A5032527419- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Colorectal Cancer Screening and Detection
- Lung Cancer Diagnosis and Treatment
- AI in cancer detection
- Medical Imaging Techniques and Applications
- Advanced Neural Network Applications
- Robotics and Sensor-Based Localization
- Surgical Simulation and Training
- Gastric Cancer Management and Outcomes
- Medical Imaging and Analysis
- Augmented Reality Applications
- Advanced Image and Video Retrieval Techniques
- COVID-19 diagnosis using AI
- Image Retrieval and Classification Techniques
- Advanced X-ray and CT Imaging
- Colorectal Cancer Surgical Treatments
- Advanced Vision and Imaging
- Gastrointestinal Bleeding Diagnosis and Treatment
- 3D Shape Modeling and Analysis
- Anatomy and Medical Technology
- Computer Graphics and Visualization Techniques
- Soft Robotics and Applications
- Retinal Imaging and Analysis
- Pancreatic and Hepatic Oncology Research
Nagoya University
2016-2025
National Institute of Informatics
2018-2025
University of Tsukuba
2006-2024
National Institute of Technology, Kumamoto College
2024
National Institute of Technology, Kagoshima College
2024
The Cancer Institute Hospital
2024
Aichi Cancer Center
2016-2024
Tokyo Denki University
2020
Osaka University
2014-2020
Blazegraph (United States)
2020
We propose a novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes. Models trained with AGs implicitly learn suppress irrelevant regions in an input image while highlighting salient features useful specific task. This enables us eliminate the necessity using explicit external tissue/organ localisation modules cascaded convolutional neural networks (CNNs). can be easily integrated into standard CNN architectures...
Background: Computer-aided diagnosis (CAD) for colonoscopy may help endoscopists distinguish neoplastic polyps (adenomas) requiring resection from nonneoplastic not resection, potentially reducing cost. Objective: To evaluate the performance of real-time CAD with endocytoscopes (×520 ultramagnifying colonoscopes providing microvascular and cellular visualization colorectal after application narrow-band imaging [NBI] methylene blue staining modes, respectively). Design: Single-group,...
The adenoma detection rate is an established quality indicator for colonoscopy. For instance, a 1% increase in the was associated with 3% decrease interval colorectal cancer incidence.1Corley D.A. Jensen C.D. Marks A.R. et al.Adenoma and risk of death.N Engl J Med. 2014; 370: 1298-1306Crossref PubMed Scopus (1166) Google Scholar However, previous meta-analysis showed that approximately 26% neoplastic diminutive polyps were missed single colonoscopy.2van Rijn J.C. Reitsma J.B. Stoker J....
Convolutional neural networks (CNNs) have revolutionized medical image analysis over the past few years. The U-Net architecture is one of most well-known CNN architectures for semantic segmentation and has achieved remarkable successes in many different applications. consists standard convolution layers, pooling upsampling layers. These layers learn representative features input images construct segmentations based on features. However, learned by are not distinctive when differences among...
A robust automated segmentation of abdominal organs can be crucial for computer aided diagnosis and laparoscopic surgery assistance. Many existing methods are specialized to the individual struggle deal with variability shape position organs. We present a general, fully-automated method multi-organ computed tomography (CT) scans. The is based on hierarchical atlas registration weighting scheme that generates target specific priors from an database by combining aspects multi-atlas patch-based...
In the treatment of ulcerative colitis (UC), an incremental benefit achieving histologic healing beyond that endoscopic mucosal has been suggested; persistent inflammation increases risk exacerbation and dysplasia. However, identification is extremely difficult using conventional endoscopy. Furthermore, reproducibility disease activity poor. We developed evaluated a computer-aided diagnosis (CAD) system to predict endocytoscopy (EC; 520-fold ultra-magnifying endoscope).We accuracy CAD test...
Recently, the American Society of Gastrointestinal Endoscopy established Preservation and Incorporation Valuable Endoscopic Innovations1Rex D.K. et al.Gastrointest Endosc. 2011; 73: 419-422Abstract Full Text PDF PubMed Scopus (433) Google Scholar for diminutive colorectal polyps. Innovations suggests that, if an endoscopist diagnoses agreement >90% in determining postpolypectomy surveillance intervals a negative predictive value with adenomatous histology, pathologic diagnosis might not be...
BACKGROUND: Artificial intelligence using computer-aided diagnosis (CADx) in real time with images acquired during colonoscopy may help colonoscopists distinguish between neoplastic polyps requiring removal and nonneoplastic not removal. In this study, we tested whether CADx analyzed helped decision-making process. METHODS: We performed a multicenter clinical study comparing novel CADx-system that uses real-time ultra-magnifying polyp visualization standard visual inspection of small (≤5 mm...
An automated segmentation method is presented for multi-organ in abdominal CT images. Dictionary learning and sparse coding techniques are used the proposed to generate target specific priors segmentation. The simultaneously learns dictionaries which have reconstructive power classifiers discriminative ability from a set of selected atlases. Based on learnt classifiers, probabilistic atlases then generated provide unseen final obtained by applying post-processing step based graph-cuts...
Abstract Background and study aims Decisions concerning additional surgery after endoscopic resection of T1 colorectal cancer (CRC) are difficult because preoperative prediction lymph node metastasis (LNM) is problematic. We investigated whether artificial intelligence can predict LNM presence, thus minimizing the need for surgery. Patients methods Data on 690 consecutive patients with CRCs that were surgically resected in 2001 – 2016 retrospectively analyzed. divided into two groups...
Duplication of image regions is a common method for manipulating original images, using typical software like Adobe Photoshop, 3DS MAX, etc. In this study, we propose duplication detection approach that can adopt two robust features based on discrete wavelet transform (DWT) and kernel principal component analysis (KPCA). Both schemes provide excellent representations the data block matching. Multiresolution coefficients KPCA-based projected vectors corresponding to image-blocks are arranged...
Abstract Background and study aims Invasive cancer carries the risk of metastasis, therefore, ability to distinguish between invasive cancerous lesions less-aggressive is important. We evaluated a computer-aided diagnosis system that uses ultra-high (approximately × 400) magnification endocytoscopy (EC-CAD). Patients methods generated an image database from consecutive series 5843 images 375 lesions. For construction diagnostic algorithm, 5543 238 were randomly extracted for machine...
Recent advances in 3D fully convolutional networks (FCN) have made it feasible to produce dense voxel-wise predictions of full volumetric images. In this work, we show that a multi-class FCN trained on manually labeled CT scans seven abdominal structures (artery, vein, liver, spleen, stomach, gallbladder, and pancreas) can achieve competitive segmentation results, while avoiding the need for handcrafting features or training organ-specific models. To end, propose two-stage, coarse-to-fine...