Detection of meibomian glands and classification of meibography images

Koh, Yang Wei; Çelik, Turgay; Lee, Hwee Kuan; Petznick, Andrea; Tong, Louis

doi:10.1117/1.jbo.17.8.086008

Cited by 79 publications

(62 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Different examiners may draw the gland region differently, leading to inter-observer variability. Koh et al 25 automatically analysed images of meibomian glands using original algorithms to identify them, and demonstrated a clear distinction between healthy and unhealthy glands based on both mean arc length and mean entropy only in the upper eyelids. Their method provides such parameters as central length of the detected meibomian glands and spaces between neighbouring meibomian glands, which are not necessarily associated with MGD.…”

Section: Discussionmentioning

confidence: 99%

“…Different examiners may draw the gland region differently, leading to inter-observer variability. Koh et al 25 were the first to apply original algorithms to automatically analyse meibography images to identify meibomian glands, and showed a clear distinction between healthy and unhealthy images based on both the mean arc length and mean entropy. Their method of measuring meibomian gland loss, however, is an indirect method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Objective image analysis of the meibomian gland area

et al. 2013

View full text Add to dashboard Cite

AimsTo evaluate objectively the meibomian gland area using newly developed software for non-invasive meibography.MethodsEighty eyelids of 42 patients without meibomian gland loss (meiboscore=0), 105 eyelids of 57 patients with loss of less than one-third total meibomian gland area (meiboscore=1), 13 eyelids of 11 patients with between one-third and two-thirds loss of meibomian gland area (meiboscore=2) and 20 eyelids of 14 patients with two-thirds loss of meibomian gland area (meiboscore=3) were studied. Lid borders were automatically determined. The software evaluated the distribution of the luminance and, by enhancing the contrast and reducing image noise, the meibomian gland area was automatically discriminated. The software calculated the ratio of the total meibomian gland area relative to the total analysis area in all subjects. Repeatability of the software was also evaluated.ResultsThe mean ratio of the meibomian gland area to the total analysis area in the upper/lower eyelids was 51.9±5.7%/54.7±5.4% in subjects with a meiboscore of 0, 47.7±6.0%/51.5±5.4% in those with a meiboscore of 1, 32.0±4.4%/37.2±3.5% in those with a meiboscore of 2 and 16.7±6.4%/19.5±5.8% in subjects with a meiboscore of 3.ConclusionsThe meibomian gland area was objectively evaluated using the developed software. This system could be useful for objectively evaluating the effect of treatment on meibomian gland dysfunction.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Objective image analysis of the meibomian gland area

et al. 2013

View full text Add to dashboard Cite

show abstract

“…[98] Koh and colleagues developed a semi-automated method to digitally quantify infra-red meibographs that can objectively measure meibomian gland length and width. [99] This software advancement is exciting in that it has high sensitivity and specificity, but data regarding inter-observer reliability are not available. [99] Perhaps with the recent development of 3D reconstruction using FD-OCT meibography, further quantifiable parameters are likely to be developed toward improved assessment and grading systems.…”

Section: Methods and Limitations In The Diagnosis And Treatment Of Mementioning

confidence: 99%

“…[99] This software advancement is exciting in that it has high sensitivity and specificity, but data regarding inter-observer reliability are not available. [99] Perhaps with the recent development of 3D reconstruction using FD-OCT meibography, further quantifiable parameters are likely to be developed toward improved assessment and grading systems. [100] Despite advances made to date, as a function of the limited magnification offered by these devices, current methods fail to detect cellular detail and consequently identification of patients with subclinical inflammation, which may account for symptoms with undetectable signs using traditional examination methods.…”

Section: Methods and Limitations In The Diagnosis And Treatment Of Mementioning

confidence: 99%

Image-guided evaluation and monitoring of treatment response in patients with dry eye disease

