1
|
Abdelmotaal H, Hazarbassanov RM, Salouti R, Nowroozzadeh MH, Taneri S, Al-Timemy AH, Lavric A, Yousefi S. Keratoconus Detection-based on Dynamic Corneal Deformation Videos Using Deep Learning. OPHTHALMOLOGY SCIENCE 2024; 4:100380. [PMID: 37868800 PMCID: PMC10587634 DOI: 10.1016/j.xops.2023.100380] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/14/2023] [Revised: 07/21/2023] [Accepted: 08/04/2023] [Indexed: 10/24/2023]
Abstract
Objective To assess the performance of convolutional neural networks (CNNs) for automated detection of keratoconus (KC) in standalone Scheimpflug-based dynamic corneal deformation videos. Design Retrospective cohort study. Participants We retrospectively analyzed datasets with records of 734 nonconsecutive, refractive surgery candidates, and patients with unilateral or bilateral KC. Methods We first developed a video preprocessing pipeline to translate dynamic corneal deformation videos into 3-dimensional pseudoimage representations and then trained a CNN to directly identify KC from pseudoimages. We calculated the model's KC probability score cut-off and evaluated the performance by subjective and objective accuracy metrics using 2 independent datasets. Main Outcome Measures Area under the receiver operating characteristics curve (AUC), accuracy, specificity, sensitivity, and KC probability score. Results The model accuracy on the test subset was 0.89 with AUC of 0.94. Based on the external validation dataset, the AUC and accuracy of the CNN model for detecting KC were 0.93 and 0.88, respectively. Conclusions Our deep learning-based approach was highly sensitive and specific in separating normal from keratoconic eyes using dynamic corneal deformation videos at levels that may prove useful in clinical practice. Financial Disclosures Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
Collapse
Affiliation(s)
| | - Rossen Mihaylov Hazarbassanov
- Hospital de Olhos-CRO, Guarulhos, São Paulo, Brazil
- Department of Ophthalmology and Visual Sciences, Paulista Medical School, Federal University of São Paulo, São Paulo, Brazil
| | - Ramin Salouti
- Poostchi Ophthalmology Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
| | | | - Suphi Taneri
- Ruhr University, Bochum, Germany
- Zentrum für Refraktive Chirurgie, Muenster, Germany
| | - Ali H. Al-Timemy
- Biomedical Engineering Department, Al-Khwarizmi College of Engineering, University of Baghdad, Baghdad, Iraq
| | - Alexandru Lavric
- Computers, Electronics and Automation Department, Stefan cel Mare University of Suceava, Suceava, Romania
| | - Siamak Yousefi
- Department of Ophthalmology, University of Tennessee Health Science Center, Memphis, Tennessee
- Department of Genetics, Genomics, and Informatics, University of Tennessee Health Science Center, Memphis, Tennessee
| |
Collapse
|
2
|
Miao YY, Ma XM, Qu ZX, Eliasy A, Wu BW, Xu H, Wang P, Zheng XB, Wang JJ, Ye YF, Chen SH, Elsheikh A, Bao FJ. Performance of Corvis ST Parameters Including Updated Stress-Strain Index in Differentiating Between Normal, Forme-Fruste, Subclinical, and Clinical Keratoconic Eyes. Am J Ophthalmol 2024; 258:196-207. [PMID: 37879454 DOI: 10.1016/j.ajo.2023.10.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Revised: 10/18/2023] [Accepted: 10/20/2023] [Indexed: 10/27/2023]
Abstract
