https://scholar.dgist.ac.kr/handle/20.500.11750/16192 2026-11-15T15:20:04Z https://scholar.dgist.ac.kr/handle/20.500.11750/61097 Title: Multi-modality image fusion model of AFM-derived extracellular vesicles for NSCLC subtype diagnosis Author(s): Kim, Haeyoung; 박수현; Lee, Yoonhee; Ban, Jaepil; Koo, Gyogwon Abstract: Non-small cell lung cancer (NSCLC) comprises multiple subtypes with distinct treatment strategies, making accurate subtype classification important. Therefore, this study aims to develop a multi-modality AFM-based deep learning model to improve NSCLC subtype diagnosis because extracellular vesicles (EVs) measured by atomic force microscopy (AFM) contain nanoscale biophysical information with diagnostic potential. The proposed model introduces two key components: (i) an intra-image feature extractor (IFE), which captures parameter-specific local and global dependencies, and (ii) a cross-image feature fusion module (CFFM), which mitigates domain mismatch among heterogeneous AFM parameters. Through three fusion strategies at the image, low-level feature, and high-level feature stages, the proposed model simultaneously learns intraparameter and inter-parameter relationships. The proposed model achieved an accuracy of 0.9245 and an area under the receiver operating characteristic curve (AUROC) of 0.9804, outperforming the AFM-based conventional state-of-the-art (SOTA) model by improvements of 0.1328 in accuracy and 0.0273 in AUROC. These results demonstrate that the proposed multi-modality fusion approach achieves superior diagnostic performance for AFM-based EV analysis. Furthermore, the proposed framework has the potential to be extended to AFM-based analysis of other cell types and diseases once large-scale datasets are secured. Code is released at https://github.com/sunh124/MMIF_Model_of_AFM-derived_EV. 2026-09-30T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/59191 Title: METHOD AND DEVICE FOR PROVIDING INFORMATION FOR CANCER DIAGNOSIS BY USING EXTRACELLULAR VESICLES Author(s): 김해영; 구교권; 김영규; 김은주; 이윤희; 박수현 Abstract: This method utilizes machine learning on the basis of extracellular vesicles obtained through a liquid biopsy, so as to provide information necessary for efficient cancer diagnosis, and comprises: collecting learning data including surface characteristic images of extracellular vesicles extracted from cancer cells; using the learning data so as to construct an artificial intelligence diagnosis model; and deriving cancer-related disease information through the constructed artificial intelligence diagnosis model on the basis of surface characteristic data of extracellular vesicles to be diagnosed. https://scholar.dgist.ac.kr/handle/20.500.11750/58997 Title: Surface Tension-Guided Drop-and-Spread Inkjet Printing for Additive Fabrication of CNT Field-Effect Transistor Biosensors Author(s): Park, Soohyun; Shin, Minhye; Kim, Eunui; Kang, Hongki; Lee, Yoonhee Abstract: Carbon nanotube field-effect transistors (CNT FETs) are highly regarded in nanoelectronics for their superior electrical properties, yet their broader adoption in nanotechnology is hindered by challenges in scalable fabrication. These challenges are primarily related to controlling nanotube density and achieving consistent alignment at electrode junctions for large-scale production. Here, we present a novel in-place inkjet printing technique to construct CNT FETs, ensuring controlled numbers of connected CNTs. We print a series of pico-liter droplets of CNT ink onto prepatterned electrode arrays over a 4-in. silicon wafer, promoting additive device manufacturing without supplementary lithographic steps. Our technique leverages surface tension-driven flow, guiding droplet spread along electrodes, preventing unwanted CNT networks. This approach enhances manufacturing throughput and device yield and efficiently connects an individualized CNT array to electrodes with less than 10 tubes per device. Moreover, we demonstrate biosensing application by functionalizing devices with DNA aptamers, achieving serotonin detection at thresholds as low as 42 pM. This method establishes cost-efficient and simple micromanufacturing protocols essential for the mass production of CNT FET arrays, particularly beneficial for high-throughput bioassays. 2025-07-31T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/58695 Title: Deep Learning-Based Classification of NSCLC-Derived Extracellular Vesicles Using AFM Nanomechanical Signatures Author(s): Park, Soohyun; Kim, Youngkyu; Kim, Jung-Hee; Kim, Haeyoung; Kim, Kwang-Youl; Kim, Eunjoo; Koo, Gyogwon; Lee, Yoonhee Abstract: Nonsmall cell lung cancer (NSCLC) remains a leading cause of cancer-related mortality, with liquid biopsy emerging as a promising tool for noninvasive diagnostics. Extracellular vesicles (EVs) serve as molecular messengers of the tumor microenvironment, yet precise characterization methods remain limited. Using atomic force microscopy (AFM), we analyzed EVs from NSCLC subtypes (A549, PC9, PC9/GR) and nontumorigenic bronchial epithelial cells (BEAS-2B), revealing that A549-derived EVs exhibited significantly higher stiffness, likely due to KRAS mutation-associated lipid alterations. EGFR mutant EVs (PC9, PC9/GR) showed overlapping nanomechanical properties, correlating with their shared genetic background. To enhance classification, we implemented a DenseNet-based deep learning model for AFM image analysis, integrating nanomechanical and morphological features. This approach significantly improved diagnostic performance, achieving an AUC of 0.92, and notably, EVs from the A549 (KRAS mutant) cell line were classified with 96% accuracy. This study provides the first demonstration of the nanomechanical classification of NSCLC-derived EVs, highlighting the potential of deep learning-enhanced AFM analysis as a powerful tool for advancing liquid biopsy and precision diagnostics. Addressing sample variability and validating performance across clinical samples will be key to enabling its clinical translation. 2025-06-30T15:00:00Z