Binh Duong Giap
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
Binh Duong Giap has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Nambi Nallasamy
Kellogg Eye Center, Department of Ophthalmology & Visual Sciences, University of Michigan, Ann Arbor, USA
9 shared publications Ossama Mahmoud
5 shared publicationsBradford L. Tannen
4 shared publications- Devendra Maheshwari
Aravind Eye Hospital
3 shared publications - Jing-Wein Wang
Institute of Photonics Engineering, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan
3 shared publications - Meenakshi Ravindran
Aravind Eye Hospital and Post graduate Institute of Ophthalmology, Tirunelveli, India
3 shared publications
Latest Publications
- Open Access
- 1 August 2026
- Published by Springer Nature in Graefe's Archive for Clinical and Experimental Ophthalmology
- Vol. 264 (10) , 3273
Correction: Artificial intelligence in pediatric myopia - a narrative review
- 1 August 2026
- Published by Springer Nature in Graefe's Archive for Clinical and Experimental Ophthalmology
- Vol. 264 (10) , 3273
Open AccessCorrection: Artificial intelligence in pediatric myopia - a narrative review
- Open Access
- 25 March 2026
- Published by Springer Nature in Graefe's Archive for Clinical and Experimental Ophthalmology
- Vol. 264 (8) , 1-32
Artificial intelligence in pediatric myopia - a narrative review
This review examines the promising potential of Artificial Intelligence (AI) in pediatric ophthalmology, specifically in the assessment, prediction, management, and treatment of myopia in children. The use of AI, particularly machine learning (ML) and deep learning (DL), in predicting myopia in children has garnered significant interest for its potential in early screening, detection, prognosis prediction, monitoring of anti-myopia treatment, personalized interventions, and proactive management strategies. This review aims to summarize the current literature on myopia and AI, presenting them as emerging trends and future directions in the pediatric population, and highlighting emerging strategies for the future of myopia management.
- 25 March 2026
- Published by Springer Nature in Graefe's Archive for Clinical and Experimental Ophthalmology
- Vol. 264 (8) , 1-32
Open AccessArtificial intelligence in pediatric myopia - a narrative review
This review examines the promising potential of Artificial Intelligence (AI) in pediatric ophthalmology, specifically in the assessment, prediction, management, and treatment of myopia in children. The use of AI, particularly machine learning (ML) and deep learning (DL), in predicting myopia in children has garnered significant interest for its potential in early screening, detection, prognosis prediction, monitoring of anti-myopia treatment, personalized interventions, and proactive management strategies. This review aims to summarize the current literature on myopia and AI, presenting them as emerging trends and future directions in the pediatric population, and highlighting emerging strategies for the future of myopia management.
- 29 January 2026
- Published by Wolters Kluwer Health in Cornea
- Vol. 45 (8) , 1030-1040
Deep Learning–Based Eye Rubbing Detection Using Wrist-Based Wearable Devices to Enable Rigorous Study of Risk Factors for Ectasia Progression
Purpose: To develop and validate an artificial intelligence (AI)-enabled eye rubbing detection tool using sensor data collected from wrist-based wearable devices. Methods: An automated system was designed to detect eye rubbing using wrist-based wearable devices. The system involves 3 components: sensor data acquisition, data preprocessing, and deep learning–based classification model. Six different deep learning architectures were developed, including 1D and 2D CNN-LSTM models and an ensemble, to identify the most effective approach. Two datasets were established in the time and frequency domains: a timeseries dataset contains 8640 recordings and a scalogram dataset 15 comprising 112,320 images from 20 subjects. Results: The proposed system demonstrated strong performance, achieving an F1-score of 95.27 ± 0.87% and AUC of 98.26 ± 0.92% across 5 cross-validation folds when using the 1D CNN-LSTM model to distinguish eye rubbing and noneye rubbing activities. When evaluated on the testing set, the system maintained high performance, with an F1-score of 92.54% and AUC of 96.70%. Model inference required 15.32 milliseconds per segment, supporting real-time operation and practical deployments. Conclusions: The proposed system provides high reliability in detecting eye rubbing behaviors, indicating its potential as a tool to support ophthalmologists and researchers in the rigorous study of the contributions of eye rubbing to the development and progression of keratoconus and other corneal ectasias.
