A5064312777- Cell Image Analysis Techniques
- Image Processing Techniques and Applications
- AI in cancer detection
- Medical Image Segmentation Techniques
- Digital Imaging for Blood Diseases
- Domain Adaptation and Few-Shot Learning
- COVID-19 diagnosis using AI
- Advanced Image and Video Retrieval Techniques
- Photoacoustic and Ultrasonic Imaging
- Image Retrieval and Classification Techniques
- Advanced Vision and Imaging
- Image and Object Detection Techniques
- Machine Learning and Algorithms
- Advanced Fluorescence Microscopy Techniques
- Single-cell and spatial transcriptomics
- 3D Printing in Biomedical Research
- Digital Holography and Microscopy
- Colorectal Cancer Screening and Detection
- Video Surveillance and Tracking Methods
- Text and Document Classification Technologies
- Optical Imaging and Spectroscopy Techniques
- Machine Learning and Data Classification
- Cellular Mechanics and Interactions
- Image Enhancement Techniques
- Gastrointestinal Bleeding Diagnosis and Treatment
Kyushu University
2003-2024
National Institute of Informatics
2016-2024
Kyushu University Hospital
2022-2024
Kyoto University Hospital
2019
Japan Science and Technology Agency
2019
Kyoto University
2019
Dai Nippon Printing (Japan)
2003-2018
Carnegie Mellon University
2010-2012
Automated digital histopathology image segmentation is an important task to help pathologists diagnose tumors and cancer subtypes. For pathological diagnosis of subtypes, usually change the magnification whole-slide images (WSI) viewers. A key assumption that importance magnifications depends on characteristics input image, such as In this paper, we propose a novel semantic method, called Adaptive-Weighting-Multi-Field-of-View-CNN (AWMF-CNN), can adaptively use features from with different...
Due to the enormous potential and impact that stem cells may have on regenerative medicine, there has been a rapidly growing interest for tools analyze characterize behaviors of these in vitro an automated high throughput fashion. Among behaviors, mitosis, or cell division, is important since proliferate renew themselves through mitosis. However, current systems measuring proliferation often require destructive sacrificial methods manipulation such as lysis staining. In this paper, we...
We present several algorithms for cell image analysis including microscopy restoration, event detection and tracking in a large population. The are integrated into an automated system capable of quantifying proliferation metrics vitro real-time. This offers unique opportunities biological applications such as efficient behavior discovery response to different culturing conditions adaptive experiment control. quantitatively evaluated our system's performance on 16 sequences with satisfactory...
Automated cell tracking in populations is important for research and discovery biology medicine. In this paper, we propose a method based on global spatio-temporal data association which considers hypotheses of initialization, termination, translation, division false positive an integrated formulation. Firstly, reliable tracklets (i.e., short trajectories) are generated by linking detection responses frame-by-frame association. Next, these globally associated over time to obtain final...
Cell segmentation in microscopy imagery is essential for many bioimage applications such as cell tracking. To segment cells from the background accurately, we present a pixel classification approach that independent of type or imaging modality. We train set Bayesian classifiers clustered local training image patches. Each classifier an expert to make decision its specific domain. The mixture experts determines how likely new pixel. demonstrate effectiveness this on four types with diverse...
Abstract Phase contrast time-lapse microscopy is a non-destructive technique that generates large volumes of image-based information to quantify the behaviour individual cells or cell populations. To guide development algorithms for computer-aided tracking and analysis, 48 image sequences, each spanning approximately 3.5 days, were generated with accompanying ground truths C2C12 myoblast cultured under 4 different media conditions, including fibroblast growth factor 2 (FGF2), bone...
Abstract Prognosis after neoadjuvant chemotherapy (NAC) for osteosarcoma is generally predicted using manual necrosis-rate assessments; however, necrosis rates obtained in these assessments are not reproducible and do adequately reflect individual cell responses. We aimed to investigate whether viable tumor density assessed a deep-learning model (DLM) reflects the prognosis of osteosarcoma. Seventy-one patients were included this study. Initially, DLM was trained detect cells, following...
Abstract Cell states are regulated by the response of signaling pathways to receptor ligand-binding and intercellular interactions. High-resolution imaging has been attempted explore dynamics these processes and, recently, multiplexed profiled cell achieving a comprehensive acquisition spatial protein information from cells. However, specificity antibodies is still compromised when visualizing activated signals. Here, we develop Precise Emission Canceling Antibodies (PECAbs) that have...
Photoacoustic(PA) imaging is a non-destructive and non-invasive technology for visualizing minute blood vessel structures in the body using ultrasonic sensors. In PA imaging, image quality of single-shot poor, it necessary to improve by averaging many images. Therefore, entire subject requires high costs. our study, we propose method images diffusion models. method, reverse process sensor information introduce guidance condition generate high-quality
Conventional cell tracking methods detect multiple cells in each frame (detection) and then associate the detection results successive time-frames (association). Most perform association task independently from task. However, there is no guarantee of preserving coherence between these tasks, lack may adversely affect performance. In this paper, we propose Motion Position Map (MPM) that jointly represents both for not only migration but also division. It guarantees such if a detected,...
Cell detection in microscopy images is essential for automated cell behavior analysis including shape and tracking. Robust high-density low-contrast still challenging since cells often touch partially overlap, forming a cluster with blurry intercellular boundaries. In such cases, current methods tend to detect multiple as cluster. If the control parameters are adjusted separate touching cells, other problems occur: single may be segmented into several regions, low-intensity regions not...
The geometric organization of collagen fibers in human reticular dermis and its relationship to that elastic remain unclear. tight packing complex intertwining dermal hinder accurate analysis fiber orientation. We hypothesized combined multiphoton microscopy biaxial extension could overcome this issue. Continuous observation fresh sheets under revealed the geometry network is maintained during expansion. Full-thickness thigh skin samples were biaxially extended cleared visualize entire...
Medical image segmentation is an important task in medical imaging and diagnosis. Data augmentation can substantially improve the accuracy of when dataset has a small amount images. However, data methods for are usually based on big models that require extensive search space. Furthermore, excessively complex often have heavy burden general healthcare organization or researcher. To address this problem, we propose method simple to implement even researcher transplant across various models....
Label-free, live cell recognition (i.e. instance segmentation) and tracking using computer vision-aided can be a powerful tool that rapidly generates multi-modal readouts of populations at single resolution. However, this technology remains hindered by the lack accurate, universal algorithms. This review presents related biological vision concepts to bridge these disciplines, paving way for broad applications in cell-based diagnostics, drug discovery, biomanufacturing.
The wound healing assay in vitro is widely used for research and discovery biology medicine. This allows observing the process which cells on edges of artificial migrate toward area. influence different culture conditions can be measured by change size For further investigation, more detailed measurements cell behaviors are required. In this paper, we present an application automatic tracking phase-contrast microscopy images to assay. under three have been analyzed. Our system track...
Objectives Existing endoscopic scores for ulcerative colitis (UC) objectively categorize disease severity based on the presence or absence of findings; therefore, it may not reflect range clinical within each category. However, inflammatory bowel (IBD) expert endoscopists and diagnose overall impression degree inflammation. This study aimed to develop an artificial intelligence (AI) system that can accurately represent assessment UC by IBD endoscopists. Methods A ranking‐convolutional neural...
Current cell culture practices are dependent upon human operators and remain laborious highly subjective, resulting in large variations inconsistent outcomes, especially when using visual assessments of confluency to determine the appropriate time subculture cells. Although efforts automate with robotic systems underway, majority such still require intervention subculture. Thus, it is necessary accurately objectively for passaging. Optimal stem culturing that maintains pluripotency while...