A deep learning approach to identify blepharoptosis by convolutional neural networks

Hung, Ju Yi; Perera, Chandrashan; Chen, Kewei; Myung, David; Chiu, Hsu Kuang; Fuh, Chiou-Shann; Hsu, Cherng-Ru; Liao, Shu‐Lang; Kossler, Andrea L

doi:10.1016/j.ijmedinf.2021.104402

Cited by 16 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, J. Hung et al reported in their article 'A Deep Learning Approach to Identify Blepharoptosis by Convolutional Neural Networks' that their top-performing CNN model attained a sensitivity of 90.1% and a specificity of 82.4% 9 . In a subsequent investigation, Hung et al deployed an AI model based on the VGG-16 architecture and utilized more extensive and diverse datasets to diagnose blepharoptosis accurately.…”

Section: Discussionmentioning

confidence: 99%

“…Recently, however, there has been a shift towards the application of deep learning DL, specifically CNNs, for diagnosing blepharoptosis. A study by Hung et al reported the successful use of AI to accurately diagnose blepharoptosis from clinical photographs, without the need for external reference markers or user input, using single-eye images from an Asian ethnic background 9 , 10 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development and validation of a convolutional neural network to identify blepharoptosis

Abascal Azanza,

Barrio-Barrio,

Ramos Cejudo

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Blepharoptosis is a recognized cause of reversible vision loss and a non-specific indicator of neurological issues, occasionally heralding life-threatening conditions. Currently, diagnosis relies on human expertise and eyelid examination, with most existing Artificial Intelligence algorithms focusing on eyelid positioning under specialized settings. This study introduces a deep learning model with convolutional neural networks to detect blepharoptosis in more realistic conditions. Our model was trained and tested using high quality periocular images from patients with blepharoptosis as well as those with other eyelid conditions. The model achieved an area under the receiver operating characteristic curve of 0.918. For validation, we compared the model's performance against nine medical experts—oculoplastic surgeons, general ophthalmologists, and general practitioners—with varied expertise. When tested on a new dataset with varied image quality, the model's performance remained statistically comparable to that of human graders. Our findings underscore the potential to enhance telemedicine services for blepharoptosis detection.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Development and validation of a convolutional neural network to identify blepharoptosis

Abascal Azanza,

Barrio-Barrio,

Ramos Cejudo

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Bodner et al [14] reported development of a software algorithm to automate measurement of MRD1 from digital photographs of patients taken in an oculoplastic surgery clinic using a standardized protocol. Several groups have recently reported AI algorithms for recognition of eyelid positioning, specifically the measurement of MRD1 and palpebral fissure height [15][16][17][18][19][20][21][22]. Notably, these studies report the use of datasets acquired by taking patient photographs using commercially available cameras or a smartphone camera on a single device [16,17], under highly standardized and optimized conditions.…”

Section: Introductionmentioning

confidence: 99%

Development and Assessment of an Artificial Intelligence-Based Tool for Ptosis Measurement in Adult Myasthenia Gravis Patients Using Selfie Video Clips Recorded on Smartphones

