A5063270312- AI in cancer detection
- Advanced Vision and Imaging
- Radiomics and Machine Learning in Medical Imaging
- Video Coding and Compression Technologies
- Surgical Simulation and Training
- Image and Video Quality Assessment
- Gallbladder and Bile Duct Disorders
- Optical measurement and interference techniques
- Medical Imaging and Analysis
- Advanced Data Compression Techniques
- Advanced Image Processing Techniques
- Retinal Imaging and Analysis
- Advanced Image and Video Retrieval Techniques
- Robotics and Sensor-Based Localization
- Digital Imaging for Blood Diseases
- Pediatric Hepatobiliary Diseases and Treatments
- Medical Image Segmentation Techniques
- Advanced X-ray and CT Imaging
- Hepatocellular Carcinoma Treatment and Prognosis
- Image and Object Detection Techniques
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Anatomy and Medical Technology
- Pancreatic and Hepatic Oncology Research
- Advanced Neural Network Applications
- Medical Imaging Techniques and Applications
Muroran Institute of Technology
2022-2025
Kyushu Institute of Technology
2025
Konica Minolta (Japan)
2014-2023
Technische Hochschule Ingolstadt
2023
Panasonic (Japan)
2004-2015
Kavli Institute for the Physics and Mathematics of the Universe
2015
National Research University Higher School of Economics
2015
The University of Tokyo
2015
Tokyo University of Agriculture and Technology
2011
Hokkaido University
2000-2010
Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase safety operation through context-sensitive warnings semi-autonomous robotic or improve training surgeons via data-driven feedback. In up to 91% average precision has been reported phase recognition on an open data single-center video dataset. this work we investigated generalizability algorithms in a multicenter setting including more...
Changes in lobar volume of the liver and total hepatic function were studied 19 patients with biliary tract cancer who underwent right portal vein embolization as preoperative management for extensive resection. Computed tomography (CT) was performed to estimate before approximately 11 days after embolization. An indocyanine green (ICG) test 13 The calculated lobe decreased from 761 +/- 181 cm3 625 110 (P < .0001), whereas left increased 420 94 555 .0001). Thus, produced a gain 136 62 an...
In 2015 we began a sub-challenge at the EndoVis workshop MICCAI in Munich using endoscope images of ex-vivo tissue with automatically generated annotations from robot forward kinematics and instrument CAD models. However, limited background variation simple motion rendered dataset uninformative learning about which techniques would be suitable for segmentation real surgery. 2017, same Quebec introduced robotic 10 teams participating challenge to perform binary, articulating parts type da...
Domain Adaptation (DA) has recently raised strong interests in the medical imaging community. While a large variety of DA techniques been proposed for image segmentation, most these have validated either on private datasets or small publicly available datasets. Moreover, mostly addressed single-class problems. To tackle limitations, Cross-Modality (crossMoDA) challenge was organised conjunction with 24th International Conference Medical Image Computing and Computer Assisted Intervention...
The early detection of glaucoma is essential in preventing visual impairment. Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) a cost-effective manner, making screening more accessible. While AI models for from CFPs have shown promising results laboratory settings, their performance decreases significantly real-world scenarios due the presence out-of-distribution and low-quality images. To address this issue, we propose Intelligence Robust Glaucoma...
Radiation therapy plays a crucial role in cancer treatment, necessitating precise delivery of radiation to tumors while sparing healthy tissues over multiple days. Computed tomography (CT) is integral for treatment planning, offering electron density data accurate dose calculations. However, accurately representing patient anatomy challenging, especially adaptive radiotherapy, where CT not acquired daily. Magnetic resonance imaging (MRI) provides superior soft-tissue contrast. Still, it...
Purpose: The amount of coronary artery calcification (CAC) is a strong and independent predictor cardiovascular disease (CVD) events. In clinical practice, CAC manually identified automatically quantified in cardiac CT using commercially available software. This tedious time-consuming process large-scale studies. Therefore, number automatic methods that require no interaction semiautomatic very limited for the identification have been proposed. Thus far, comparison their performance has...
This paper proposes an automatic classification method based on machine learning in contrast-enhanced ultrasonography (CEUS) of focal liver lesions using the contrast agent Sonazoid. yields spatial and temporal features arterial phase, portal post-vascular as well max-hold images. The are classified benign or malignant again benign, hepatocellular carcinoma (HCC), metastatic tumor support vector machines (SVM) with a combination selected optimal features. Experimental results 98 subjects...
The alignment of tissue between histopathological whole-slide-images (WSI) is crucial for research and clinical applications. Advances in computing, deep learning, availability large WSI datasets have revolutionised analysis. Therefore, the current state-of-the-art registration unclear. To address this, we conducted ACROBAT challenge, based on largest dataset to date, including 4,212 WSIs from 1,152 breast cancer patients. challenge objective was align that stained with routine diagnostic...
The Challenge on Liver Ultrasound Tracking (CLUST) was held in conjunction with the MICCAI 2014 conference to enable direct comparison of tracking methods for this application.This paper reports outcome challenge, including setup, methods, results and experiences.The database included 54 2D 3D sequences liver healthy volunteers tumor patients under free breathing.Participants had provide 90% data (test set) pre-defined point-landmarks (healthy volunteers) or segmentations (patient data).In...
Purpose Compensation for respiratory motion is important during abdominal cancer treatments. In this work we report the results of 2015 MICCAI Challenge on Liver Ultrasound Tracking and extend 2D to relate them clinical relevance in form reducing treatment margins hence sparing healthy tissues, while maintaining full duty cycle. Methods We describe methodologies estimating temporally predicting liver from continuous ultrasound imaging, used ultrasound‐guided radiation therapy. Furthermore,...
Gastric radiography is an important tool for early detection of cancer. During gastric radiography, the stomach monitored using barium and effervescent granules. However, compression physiological phenomena during examination can cause air to escape stomach. When contracts, physicians cannot accurately observe its condition, which may result in missed lesions. Notably, no research artificial intelligence (AI) has explored use estimate amount Therefore, this study aimed develop AI system...
Plant diseases and nutrient deficiencies pose significant challenges to food production, making it crucial identify them accurately quickly, as their symptoms can often be similar. Prompt precise detection is essential implement effective measures that prevent crop losses. While computer vision techniques have demonstrated effectiveness in classification, high computational demands limited adoption by farmers the field. In this study, a Corn leaf Nutrition Deficiency Disease network...
One of the most essential steps in surgical workflow analysis is recognition tool presence. We propose a method to detect presence tools laparoscopic surgery videos, called LapFormer. The novelty LapFormer use Transformer architecture, which feed-forward neural network architecture with attention mechanism, growing popularity for natural language processing, analysing inter-frame correlation videos instead using recurrent families. To best our knowledge, no methods have been proposed....