Yuji Hatanaka

Prof. Yuji Hatanaka

Oita University, Ōita, Japan
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
5 November 2022 in Diagnostics
Verified
Journal Article
Open access
PDF file
HKHiroshi Keino
Hiroshi Keino
TATakuto Aman
Takuto Aman
RFRyota Furuya
Ryota Furuya
MNMakiko Nakayama
Makiko Nakayama
AOAnnabelle A. Okada
Annabelle A. Okada
YHYuji Hatanaka
Yuji Hatanaka
Background: The aim of this study is to develop an automated evaluation of anterior chamber (AC) cells in uveitis using anterior segment (AS) optical coherence tomography (OCT) images. Methods: We analyzed AS swept-source (SS)-OCT (CASIA 2) images of 31 patients (51 eyes) with uveitis using image analysis software (Python). An automated algorithm was developed to detect cellular spots corresponding to hyper-reflective spots in the AC, and the correlation with Standardization of Uveitis Nomenclature (SUN) grading AC cells score was evaluated. The approximated AC grading value was calculated based on the logarithmic approximation curve between the number of cellular spots and the SUN grading score. Results: Among 51 eyes, cellular spots were automatically segmented in 48 eyes, whereas three eyes (all SUN grading AC cells score: 4+) with severe fibrin formation in the AC were removed by the automated algorithm. The AC cellular spots increased with an increasing SUN grading score (p < 0.001). The 48 eyes were split into training data (26 eyes) and test data (22 eyes). There was a significant correlation between the SUN grading score and the number of cellular spots in 26 eyes (rho: 0.843, p < 0.001). There was a significant correlation between the SUN grading score and the approximated grading value of 22 eyes based on the logarithmic approximation curve (rho: 0.774, p < 0.001). Leave-one-out cross-validation analysis demonstrated a significant correlation between the SUN grading score and the approximated grading value of 48 eyes (rho: 0.748, p < 0.001). Conclusions: This automated anterior AC cell analysis using AS SS-OCT showed a significant correlation with clinical SUN grading scores and provided SUN AC grading values as a continuous variable. Our findings suggest that automated grading of AC cells could improve the accuracy of a quantitative assessment of AC inflammation using AS-OCT images and allow the objective and rapid evaluation of anterior segment inflammation in uveitis. Further investigations on a large scale are required to validate this quantitative measurement of anterior segment inflammation in uveitic eyes.

12 December 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HKHiroshi Keino
Hiroshi Keino
TWTomoki Wakitani
Tomoki Wakitani
WSWataru Sunayama
Wataru Sunayama
YHYuji Hatanaka
Yuji Hatanaka
Retinal vascular leakage is known to be an important biomarker to monitor the disease activity of uveitis. Although fluorescein angiography (FA) is a gold standard for the diagnosis and assessment of the disease activity of uveitis, the evaluation of FA findings, especially retinal vascular leakage, remains subjective and descriptive. In the current study, we developed an automatic segmentation model using a deep learning system, U-Net, and subtraction of the retinal vessel area between early-phase and late-phase FA images for the detection of the retinal vascular leakage area in ultrawide field (UWF) FA images in three patients with Behçet’s Disease and three patients with idiopathic uveitis with retinal vasculitis. This study demonstrated that the automated model for segmentation of the retinal vascular leakage area through the UWF FA images reached 0.434 (precision), 0.529 (recall), and 0.467 (Dice coefficient) without using UWF FA images for training. There was a significant positive correlation between the automated segmented area (pixels) of retinal vascular leakage and the FA vascular leakage score. The mean pixels of automatic segmented vascular leakage in UWF FA images with treatment was significantly reduced compared with before treatment. The automated segmentation of retinal vascular leakage in UWF FA images may be useful for objective and quantitative assessment of disease activity in posterior segment uveitis. Further studies at a larger scale are warranted to improve the performance of this automatic segmentation model to detect retinal vascular leakage.

