Takuya Takayama
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Takuya Takayama has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Hidenori Takahashi
Department of Ophthalmology, Jichi Medical University, Shimotsuke-shi, Japan
4 shared publications Hidetoshi Kawashima
Department of Ophthalmology, Jichi Medical University, Shimotsuke-shi, Tochigi, Japan
2 shared publicationsHironobu Tampo
Jichi Ika Daigaku
2 shared publications- Satoru Inoda
Department of Ophthalmology, Jichi Medical University, Shimotsuke-shi, Tochigi, Japan
2 shared publications Yasuo Yanagi
Yokohama City University: Yokohama Shiritsu Daigaku
2 shared publications- Yasuo Yanagi
Department of Ophthalmology and Micro-technology, Yokohama City University, Yokohama, Japan
2 shared publications
Latest Publications
- Open Access
Pixel-Level Segmentation of Retinal Breaks in Ultra-Widefield Fundus Images with a PraNet-Based Machine Learning Model
Retinal breaks are critical lesions that can cause retinal detachment and vision loss if not detected and treated early. Automated, accurate delineation of retinal breaks in ultra-widefield fundus (UWF) images remains challenging. In this study, we developed and validated a deep learning segmentation model based on the PraNet architecture to localize retinal breaks in break-positive cases. We trained and evaluated the model using a dataset comprising 34,867 UWF images of 8083 cases. Performance was assessed using image-level segmentation metrics, including accuracy, precision, recall, Intersection over Union (IoU), dice score, and centroid distance score. The model achieved an accuracy of 0.996, precision of 0.635, recall of 0.756, IoU of 0.539, dice score of 0.652, and centroid distance score of 0.081. To our knowledge, this is the first study to present pixel-level segmentation of retinal breaks in UWF images using deep learning. The proposed PraNet-based model showed high accuracy and robust segmentation performance, highlighting its potential for clinical application.
Open AccessPixel-Level Segmentation of Retinal Breaks in Ultra-Widefield Fundus Images with a PraNet-Based Machine Learning Model
Retinal breaks are critical lesions that can cause retinal detachment and vision loss if not detected and treated early. Automated, accurate delineation of retinal breaks in ultra-widefield fundus (UWF) images remains challenging. In this study, we developed and validated a deep learning segmentation model based on the PraNet architecture to localize retinal breaks in break-positive cases. We trained and evaluated the model using a dataset comprising 34,867 UWF images of 8083 cases. Performance was assessed using image-level segmentation metrics, including accuracy, precision, recall, Intersection over Union (IoU), dice score, and centroid distance score. The model achieved an accuracy of 0.996, precision of 0.635, recall of 0.756, IoU of 0.539, dice score of 0.652, and centroid distance score of 0.081. To our knowledge, this is the first study to present pixel-level segmentation of retinal breaks in UWF images using deep learning. The proposed PraNet-based model showed high accuracy and robust segmentation performance, highlighting its potential for clinical application.
- Open Access
Delineating retinal breaks in ultra-widefield fundus images with a PraNet-based machine learning model
Background: Retinal breaks are critical lesions that can lead to retinal detachment and vision loss if not detected and treated early. Automated and precise delineation of retinal breaks using ultra- widefield fundus (UWF) images remain a significant challenge in ophthalmology. Objective: This study aimed to develop and validate a deep learning model based on the PraNet architecture for the accurate delineation of retinal breaks in UWF images, with a particular focus on segmentation performance in retinal break–positive cases. Methods: We developed a deep learning segmentation model based on the PraNet architecture. This study utilized a dataset consisting of 8,083 cases and a total of 34,867 UWF images. Of these, 960 images contained retinal breaks, while the remaining 33,907 images did not. The dataset was split into 34,713 images for training, 81 for validation, and 73 for testing. The model was trained and validated on this dataset. Model performance was evaluated using both image-wise segmentation metrics (accuracy, precision, recall, Intersection over Union (IoU), dice score, centroid distance score) and lesion-wise detection metrics (sensitivity, positive predictive value). Results: The PraNet-based model achieved an accuracy of 0.996, a precision of 0.635, a recall of 0.756, an IoU of 0.539, a dice score of 0.652, and a centroid distance score of 0.081 for pixel-level detection of retinal breaks. The lesion-wise sensitivity was calculated as 0.885, and the positive predictive value (PPV) was 0.742. Conclusions: To our knowledge, this is the first study to present pixel-level localization of retinal breaks using deep learning on UWF images. Our findings demonstrate that the PraNet-based model provides precise and robust pixel-level segmentation of retinal breaks in UWF images. This approach offers a clinically applicable tool for the precise delineation of retinal breaks, with the potential to improve patient outcomes. Future work should focus on external validation across multiple institutions and integration of additional annotation strategies to further enhance model performance and generalizability.