Lootus,

Beatson,

Atwood

et al. 2023

Digit Biomark

View full text Add to dashboard Cite

Introduction: Myasthenia gravis (MG) is a rare autoimmune disease characterized by muscle weakness and fatigue. Ptosis (eyelid drooping) occurs due to fatigue of the muscles for eyelid elevation and is one symptom widely used by patients and healthcare providers to track progression of the disease. Margin reflex distance 1 (MRD1) is an accepted clinical measure of ptosis and is typically assessed using a hand-held ruler. In this work, we develop an AI model that enables automated measurement of MRD1 in self-recorded video clips collected using patient smartphones. Methods: A 3-month prospective observational study collected a dataset of video clips from patients with MG. Study participants were asked to perform an eyelid fatigability exercise to elicit ptosis while filming “selfie” videos on their smartphones. These images were collected in nonclinical settings, with no in-person training. The dataset was annotated by non-clinicians for (1) eye landmarks to establish ground truth MRD1 and (2) the quality of the video frames. The ground truth MRD1 (in millimeters, mm) was calculated from eye landmark annotations in the video frames using a standard conversion factor, the horizontal visible iris diameter of the human eye. To develop the model, we trained a neural network for eye landmark detection consisting of a ResNet50 backbone plus two dense layers of 78 dimensions on publicly available datasets. Only the ResNet50 backbone was used, discarding the last two layers. The embeddings from the ResNet50 were used as features for a support vector regressor (SVR) using a linear kernel, for regression to MRD1, in mm. The SVR was trained on data collected remotely from MG patients in the prospective study, split into training and development folds. The model’s performance for MRD1 estimation was evaluated on a separate test fold from the study dataset. Results: On the full test fold (N = 664 images), the correlation between the ground truth and predicted MRD1 values was strong (r = 0.732). The mean absolute error was 0.822 mm; the mean of differences was −0.256 mm; and 95% limits of agreement (LOA) were −0.214–1.768 mm. Model performance showed no improvement when test data were gated to exclude “poor” quality images. Conclusions: On data generated under highly challenging real-world conditions from a variety of different smartphone devices, the model predicts MRD1 with a strong correlation (r = 0.732) between ground truth and predicted MRD1.

show abstract

“…Digital photograph is the most commonly used approach to analyze facial data due to the conveniency and intuition. The application of DL based on digital photograph has achieved physician-equivalent classification accuracy in lid position [19][20][21][22] and skin cancer [23,24]. Moreover, importing photograph into a smartphone can achieve portable and convenient telemedicine-technology [25] to determine whether an emergency medical treatment is required.…”

mentioning

confidence: 99%

Noninvasive identification of Benign and malignant eyelid tumors using clinical images via deep learning system

Hui

Zhang

et al. 2022

J Big Data

View full text Add to dashboard Cite

Eyelid tumors accounts for 5–10% of skin tumors. It is important but difficult to identify malignant eyelid tumors from benign lesions in a cost-effective way. Traditional screening methods for malignancy in eyelid tumors require laborious and time-consuming histopathological process. Therefore, we aimed to develop a deep learning (DL)-based image analysis system for automatic identification of benign and malignant eyelid tumors. Using a common digital camera, we collected clinical images from patients who were histopathologically diagnosed with eyelid tumors. We trained 8 convolutional neural network (CNN) models to identify benign and malignant eyelid tumors, including ResNet-50, ResNet-101, InceptionV3, and InceptionResNetV2. Another group of patients with eyelid tumors were also collected as the prospective validation dataset. Performance of DL models and human clinicians in prospective validation dataset were evaluated and compared. A total of 309 images from 209 patients were used for training DL system, all eight models reached an average accuracy greater than 0.958 in the internal cross-validation. 36 images from 36 patients were included for the prospective validation, the models reached the best performance in accuracy, sensitivity, specificity, and area under curve (AUC) of 0.889 (95% CI 0.747–0.956), 0.933 (95% CI 0.702–0.988), 0.857 (95% CI 0.654–0.950), and 0.966 (95% CI 0.850–0.993), respectively. DL system had a similar performance as the senior ophthalmologists, and outreached the performance of junior ophthalmologists and medical students. DL system can identify benign and malignant tumors through common clinical images, with a better performance than most ophthalmologists. Combining DL system with smartphone may enable patients’ self-monitoring for eyelid tumors and assist in doctors’ clinical decision making.

show abstract

A deep learning approach to identify blepharoptosis by convolutional neural networks

Cited by 16 publications

References 20 publications

Development and validation of a convolutional neural network to identify blepharoptosis

Development and validation of a convolutional neural network to identify blepharoptosis

Development and Assessment of an Artificial Intelligence-Based Tool for Ptosis Measurement in Adult Myasthenia Gravis Patients Using Selfie Video Clips Recorded on Smartphones

Noninvasive identification of Benign and malignant eyelid tumors using clinical images via deep learning system

Contact Info

Product

Resources

About