673-4591/120/1/4 [10] Olawade DB, Clement David-Olawade A, Adereni T, Egbon E, Teke J, Boussios S. Integrating AI into cancer immunotherapy—A narrative review of current applications and future directions. Diseases. 2025 Jan 20;13(1):24. https://www.mdpi.com/2079-9721/13/1/24
Publication Date
10/22/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
2
Total views since publication
PDF Downloads
5
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...