Qazi

Aggarwal

Hamrah

2014

Graefes Arch Clin Exp Ophthalmol

View full text Add to dashboard Cite

Dry eye disease (DED) is one of the most common ocular disorders worldwide. The pathophysiological mechanisms involved in the development of DED are not well understood and thus treating DED has been a significant challenge for ophthalmologists. Most of the currently available diagnostic tests demonstrate low correlation to patient symptoms and have low reproducibility. Recently, sophisticated in vivo imaging modalities have become available for patient care, namely, in vivo confocal microscopy (IVCM) and optical coherence tomography (OCT). These emerging modalities are powerful and non-invasive, allowing real-time visualization of cellular and anatomical structures of the cornea and ocular surface. Here we discuss how, by providing both qualitative and quantitative assessment, these techniques can be used to demonstrate early subclinical disease, grade layer-by-layer severity, and allow monitoring of disease severity by cellular alterations. Imaging-guided stratification of patients may also be possible in conjunction with clinical examination methods. Visualization of subclinical changes and stratification of patients in vivo, allows objective image-guided evaluation of tailored treatment response based on cellular morphological alterations specific to each patient. This image-guided approach to DED may ultimately improve patient outcomes and allow studying the efficacy of novel therapies in clinical trials.

show abstract

“…A team from Singapore has developed an image analysis software that can enhance infrared images of meibomian glands, segment the strip-like patterns and extract important features for classifying the images [107].…”

Section: Image Analysis In Assessing the Dry Eye Conditionmentioning

confidence: 99%

Clinical Proteomics and Omics Clues Useful in Translational Medicine Research

2014

Omics in Clinical Practice

View full text Add to dashboard Cite

Abstract:The currently hyped expectation of personalized medicine is often associated with just achieving the information technology led integration of biomolecular sequencing, expression and histopathological bioimaging data with clinical records at the individual patients' level as if the significant biomedical conclusions would be its more or less mandatory result. It remains a sad fact that many, if not most biomolecular mechanisms that translate the human genomic information into phenotypes are not known and, thus, most of the molecular and cellular data cannot be interpreted in terms of biomedically relevant conclusions. Whereas the historical trend will certainly be into the general direction of personalized diagnostics and cures, the temperate view suggests that biomedical applications that rely either on the comparison of biomolecular sequences and/or on the already known biomolecular mechanisms have much greater chances to enter clinical practice soon. In addition to considering the general trends, we exemplarily review advances in the area of cancer biomarker discovery, in the clinically relevant characterization of patient-specific viral and bacterial pathogens (with emphasis on drug selection for influenza and enterohemorrhagic E. coli) as well as progress in the automated assessment of histopathological images. As molecular and cellular data analysis will become instrumental for achieving desirable clinical outcomes, the role of bioinformatics and computational biology approaches will dramatically grow.Author summary: With DNA sequencing and computers becoming increasingly cheap and accessible to the layman, the idea of integrating biomolecular and clinical patient data seems to become a realistic, short-term option that will lead to patient-specific diagnostics and treatment design for many diseases such as cancer, metabolic disorders, inherited conditions, etc. These hyped expectations will fail since many, if not most biomolecular mechanisms that translate the human genomic information into phenotypes are not known yet and, thus, most of the molecular and cellular data collected will not lead to biomedically relevant conclusions. At the same time, less spectacular biomedical applications based on biomolecular sequence comparison and/or known biomolecular mechanisms have the potential to unfold enormous potential for healthcare and public health. Since the analysis of heterogeneous biomolecular data in context with clinical data will be increasingly critical, the role of bioinformatics and computational biology will grow correspondingly in this process.

show abstract

Detection of meibomian glands and classification of meibography images

Cited by 79 publications

References 17 publications

Objective image analysis of the meibomian gland area

Objective image analysis of the meibomian gland area

Image-guided evaluation and monitoring of treatment response in patients with dry eye disease

Clinical Proteomics and Omics Clues Useful in Translational Medicine Research

Contact Info

Product

Resources

About