George M. Saleh

Localizing Microaneurysms in Fundus Images Through Singular Spectrum Analysis

Goal: Reliable recognition of microaneurysms (MAs) is an essential task when developing an automated analysis system for diabetic retinopathy (DR) detection. In this study, we propose an integrated approach for automated MA detection with high accuracy. Methods: Candidate objects are first located by applying a dark object filtering process. Their cross-section profiles along multiple directions are processed through singular spectrum analysis. The correlation coefficient between each processed profile and a typical MA profile is measured and used as a scale factor to adjust the shape of the candidate profile. This is to increase the difference in their profiles between true MAs and other non-MA candidates. A set of statistical features of those profiles is then extracted for a K-nearest neighbor classifier. Results: Experiments show that by applying this process, MAs can be separated well from the retinal background, the most common interfering objects and artifacts. Conclusion: The results have demonstrated the robustness of the approach when testing on large scale datasets with clinically acceptable sensitivity and specificity. Significance: The approach proposed in the evaluated system has great potential when used in an automated DR screening tool or for large scale eye epidemiology studies.

The development of a virtual reality training programme for ophthalmology: repeatability and reproducibility (part of the International Forum for Ophthalmic Simulation Studies)

PurposeTo evaluate the variability of performance among novice ophthalmic trainees in a range of repeated tasks using the Eyesi virtual reality (VR) simulator.MethodsEighteen subjects undertook three attempts of five cataract specific and generic three-dimensional tasks: continuous curvilinear capsulorhexis, cracking and chopping, cataract navigation, bimanual cataract training, anti-tremor. Scores for each attempt were out of a maximum of 100 points. A non-parametric test was used to analyse the data, where a P-value of <0.05 was considered statistically significant.ResultsHighly significant differences were found between the scores achieved in the first attempt and that during the second (P<0.0001) and third (P<0.0001) but not between the second and third attempt (P=0.65). There was no significant variability in the overall score between the users (P=0.1104) or in the difference between their highest and lowest score (P=0.3878). Highly significant differences between tasks were shown both in the overall score (P=0.0001) and in the difference between highest and lowest score (P=0.003).ConclusionThis study, which is the first to quantify reproducibility of performance in entry level trainees using a VR tool, demonstrated significant intra-novice variability. The cohort of subjects performed equally overall in the range of tasks (no inter-novice variability) but each showed that performance varies significantly with the complexity of the task when using this high-fidelity instrument.

High correlation between performance on a virtual-reality simulator and real-life cataract surgery

To investigate the correlation in performance of cataract surgery between a virtual‐reality simulator and real‐life surgery using two objective assessment tools with evidence of validity.

Optimal and simultaneous designs of Hermitian transforms and masks for reducing intraclass separations of feature vectors for anomaly detection of diabetic retinopathy images

This paper proposes a novel methodology for the optimal and simultaneous designs of both Hermitian transforms and masks for reducing the intraclass separations of feature vectors for anomaly detection of diabetic retinopathy images. Each class of training images associates with a Hermitian transform, a mask and a known represented feature vector. The optimal and simultaneous designs of both the Hermitian transforms and the masks are formulated as least squares optimization problems subject to the Hermitian constraints. Since the optimal mask of each class of training images is dependent on the corresponding optimal Hermitian transform, only the Hermitian transforms are required to be designed. Nevertheless, the Hermitian transform design problems are optimization problems with highly nonlinear objective functions subject to the complex valued quadratic Hermitian constraints. This kind of optimization problems is very difficult to solve. To address the difficulty, this paper proposes a singular value decomposition approach for deriving a condition on the solutions of the optimization problems as well as an iterative approach for solving the optimization problems. Since the matrices characterizing the discrete Fourier transform, discrete cosine transform and discrete fractional Fourier transform are Hermitian, the Hermitian transforms designed by our proposed approach are more general than existing transforms. After both the Hermitian transforms and the masks for all classes of training images are designed, they are applied to test images. The test images will assign to the classes where the Euclidean 2-norms of the differences between the processed feature vectors of the test images and the corresponding represented feature vectors are minimum. Computer numerical simulation results show that the proposed methodology for the optimal and simultaneous designs of both the Hermitian transforms and the masks is very efficient and effective. The proposed technique is also very efficient and effective for reducing the intraclass separations of feature vectors for anomaly detection of diabetic retinopathy images.

