Yasushi Hirano

Yasushi Hirano

Auto-generated profile, based on publicly available information

Yasushi Hirano

Medical Informatics and Decision Sciences, Yamaguchi University Hospital, 1-1-1 MinamiKogushi, Ube, Yamaguchi 755-8505, Japan

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 November 2019 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
RXRui Xu
Rui Xu
ZCZhen Cong
Zhen Cong
XYXinchen Ye
Xinchen Ye
YHYasushi Hirano
Yasushi Hirano
SKShoji Kido
Shoji Kido
NTNoriyuki Tomiyama
Noriyuki Tomiyama
Precise classification of pulmonary textures is crucial to develop a computer aided diagnosis (CAD) system of diffuse lung diseases (DLDs). Although deep learning techniques have been applied to this task, the classification performance is not satisfied for clinical requirements due to that commonly-used deep networks built by stacking convolutional blocks are not able to learn discriminative feature representation to distinguish complex pulmonary textures. For addressing this problem, we design a multi-scale attention network (MSAN) architecture comprised by several stacked residual attention modules followed by a multi-scale fusion module. Our deep network can not only exploit powerful information on different scales but also automatically select optimal features for more discriminative feature representation. Besides, we develop visualization techniques to make the proposed deep model transparent for humans. The proposed method is evaluated by using a large dataset. Experimental results show that our method has achieved the average classification accuracy of 94.78 and the average f-value of 0.9475 in the classification of 7 categories of pulmonary textures. Besides, visualization results intuitively explain the working behavior of the deep network. The proposed method has achieved the state-of-the-art performance to classify pulmonary textures on high resolution CT images.

1 June 2017
Verified
Conference Paper
Closed access
TKTamotsu Kawamura
Tamotsu Kawamura
MFMasaru Fukushi
Masaru Fukushi
YHYasushi Hirano
Yasushi Hirano
YFYusuke Fujita
Yusuke Fujita
YHYoshihiko Hamamoto
Yoshihiko Hamamoto
This paper proposes an event detection module for distributed denial of service (DDoS) attacks on Internet of Things (IoT). Different from existing detection modules using knowledge-based filtering, the proposed module focuses on the system behavior under DDoS attacks and detects it utilizing information obtained from NTP used in synchronization service. We conducted demonstration experiments with the developed module generating pseudo DDoS attacks. The result shows that the proposed module achieves high recall and precision values, indicating its usefulness in the real time event detection on IoT.

1 January 2015 in Computational and Mathematical Methods in Medicine
Verified
Journal Article
Open access
PDF file
WZWei Zhao
Wei Zhao
RXRui Xu
Rui Xu
YHYasushi Hirano
Yasushi Hirano
RTRie Tachibana
Rie Tachibana
SKShoji Kido
Shoji Kido
We applied and optimized the sparse representation (SR) approaches in the computer-aided diagnosis (CAD) to classify normal tissues and five kinds of diffuse lung disease (DLD) patterns: consolidation, ground-glass opacity, honeycombing, emphysema, and nodule. By using the K-SVD which is based on the singular value decomposition (SVD) and orthogonal matching pursuit (OMP), it can achieve a satisfied recognition rate, but too much time was spent in the experiment. To reduce the runtime of the method, the K-Means algorithm was substituted for the K-SVD, and the OMP was simplified by searching the desired atoms at one time (OMP1). We proposed three SR based methods for evaluation: SR1 (K-SVD+OMP), SR2 (K-Means+OMP), and SR3 (K-Means+OMP1). 1161 volumes of interest (VOIs) were used to optimize the parameters and train each method, and 1049 VOIs were adopted to evaluate the performances of the methods. The SR based methods were powerful to recognize the DLD patterns (SR1: 96.1%, SR2: 95.6%, SR3: 96.4%) and significantly better than the baseline methods. Furthermore, when the K-Means and OMP1were applied, the runtime of the SR based methods can be reduced by 98.2% and 55.2%, respectively. Therefore, we thought that the method using the K-Means and OMP1(SR3) was efficient for the CAD of the DLDs.

11 February 2022 in Dermatologic Therapy
Verified
Journal Article
Closed access
PDF file
ASAtsuyuki Saisyo
Atsuyuki Saisyo
MYMichiya Yamaguchi
Michiya Yamaguchi
KKKoichi Kashibe
Koichi Kashibe
HIHaku Ishida
Haku Ishida
YHYasushi Hirano
Yasushi Hirano
TKTakashi Kitahara
Takashi Kitahara

17 April 2023 in American Journal of Infection Control
Verified
Journal Article
Closed access
TOTomoyuki Oka
Tomoyuki Oka
KKKyoji Kouda
Kyoji Kouda
NONaoto Okada
Naoto Okada
ASAtsuyuki Saisyo
Atsuyuki Saisyo
KKKouichi Kashibe
Kouichi Kashibe
TKTakashi Kitahara
Takashi Kitahara

20 April 2021
Verified
Conference Paper
Closed access
PDF file
EIErena Ise
Erena Ise
SKShoji Kido
Shoji Kido
YHYasushi Hirano
Yasushi Hirano
In this study, we aimed to classify lung cancers in chest CT images into adenocarcinoma (AD) and squamous cell carcinoma (SQ) using 3D Convolutional Neural Networks (CNN), and to visualize grounds used in the classification process by CNN. Although CNN is a powerful tool for classifying types of lung cancers, it does not provide grounds for decision explicitly, and there is a possibility that doctors and patients may not be satisfied with the decision by CNN. First, we developed a CNN based classifier to classify lung tumors into AD and SQ. The recognition rate of the proposed method was 69.9 ± 3.8%. Furthermore, the grounds of the classification by CNN was visualized by using Gradient-weighted Class Activation Mapping (Grad-CAM)[1].