Ophthalmology (Eye & Ear Hospital) - Theses
Permanent URI for this collection
Search Results
1 - 4 of 4
-
ItemMachine learning approaches to identify early keratoconus and classify keratoconus progression( 2021)Background: Keratoconus (KC) is a common corneal condition affecting children and young adults that has remained a major cause of corneal transplant surgery during the last decade. A newer management method named corneal collagen crosslinking (CXL) may now be used to slow the progression of KC in many individuals. Several studies have shown that the introduction of CXL resulted in a decrease in corneal transplantation rates in many countries. The CXL strategy is most beneficial to patients in early stage of KC to preserve best visual outcomes. The progression of KC must also be documented before executing a CXL procedure on KC patients. Identifying individuals with early KC and progressive KC is thus critical for planning early intervention care. Despite these requirements, existing approaches to early KC diagnosis and progression detection are inefficient. This includes a subjective assessment of early KC, as well as the absence of standardised criteria for KC progression that has resulted in the absence of a globally accepted KC management plan. The advancement of corneal topography and tomography imaging equipment has dramatically increased the quality and quantity of data acquired in KC clinics. There are currently no tools available in clinics that allow for the analysis of all corneal topography data to identify early KC and progression of KC, further signalling that their existing decision-making process may be inadequate. Purpose: This thesis sought to combine all 1692 parameters (containing demographic information and examination characteristics that are not clinical measurements.) available from an advanced corneal tomography system known as Pentacam into the decision-making process for improving early KC identification and progression classification. To cope with large amounts of data, this thesis used a variety of machine learning algorithms to accomplish the following aims: 1. To evaluate the performance of a number of various machine learning algorithms for discrimination of early keratoconus from eyes without KC (control eyes) using 11 commonly derived KC parameters; 2. To explore the impact of using all available Pentacam parameters with the highest-performing machine learning model for detection of early keratoconus; 3. To identify a key set of parameters supporting detection of early keratoconus as an optimal subset of all Pentacam parameters; and 4. To improve the classification of keratoconus progression by stratifying longitudinal clinical changes in KC using all Pentacam parameters with unsupervised machine learning algorithms. Research Design and Methods: This thesis is part of the Australian Study of Keratoconus (ASK), and was undertaken on a retrospective cohort of 3042 KC eyes and 700 eyes without KC (control eyes) collected at the Royal Victorian Eye and Ear Hospital. The diagnosis of each subject was retrieved from their electronic medical records. Early KC eyes were further labelled from the KC group by an expert optometrist. Early KC was defined as having a normal appearance on slit-lamp biomicroscopy and retinoscopy examination and abnormal corneal topography, such as inferior-superior localised steepening or an asymmetric bowtie pattern. The fellow eye may or may not be affected by KC. All 1692 accessible parameters on each individual eye were acquired on their first (baseline) visit and subsequent visits using the Pentacam v1.20r127 (Oculus, Wetzlar, Germany). Two clinical measurements, vision and refraction, were obtained from the patient's electronic medical record (where available) and included in the analysis for aim 3. From aims 1 to 3, supervised machine learning methods were used to develop models for distinguishing early KC and control eyes while in aim 4, an unsupervised machine learning method was used. Results: In Aim 1, the random forest algorithm was found to be the optimal machine learning algorithm to detect early KC from control eyes in the current dataset. This result was obtained by comparing the performance of eight different machine learning algorithms across 11 commonly derived KC parameters using 49 early KC eyes (49 patients) and 39 control eyes (39 patients). Notably, Aim 1 proved the usefulness of performing a machine learning algorithm comparison and feature selection to identify an optimal model that provided the maximal model performance. Aim 2 established the effectiveness of integrating all Pentacam parameters in identifying early KC. Using a reduced dimensionality space of all Pentacam parameters, the random forest model achieved a 98% accuracy (97% sensitivity and 98% specificity) in detecting early KC with 145 early KC (141 patients) and 122 controls eyes (85 patients). This machine learning model outperformed the majority of established machine learning modes in the literature. Further, in Aim 3, the same dataset as in Aim 2 was