A Fully Automated Segmentation and Morphometric Parameter Estimation System for Assessing Corneal Endothelial Cell Images

Qu, Jinghao; Qin, Xiaoran; Peng, Rongmei; Xiao, Gege; Cheng, Jian; Gu, Shaofeng; Wang, Hai-Kun; Hong, Jing

doi:10.1016/j.ajo.2022.02.026

Cited by 15 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IVCM photography and examination are well-established diagnostic imaging techniques for corneal diseases, while in clinical conditions, ophthalmologists mainly analyze images for multiple times to ensure accuracy of diagnosis. In the IVCM image recognition, there have been studies on AI-assisted quantification and segmentation of corneal nerves ( 14 ), classification of nerve fiber curvature ( 28 ), identification of nerve fibers and dendritic cells and fungal hyphae ( 12 ), discrimination of activated dendritic cells and inflammatory cells ( 9 ), segmentation of corneal endothelial cells, and evaluation of morphological parameters ( 15 ), fully highlighting that AI is used to assist IVCM image recognition to explore multiple structures. However, to our knowledge, cornea is a tissue with multiple layers, and few studies have concentrated on automatic multiple-layer corneal recognition even using traditional digital image analysis techniques, therefore, developing a more extensive tool to evaluate the cornea as thoroughly as possible can bridge the gap in this research area.…”

Section: Discussionmentioning

confidence: 99%

“…Advances in artificial intelligence (AI) are transforming screening, diagnosis, and treatment in all areas of medicine (11), and the application of AI to ophthalmic diseases has also significantly evolved over the past decade. To date, AI has made significant breakthroughs in the segmentation, quantification, and identification of corneal epithelial cells, corneal nerves, corneal endothelial cells, fungal hyphae, dendritic cells, and inflammatory cells in IVCM images (9,(12)(13)(14)(15), and it has demonstrated an excellent performance in terms of speed and accuracy of film reading, which can make healthcare more accessible and cost-effective. However, no relevant study has yet evaluated multilevel corneal IVCM images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of a computer-aided diagnostic model for corneal diseases by analyzing in vivo confocal microscopy images

et al. 2023

View full text Add to dashboard Cite

ObjectiveIn order to automatically and rapidly recognize the layers of corneal images using in vivo confocal microscopy (IVCM) and classify them into normal and abnormal images, a computer-aided diagnostic model was developed and tested based on deep learning to reduce physicians’ workload.MethodsA total of 19,612 corneal images were retrospectively collected from 423 patients who underwent IVCM between January 2021 and August 2022 from Renmin Hospital of Wuhan University (Wuhan, China) and Zhongnan Hospital of Wuhan University (Wuhan, China). Images were then reviewed and categorized by three corneal specialists before training and testing the models, including the layer recognition model (epithelium, bowman’s membrane, stroma, and endothelium) and diagnostic model, to identify the layers of corneal images and distinguish normal images from abnormal images. Totally, 580 database-independent IVCM images were used in a human-machine competition to assess the speed and accuracy of image recognition by 4 ophthalmologists and artificial intelligence (AI). To evaluate the efficacy of the model, 8 trainees were employed to recognize these 580 images both with and without model assistance, and the results of the two evaluations were analyzed to explore the effects of model assistance.ResultsThe accuracy of the model reached 0.914, 0.957, 0.967, and 0.950 for the recognition of 4 layers of epithelium, bowman’s membrane, stroma, and endothelium in the internal test dataset, respectively, and it was 0.961, 0.932, 0.945, and 0.959 for the recognition of normal/abnormal images at each layer, respectively. In the external test dataset, the accuracy of the recognition of corneal layers was 0.960, 0.965, 0.966, and 0.964, respectively, and the accuracy of normal/abnormal image recognition was 0.983, 0.972, 0.940, and 0.982, respectively. In the human-machine competition, the model achieved an accuracy of 0.929, which was similar to that of specialists and higher than that of senior physicians, and the recognition speed was 237 times faster than that of specialists. With model assistance, the accuracy of trainees increased from 0.712 to 0.886.ConclusionA computer-aided diagnostic model was developed for IVCM images based on deep learning, which rapidly recognized the layers of corneal images and classified them as normal and abnormal. This model can increase the efficacy of clinical diagnosis and assist physicians in training and learning for clinical purposes.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evaluation of a computer-aided diagnostic model for corneal diseases by analyzing in vivo confocal microscopy images

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Eleiwa et al 22 reported an accurate deep learning model to determine FECD severity using AS-OCT images. Qu et al 23 reported a fully automated deep learning system to evaluate corneal endothelial cell morphology using in vivo confocal microscopy images. However, we consider that the AS-OCT parameters in the current study have advantages over AI models in that these indices are specific to the DM AS-OCT reflectivity or the ratio of the DM AS-OCT reflectivity to the stroma.…”

Section: Discussionmentioning

confidence: 99%

Three-Dimensional Assessment of Descemet Membrane Reflectivity by Optical Coherence Tomography in Fuchs Endothelial Corneal Dystrophy