PURPOSE This study seeks to evaluate the ability of the updated stress strain index (SSIv2) and other Corvis ST biomechanical parameters in distinguishing between keratoconus at different disease stages and normal eyes. DESIGN Diagnostic accuracy analysis to distinguish disease stages. METHODS 1084 eyes were included and divided into groups of normal (199 eyes), forme fruste keratoconus (FFKC, 194 eyes), subclinical keratoconus (SKC, 113 eyes), mild clinical keratoconus (CKC-Ⅰ, 175 eyes), moderate clinical keratoconus (CKC-Ⅱ, 204 eyes), and severe clinical keratoconus (CKC-Ⅲ, 199 eyes). Each eye was subjected to a Corvis ST examination to determine the central corneal thickness (CCT), biomechanically corrected intraocular pressure (bIOP), SSIv2 (updated stress-strain index), and other 8 Corvis parameters including the stress-strain index (SSIv1), stiffness parameter at first applanation (SP-A1), first applanation time (A1T), Ambrósio relational thickness to the horizontal profile (ARTh), integrated inverse radius (IIR), maximum deformation amplitude (DAM), ratio between deformation amplitude at the apex and at 2 mm nasal and temporal (DARatio2), and Corvis biomechanical index (CBI). The sensitivity and specificity of these parameters in diagnosing keratoconus were analyzed through receiver operating characteristic curves. RESULTS Before and after correction for CCT and bIOP, SSIv2 and ARTh were significantly higher and IIR and CBI were significantly lower in the normal group than in the FFKC group, SKC group and the 3 CKC groups (all P < .05). There were also significant correlations between the values of SSIv2, ARTh, IIR, CBI, and the CKC severity (all P < .05). AUC of SSIv2 was significantly higher than all other Corvis parameters in distinguishing normal eyes from FFKC, followed by IIR, ARTh and CBI. CONCLUSION Corvis ST's updated stress-strain index, SSIv2, demonstrated superior performance in differentiating between normal and keratoconic corneas, and between corneas with different keratoconus stages. Similar, but less pronounced, performance was demonstrated by the IIR, ARTh and CBI.
Collapse
Affiliation(s)
- Yuan-Yuan Miao
- National Clinical Research Center for Ocular Diseases, Eye Hospital, WenZhou Medical University (Y.-Y.M., Z.-X.Q., B.-W.W., H.X., P.W., X.-B.Z., J.-J.W., Y.-F.Y., S.-H.C., F.-J.B), Wenzhou, Zhejiang, China
| | - Xiao-Min Ma
- Shanghai Eighth People's Hospital (X.-M.M.), Shanghai, China
| | - Zhan-Xin Qu
- National Clinical Research Center for Ocular Diseases, Eye Hospital, WenZhou Medical University (Y.-Y.M., Z.-X.Q., B.-W.W., H.X., P.W., X.-B.Z., J.-J.W., Y.-F.Y., S.-H.C., F.-J.B), Wenzhou, Zhejiang, China
| | - Ashkan Eliasy
- School of Engineering, University of Liverpool (A.Eli., A.Els.), Liverpool, United Kingdom
| | - Bo-Wen Wu
- National Clinical Research Center for Ocular Diseases, Eye Hospital, WenZhou Medical University (Y.-Y.M., Z.-X.Q., B.-W.W., H.X., P.W., X.-B.Z., J.-J.W., Y.-F.Y., S.-H.C., F.-J.B), Wenzhou, Zhejiang, China
| | - Hui Xu
- National Clinical Research Center for Ocular Diseases, Eye Hospital, WenZhou Medical University (Y.-Y.M., Z.-X.Q., B.-W.W., H.X., P.W., X.-B.Z., J.-J.W., Y.-F.Y., S.-H.C., F.-J.B), Wenzhou, Zhejiang, China
| | - Pu Wang
- National Clinical Research Center for Ocular Diseases, Eye Hospital, WenZhou Medical University (Y.-Y.M., Z.-X.Q., B.-W.W., H.X., P.W., X.-B.Z., J.-J.W., Y.-F.Y., S.-H.C., F.-J.B), Wenzhou, Zhejiang, China
| | - Xiao-Bo Zheng
- National Clinical Research Center for Ocular Diseases, Eye Hospital, WenZhou Medical University (Y.-Y.M., Z.-X.Q., B.-W.W., H.X., P.W., X.-B.Z., J.-J.W., Y.-F.Y., S.-H.C., F.-J.B), Wenzhou, Zhejiang, China; The Institute of Ocular Biomechanics, Wenzhou Medical University (X.-B.Z., J.-J.W., S.-H.C., F.-J.B.), Wenzhou, Zhejiang, China
| | - Jun-Jie Wang
- National Clinical Research Center for Ocular Diseases, Eye Hospital, WenZhou Medical University (Y.-Y.M., Z.-X.Q., B.-W.W., H.X., P.W., X.-B.Z., J.-J.W., Y.-F.Y., S.-H.C., F.-J.B), Wenzhou, Zhejiang, China; The Institute of Ocular Biomechanics, Wenzhou Medical University (X.-B.Z., J.-J.W., S.-H.C., F.-J.B.), Wenzhou, Zhejiang, China
| | - Yu-Feng Ye
- National Clinical Research Center for Ocular Diseases, Eye Hospital, WenZhou Medical University (Y.-Y.M., Z.-X.Q., B.-W.W., H.X., P.W., X.-B.Z., J.-J.W., Y.-F.Y., S.-H.C., F.-J.B), Wenzhou, Zhejiang, China