analysed, and a key combination of Pentacam parameters was identified for recognising early KC. This key set of parameters included the eccentricity value at a 30-degree angle of the front cornea, the eccentricity value in the 9 mm diameter zone of the cornea, and the inferior versus superior corneal asymmetry. The random forest model developed using these parameters correctly identified 94% of eyes and had a sensitivity of 97% and a specificity of 91% for distinguishing early KC from controls in the internal test dataset. Additionally, Aim 3 revealed the beneficial impact of combining vision and refraction measurements towards early KC detection. Finally, for the progression study of KC in Aim 4, three clusters/subgroups were identified with KC clinical change, defined as rapid-change, moderate-change and limited-change groups. The clusters were derived using hierarchical clustering based on half-year longitudinal clinical changes in all Pentacam parameters in 903 KC (588 patients) and 119 control eyes (92 patients). In Aim 4, 39 corneal curvature-related parameters were also found to be significantly different across the three subgroups. Discussion: By incorporating all Pentacam parameters in the machine learning model, the machine learning methods created in this work considerably improve the completeness of early KC detection. This enables assessment of the whole cornea during the early KC evaluation, possibly boosting the accuracy of current approaches for identifying early KC. These findings demonstrate the value of incorporating more pertinent information in order to improve early KC identification. Additionally, a key set of parameters for diagnosing early KC was identified, and this finding established the vital importance of corneal eccentricity in the early identification of KC, and the pertinent parameters could be used in clinics for early detection. These findings increase the generalizability of early KC diagnosis. There are numerous corneal topography systems available for usage in various clinics, but no machine learning model created in the literature so far can be applied across multiple imaging systems. The machine learning models developed in this thesis have a greater chance of being applicable to a variety of imaging systems due to the small number of parameters required and their widespread availability. For the first time, a three-classification scheme for KC clinical changes associated with progression was established using data-driven clustering. The finding may change our view of disease progression, since there were more categories than previously thought, in addition to progressed and non-progressed KC. This classification may alter the therapy protocol for individuals with KC since the care of patients with varying degrees of progression may differ. Finally, the research emphasises the critical need of monitoring the complete corneal curvature while assessing KC progression, rather than concentrating just on the central corneal curvature, as is presently done in clinics. Conclusion: The use of machine learning indicates its ability to better define early KC as well as begin to dissect out key aspects of KC progression. The machine learning-based potential decision support systems developed in this thesis addressed several gaps in the field and have the potential to improve clinical examination of KC patients and lead to better patient management.
-
ItemNo Preview AvailableApplication of artificial intelligence to analysis and progression of geographic atrophy in age-related macular degeneration( 2021)Background: Geographic atrophy (GA) is a debilitating eye disease affecting adults 50 years and older and is the late stage of age-related macular degeneration (AMD). It is characterised by the presence of lesions in the retina, which are areas of cellular death that cause irreversible vision loss. The dark lesions are usually surrounded by bright regions of hyperfluorescence. GA is a progressive condition with no therapeutic treatments available to arrest or slow down its course. GA is highly variable in its progression, with some patients progressing faster to vision loss than others. While a plethora of publications are available on the investigation of this disease, there remains an uncertainty with regards to our understanding of the disease, its manifestation and progression. Several clinical and non-clinical features along with different statistical modelling techniques have been explored to date. However, there is a lack of consensus regarding the most appropriate model or features that are thought to be useful in a real-time clinical setting. Current available tools only annotate GA lesions using the semi-automated region-growing algorithm. In addition to its semi-automation (which still requires manual and time-consuming work from clinical graders), the current tool can only retrospectively assess progression based on all available data; the software does not have predictive capabilities. Ideally, being able to predict the disease state and progression of GA at initial consultation