U-Net Convolutional Neural Network for Segmenting the Corneal Endothelium in a Mouse Model of Fuchs Endothelial Corneal Dystrophy

Okumura, Naoki; Yamada, Shohei; Nishikawa, Takeru; Narimoto, Kaito; Okamura, Kengo; Izumi, Ayaka; Hiwa, Satoru; Hiroyasu, Tomoyuki; Koizumi, Noriko

doi:10.1097/ico.0000000000002956

Cited by 7 publications

(4 citation statements)

References 40 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The more densely pixelated regions were congruent with guttae (Fig. 5 ), confirming that the algorithm was able to detect FECD based on clinically appropriate features of the disease [ 20 ]. In addition, our DL model could identify peripheral SM images with ECD > 1000 cells/mm 2 in FECD eyes.…”

Section: Discussionmentioning

confidence: 66%

Deep learning for detection of Fuchs endothelial dystrophy from widefield specular microscopy imaging: a pilot study

Foo,

Lim,

Liu

et al. 2024

Eye and Vis

View full text Add to dashboard Cite

Background To describe the diagnostic performance of a deep learning (DL) algorithm in detecting Fuchs endothelial corneal dystrophy (FECD) based on specular microscopy (SM) and to reliably detect widefield peripheral SM images with an endothelial cell density (ECD) > 1000 cells/mm2. Methods Five hundred and forty-seven subjects had SM imaging performed for the central cornea endothelium. One hundred and seventy-three images had FECD, while 602 images had other diagnoses. Using fivefold cross-validation on the dataset containing 775 central SM images combined with ECD, coefficient of variation (CV) and hexagonal endothelial cell ratio (HEX), the first DL model was trained to discriminate FECD from other images and was further tested on an external set of 180 images. In eyes with FECD, a separate DL model was trained with 753 central/paracentral SM images to detect SM with ECD > 1000 cells/mm2 and tested on 557 peripheral SM images. Area under curve (AUC), sensitivity and specificity were evaluated. Results The first model achieved an AUC of 0.96 with 0.91 sensitivity and 0.91 specificity in detecting FECD from other images. With an external validation set, the model achieved an AUC of 0.77, with a sensitivity of 0.69 and specificity of 0.68 in differentiating FECD from other diagnoses. The second model achieved an AUC of 0.88 with 0.79 sensitivity and 0.78 specificity in detecting peripheral SM images with ECD > 1000 cells/mm2. Conclusions Our pilot study developed a DL model that could reliably detect FECD from other SM images and identify widefield SM images with ECD > 1000 cells/mm2 in eyes with FECD. This could be the foundation for future DL models to track progression of eyes with FECD and identify candidates suitable for therapies such as Descemet stripping only.

show abstract

Section: Discussionmentioning

confidence: 66%

Deep learning for detection of Fuchs endothelial dystrophy from widefield specular microscopy imaging: a pilot study

Foo,

Lim,

Liu

et al. 2024

Eye and Vis

View full text Add to dashboard Cite

show abstract

“…We previously achieved the segmentation of CECs with the presence of guttae in a Fuchs endothelial corneal dystrophy model mouse [39]. Here, we expanded the use of U-Net from the analysis of in vivo cells to the analysis of in vitro cells for the purpose of quality control in the context of regenerative medicine.…”

Section: Discussionmentioning

confidence: 99%

U-Net Convolutional Neural Network for Real-Time Prediction of the Number of Cultured Corneal Endothelial Cells for Cellular Therapy

Okumura,

Nishikawa,

Imafuku

et al. 2024

Bioengineering

Self Cite

View full text Add to dashboard Cite

Corneal endothelial decompensation is treated by the corneal transplantation of donor corneas, but donor shortages and other problems associated with corneal transplantation have prompted investigations into tissue engineering therapies. For clinical use, cells used in tissue engineering must undergo strict quality control to ensure their safety and efficacy. In addition, efficient cell manufacturing processes are needed to make cell therapy a sustainable standard procedure with an acceptable economic burden. In this study, we obtained 3098 phase contrast images of cultured human corneal endothelial cells (HCECs). We labeled the images using semi-supervised learning and then trained a model that predicted the cell centers with a precision of 95.1%, a recall of 92.3%, and an F-value of 93.4%. The cell density calculated by the model showed a very strong correlation with the ground truth (Pearson’s correlation coefficient = 0.97, p value = 8.10 × 10−52). The total cell numbers calculated by our model based on phase contrast images were close to the numbers calculated using a hemocytometer through passages 1 to 4. Our findings confirm the feasibility of using artificial intelligence-assisted quality control assessments in the field of regenerative medicine.

show abstract

“…Okumura et al [ 62 ] developed a method using CNN U-Net for the segmentation of corneal endothelial cell borders and guttae in specular microscopy images of a mouse FECD model (Col8a2L450W/L450W knock-in mice). This method showed strong agreement with the manual determination for the analysis of the area and number of guttae and ECD, CV, and hexagonality, suggesting its potential as a tool for objective and fast analysis of corneal endothelial abnormalities in FECD.…”

Section: Specular Microscopymentioning

confidence: 99%

Applications of Imaging Technologies in Fuchs Endothelial Corneal Dystrophy: A Narrative Literature Review

Han,

Liu,

Liu

et al. 2024

Bioengineering

View full text Add to dashboard Cite

Fuchs endothelial corneal dystrophy (FECD) is a complex genetic disorder characterized by the slow and progressive degeneration of corneal endothelial cells. Thus, it may result in corneal endothelial decompensation and irreversible corneal edema. Moreover, FECD is associated with alterations in all corneal layers, such as thickening of the Descemet membrane, stromal scarring, subepithelial fibrosis, and the formation of epithelial bullae. Hence, anterior segment imaging devices that enable precise measurement of functional and anatomical changes in the cornea are essential for the management of FECD. In this review, the authors will introduce studies on the application of various imaging modalities, such as anterior segment optical coherence tomography, Scheimpflug corneal tomography, specular microscopy, in vitro confocal microscopy, and retroillumination photography, in the diagnosis and monitoring of FECD and discuss the results of these studies. The application of novel technologies, including image processing technology and artificial intelligence, that are expected to further enhance the accuracy, precision, and speed of the imaging technologies will also be discussed.

show abstract

U-Net Convolutional Neural Network for Segmenting the Corneal Endothelium in a Mouse Model of Fuchs Endothelial Corneal Dystrophy

Abstract: Supplemental Digital Content is Available in the Text.

Cited by 7 publications

References 40 publications

Deep learning for detection of Fuchs endothelial dystrophy from widefield specular microscopy imaging: a pilot study

Deep learning for detection of Fuchs endothelial dystrophy from widefield specular microscopy imaging: a pilot study

U-Net Convolutional Neural Network for Real-Time Prediction of the Number of Cultured Corneal Endothelial Cells for Cellular Therapy

Applications of Imaging Technologies in Fuchs Endothelial Corneal Dystrophy: A Narrative Literature Review

Contact Info

Product

Resources

About