A5075057502- Advanced X-ray and CT Imaging
- Medical Imaging and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Advanced Neural Network Applications
- Orthopaedic implants and arthroplasty
- Radiation Dose and Imaging
- Cell Image Analysis Techniques
- Orthopedic Surgery and Rehabilitation
- COVID-19 diagnosis using AI
- Frailty in Older Adults
- Generative Adversarial Networks and Image Synthesis
- Digital Imaging for Blood Diseases
- Shoulder Injury and Treatment
- Hip disorders and treatments
- Total Knee Arthroplasty Outcomes
- Artificial Intelligence in Healthcare and Education
- Anatomy and Medical Technology
- Surgical Simulation and Training
- Nutrition and Health in Aging
- Augmented Reality Applications
- Dental Radiography and Imaging
- Human Pose and Action Recognition
- Tuberculosis Research and Epidemiology
- Cellular Mechanics and Interactions
Fujifilm (Japan)
2023-2024
Nara Institute of Science and Technology
2016-2023
Fukujuji Hospital
2023
Japan Anti Tuberculosis Association
2023
Nagoya University
2017
National Institute of Technology, Niihama College
2013
We propose a method for automatic segmentation of individual muscles from clinical CT. The uses Bayesian convolutional neural networks with the U-Net architecture, using Monte Carlo dropout that infers an uncertainty metric in addition to label. evaluated performance proposed two data sets: 20 fully annotated CTs hip and thigh regions 18 partially are publicly available Cancer Imaging Archive (TCIA) database. experiments showed Dice coefficient (DC) 0.891±0.016 (mean±std) average symmetric...
The purpose of the study was to develop a deep learning network for estimating and constructing highly accurate 3D bone models directly from actual X-ray images verify its accuracy. data used were 173 computed tomography (CT) 105 healthy wrist joint. To compensate small size dataset, digitally reconstructed radiography (DRR) generated CT as training instead images. DRR-like in test adapted network, high-accuracy estimation model set possible. shape radius ulna estimated with accuracies 1.05...
Abstract Background Artificial intelligence-based computer-aided detection (AI–CAD) for tuberculosis (TB) has become commercially available and several studies have been conducted to evaluate the performance of AI–CAD pulmonary in clinical settings. However, little is known about its applicability community-based active case-finding (ACF) TB. Methods We analysed an anonymized data set obtained from a ACF Cambodia, targeting persons aged 55 years or over, with any TB symptoms, such as chronic...
In this paper, we propose a real-time visualization system utilizing Augmented Reality Technology for electromagnetics education. It gives an image of magnetic field generated by bar magnet with piece iron in real-time, however the and are represented mock ones. newly proposed system, these mocks captured web camera, mesh needed calculation is deformed. Subsequently, finite element analysis carried out very short time then immediately visualized. Thereby, it is, observable that flux lines...
CT is commonly used in orthopedic procedures. MRI along with to identify muscle structures and diagnose osteonecrosis due its superior soft tissue contrast. However, has poor contrast for bone structures. Clearly, it would be helpful if a corresponding were available, as boundaries are more clearly seen standardized (i.e., Hounsfield) units. Therefore, we aim at MR-to-CT synthesis. The CycleGAN was successfully applied unpaired MR images of the head, these do not have much variation...
With the increasing usage of radiograph images as a most common medical imaging system for diagnosis, treatment planning, and clinical studies, it is increasingly becoming vital factor to use machine learning-based systems provide reliable information surgical pre-planning. Segmentation pelvic bone in critical preprocessing step some applications such automatic pose estimation disease detection. However, encoder-decoder style network known U-Net has demonstrated limited results due...
Protein localization in cells has been analyzed by fluorescent labeling using indirect immunofluorescence and protein tagging. However, the relationships between of different proteins had not artificial intelligence. Here, we applied convolutional networks for prediction cytoskeletal from other proteins. Lamellipodia are one actin-dependent subcellular structures involved cell migration mainly generated Wiskott-Aldrich syndrome (WASP)-family verprolin homologous 2 (WAVE2) membrane remodeling...
Alignment of the bones in standing position provides useful information surgical planning. In total hip arthroplasty (THA), pelvic sagittal inclination (PSI) angle is an important factor planning cup alignment and has been estimated mainly from radiographs. Previous methods for PSI estimation used a patient-specific CT to create digitally reconstructed radiographs (DRRs) compare them with radiograph estimate relative between pelvis x-ray detector. this study, we developed method that...
In total hip arthroplasty, analysis of postoperative images is important to evaluate surgical outcome. Since CT most prevalent modality in orthopedic surgery, we aimed at the image. The challenge this work metal artifact caused by metallic implant, which reduces accuracy segmentation especially vicinity implant. Our goal was develop an automated method muscles images. paper, propose a that combines Normalized Metal Artifact Reduction (NMAR), one state-of-the-art reduction methods, and CNN-...
Abstract This paper presents methods of decomposition musculoskeletal structures from radiographs into multiple individual muscle and bone structures. While existing solutions require dual-energy scan for the training dataset are mainly applied to with high-intensity contrast, such as bones, we focused on superimposed muscles subtle contrast in addition bones. The problem is formulated an image translation between (1) a real X-ray (2) digitally reconstructed radiographs, each which contains...
We propose a method for automatic segmentation of individual muscles from clinical CT. The uses Bayesian convolutional neural networks with the U-Net architecture, using Monte Carlo dropout that infers an uncertainty metric in addition to label. evaluated performance proposed two data sets: 20 fully annotated CTs hip and thigh regions 18 partially are publicly available Cancer Imaging Archive (TCIA) database. experiments showed Dice coefficient (DC) 0.891 +/- 0.016 (mean std) average...
With the increasing usage of radiograph images as a most common medical imaging system for diagnosis, treatment planning, and clinical studies, it is increasingly becoming vital factor to use machine learning-based systems provide reliable information surgical pre-planning. Segmentation pelvic bone in critical preprocessing step some applications such automatic pose estimation disease detection. However, encoder-decoder style network known U-Net has demonstrated limited results due...
In total hip arthroplasty, analysis of postoperative medical images is important to evaluate surgical outcome. Since Computed Tomography (CT) most prevalent modality in orthopedic surgery, we aimed at the CT image. this work, focus on metal artifact caused by metallic implant, which reduces accuracy segmentation especially vicinity implant. Our goal was develop an automated method bones and muscles images. We propose a that combines Normalized Metal Artifact Reduction (NMAR), one...