6 citations · 10 across the 9 of their papers we have counts for
10 papers
Quasi-Binarized Autoencoders: An Architecture-Independent Information Bottleneck for Medical Image Anomaly Detection
Shouhei Hanaoka, Takahiro Nakao, Atsushi Takamatsu +2
Unsupervised anomaly detection, which learns only from normal images, is a central task in medical image analysis and remains an open problem. Reconstruction-based methods pass an…
CADD: Context aware disease deviations via restoration of brain images using normative conditional diffusion models
Ana Lawry Aguila, Ayodeji Ijishakin, Juan Eugenio Iglesias +5
Applying machine learning to real-world medical data, e.g. from hospital archives, has the potential to revolutionize disease detection in brain images. However, detecting patholog…
ModernBERT is More Efficient than Conventional BERT for Chest CT Findings Classification in Japanese Radiology Reports
Yosuke Yamagishi, Tomohiro Kikuchi, Shouhei Hanaoka +2
Japanese language models for medical text classification face challenges with complex vocabulary and linguistic structures in radiology reports. This study compared three Japanese…
Development of a Large-scale Dataset of Chest Computed Tomography Reports in Japanese and a High-performance Finding Classification Model
Yosuke Yamagishi, Yuta Nakamura, Tomohiro Kikuchi +7
Background: Recent advances in large language models highlight the need for high-quality multilingual medical datasets. While Japan leads globally in CT scanner deployment and util…
Local Differential Privacy Image Generation Using Flow-based Deep Generative Models
Hisaichi Shibata, Shouhei Hanaoka, Yang Cao +5
Diagnostic radiologists need artificial intelligence (AI) for medical imaging, but access to medical images required for training in AI has become increasingly restrictive. To rele…
Aging prediction using deep generative model toward the development of preventive medicine
Hisaichi Shibata, Shouhei Hanaoka, Yukihiro Nomura +2
From birth to death, we all experience surprisingly ubiquitous changes over time due to aging. If we can predict aging in the digital domain, that is, the digital twin of the human…
X2CT-FLOW: Maximum a posteriori reconstruction using a progressive flow-based deep generative model for ultra sparse-view computed tomography in ultra low-dose protocols
Hisaichi Shibata, Shouhei Hanaoka, Yukihiro Nomura +4
Ultra sparse-view computed tomography (CT) algorithms can reduce radiation exposure of patients, but those algorithms lack an explicit cycle consistency loss minimization and an ex…
KART: Parameterization of Privacy Leakage Scenarios from Pre-trained Language Models
Yuta Nakamura, Shouhei Hanaoka, Yukihiro Nomura +5
For the safe sharing pre-trained language models, no guidelines exist at present owing to the difficulty in estimating the upper bound of the risk of privacy leakage. One problem i…
On the Matrix-Free Generation of Adversarial Perturbations for Black-Box Attacks
Hisaichi Shibata, Shouhei Hanaoka, Yukihiro Nomura +2
In general, adversarial perturbations superimposed on inputs are realistic threats for a deep neural network (DNN). In this paper, we propose a practical generation method of such…
A versatile anomaly detection method for medical images with a flow-based generative model in semi-supervision setting
H. Shibata, S. Hanaoka, Y. Nomura +5
Oversight in medical images is a crucial problem, and timely reporting of medical images is desired. Therefore, an all-purpose anomaly detection method that can detect virtually al…