Computer analysis of individual cataract surgery segments in the operating room

PurposeObjective feedback is important for the continuous development of surgical skills. Motion tracking, which has previously been validated across an entire cataract procedure, can be a useful adjunct. We aimed to measure quantitative differences between junior and senior surgeons’ performance in three distinct segments. We further explored whether automated analysis of trainee surgical videos through PhacoTracking could be aligned with metrics from the EyeSi virtual reality simulator, allowing focused improvement of these areas in a controlled environment.MethodsProspective cohort analysis, comparing junior vs. senior surgeons’ real-life performance in distinct segments of cataract surgery: continuous curvilinear capsulorhexis (CCC), phacoemulsification, and irrigation and aspiration (I&A). EyeSi metrics that could be aligned with motion tracking parameters were identified. Motion tracking parameters (instrument path length, number of movements and total time) were measured. t-test used between the two cohorts for each component to check for any significance (p < 0.05).ResultsA total of 120 segments from videos of 20 junior and 20 senior surgeons were analysed. Significant differences between junior and senior surgeons were found during CCC (path length p = 0.0004; number of movements p < 0.0001; time taken p < 0.0001), phacoemulsification (path length p < 0.0001; number of movements p < 0.0001; time taken p < 0.0001), and irrigation and aspiration (path length p = 0.006; number of movements p = 0.013; time taken p = 0.036).ConclusionIndividual segments of cataract surgery analysed using motion tracking appear to discriminate between junior and senior surgeons. Alignment of motion tracking and EyeSi parameters could enable independent, task specific, objective and quantitative feedback for each segment of surgery thus mirroring the widely utilised modular training.

Surgical efficiency in femtosecond laser cataract surgery compared with phacoemulsification cataract surgery: a case–control study

Objectives To investigate differences in surgical time, the distance the surgical instrument travelled and number of movements required to complete manual phacoemulsification cataract surgery versus femtosecond laser cataract surgery. Design Non-randomised comparative case series. Setting Single surgery site, Moorfields Eye Hospital, UK. Participants 40 cataract surgeries of 40 patients. Interventions Laser-assisted and manual phacoemulsification cataract surgery. Laser-assisted surgery cases were performed using the AMO Catalys platform. Primary and secondary outcome measures Computer vision tracking software PhacoTracking were applied to the recordings to establish the distance the instrument travelled, total number of movements (the number of times an instrument stops and starts moving) and time taken for surgery steps including phacoemulsification, irrigation–aspiration (IA) and overall surgery time. The time taken for laser docking and delivery was not included in the analyses. Results Data on 19 laser-assisted and 19 manual phacoemulsification surgeries were analysed (two cases were excluded due to insufficient video-recording quality). There were no differences in the number of instrument moves, the distance the instrument travelled or time taken to complete the phacoemulsification stage. However for IA, the number of instrument moves (manual: mean 20 (SD 15) vs laser: mean 38 (SD 22), P=0.008) and time taken (manual: mean 75 s (SD 24) vs laser: mean 108 s (SD 36), P=0.003) were significantly greater for laser cases. For laser versus manual cases overall, there was no difference in number of moves or the distance the instrument travelled, but laser cases took longer (mean 88 s, P=0.049). Conclusions Laser cataract surgery cases took longer to complete without accounting for the time taken to complete the laser procedure itself. This appears to be in part due to IA requiring more instrument manoeuvres and taking longer to complete. Data from a large randomised series would better elucidate this relationship.

Very late onset orbital sarcoma and breast carcinoma following retinoblastoma treatment with radon seed brachytherapy

Moorfields Eye Hospital NHS Foundation Trust, London, United Kingdom; Retinoblastoma Unit, Royal London Hospital, London, United Kingdom; UCL Institute of Ophthalmology, London, United Kingdom; The National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and the UCL Institute of Ophthalmology, London, United Kingdom; Bedford Hospital NHS Foundation Trust, Bedford, United Kingdom; Great Ormond Street Hospital, NHS Trust, London, United Kingdom

Response to Swampillai et al

Sir, We thank Dr Swampillai et al for their correspondence1 regarding our article.2 In our study, the main inclusion criterion was ophthalmic trainees with minimal surgical experience2 (as defined in the paper). No other essential or desirable criteria from the ophthalmology training selection process were tested as trainees recruited had already passed through all this process. As Swampillai et al rightly pointed out, the importance of stereopsis in achieving satisfactory skill in ophthalmic surgery still remains debated.3 There are various gradations of stereopsis impairment, and until a clear relationship between these and surgical skills performance is defined their influence on data can only be speculated. There is also a range of other potential extraneous factors that could potentially influence surgical performance, some described, for example, sleep deprivation,4 and likely many more that have not been examined formally. It was for this combination of reasons that during the study, outset inclusion and exclusion criteria were defined as they were. Defining the surgical learning curves will become central as the use of simulators broadens. We thank Swampillai et al for highlighting their observation and pretraining description. Importantly, our study showed that there were statistically significant differences in the results between the different tasks, thus the learning curves are likely to vary significantly depending on the task selection. Without more detailed quantitative analysis of how the simulator scores vary during this pre-training process, along with its effects thereafter, we feel the validity of this methodology cannot be assumed and cannot be uniformly applied to all tasks. It is likely that as training systems progress that the definition of competency of performance for an individual will not just include being able to perform a task to a high level, but also demonstrate that this can be done consistently (with low variability). The authors feel that this is a very important question and significantly more work will be required in this field to best define methods for increasing consistency of performance.