Open AccessDelineating retinal breaks in ultra-widefield fundus images with a PraNet-based machine learning model
Background: Retinal breaks are critical lesions that can lead to retinal detachment and vision loss if not detected and treated early. Automated and precise delineation of retinal breaks using ultra- widefield fundus (UWF) images remain a significant challenge in ophthalmology. Objective: This study aimed to develop and validate a deep learning model based on the PraNet architecture for the accurate delineation of retinal breaks in UWF images, with a particular focus on segmentation performance in retinal break–positive cases. Methods: We developed a deep learning segmentation model based on the PraNet architecture. This study utilized a dataset consisting of 8,083 cases and a total of 34,867 UWF images. Of these, 960 images contained retinal breaks, while the remaining 33,907 images did not. The dataset was split into 34,713 images for training, 81 for validation, and 73 for testing. The model was trained and validated on this dataset. Model performance was evaluated using both image-wise segmentation metrics (accuracy, precision, recall, Intersection over Union (IoU), dice score, centroid distance score) and lesion-wise detection metrics (sensitivity, positive predictive value). Results: The PraNet-based model achieved an accuracy of 0.996, a precision of 0.635, a recall of 0.756, an IoU of 0.539, a dice score of 0.652, and a centroid distance score of 0.081 for pixel-level detection of retinal breaks. The lesion-wise sensitivity was calculated as 0.885, and the positive predictive value (PPV) was 0.742. Conclusions: To our knowledge, this is the first study to present pixel-level localization of retinal breaks using deep learning on UWF images. Our findings demonstrate that the PraNet-based model provides precise and robust pixel-level segmentation of retinal breaks in UWF images. This approach offers a clinically applicable tool for the precise delineation of retinal breaks, with the potential to improve patient outcomes. Future work should focus on external validation across multiple institutions and integration of additional annotation strategies to further enhance model performance and generalizability.
- Open Access
- 10 January 2025
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 26 (2) , 556
Comparative Pharmacokinetic Analysis of Aflibercept and Brolucizumab in Human Aqueous Humor Using Nano-Surface and Molecular-Orientation Limited Proteolysis
Aflibercept and brolucizumab, two anti-VEGF agents used as intravitreal injections in ophthalmology, differ significantly in molecular weight (aflibercept—115 kDa and brolucizumab—26 kDa). Using aqueous humor samples collected after drug administration, we measured and performed a comparative analysis of pharmacokinetics and half-lives of these drugs in the human eye. Since the quantification of monoclonal antibodies (mAbs) using antigen–antibody reactions, such as ELISA, is influenced by endogenous ligands or anti-drug antibodies, we employed nano-surface and molecular-orientation limited proteolysis (nSMOL), combined with liquid chromatography–tandem mass spectrometry (LC-MS/MS), for accurate measurements. Aqueous humor samples were collected from 59 eyes of 59 patients treated with aflibercept and 52 eyes of 52 patients treated with brolucizumab. Samples were obtained with a median post-injection period of 30 (range, 2–49) days for aflibercept and 28 (range, 4–60) days for brolucizumab. A population pharmacokinetic (PPK) analysis revealed that the half-life of aflibercept in human aqueous humor was significantly shorter than that of brolucizumab, 2.88 days versus 9.00 days, respectively (p = 1.16 × 10−7). Using the same mass spectrometry conditions, we calculated the half-lives of the two drugs. These results may be useful for optimizing the efficacy of these drugs in clinical practice.