| | - Shi-Hao Chen
- National Clinical Research Center for Ocular Diseases, Eye Hospital, WenZhou Medical University (Y.-Y.M., Z.-X.Q., B.-W.W., H.X., P.W., X.-B.Z., J.-J.W., Y.-F.Y., S.-H.C., F.-J.B), Wenzhou, Zhejiang, China; The Institute of Ocular Biomechanics, Wenzhou Medical University (X.-B.Z., J.-J.W., S.-H.C., F.-J.B.), Wenzhou, Zhejiang, China.
| | - Ahmed Elsheikh
- School of Engineering, University of Liverpool (A.Eli., A.Els.), Liverpool, United Kingdom; National Institute for Health Research (NIHR) Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology (A.Els.), London, United Kingdom; Beijing Advanced Innovation Center for Biomedical Engineering, Beihang University (A.Els.), Beijing, China
| | - Fang-Jun Bao
- National Clinical Research Center for Ocular Diseases, Eye Hospital, WenZhou Medical University (Y.-Y.M., Z.-X.Q., B.-W.W., H.X., P.W., X.-B.Z., J.-J.W., Y.-F.Y., S.-H.C., F.-J.B), Wenzhou, Zhejiang, China; The Institute of Ocular Biomechanics, Wenzhou Medical University (X.-B.Z., J.-J.W., S.-H.C., F.-J.B.), Wenzhou, Zhejiang, China.
| |
Collapse
|
3
|
Feld S, Flockerzi E, Daas L, Xanthopoulou K, Sideroudi H, Langenbucher A, Seitz B. [Corneal biomechanics before and after cross-linking in patients with keratoconus]. DIE OPHTHALMOLOGIE 2023; 120:940-946. [PMID: 37043004 DOI: 10.1007/s00347-023-01839-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/09/2022] [Revised: 02/10/2023] [Accepted: 03/01/2023] [Indexed: 04/13/2023]
Abstract
OBJECTIVE The aim of this study was to analyze the effect of corneal cross-linking (CXL) on corneal biomechanics and visual acuity. PATIENTS AND METHODS The examination results before and after CXL in 56 eyes of 56 patients between 2017 and 2021 were evaluated retrospectively. The last preoperative examination was compared to the postoperative follow-up values after 6 and 12 months. The main outcome measures included various biomechanical parameters from the Corvis ST (CST), Pentacam and the visual acuity (logMAR, "logarithm of the Minimal Angle of Resolution"). For longitudinal evaluation, a general linear model for repeated measurements was used. A p-value of less than 0.05 was considered to show a statistically significant result. Bonferroni correction was applied for multiple comparisons. RESULTS The maximum corneal refractive power Kmax decreased slightly without statistical significance from 57.1 ± 6.1 diopters (dpt) to 56.6 ± 6.3 dpt after 6 months (p = 0.076) and 56.8 ± 6.6 dpt after 12 months (p = 0.443). The Pentacam parameter Belin/Ambrósio Enhanced Ectasia Total Deviation Display (BAD D) showed a statistically significant increase from the preoperative value of 8.4 ± 3.7 to the postoperative value of 9.1 ± 3.6 after 6 months (p < 0.001) and to 8.9 ± 3.5 after 12 months (p = 0.051). The CST parameter Ambrósio's relational thickness to horizontal profile (ARTh) decreased statistically significantly from 229.9 ± 109.6 to 204.8 ± 84.9 at 6 months (p = 0.017) and 205.3 ± 93.7 at 12 months (p = 0.022). The CST parameter stiffness parameter A1 (SP A1) increased slightly from the preoperative value 69.9 ± 17.2 to 70.4 ± 17.2 after 6 months (p = 1) and 71 ± 18.2 after 1 year (p = 1). Mean best-corrected visual acuity (logMAR) showed an improvement from 0.39 ± 0.3 to 0.34 ± 0.3 at 6 months (p = 0.286) and to 0.31 ± 0.3 at 12 months (p = 0.077). Regarding the ABCD classification, the parameters were determined preoperatively with an average of A2B3C1D2. They showed the same value of A2B3C1D2 after 6 and 12 months. CONCLUSION In progressive keratoconus, corneal cross-linking has the potential to positively influence the biomechanics of the cornea and visual acuity as a low complication treatment option.