23 November 2025 in Journal of Applied Clinical Medical Physics
Verified
Journal Article
Open access
YIYoshiyuki Iwao
Yoshiyuki Iwao
KSKenshi Shiotsuki
Kenshi Shiotsuki
FHFumio Hashimoto
Fumio Hashimoto
TOTakahiro Ochiai
Takahiro Ochiai
TKTsuneo Kagawa
Tsuneo Kagawa
YAYoshiki Asayama
Yoshiki Asayama
Purpose: Although bone mineral density (BMD) measurement using dual‐energy x‐ray absorptiometry (DXA) is the most common method of diagnosing osteoporosis, it is not widely used to screen patients. In this exploratory study, we developed a multi‐task learning model that predicts BMD from chest radiographs using clavicular features and supports network explainability. Methods: The proposed multi‐task learning model integrates segmentation and regression tasks by incorporating a regression branch into the U‐Net architecture in an end‐to‐end manner. A total of 1600 patients who underwent chest radiography and DXA of the lumbar vertebrae were included in this study. We compared the BMD predictive performance of the mean absolute error (MAE) and Pearson correlation coefficient ( R value) between the proposed multi‐task learning model and the single‐task learning model, which was defined as the comparison model that only performed BMD prediction. Additionally, model performance for classifying osteoporosis, osteopenia, and normal bone status was evaluated via reclassification analysis based on the World Health Organization (WHO) criteria. Confusion matrices were generated, and classwise and macro‐averaged performance metrics were calculated. To confirm the rationale for the BMD predictions, we evaluated heat maps generated using the gradient‐weighted class activation mapping technique to determine whether the highlighted regions overlapped with the clavicle. Results: The multi‐task learning model demonstrated superior predictive performance (MAE of 0.092 g/cm 2 and R value of 0.769) compared with the single‐task learning model (MAE of 0.101 g/cm 2 and R value of 0.724), a statistically significant ( p < 0.001) difference in MAE. Bland–Altman analysis showed that the multi‐task learning model had good agreement with narrower limits of agreement, although a bias was present (bias: −0.013 g/cm 2 ; limits of agreement: −0.248 to 0.223 g/cm 2 ). In contrast, the single‐task model showed slightly wider agreement limits (bias: −0.003 g/cm 2 ; limits of agreement: −0.257 to 0.252 g/cm 2 ). In the reclassification analysis based on the WHO criteria, the multi‐task learning model resulted in fewer misclassifications than the single‐task learning model. The macro‐averaged sensitivity, specificity, precision, and F1 score were 0.647, 0.826, 0.680, and 0.659, respectively, for the multi‐task model, compared with 0.597, 0.809, 0.660, and 0.616, respectively, for the single‐task model. The heat maps in the multi‐task learning model highlighted different regions compared with the single‐task model, the clavicular area. Conclusion: The proposed multi‐task learning model demonstrated the predictive rationale by focusing on the clavicle in chest radiographs, which is clinically relevant to BMD, and showed improved performance compared with the single‐task model.

1 January 2024 in Japanese Journal of Radiological Technology
Verified
Journal Article
Open access
PDF file
MEMichihiro Eto
Michihiro Eto
YOYasushi Ono
Yasushi Ono
TNTomofumi Nakawatari
Tomofumi Nakawatari
DHDaisuke Hanamiya
Daisuke Hanamiya
YHYuji Hatanaka
Yuji Hatanaka
【目的】本研究では,動画像から人間の姿勢を推定する技術(以下,姿勢推定手法)とRGB画像を取得できる2台のカメラを組み合わせ,ポジショニング時の体位を取得することで,頭部X線撮影をシミュレートするシステムを提案する.【方法】カメラで撮影したポジショニング後の正面と側面の画像から姿勢推定手法を用いて正中矢状面(median sagittal plane: MS),体軸断面(axial plane: AX),眼窩耳孔線(orbitomeatal baseline: OM)の角度を取得し,結果に応じたX線画像を表示する.【結果】姿勢推定手法で取得した特徴点の座標データをもとに,ポジショニング時の頭部の傾きを判定することができた.人体を模擬患者とした撮影実験では,頭部の傾きが大きくなると測定誤差は大きくなったが,正しくポジショニングされたときの各軸の測定誤差の平均値は,MS 0.9°,AX 0.8°,OM 1.5°であった.【結語】姿勢推定手法を用いることで,X線撮影時のポジショニング精度を評価でき,シミュレータシステムとしての可能性が期待できる.

14 June 2024 in Radiological Physics and Technology
Verified
Journal Article
Closed access
PDF file
MEMichihiro Eto
Michihiro Eto
TNTomofumi Nakawatari
Tomofumi Nakawatari
YHYuji Hatanaka
Yuji Hatanaka