would be of immense clinical benefit to both the ophthalmologist and patient. Artificial intelligence (AI) has been suggested over the past decade to having the capabilities to achieve such a goal. However, the publications in the GA-AI space thus far have predominantly focused on the automation of the primary GA feature of interest, lesions, with minor focus on GA progression. The automation and detection of hyperfluorescence has been neglected altogether. Thus, there is great scope to apply AI to understand GA manifestation and progression. Purpose and Aims: This thesis describes research to automate the diagnosis of GA, as well as understand the patterns of GA progression using a combination of AI, image processing, mathematics, statistics and computer science. The aims of the thesis were to (1) automate the detection of lesions, but with greater accuracy and efficiency as compared to the current work in the literature, while simultaneously automating hyperfluorescence areas for the first time ever to offer ophthalmologists complete automation of GA features, (2) investigate patterns of GA progression by evaluating prospective regression models by applying our current understanding of the clinical and physical assumptions of GA growth, (3) understand the impact of epistemic uncertainty – a metric to measure variability due to incomplete knowledge of a disease or process – in GA modelling, (4) quantify and identify subgroups of GA lesions and hyperfluorescence areas using machine learning (ML) techniques in order to explain whether varying shapes and sizes of GA features could explain varying progression rates, (5) extract and rank relevant imaging features using ML and develop a statistical model for GA growth, and (6) present a preliminary software platform which can be extended beyond the scope of this thesis. The Methods and Results achieved for the Aims are summarised below. Methods: Data Subjects included in this thesis were AMD participants diagnosed with GA. Data were collected from macular studies from the Centre for Eye Research Australia (CERA) and from a private ophthalmology practice. Extracted data included basic demographic information, such as age and sex, and the imaging modality fundus autofluorescence (FAF) – which produces a grayscale image that enhances the detection of lesions and hyperfluorescence regions. Ground truth labels were also annotated by two graders, and the intraclass correlation coefficient (ICC) was used to measure consistency between graders. Aim 1 Lesion automation included a pipeline of image pre-processing (e.g., contrast limited adaptive histogram equalisation) and semantic segmentation using the U-Net architecture and ground truth labels. Metrics used for assessing lesion automation included the Dice similarity coefficient (DSC), specificity, sensitivity, mean absolute error (MAE), accuracy, and precision. The automation of the hyperfluorescent regions were conducted using pseudocolouring techniques. This involved the application of a colour palette to the FAF images (i.e., specifically the JET colour map), which highlighted the changing intensities in hyperfluorescent regions. Hyperfluorescence was automatically extracted by specifying the colour ranges which covered hyperfluorescent regions. For hyperfluorescence automation, no ground truth labels were available, and thus qualitative assessments were conducted. Aims 2 & 3 Patterns of GA growth – the cumulative increase of total GA surface area within the retina over time – were investigated by evaluating a range of regression models: linear, logarithmic, power, exponential, quadratic, and quadratic without linear term. The physical and clinical assumptions of growth were included as part of the analyses (i.e., growth cannot be infinite; there is finite retinal area in which the lesion growth will hit and then the growth curve should plateau). For Aim 3, the prospective models were evaluated using epistemic uncertainty, particularly model structure uncertainty. Uncertainty was quantified as U=1-r2 where r2=1-SSR/SSO and SSR/SSO is the sum of square residuals divided by the total sum of squares in the data. The metric U is the proportion of total unexplained variability not accounted for by the regression model. The smaller the U, the better the fit of a model. Aim 4 Prospective patterns and groupings of lesions and hyperfluorescent areas were elucidated using several unsupervised clustering methods. Cluster performance was measured using Silhouette coefficient (SC), Davies-Bouldin Index (DBI), and Calinski-Harabasz Index (CHI). If appropriate groups were identified, nomenclature was assigned to these groups based on the patterns seen within the cluster. Aim 5 Feature extraction and ranking was conducted using the ML algorithm XGBoost. An image-based linear mixed-effects model was designed to account for slope change based on within-subject variability and inter-eye correlation. Metrics used to assess the linear mixed-effects model included marginal and condition R2 (RM2 and RC2), Pearson’s correlation coefficient (r), root mean square error (RMSE), mean error (ME), MAE, mean absolute deviation (MAD), Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), and log-likelihood. Aim 6 Aim 6 involved the design of a software that will be built upon further but is beyond the scope of this thesis. This software was built using Python and PyQT5. Results: Data The final dataset consisted of 702 images from 51 patients. The cohort consisted of 99 eyes, 49 left eyes (49.5%) and 50 right eyes (50.5%). A total of 359 images were for the left eye and 343 images were for the right eye. The cohort consisted of 38 females (74.5%) and 13 males (25.5%) with an average age of 76.7 +/- 8.9 years. Total follow-up time was 61.5 +/- 25.3 months. For manual annotation of ground truth labels, the ICC for consistency between the two graders was 0.9855 (95% CI: 0.9298, 0.9971). Aim 1 For lesion automation, the DSC was 0.9780 +/- 0.0124, sensitivity was 0.9903 +/- 0.0041, specificity was 0.7498 +/- 0.0955, MAE was 0.0376 +/- 0.0184, accuracy was 0.9774 +/- 0.0090, and precision was 0.9837 +/- 0.0116. Assessments of hyperfluorescence areas revealed three distinct regions of hyperfluorescence. They have been named as: early-stage hyperfluorescence, intermediate-stage hyperfluorescence, and late-stage hyperfluorescence. Qualitatively, both the lesion and hyperfluorescence automations produced visually accurate outcomes. The automations ran 10 times faster than the current semi-automated segmentation. Aims 2 & 3 The linear regression model was identified as most representative of peak GA growth. It had the lowest average uncertainty (U = 0.025), highest average coefficient-of-determination (R2 = 0.92), and applicability of the model was supported by a high correlation coefficient, r, with statistical significance (P = 0.01). Given the assumptions of GA growth (i.e., plateau due to limited retinal space) and the results confirming peak growth was linear, a hypothesis was made that GA growth overall followed a sigmoidal growth curve from disease onset to plateau. Using records from existing patients, the sigmoidal hypothesis was tested in case studies with sufficient longitudinal data from clinical follow-ups. The sigmoidal growth curve revealed a closer fit in these rare cases, and it is recommended that future GA progression studies include additional data to further validate the lower- and upper-tail ends of the sigmoidal function. Aim 4 GA lesions, together with early-, intermediate-, and late-stage hyperfluorescence areas were subject to cluster analysis using the method of k-Means. Meaningful clusters were identified for lesions, early- and late-stage hyperfluorescence regions, with each GA feature having k=3 clusters. For lesions, SC = 0.799, DBI = 0.180, and CHI = 4313.316. For early-stage hyperfluorescence, SC = 0.597, DBI = 0.915, and CHI = 186.989. For late-stage hyperfluorescence, SC = 0.593, DBI = 1.013, and CHI = 217.325. No meaningful clusters were identified for intermediate-stage hyperfluorescence. Aim 5 A linear mixed-effects model with 15 FAF imaging features produced average RM2 = 0.84 +/- 0.01, RC2 = 0.95 +/- 0.002, r = 0.97 +/- 0.006, RMSE = 1.44 +/- 0.06, ME = 0.09 +/- 0.15, MAE = 1.04 +/- 0.06, MAD = 3.52 +/- 0.67, AIC = 1718.41 +/- 11.08, BIC = 1798.99 +/- 11.20, and log-likelihood = -839.21 +/- 5.54. The model was also executed using the popularised square root and log(Yi+1) transformations, however, the original scaled GA total area using mm2/year produced the best results. Aim 6 A preliminary and user-friendly software was designed, which allows the end-user to select a baseline FAF image and then automatically segment lesion, early-, intermediate-, and late-stage hyperfluorescence regions from the image. Then, if the user wishes to toggle from image to image with all features being automatically updated, they simply need to select the ‘Next’ button rather than reloading a new image. A demonstration video can be found at https://youtu.be/WidWf70MKX4. Conclusions: This thesis adopted a multidisciplinary approach combining AI, image processing, mathematics, statistics and computer science to automate GA feature extraction, ranking of GA features, understanding the pattern of GA growth, and the development of a preliminary GA growth model and software. There are many clinical impacts of this work. The automation of clinical processes enables clinicians to focus on their patients and not on the repetitive and time-consuming components of diagnostic and prognostic processes. Furthermore, the automation also guarantees that both clinicians and patients save considerable time in consultations. Additionally, by understanding the underlying patterns of GA growth, we could take more decisive steps to develop appropriate interventions to arrest the progression of the disease or cure it altogether. Future development of the software could extend to multimodal imaging, such as spectral domain optical coherence tomography images or colour fundus photographs. The addition of other predictors is possible, such as genetic heritability.
