노석범 (고려대학교) | 한빛사논문 > 한빛사

한빛사논문

조회223

고려대학교

CV File

ACS Nano, Apr 23 2026, | https://doi.org/10.1021/acsnano.6c02895 AI in Atomic Force Microscopy: Advancing Biological Nanoscale Imaging and Autonomous Discovery

Seungmin Lee ^{1 2 †}, Seokbeom Roh ^{3 4 †}, Hyowon Woo ^{1 5}^†, Gyudo Lee ^{3 4}, Hyo Gi Jung ⁶, Ki-Baek Lee ⁷, Hakho Lee ^{6 8 *}, Dae Sung Yoon^{9 10 11 *}, Jeong Hoon Lee ^{1 5 *}

¹KU-KIST Graduate School of Converging Science and Technology, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea.
²Institute of Advanced Machinery Design Technology, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea.
³Department of Biotechnology and Bioinformatics, Korea University, Sejong 30019, Republic of Korea.
⁴Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology, Korea University, Sejong 30019, Republic of Korea.
⁵Department of Integrative Energy Engineering, College of Engineering Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea.
⁶Center for Systems Biology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts 02114, United States.
⁷Department of Electrical Engineering, Kwangwoon University, 20 Kwangwoon-ro, Nowon, Seoul 01897, Republic of Korea.
⁸Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts 02115, United States.
⁹School of Biomedical Engineering, Korea University, 145 Anam-ro, Seongbuk, Seoul 02841, Republic of Korea.
¹⁰Interdisciplinary Program in Precision Public Health, Korea University, Seoul 02841, Republic of Korea.
¹¹Astrion Inc., Seoul 02841, Republic of Korea.

^†These authors contributed equally

^*Corresponding authors: correspondence to Hakho Lee, Dae Sung Yoon or Jeong Hoon Lee

Abstract

Atomic force microscopy (AFM) enables label-free nanoscale imaging and nanomechanical profiling but remains constrained by low throughput, operator dependence, and variability in data interpretation. Artificial intelligence (AI) transforms AFM into a scalable and adaptive platform. Initially applied in materials science for super-resolution imaging, tip deconvolution, segmentation, and force-curve analysis, AI approaches are now being extended to biological AFM. These methods support robust denoising of soft matter maps, automated recognition of heterogeneous structures, and three-dimensional reconstruction of biomolecular assemblies. This review provides an end-to-end workflow of AI-enabled AFM─from probe optimization and adaptive control to multimodal data integration─highlighting advances relevant to mechanobiology and biomedical engineering. By surveying studies with amyloid fibrils, extracellular vesicles, membranes, and living cells, we show how AI-AFM convergence enhances reproducibility, throughput, and clinical utility. AI-driven AFM is poised to enable disease modeling, therapeutic screening, and precision diagnostics, establishing itself as a next-generation tool for biomedical discovery.

논문정보