1 January 2022 in Progress in Retinal and Eye Research
Retinal fluid as the major biomarker in exudative macular disease is accurately visualized by high-resolution three-dimensional optical coherence tomography (OCT), which is used world-wide as a diagnostic gold standard largely replacing clinical examination. Artificial intelligence (AI) with its capability to objectively identify, localize and quantify fluid introduces fully automated tools into OCT imaging for personalized disease management. Deep learning performance has already proven superior to human experts, including physicians and certified readers, in terms of accuracy and speed. Reproducible measurement of retinal fluid relies on precise AI-based segmentation methods that assign a label to each OCT voxel denoting its fluid type such as intraretinal fluid (IRF) and subretinal fluid (SRF) or pigment epithelial detachment (PED) and its location within the central 1-, 3- and 6-mm macular area. Such reliable analysis is most relevant to reflect differences in pathophysiological mechanisms and impacts on retinal function, and the dynamics of fluid resolution during therapy with different regimens and substances. Yet, an in-depth understanding of the mode of action of supervised and unsupervised learning, the functionality of a convolutional neural net (CNN) and various network architectures is needed. Greater insight regarding adequate methods for performance, validation assessment, and device- and scanning-pattern-dependent variations is necessary to empower ophthalmologists to become qualified AI users. Fluid/function correlation can lead to a better definition of valid fluid variables relevant for optimal outcomes on an individual and a population level. AI-based fluid analysis opens the way for precision medicine in real-world practice of the leading retinal diseases of modern times.
14 August 2024 in Ophthalmology
To quantify morphological changes of the photoreceptors (PRs) and retinal pigment epithelium (RPE) layers under pegcetacoplan therapy in geographic atrophy (GA) using deep learning-based analysis of OCT images. Post hoc longitudinal image analysis. Patients with GA due to age-related macular degeneration from 2 prospective randomized phase III clinical trials (OAKS and DERBY). Deep learning-based segmentation of RPE loss and PR degeneration, defined as loss of the ellipsoid zone (EZ) layer on OCT, over 24 months. Change in the mean area of RPE loss and EZ loss over time in the pooled sham arms and the pegcetacoplan monthly (PM)/pegcetacoplan every other month (PEOM) treatment arms. A total of 897 eyes of 897 patients were included. There was a therapeutic reduction of RPE loss growth by 22% and 20% in OAKS and 27% and 21% in DERBY for PM and PEOM compared with sham, respectively, at 24 months. The reduction on the EZ level was significantly higher with 53% and 46% in OAKS and 47% and 46% in DERBY for PM and PEOM compared with sham at 24 months. The baseline EZ-RPE difference had an impact on disease activity and therapeutic response. The therapeutic benefit for RPE loss increased with larger EZ-RPE difference quartiles from 21.9%, 23.1%, and 23.9% to 33.6% for PM versus sham (all P < 0.01) and from 13.6% (P = 0.11), 23.8%, and 23.8% to 20.0% for PEOM versus sham (P < 0.01) in quartiles 1, 2, 3, and 4, respectively, at 24 months. The therapeutic reduction of EZ loss increased from 14.8% (P = 0.09), 33.3%, and 46.6% to 77.8% (P < 0.0001) between PM and sham and from 15.9% (P = 0.08), 33.8%, and 52.0% to 64.9% (P < 0.0001) between PEOM and sham for quartiles 1 to 4 at 24 months. Deep learning-based OCT analysis objectively identifies and quantifies PR and RPE degeneration in GA. Reductions in further EZ loss on OCT are even higher than the effect on RPE loss in phase 3 trials of pegcetacoplan treatment. The EZ-RPE difference has a strong impact on disease progression and therapeutic response. Identification of patients with higher EZ-RPE loss difference may become an important criterion for the management of GA secondary to AMD. Proprietary or commercial disclosure may be found after the references.