-
ItemShould Australia Export Corneas? Eye banks, exports and Australian Opinion: Exploring national utility of human corneal tissue donation( 2021)ABSTRACT: There are 12.7 million people, globally, waiting for a corneal transplant. Most reside in low-middle-income nations or locations without sufficient local access to corneal tissue (CT) from an eye bank (EB). As such they are unable to access donated end-of-life CT, necessary to perform a sight restoring or enhancing corneal transplant. They are reliant on CT importation from EBs in other nations that are in a position to export. Despite export and import services commencing in 1961, and the practice now responsible for around 23% of all annual corneal transplantations, there has never been a review of the practice. There is no information to indicate if donors are aware or consented, how the practice impacts the export nation’s own access, or how it impacts the import nation’s ability to build their own EB service. There is no indication if the current approach is effective and equitable in allocating the CT, or if nations, in a position to export, should routinely do so. Therefore, through the example of my own nation, Australia – a nation with a history of ad hoc exportation, but reported to be in a position to potentially export routinely, I examined if Australia should export CT? Importation was examined through this research however its primary focus was examination from the perspective of the exporter. Method: I use a mixed methods approach to determine if Australia should export CT. Firstly, data was captured from all n=5 Australian Eye Banks (AUEBs) regarding their collection and non-collection of CT (Aim 1). This provided information on the potential export level and ascertained if Australia was meeting domestic demand and in a position to export. Secondly, grounded theory semi-structured interviews were conducted with n=92 purposively selected eye care and eye tissue experts (Aim 2). I interviewed until themed saturation was met. Their responses were sentiment analysed to determine their opinion on Australia’s export potential and unearth foundation information about the practice. Finally, e-surveys were conducted with a sample of the Australian public (n=1044) (Aim 3). The e-survey determined their willingness to export their CT on their death. Correlation coefficients were used to examine association between categorical variables, and determine their willingness and opinion on how the practice should occur. Results: Aim 1 indicated that there were sufficient donations collected to meet domestic demand, and that excess CT could potentially be exported. Importantly, it also highlighted that AUEBs were not meeting domestic demand all of the time and steps to improve domestic allocation were required prior to or simultaneously to examining routine exportation. Aim 2 indicated that sector professionals supported the notion of Australia routinely exporting CT (n=84/92, 67%), on the proviso that a nationally coordinated system was implemented, and donors were consented, or at the least informed, that their donation may be moved to another location, though day-to-day decisions on allocation, they believed, should be left to the professionals. They favoured exportation to Western Pacific Nations, neighbouring nations, and low-middle-income nations. Aim 2 also provided foundation information about the export and import practice. For example, there is no indication that donors are uniformly aware or consented for exportation of their donation, and current practice does not provide equitable access to CT - with the primary decision to export to another nation based on the importers ability to pay. This meant that those in low-to-middle-income nations were least likely to access CT. Finally, Aim 3 indicated that there were Australians willing to export their corneas (n=397/1044, 38%). It also indicated that there were Australians who would not (n=248/1044, 23.8%), and others who required further information before deciding (n=399/1044, 38.2%). Collectively, they indicated that donors must be consented or, at the least, informed that their donation may be moved to another location for use. They also indicated that the sector professionals should decide on the allocation location, on the proviso that a nationally coordinated system was in place that clearly explained their decision making. Discussion: This research highlighted that there is a paucity of information available to describe the practice of exportation and importation of CT. It indicated that the practice is not conducted in a structured or planned manner by the exporters nor the importers. It proposed that Australia could potentially export CT to other nations, with low-middle-income, neighbouring, or Western Pacific nations prioritised. It also recommended that additional steps be implemented to ensure that domestic demand was routinely being met, and that CT donors were consented, or at the least, informed that their donation may be moved outside their local EB location.
