Infrastructure such as roads, tunnels and bridges needs periodical inspection. The conventional structure inspection method, in which a human inspector uses a crack gauge, may lead to problems such as measurement errors and lengthy inspection times. Mobile robots and image processing have been used in the infrastructure inspection field. An image sensor or any sensor is used for measuring the state of the infrastructures. It is necessary that the mobile robot knows its own position and posture during automatic inspection. Generally, the Global Positioning System (GPS) has been used to sense the position of the mobile robot. However, GPS is not usable in places with the ceilings such as under bridges and in tunnels. Therefore, we developed a system to sense the position and posture of mobile robots. This system uses laser projection markers and cameras, and it has a very simple configuration. The camera photographs a target structure and projection laser markers, and the position and posture of the camera and mobile robot were calculated by an image application. The system makes infrastructure inspection more effective and decreases the time needed for inspection. In this paper, we examined the number of necessary laser markers, and we verified our method by experiment.

Background/Objectives: Circulating tumor cells (CTCs) are important biomarkers for predicting prognosis and evaluating treatment efficacy in cancer. We developed the “CTC-Chip” system based on microfluidics, enabling highly sensitive CTC detection and prognostic assessment in lung cancer and malignant pleural mesothelioma. However, the final identification and enumeration of CTCs require manual intervention, which is time-consuming, prone to human error, and necessitates the involvement of experienced medical professionals. Medical image recognition using machine learning can reduce workload and improve automation. However, CTCs are rare in clinical samples, limiting the training data available to construct a robust CTC image recognition system. In this study, we established a highly accurate artificial intelligence-based CTC recognition system by pre-training convolutional neural networks using images from lung cancer cell lines. Methods: We performed transfer learning of convolutional neural networks. Initially, the models were pre-trained using images obtained from lung cancer cell lines. The model’s accuracy was improved by training with a limited number of clinical CTC images. Results: Transfer learning significantly improved the CTC classification accuracy to an average of 99.51%, compared to 96.96% for a model trained solely on pre-trained cell lines (p < 0.05). This approach showed notable efficacy when clinical training images were limited, achieving statistically significant accuracy improvements with as few as 17 clinical CTC images (p < 0.05). Conclusions: Overall, our findings demonstrate that pre-training with cancer cell lines enables rapid and highly accurate automated CTC recognition even with limited clinical data, significantly enhancing clinical applicability and potential utility across diverse cancer diagnostic workflows.

Background/Objectives: Appropriate biomarkers are necessary for early diagnosis and multidisciplinary treatment of pancreatic ductal adenocarcinoma (PDAC). In recent years, the clinical utility of circulating tumor cells (CTC) as biomarkers for various can-cers has been reported; however, their detection rate in PDAC remains low, and clinical evidence is not yet established. CTC detection methods with high reliability and per-formance are essential for clarifying the importance of CTC in patients with PDAC. Methods: A total of 5 mL peripheral blood samples were collected from 38 patients newly diagnosed with PDAC and 17 healthy controls. Negatively enriched cells were immunofluorescently stained with EpCAM-phycoerythrin and cell surface vi-mentin-fluorescein isothiocyanate (CSV). Images were automatically captured using an all-in-one fluorescence microscope. Cellular regions were detected from these images, and the average luminance of the cellular regions was calculated. A total of 9086 and 1071 cell images were obtained from patients with PDAC and healthy controls, respec-tively. Results: In the EpCAM assay, a threshold that included 95% of healthy individuals was optimal for distinguishing patients with PDAC from healthy controls, with a sensi-tivity, specificity, and area under the curve of 0.74, 0.76, and 0.84, respectively. At this threshold, the CTC-positivity rate in patients with PDAC was 76.3%. Conversely, the CSV assay failed to demonstrate a valid threshold to distinguish patients with PDAC from healthy controls. No significant differences were found between CTC and clini-copathological features among patients with PDAC. Conclusions: The method using high-resolution image scanning has the potential to identify CTC with greater objectiv-ity by quantifying cell luminance values.

Background/Objectives: Appropriate biomarkers are necessary for early diagnosis and multidisciplinary treatment of pancreatic ductal adenocarcinoma (PDAC). In recent years, the effectiveness of circulating tumor cells (CTCs) as biomarkers for various cancers has been reported; however, their detection rate in PDAC remains low, and sufficient evidence are not yet established. CTC detection methods with high reliability and performance are essential for clarifying the importance of CTCs in patients with PDAC. Methods: A total of 5 mL peripheral blood samples were collected from 38 patients newly diagnosed with PDAC and 17 healthy controls. Negative enriched cells were immunoflu-orescently stained with EpCAM-phycoerythrin and cell surface vimentin-fluorescein isothiocyanate(CSV). Images were automatically captured using an all-in-one fluorescence microscope. Cellular regions were detected from the captured images and the average lu-minance of the cellular regions was calculated. A total of 9086 and 1071 cell images were obtained from patients with PDAC and healthy controls, respectively. Results: In the Ep-CAM assay, a threshold that included 95% of healthy individuals was optimal for distin-guishing patients with PDAC from healthy controls, with a sensitivity, specificity, and AUC of 0.74, 0.76, and 0.84, respectively. At this threshold, the CTC-positivity rate in pa-tients with PDAC was 76.3%. Conversely, the CSV assay failed to demonstrate a valid threshold to distinguish patients with PDAC from healthy controls. No significant differ-ences were found between CTC and clinicopathological features among patients with PDAC. Conclusions: This method using high resolution image scanning has the potential to identify CTCs with greater objectivity by quantifying cell luminance values.