- 29 January 2026
- Published by Wolters Kluwer Health in Cornea
- Vol. 45 (8) , 1030-1040
Deep Learning–Based Eye Rubbing Detection Using Wrist-Based Wearable Devices to Enable Rigorous Study of Risk Factors for Ectasia Progression
Purpose: To develop and validate an artificial intelligence (AI)-enabled eye rubbing detection tool using sensor data collected from wrist-based wearable devices. Methods: An automated system was designed to detect eye rubbing using wrist-based wearable devices. The system involves 3 components: sensor data acquisition, data preprocessing, and deep learning–based classification model. Six different deep learning architectures were developed, including 1D and 2D CNN-LSTM models and an ensemble, to identify the most effective approach. Two datasets were established in the time and frequency domains: a timeseries dataset contains 8640 recordings and a scalogram dataset 15 comprising 112,320 images from 20 subjects. Results: The proposed system demonstrated strong performance, achieving an F1-score of 95.27 ± 0.87% and AUC of 98.26 ± 0.92% across 5 cross-validation folds when using the 1D CNN-LSTM model to distinguish eye rubbing and noneye rubbing activities. When evaluated on the testing set, the system maintained high performance, with an F1-score of 92.54% and AUC of 96.70%. Model inference required 15.32 milliseconds per segment, supporting real-time operation and practical deployments. Conclusions: The proposed system provides high reliability in detecting eye rubbing behaviors, indicating its potential as a tool to support ophthalmologists and researchers in the rigorous study of the contributions of eye rubbing to the development and progression of keratoconus and other corneal ectasias.
- Open Access
- 14 March 2025
- Published by Elsevier in Ophthalmology Science
- Vol. 5 (4)
CatSkill: Artificial Intelligence-Based Metrics for the Assessment of Surgical Skill Level from Intraoperative Cataract Surgery Video Recordings
- 14 March 2025
- Published by Elsevier in Ophthalmology Science
- Vol. 5 (4)
Open AccessCatSkill: Artificial Intelligence-Based Metrics for the Assessment of Surgical Skill Level from Intraoperative Cataract Surgery Video Recordings
- Open Access
- 23 August 2024
- Published by Elsevier in Ophthalmology Science
- Vol. 5 (1) , 100597
A Computational Framework for Intraoperative Pupil Analysis in Cataract Surgery
- 23 August 2024
- Published by Elsevier in Ophthalmology Science
- Vol. 5 (1) , 100597
Open AccessA Computational Framework for Intraoperative Pupil Analysis in Cataract Surgery
- Open Access
A Computational Framework for Intraoperative Pupil Analysis in Cataract Surgery
Purpose Pupillary instability is a known risk factor for complications in cataract surgery. This study aims to develop and validate an innovative and reliable computational framework for the automated assessment of pupil morphologic changes during the various phases of cataract surgery. Design Retrospective surgical video analysis. Subjects Two hundred forty complete surgical video recordings, among which 190 surgeries were conducted without the use of pupil expansion devices and 50 were performed with the use of a pupil expansion device. Methods The proposed framework consists of three stages: feature extraction, deep learning (DL)-based anatomy recognition, and obstruction detection/compensation. In the first stage, surgical video frames undergo noise reduction using a tensor-based wavelet feature extraction method. In the second stage, DL-based segmentation models are trained and employed to segment the pupil, limbus, and palpebral fissure. In the third stage, obstructed visualization of the pupil is detected and compensated for using a DL-based algorithm. A dataset of 5,700 intraoperative video frames across 190 cataract surgeries in the BigCat database was collected for validating algorithm performance. Main Outcome Measures The pupil analysis framework was assessed on the basis of segmentation performance for both obstructed and unobstructed pupils. Classification performance of models utilizing the segmented pupil time series to predict surgeon use of a pupil expansion device was also assessed. Results An architecture based on the FPN model with VGG16 backbone integrated with the AWTFE feature extraction method demonstrated the highest performance in anatomy segmentation, with Dice coefficient of 96.52%. Incorporation of an obstruction compensation algorithm improved performance further (Dice 96.82%). Downstream analysis of framework output enabled the development of an SVM-based classifier that could predict surgeon usage of a pupil expansion device prior to its placement with 96.67% accuracy and AUC of 99.44%. Conclusions The experimental results demonstrate that the proposed framework 1) provides high accuracy in pupil analysis compared to human-annotated ground truth, 2) substantially outperforms isolated use of a DL segmentation model, and 3) can enable downstream analytics with clinically valuable predictive capacity.