Collapse
Affiliation(s)
- S Feld
- Klinik für Augenheilkunde, Universitätsklinikum des Saarlandes (UKS), Kirrberger Str. 100, 66424, Homburg/Saar, Deutschland.
| | - E Flockerzi
- Klinik für Augenheilkunde, Universitätsklinikum des Saarlandes (UKS), Kirrberger Str. 100, 66424, Homburg/Saar, Deutschland
| | - L Daas
- Klinik für Augenheilkunde, Universitätsklinikum des Saarlandes (UKS), Kirrberger Str. 100, 66424, Homburg/Saar, Deutschland
| | - K Xanthopoulou
- Klinik für Augenheilkunde, Universitätsklinikum des Saarlandes (UKS), Kirrberger Str. 100, 66424, Homburg/Saar, Deutschland
| | - H Sideroudi
- Klinik für Augenheilkunde, Universitätsklinikum des Saarlandes (UKS), Kirrberger Str. 100, 66424, Homburg/Saar, Deutschland
| | - A Langenbucher
- Institut für Experimentelle Ophthalmologie, Universität des Saarlandes, Homburg/Saar, Deutschland
| | - B Seitz
- Klinik für Augenheilkunde, Universitätsklinikum des Saarlandes (UKS), Kirrberger Str. 100, 66424, Homburg/Saar, Deutschland
| |
Collapse
|
4
|
Sedaghat MR, Momeni-Moghaddam H, Heravian J, Ansari A, Shayanfar H, Moshirfar M. Detection ability of corneal biomechanical parameters for early diagnosis of ectasia. Eye (Lond) 2023; 37:1665-1672. [PMID: 36038724 PMCID: PMC10220061 DOI: 10.1038/s41433-022-02218-9] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2022] [Revised: 07/12/2022] [Accepted: 08/12/2022] [Indexed: 11/09/2022] Open
Abstract
PURPOSE To assess the detection ability of corneal biomechanical parameters for early diagnosis of ectasia. METHODS This retrospective descriptive-analytical study included 134 normal eyes (control group) from 134 healthy subjects and 128 eyes with asymmetric contralateral corneal ectasia with normal topography (ACE-NT, study group) from 128 subjects with definite keratoconus in the opposite eye. Placido-disk-based corneal topography with TMS-4, Scheimpflug corneal tomography with Pentacam HR, and corneal biomechanical assessment with Corvis ST and ocular response analyzer (ORA) were performed. A general linear model was used to compare Corvis ST and ORA biomechanical parameters between groups, while central corneal thickness (CCT) and biomechanically corrected intraocular pressure (bIOP) were considered covariates. Receiving operator sensitivity curve (ROC) analysis was used to determine the cut-off point with the highest sensitivity and specificity along with the area under the curve (AUC) for each parameter. RESULT All parameters of Corvis ST and ORA showed a statistically significant difference between the two groups except for the first (P = 0.865) and second (P = 0.226) applanation lengths, and deformation amplitude (P = 0.936). The discriminative analysis of corneal biomechanical showed that the highest accuracy for the classic, new, and combined parameters of Corvis ST was related to HCR (AUC: 0.766), IR & DAR (0.846), and TBI (0.966), respectively. Using ORA, the corneal resistance factor (0.866) had a higher detection ability than corneal hysteresis (0.826). CONCLUSIONS TBI has the best accuracy and the highest effect size for differential diagnosis of normal from ACE-NT eyes with a cut-off point of 0.24.