-
ItemOptimising the management of diabetic retinopathy in pregnant women with pre-existing diabetes in Australia( 2021)Background: Diabetic Retinopathy (DR) is a leading cause of blindness among people of reproductive age and is thought to be worsened by pregnancy. Findings from prior studies have been conflicting, many are outdated, and the majority only studied women with type 1 diabetes (T1DM). It is crucial to identify those within this population who are most at risk of developing DR progression towards sight-threatening disease, so that appropriate management can be planned. Clinical decisions regarding DR management in pregnancy can be fraught, due to the need to give timely sight-saving treatment while also minimising adverse effects to the foetus. Despite these concerns, DR management guidelines have been inconsistent across the globe due to disparate findings. Purpose: This thesis aimed to 1) report the prevalence of DR, sight-threatening DR (STDR), and its progression rate during pregnancy in Metropolitan Melbourne; 2) assess the use of optical coherence tomography angiography (OCTA) in evaluating retinal changes in diabetic patients during different stages of pregnancy; and 3) determine the adherence rate and the barriers to the recommended eye screening guidelines in pregnant women with pre-existing diabetes. Research Design and Methods: This doctoral research project was a prospective longitudinal cohort study of women with T1DM or type 2 diabetes who were pregnant or planning to get pregnant from two tertiary maternity hospitals in Melbourne, Australia. Eye examinations were scheduled in each trimester and at 3-months postpartum. DR severity was graded for each eye from 2-field retinal photographs. Progression was defined as worsening by >= 1-step on the Airlie House classification, development of diabetic macular oedema (DMO), or the need for laser treatment during pregnancy. Sight-threatening (ST) progression was defined as development of proliferative DR or DMO. Additionally, 3x3-mm OCTA scans (macula-centred) were taken from participants who attended Melbourne Eyecare Clinic using swept-source OCT (Triton, Topcon Corp). Foveal avascular zone (FAZ) area and vessel density (VD) from the superficial capillary plexus were measured. Barriers to attending eye screening were assessed with the modified Compliance with Annual Diabetic Eye Exams Survey. Results: Aim 1: A total of 147 from 191 eligible women (77%) were recruited, with at least one eye exam performed in 130 (88.4%). Sixty-two women (47.7%) had T1DM. DR and STDR prevalence were 20.8 (95% confidence interval [CI] 16.3-26.1) and 6.6 (CI 4.1 - 10.4) per 100 eyes, respectively. Among the 144 eyes (72 women) with more than one eye exam, 9.7% (CI 5.8 - 15.8) had DR progression and 4.5% (CI 1.9 - 9.6) had ST progression. Elevated systolic blood pressure (risk ratio [RR] 10.36, CI 3.14 - 34.12) and pre-existing DR (RR 5.07, CI 1.90 - 13.49) in early pregnancy significantly increased the risk of progression. Aim 2: A total of 125 eyes from 64 women were imaged. The majority of women were in the pregnant group (77%) with 38 (59%) having T1DM. The majority of eyes had no DR (81.6%) or DMO (97.6%). The VD in the pericentral region and superior, temporal, and nasal subfields were significantly lower in eyes with DR than eyes without in the non-pregnant and pregnant groups (p-values <=0.039). The nasal VD in eyes with no DR in the pregnant group was significantly higher than that of the postpartum group (p=0.010). Although not reaching statistical significance, a trend towards higher VD in the pregnant group than the non-pregnant group was observed in all subfields, except in the temporal subfield. The temporal VD was lower in the pregnant group than the non-pregnant group and was especially marked in eyes with DR. No significant difference was found in the mean FAZ area between various pregnancy statuses and DR severities. Aim 3: There were 125 pregnant women who completed the survey. The median age was 34 years (range 19-47). Sixty-four respondents (51.2%) had T1DM. A retinal assessment was performed at least once in the first trimester in 56 (44.8%) and 33 (26.4%) had the ideal number of examinations. Competing priorities (p=0.012) and the belief of having reasonable diabetes control (p=0.007) were the main reasons given for non-attendance. Interestingly, the presence of multiple eye care providers in the neighbourhood was also associated with non-adherence (p=0.003). Conclusion: This PhD study has provided updated data on the prevalence of DR and its rate of progression in the Australian pregnant population with pre-existing diabetes, illustrated the use of OCTA in this population, and reported the adherence rate and barriers to the recommended eye screening guidelines. The DR prevalence in pregnant women was similar to the non-pregnant diabetic population in Australia. However, nearly 1 in 10 eyes had DR progression during pregnancy, with almost half of these developing STDR. DR presence could be reflected by a decrease in the VD in the OCTA scan, which is in concordance with the findings from previous studies in non-pregnant populations, suggesting a potential role for OCTA in the evaluation of DR during pregnancy in a non-invasive manner. Worryingly, more than half of our cohort did not adhere to the recommended eye screening schedule in pregnancy, and about 70% did not receive frequent exams as recommended, highlighting the need to address barriers to eye screening attendance given the significant risk of vision loss from DR in this population. This study benefits society by providing findings that may help inform the future development of evidence-based guidelines for DR screening and management in this unique and growing population. Based on this study’s findings, it is recommended that pregnant women with pre-existing diabetes should have an eye examination in the first trimester or as soon as pregnancy is recognised. If no DR is found, an additional exam during pregnancy is advised only for women with T1DM. However, if DR is present, an eye exam in each trimester is recommended irrespective of diabetes type.