Open AccessA Computational Framework for Intraoperative Pupil Analysis in Cataract Surgery
Purpose Pupillary instability is a known risk factor for complications in cataract surgery. This study aims to develop and validate an innovative and reliable computational framework for the automated assessment of pupil morphologic changes during the various phases of cataract surgery. Design Retrospective surgical video analysis. Subjects Two hundred forty complete surgical video recordings, among which 190 surgeries were conducted without the use of pupil expansion devices and 50 were performed with the use of a pupil expansion device. Methods The proposed framework consists of three stages: feature extraction, deep learning (DL)-based anatomy recognition, and obstruction detection/compensation. In the first stage, surgical video frames undergo noise reduction using a tensor-based wavelet feature extraction method. In the second stage, DL-based segmentation models are trained and employed to segment the pupil, limbus, and palpebral fissure. In the third stage, obstructed visualization of the pupil is detected and compensated for using a DL-based algorithm. A dataset of 5,700 intraoperative video frames across 190 cataract surgeries in the BigCat database was collected for validating algorithm performance. Main Outcome Measures The pupil analysis framework was assessed on the basis of segmentation performance for both obstructed and unobstructed pupils. Classification performance of models utilizing the segmented pupil time series to predict surgeon use of a pupil expansion device was also assessed. Results An architecture based on the FPN model with VGG16 backbone integrated with the AWTFE feature extraction method demonstrated the highest performance in anatomy segmentation, with Dice coefficient of 96.52%. Incorporation of an obstruction compensation algorithm improved performance further (Dice 96.82%). Downstream analysis of framework output enabled the development of an SVM-based classifier that could predict surgeon usage of a pupil expansion device prior to its placement with 96.67% accuracy and AUC of 99.44%. Conclusions The experimental results demonstrate that the proposed framework 1) provides high accuracy in pupil analysis compared to human-annotated ground truth, 2) substantially outperforms isolated use of a DL segmentation model, and 3) can enable downstream analytics with clinically valuable predictive capacity.
- Open Access
- 1 March 2024
- Published by Taylor & Francis in Clinical Ophthalmology
- Vol. ume 18, 647-657
Evaluation of Methods for Detection and Semantic Segmentation of the Anterior Capsulotomy in Cataract Surgery Video
Background: The capsulorhexis is one of the most important and challenging maneuvers in cataract surgery. Automated analysis of the anterior capsulotomy could aid surgical training through the provision of objective feedback and guidance to trainees. Purpose: To develop and evaluate a deep learning-based system for the automated identification and semantic segmentation of the anterior capsulotomy in cataract surgery video. Methods: In this study, we established a BigCat-Capsulotomy dataset comprising 1556 video frames extracted from 190 recorded cataract surgery videos for developing and validating the capsulotomy recognition system. The proposed system involves three primary stages: video preprocessing, capsulotomy video frame classification, and capsulotomy segmentation. To thoroughly evaluate its efficacy, we examined the performance of a total of eight deep learning-based classification models and eleven segmentation models, assessing both accuracy and time consumption. Furthermore, we delved into the factors influencing system performance by deploying it across various surgical phases. Results: The ResNet-152 model employed in the classification step of the proposed capsulotomy recognition system attained strong performance with an overall Dice coefficient of 92.21%. Similarly, the UNet model with the DenseNet-169 backbone emerged as the most effective segmentation model among those investigated, achieving an overall Dice coefficient of 92.12%. Moreover, the time consumption of the system was low at 103.37 milliseconds per frame, facilitating its application in real-time scenarios. Phase-wise analysis indicated that the Phacoemulsification phase (nuclear disassembly) was the most challenging to segment (Dice coefficient of 86.02%). Conclusion: The experimental results showed that the proposed system is highly effective in intraoperative capsulotomy recognition during cataract surgery and demonstrates both high accuracy and real-time capabilities. This system holds significant potential for applications in surgical performance analysis, education, and intraoperative guidance systems.