Collapse
Affiliation(s)
| | - Hamed Momeni-Moghaddam
- Health Promotion Research Center, Zahedan University of Medical Sciences, Zahedan, Iran.
| | - Javad Heravian
- Department of Optometry, School of Paramedical Sciences, Mashhad University of Medical Sciences, Mashhad, Iran
| | - Atiyeh Ansari
- Department of Optometry, School of Paramedical Sciences, Mashhad University of Medical Sciences, Mashhad, Iran
| | - Helia Shayanfar
- Eye Research Center, Mashhad University of Medical Sciences, Mashhad, Iran
| | - Majid Moshirfar
- Hoopes Vision Research Center, Hoopes Vision, 11820S. State St. #200, Draper, UT, 84020, USA
- John A. Moran Eye Center, University of Utah School of Medicine, Salt Lake City, UT, USA
- Utah Lions Eye Bank, Murray, UT, USA
| |
Collapse
|
5
|
Analysis of the diagnostic accuracy of Belin/Ambrósio Enhanced Ectasia and Corvis ST parameters for subclinical keratoconus. Int Ophthalmol 2022; 43:1465-1475. [PMID: 36255612 DOI: 10.1007/s10792-022-02543-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2022] [Accepted: 10/06/2022] [Indexed: 10/24/2022]
Abstract
OBJECTIVE To investigate the diagnostic accuracy of the parameters in the Belin/Ambrósio Enhanced Ectasia Display built in Pentacam, which is designed for the screening of subclinical keratoconus (SKC) built in Pentacam, and the parameters in Corneal visualization Scheimpflug technology (Corvis ST). METHODS A retrospective study: The fellow eyes of unilateral keratoconus cases were diagnosed with SKC. Patients presented to Shanxi Eye Hospital with SKC from October 2020 to November 2021 were included as the SKC group, and myopic patients undergoing corneal refractive surgery at the Refractive Surgery Department in our hospital within the same period were included as the control group. The Belin/Ambrósio and Corvis ST parameters were extracted from the system and analyzed using independent samples t test. Receiver operating curves (ROCs) were also created to test the diagnostic accuracy of each parameter. RESULTS There were 70 patients (70 eyes) in the SKC group and 137 patients (137 eyes) in the control group. For Corvis ST parameters, Radius (P = 0.021), PachySlope (P = 0.040), SP-A1 (P = 0.002), A2 Deformation Amp. (P = 0.028), A2 Deflection Length (P < 0.001), Max ICR (P = 0.005), DA Ratio Max (1 mm) (P = 0.023), IR (P = 0.016), CBI (P = 0.003) and TBI (P < 0.001) were statistically different between the two groups. For Belin/Ambrósio parameters, PPI min. Axis, ART min, ART max, ART avg, Pachy min, Front K2, Astig, BAD-Df, BAD-Db, BAD-Dp, BAD-Dt, BAD-Da, BAD-D, PPI min, PPI max, PPI max. Axis, PPI avg and Dist.Apex-Thin.Loc. were significantly different between the two groups (all p < 0.001). TBI and BAD-D showed the best diagnostic accuracy, with AUCs of 0.944 and 0.965, respectively. CONCLUSIONS Some Belin/Ambrósio and Corvis ST parameters differed between SKC eyes and eyes with normal cornea. TBI and BAD-D showed the ideal diagnostic performance for SKC. In clinical practice, conventional corneal topography could not be replaced by Corvis ST.
Collapse
|