- 10 January 2025
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 26 (2) , 556
Open AccessComparative Pharmacokinetic Analysis of Aflibercept and Brolucizumab in Human Aqueous Humor Using Nano-Surface and Molecular-Orientation Limited Proteolysis
Aflibercept and brolucizumab, two anti-VEGF agents used as intravitreal injections in ophthalmology, differ significantly in molecular weight (aflibercept—115 kDa and brolucizumab—26 kDa). Using aqueous humor samples collected after drug administration, we measured and performed a comparative analysis of pharmacokinetics and half-lives of these drugs in the human eye. Since the quantification of monoclonal antibodies (mAbs) using antigen–antibody reactions, such as ELISA, is influenced by endogenous ligands or anti-drug antibodies, we employed nano-surface and molecular-orientation limited proteolysis (nSMOL), combined with liquid chromatography–tandem mass spectrometry (LC-MS/MS), for accurate measurements. Aqueous humor samples were collected from 59 eyes of 59 patients treated with aflibercept and 52 eyes of 52 patients treated with brolucizumab. Samples were obtained with a median post-injection period of 30 (range, 2–49) days for aflibercept and 28 (range, 4–60) days for brolucizumab. A population pharmacokinetic (PPK) analysis revealed that the half-life of aflibercept in human aqueous humor was significantly shorter than that of brolucizumab, 2.88 days versus 9.00 days, respectively (p = 1.16 × 10−7). Using the same mass spectrometry conditions, we calculated the half-lives of the two drugs. These results may be useful for optimizing the efficacy of these drugs in clinical practice.
- Open Access
- 14 April 2024
- Published by Elsevier in American Journal of Ophthalmology Case Reports
- Vol. 34, 102062
Nigrospora oryzae causing human corneal keratitis: A case report
- 14 April 2024
- Published by Elsevier in American Journal of Ophthalmology Case Reports
- Vol. 34, 102062
Open AccessNigrospora oryzae causing human corneal keratitis: A case report
- Open Access
- 29 March 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (3) , e0301467
Predicting central choroidal thickness from colour fundus photographs using deep learning
The estimation of central choroidal thickness from colour fundus images can improve disease detection. We developed a deep learning method to estimate central choroidal thickness from colour fundus images at a single institution, using independent datasets from other institutions for validation. A total of 2,548 images from patients who underwent same-day optical coherence tomography examination and colour fundus imaging at the outpatient clinic of Jichi Medical University Hospital were retrospectively analysed. For validation, 393 images from three institutions were used. Patients with signs of subretinal haemorrhage, central serous detachment, retinal pigment epithelial detachment, and/or macular oedema were excluded. All other fundus photographs with a visible pigment epithelium were included. The main outcome measure was the standard deviation of 10-fold cross-validation. Validation was performed using the original algorithm and the algorithm after learning based on images from all institutions. The standard deviation of 10-fold cross-validation was 73 μm. The standard deviation for other institutions was reduced by re-learning. We describe the first application and validation of a deep learning approach for the estimation of central choroidal thickness from fundus images. This algorithm is expected to help graders judge choroidal thickening and thinning.
- 29 March 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (3) , e0301467
Open AccessPredicting central choroidal thickness from colour fundus photographs using deep learning
The estimation of central choroidal thickness from colour fundus images can improve disease detection. We developed a deep learning method to estimate central choroidal thickness from colour fundus images at a single institution, using independent datasets from other institutions for validation. A total of 2,548 images from patients who underwent same-day optical coherence tomography examination and colour fundus imaging at the outpatient clinic of Jichi Medical University Hospital were retrospectively analysed. For validation, 393 images from three institutions were used. Patients with signs of subretinal haemorrhage, central serous detachment, retinal pigment epithelial detachment, and/or macular oedema were excluded. All other fundus photographs with a visible pigment epithelium were included. The main outcome measure was the standard deviation of 10-fold cross-validation. Validation was performed using the original algorithm and the algorithm after learning based on images from all institutions. The standard deviation of 10-fold cross-validation was 73 μm. The standard deviation for other institutions was reduced by re-learning. We describe the first application and validation of a deep learning approach for the estimation of central choroidal thickness from fundus images. This algorithm is expected to help graders judge choroidal thickening and thinning.