- 1 March 2024
- Published by Taylor & Francis in Clinical Ophthalmology
- Vol. ume 18, 647-657
Open AccessEvaluation of Methods for Detection and Semantic Segmentation of the Anterior Capsulotomy in Cataract Surgery Video
Background: The capsulorhexis is one of the most important and challenging maneuvers in cataract surgery. Automated analysis of the anterior capsulotomy could aid surgical training through the provision of objective feedback and guidance to trainees. Purpose: To develop and evaluate a deep learning-based system for the automated identification and semantic segmentation of the anterior capsulotomy in cataract surgery video. Methods: In this study, we established a BigCat-Capsulotomy dataset comprising 1556 video frames extracted from 190 recorded cataract surgery videos for developing and validating the capsulotomy recognition system. The proposed system involves three primary stages: video preprocessing, capsulotomy video frame classification, and capsulotomy segmentation. To thoroughly evaluate its efficacy, we examined the performance of a total of eight deep learning-based classification models and eleven segmentation models, assessing both accuracy and time consumption. Furthermore, we delved into the factors influencing system performance by deploying it across various surgical phases. Results: The ResNet-152 model employed in the classification step of the proposed capsulotomy recognition system attained strong performance with an overall Dice coefficient of 92.21%. Similarly, the UNet model with the DenseNet-169 backbone emerged as the most effective segmentation model among those investigated, achieving an overall Dice coefficient of 92.12%. Moreover, the time consumption of the system was low at 103.37 milliseconds per frame, facilitating its application in real-time scenarios. Phase-wise analysis indicated that the Phacoemulsification phase (nuclear disassembly) was the most challenging to segment (Dice coefficient of 86.02%). Conclusion: The experimental results showed that the proposed system is highly effective in intraoperative capsulotomy recognition during cataract surgery and demonstrates both high accuracy and real-time capabilities. This system holds significant potential for applications in surgical performance analysis, education, and intraoperative guidance systems.
- 21 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (3) , 1599-1610
Adaptive Tensor-Based Feature Extraction for Pupil Segmentation in Cataract Surgery
Cataract surgery remains the only definitive treatment for visually significant cataracts, which are a major cause of preventable blindness worldwide. Successful performance of cataract surgery relies on stable dilation of the pupil. Automated pupil segmentation from surgical videos can assist surgeons in detecting risk factors for pupillary instability prior to the development of surgical complications. However, surgical illumination variations, surgical instrument obstruction, and lens material hydration during cataract surgery can limit pupil segmentation accuracy. To address these problems, we propose a novel method named adaptive wavelet tensor feature extraction (AWTFE). AWTFE is designed to enhance the accuracy of deep learning-powered pupil recognition systems. First, we represent the correlations among spatial information, color channels, and wavelet subbands by constructing a third-order tensor. We then utilize higher-order singular value decomposition to eliminate redundant information adaptively and estimate pupil feature information. We evaluated the proposed method by conducting experiments with state-of-the-art deep learning segmentation models on our BigCat dataset consisting of 5,700 annotated intraoperative images from 190 cataract surgeries and a public CaDIS dataset. The experimental results reveal that the AWTFE method effectively identifies features relevant to the pupil region and improved the overall performance of segmentation models by up to 2.26% (BigCat) and 3.31% (CaDIS). Incorporation of the AWTFE method led to statistically significant improvements in segmentation performance (P < 1.29×10-10 for each model) and yielded the highest-performing model overall (Dice coefficients of 94.74% and 96.71% for the BigCat and CaDIS datasets, respectively). In performance comparisons, the AWTFE consistently outperformed other feature extraction methods in enhancing model performance. In addition, the proposed AWTFE method significantly improved pupil recognition performance by up to 2.87% in particularly challenging phases of cataract surgery.