1 February 2015 in Investigative Radiology
The purposes of this study were to introduce and assess an automated user-independent quantitative volumetric (AUQV) breast density (BD) measurement system on the basis of magnetic resonance imaging (MRI) using the Dixon technique as well as to compare it with qualitative and quantitative mammographic (MG) BD measurements. Forty-three women with normal mammogram results (Breast Imaging Reporting and Data System 1) were included in this institutional review board-approved prospective study. All participants were subjected to BD assessment with MRI using the following sequence with the Dixon technique (echo time/echo time, 6 milliseconds/2.45 milliseconds/2.67 milliseconds; 1-mm isotropic; 3 minutes 38 seconds). To test the reproducibility, a second MRI after patient repositioning was performed. The AUQV magnetic resonance (MR) BD measurement system automatically calculated percentage (%) BD. The qualitative BD assessment was performed using the American College of Radiology Breast Imaging Reporting and Data System BD categories. Quantitative BD was estimated semiautomatically using the thresholding technique Cumulus4. Appropriate statistical tests were used to assess the agreement between the AUQV MR measurements and to compare them with qualitative and quantitative MG BD estimations. The AUQV MR BD measurements were successfully performed in all 43 women. There was a nearly perfect agreement of AUQV MR BD measurements between the 2 MR examinations for % BD (P < 0.001; intraclass correlation coefficient, 0.998) with no significant differences (P = 0.384). The AUQV MR BD measurements were significantly lower than quantitative and qualitative MG BD assessment (P < 0.001). The AUQV MR BD measurement system allows a fully automated, user-independent, robust, reproducible, as well as radiation- and compression-free volumetric quantitative BD assessment through different levels of BD. The AUQV MR BD measurements were significantly lower than the currently used qualitative and quantitative MG-based approaches, implying that the current assessment might overestimate breast density with MG.
1 August 2017 in Investigative Ophthalmology & Visual Science
Purpose: We develop a longitudinal statistical model describing best-corrected visual acuity (BCVA) changes in anti-VEGF therapy in relation to imaging data, and predict the future BCVA outcome for individual patients by combining population-wide trends and initial subject-specific time points. Methods: Automatic segmentation algorithms were used to measure intraretinal (IRF) and subretinal (SRF) fluid volume on monthly spectral-domain optical coherence tomography scans of eyes with central retinal vein occlusion (CRVO) receiving standardized anti-VEGF treatment. The trajectory of BCVA over time was modeled as a multivariable repeated-measure mixed-effects regression model including fluid volumes as covariates. Subject-specific BCVA trajectories and final treatment outcomes were predicted using a population-wide model and individual observations from early follow-up. Results: A total of 193 eyes (one per patient, 12-month follow-up, 2420 visits) were analyzed. The population-wide mixed model revealed that the impact of fluid on BCVA is highest for IRF in the central millimeter around the fovea, with −31.17 letters/mm3 (95% confidence interval [CI], −39.70 to −23.32), followed by SRF in the central millimeter, with −17.50 letters/mm3 (−31.17 to −4.60) and by IRF in the parafovea, with −2.87 letters/mm3 (−4.71 to −0.44). The influence of SRF in the parafoveal area was −1.24 letters/mm3 (−3.37–1.05). The conditional R2 of the model, including subject-specific deviations, was 0.887. The marginal R2 considering the population-wide trend and fluid changes was 0.109. BCVA at 1 year could be predicted for an individual patient after three visits with a mean absolute error of six letters and a predicted R2 of 0.658 using imaging information. Conclusions: The mixed-effects model revealed that retinal fluid volumes and population-wide trend only explains a small proportion of the variation in BCVA. Individual BCVA outcomes after 1 year could be predicted from initial BCVA and fluid measurements combined with the population-wide model. Accounting for fluid in the predictive model increased prediction accuracy.
1 September 2017 in IEEE Transactions on Medical Imaging
Prediction of treatment responses from available data is key to optimizing personalized treatment. Retinal diseases are treated over long periods and patients' response patterns differ substantially, ranging from a complete response to a recurrence of the disease and need for re-treatment at different intervals. Linking observable variables in high-dimensional observations to outcome is challenging. In this paper, we present and evaluate two different data-driven machine learning approaches operating in a high-dimensional feature space: sparse logistic regression and random forests-based extra trees (ET). Both identify spatio-temporal signatures based on retinal thickness features measured in longitudinal spectral-domain optical coherence tomography (OCT) imaging data and predict individual patient outcome using these quantitative characteristics. We demonstrate on a data set of monthly SD-OCT scans of 155 patients with central retinal vein occlusion (CRVO) and 92 patients with branch retinal vein occlusion (BRVO) followed over one year that we can predict from initial three observations if the treated disease will recur within the covered interval. ET predicts the outcome on fivefold cross-validation with an area under the receiver operating characteristic curve (AuC) of 0.83 for BRVO and 0.76 for CRVO. Logistic regression achieved an AuC of 0.78 and 0.79, respectively. At the same time, the methods identified stable predictive signatures in the longitudinal imaging data that are the basis for accurate prediction. Furthermore, our results show that taking spatio-temporal features into account improves accuracy compared with features extracted at a single time-point. Our results demonstrate the feasibility of mining longitudinal data for predictive signatures, and building predictive models based on observed data.