Suzuki

Yamaguchi

Yagi-Yaguchi

et al. 2023

Cornea

View full text Add to dashboard Cite

Purpose: This study aimed to evaluate Descemet membrane reflectivity using anterior segment optical coherence tomography (AS-OCT) in eyes with Fuchs endothelial corneal dystrophy (FECD). Methods: We retrospectively assessed 144 eyes of 88 consecutive participants (41 FECD, 15 pseudophakic bullous keratopathies [BKs], and 32 healthy controls, 63.5 ± 16.5 years). FECD was graded 0 to 3 based on the guttae areas using specular microscopy. The sum of AS-OCT reflectivity of the 3-dimensional volume from 10 μm thickness from the endothelial surface of the cornea and residual stromal area was calculated as Dsum(endo) and Dsum(stroma) in the central area of 3- and 6-mm diameters, respectively. The DES ratio was defined as the ratio of Dsum(endo) to Dsum(stroma). The percentage of the guttae area in the specular images was calculated using MATLAB. Dsum(endo) and DES ratio were compared among FECD, BK, and healthy controls. Results: Dsum(endo) in FECD grade 3 was significantly higher than that in healthy control eyes, FECD patients with mild and moderate guttae, and BK (all P ≤ 0.040). The DES ratio in FECD patients with mild to severe guttae (grade 1–3) was significantly higher than that in healthy control eyes and BK (all P ≤ 0.035). The percentage of the guttae area was significantly correlated with Dsum(endo) (R = 0.488, P < 0.001 for 3 mm, R = 0.512, P < 0.001 for 6 mm) and DES ratio (R = 0.450, P < 0.001 for 3 mm, R = 0.588, P < 0.001 for 6 mm). Conclusions: Descemet membrane reflectivity in AS-OCT can be objective biomarkers for assessing guttae and FECD severity from early to end-stage FECD.

show abstract

“…In this prospective study, images of CECs were acquired using a LASER IVCM system (HRT III Rostock Cornea Module [RCM]; Heidelberg Engineering GmbH, Heidelberg, Germany). The specific steps of LASER IVCM image acquisition have been described in a previous article [ 13 ]. Scanning depth was increased to approximately 450–600 μm when the CECs could be seen clearly.…”

Section: Methodsmentioning

confidence: 99%

“…In a previous study, our team developed a fully automated segmentation and quantification system for normal LASER IVCM images (hereafter referred to as system_normal ) [ 13 ]. On LASER IVCM images, abnormal CECs present with low density and morphological abnormalities, resulting in substantial challenges for identification.…”

Section: Introductionmentioning

confidence: 99%

Assessing abnormal corneal endothelial cells from in vivo confocal microscopy images using a fully automated deep learning system

Qin

Peng

et al. 2023

Eye and Vis

Self Cite

View full text Add to dashboard Cite

Background The goal of this study is to develop a fully automated segmentation and morphometric parameter estimation system for assessing abnormal corneal endothelial cells (CECs) from LASER in vivo confocal microscopy (IVCM) images. Methods First, we developed a fully automated deep learning system for assessing abnormal CECs using a previous development set composed of normal images and a newly constructed development set composed of abnormal images. Second, two testing sets, one with 169 normal images and the other with 211 abnormal images, were used to evaluate the clinical validity and effectiveness of the proposed system on LASER IVCM images with different corneal endothelial conditions, particularly on abnormal images. Third, the automatically calculated endothelial cell density (ECD) and the manually calculated ECD were compared using both the previous and proposed systems. Results The automated morphometric parameter estimations of the average number of cells, ECD, coefficient of variation in cell area and percentage of hexagonal cells were 257 cells, 2648 ± 511 cells/mm2, 32.18 ± 6.70% and 56.23 ± 8.69% for the normal CEC testing set and 83 cells, 1450 ± 656 cells/mm2, 34.87 ± 10.53% and 42.55 ± 20.64% for the abnormal CEC testing set. Furthermore, for the abnormal CEC testing set, Pearson’s correlation coefficient between the automatically and manually calculated ECDs was 0.9447; the 95% limits of agreement between the manually and automatically calculated ECDs were between 329.0 and − 579.5 (concordance correlation coefficient = 0.93). Conclusions This is the first report to count and analyze the morphology of abnormal CECs in LASER IVCM images using deep learning. Deep learning produces highly objective evaluation indicators for LASER IVCM corneal endothelium images and greatly expands the range of applications for LASER IVCM.

show abstract

A Fully Automated Segmentation and Morphometric Parameter Estimation System for Assessing Corneal Endothelial Cell Images

Cited by 15 publications

References 13 publications

Evaluation of a computer-aided diagnostic model for corneal diseases by analyzing in vivo confocal microscopy images

Evaluation of a computer-aided diagnostic model for corneal diseases by analyzing in vivo confocal microscopy images

Three-Dimensional Assessment of Descemet Membrane Reflectivity by Optical Coherence Tomography in Fuchs Endothelial Corneal Dystrophy

Assessing abnormal corneal endothelial cells from in vivo confocal microscopy images using a fully automated deep learning system

Contact Info

Product

Resources

About