- 21 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (3) , 1599-1610
Adaptive Tensor-Based Feature Extraction for Pupil Segmentation in Cataract Surgery
Cataract surgery remains the only definitive treatment for visually significant cataracts, which are a major cause of preventable blindness worldwide. Successful performance of cataract surgery relies on stable dilation of the pupil. Automated pupil segmentation from surgical videos can assist surgeons in detecting risk factors for pupillary instability prior to the development of surgical complications. However, surgical illumination variations, surgical instrument obstruction, and lens material hydration during cataract surgery can limit pupil segmentation accuracy. To address these problems, we propose a novel method named adaptive wavelet tensor feature extraction (AWTFE). AWTFE is designed to enhance the accuracy of deep learning-powered pupil recognition systems. First, we represent the correlations among spatial information, color channels, and wavelet subbands by constructing a third-order tensor. We then utilize higher-order singular value decomposition to eliminate redundant information adaptively and estimate pupil feature information. We evaluated the proposed method by conducting experiments with state-of-the-art deep learning segmentation models on our BigCat dataset consisting of 5,700 annotated intraoperative images from 190 cataract surgeries and a public CaDIS dataset. The experimental results reveal that the AWTFE method effectively identifies features relevant to the pupil region and improved the overall performance of segmentation models by up to 2.26% (BigCat) and 3.31% (CaDIS). Incorporation of the AWTFE method led to statistically significant improvements in segmentation performance (P < 1.29×10-10 for each model) and yielded the highest-performing model overall (Dice coefficients of 94.74% and 96.71% for the BigCat and CaDIS datasets, respectively). In performance comparisons, the AWTFE consistently outperformed other feature extraction methods in enhancing model performance. In addition, the proposed AWTFE method significantly improved pupil recognition performance by up to 2.87% in particularly challenging phases of cataract surgery.
- Open Access
- 15 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 168216-168235
Adaptive Multiple Layer Retinex-Enabled Color Face Enhancement for Deep Learning-Based Recognition
Face image captured under uncontrolled illumination conditions is one of the most significant challenges for real-world human face recognition systems. To overcome this problem, we proposed a novel method called adaptive multiple-layer retinex-based color face enhancement (AMRF) to enhance the face images. Firstly, we use an associative filter to decompose a color face image into illumination and reflectance components at multiple layers. Then, the illumination components in each layer are adjusted automatically by multiplying with corresponded illumination compensation coefficients calculated through a referenced Gaussian template. The enhanced color face image is finally obtained by composing the compensated illumination components with the integrated reflectance component based on the Retinex theory. The experiment was performed on four popular color face datasets: LFW, IJB-C, CMU Multi-PIE, and CMU-PIE. Our proposed method makes face images more precise, natural, and smooth. The experiment results show that AMRF’s image quality assessment scores are significantly better than the original and other enhanced methods’ images. Furthermore, AMRF considerably improves the recognition accuracy of deep learning-based face recognition models, such as FaceNet, and ArcFace. Finally, our proposed method also saves computational time comparing the other techniques.
- 15 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 168216-168235
Open AccessAdaptive Multiple Layer Retinex-Enabled Color Face Enhancement for Deep Learning-Based Recognition
Face image captured under uncontrolled illumination conditions is one of the most significant challenges for real-world human face recognition systems. To overcome this problem, we proposed a novel method called adaptive multiple-layer retinex-based color face enhancement (AMRF) to enhance the face images. Firstly, we use an associative filter to decompose a color face image into illumination and reflectance components at multiple layers. Then, the illumination components in each layer are adjusted automatically by multiplying with corresponded illumination compensation coefficients calculated through a referenced Gaussian template. The enhanced color face image is finally obtained by composing the compensated illumination components with the integrated reflectance component based on the Retinex theory. The experiment was performed on four popular color face datasets: LFW, IJB-C, CMU Multi-PIE, and CMU-PIE. Our proposed method makes face images more precise, natural, and smooth. The experiment results show that AMRF’s image quality assessment scores are significantly better than the original and other enhanced methods’ images. Furthermore, AMRF considerably improves the recognition accuracy of deep learning-based face recognition models, such as FaceNet, and ArcFace. Finally, our proposed method also saves computational time comparing the other techniques.