Dataset Information

Deep learning-based automatic meibomian gland segmentation and morphology assessment in infrared meibography.

ABSTRACT: Meibomian glands (MG) are large sebaceous glands located below the tarsal conjunctiva and the abnormalities of these glands cause Meibomian gland dysfunction (MGD) which is responsible for evaporative dry eye disease (DED). Accurate MG segmentation is a key prerequisite for automated imaging based MGD related DED diagnosis. However, Automatic MG segmentation in infrared meibography is a challenging task due to image artifacts. A deep learning-based MG segmentation has been proposed which directly learns MG features from the training image dataset without any image pre-processing. The model is trained and evaluated using 728 anonymized clinical meibography images. Additionally, automatic MG morphometric parameters, gland number, length, width, and tortuosity assessment were proposed. The average precision, recall, and F1 score were achieved 83%, 81%, and 84% respectively on the testing dataset with AUC value of 0.96 based on ROC curve and dice coefficient of 84%. Single image segmentation and morphometric parameter evaluation took on average 1.33 s. To the best of our knowledge, this is the first time that a validated deep learning-based approach is applied in MG segmentation and evaluation for both upper and lower eyelids.

SUBMITTER: Setu MAK

PROVIDER: S-EPMC8027879 | biostudies-literature | 2021 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning-based automatic meibomian gland segmentation and morphology assessment in infrared meibography.

Setu Md Asif Khan MAK Horstmann Jens J Schmidt Stefan S Stern Michael E ME Steven Philipp P

Scientific reports 20210407 1

Meibomian glands (MG) are large sebaceous glands located below the tarsal conjunctiva and the abnormalities of these glands cause Meibomian gland dysfunction (MGD) which is responsible for evaporative dry eye disease (DED). Accurate MG segmentation is a key prerequisite for automated imaging based MGD related DED diagnosis. However, Automatic MG segmentation in infrared meibography is a challenging task due to image artifacts. A deep learning-based MG segmentation has been proposed which directl ...[more]

PMID: 33828177

Similar Datasets

Project description:SignificanceQuantifying meibomian gland morphology from meibography images is used for the diagnosis, treatment, and management of meibomian gland dysfunction in clinics. A novel and automated method is described for quantifying meibomian gland morphology from meibography images.PurposeMeibomian gland morphological abnormality is a common clinical sign of meibomian gland dysfunction, yet there exist no automated methods that provide standard quantifications of morphological features for individual glands. This study introduces an automated artificial intelligence approach to segmenting individual meibomian gland regions in infrared meibography images and analyzing their morphological features.MethodsA total of 1443 meibography images were collected and annotated. The dataset was then divided into development and evaluation sets. The development set was used to train and tune deep learning models for segmenting glands and identifying ghost glands from images, whereas the evaluation set was used to evaluate the performance of the model. The gland segmentations were further used to analyze individual gland features, including gland local contrast, length, width, and tortuosity.ResultsA total of 1039 meibography images (including 486 upper and 553 lower eyelids) were used for training and tuning the deep learning model, whereas the remaining 404 images (including 203 upper and 201 lower eyelids) were used for evaluations. The algorithm on average achieved 63% mean intersection over union in segmenting glands, and 84.4% sensitivity and 71.7% specificity in identifying ghost glands. Morphological features of each gland were also fed to a support vector machine for analyzing their associations with ghost glands. Analysis of model coefficients indicated that low gland local contrast was the primary indicator for ghost glands.ConclusionsThe proposed approach can automatically segment individual meibomian glands in infrared meibography images, identify ghost glands, and quantitatively analyze gland morphological features.

Project description:BackgroundBreast ultrasound (BUS) imaging is one of the most prevalent approaches for the detection of breast cancers. Tumor segmentation of BUS images can facilitate doctors in localizing tumors and is a necessary step for computer-aided diagnosis systems. While the majority of clinical BUS scans are normal ones without tumors, segmentation approaches such as U-Net often predict mass regions for these images. Such false-positive problem becomes serious if a fully automatic artificial intelligence system is used for routine screening.MethodsIn this study, we proposed a novel model which is more suitable for routine BUS screening. The model contains a classification branch that determines whether the image is normal or with tumors, and a segmentation branch that outlines tumors. Two branches share the same encoder network. We also built a new dataset that contains 1600 BUS images from 625 patients for training and a testing dataset with 130 images from 120 patients for testing. The dataset is the largest one with pixel-wise masks manually segmented by experienced radiologists. Our code is available at https://github.com/szhangNJU/BUS_segmentation.ResultsThe area under the receiver operating characteristic curve (AUC) for classifying images into normal/abnormal categories was 0.991. The dice similarity coefficient (DSC) for segmentation of mass regions was 0.898, better than the state-of-the-art models. Testing on an external dataset gave a similar performance, demonstrating a good transferability of our model. Moreover, we simulated the use of the model in actual clinic practice by processing videos recorded during BUS scans; the model gave very low false-positive predictions on normal images without sacrificing sensitivities for images with tumors.ConclusionsOur model achieved better segmentation performance than the state-of-the-art models and showed a good transferability on an external test set. The proposed deep learning architecture holds potential for use in fully automatic BUS health screening.

Dataset Information

Deep learning-based automatic meibomian gland segmentation and morphology assessment in infrared meibography.

Publications

Deep learning-based automatic meibomian gland segmentation and morphology assessment in infrared meibography.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets