Comparing code-free deep learning models to expert-designed models for detecting retinal diseases from optical coherence tomography

BACKGROUND

Code-free deep learning (CFDL) is a novel tool in artificial intelligence (AI). This study directly compared the discriminative performance of CFDL models designed by ophthalmologists without coding experience against bespoke models designed by AI experts in detecting retinal pathologies from optical coherence tomography (OCT) videos and fovea-centered images.

METHODS

Using the same internal dataset of 1,173 OCT macular videos and fovea-centered images, model development was performed simultaneously but independently by an ophthalmology resident (CFDL models) and a postdoctoral researcher with expertise in AI (bespoke models). We designed a multi-class model to categorize video and fovea-centered images into five labels: normal retina, macular hole, epiretinal membrane, wet age-related macular degeneration and diabetic macular edema. We qualitatively compared point estimates of the performance metrics of the CFDL and bespoke models.

RESULTS

For videos, the CFDL model demonstrated excellent discriminative performance, even outperforming the bespoke models for some metrics: area under the precision-recall curve was 0.984 (vs. 0.901), precision and sensitivity were both 94.1% (vs. 94.2%) and accuracy was 94.1% (vs. 96.7%). The fovea-centered CFDL model overall performed better than video-based model and was as accurate as the best bespoke model.

CONCLUSION

This comparative study demonstrated that code-free models created by clinicians without coding expertise perform as accurately as expert-designed bespoke models at classifying various retinal pathologies from OCT videos and images. CFDL represents a step forward towards the democratization of AI in medicine, although its numerous limitations must be carefully addressed to ensure its effective application in healthcare.

Automated Machine Learning versus Expert-Designed Models in Ocular Toxoplasmosis: Detection and Lesion Localization Using Fundus Images

PURPOSE

Automated machine learning (AutoML) allows clinicians without coding experience to build their own deep learning (DL) models. This study assesses the performance of AutoML in detecting and localizing ocular toxoplasmosis (OT) lesions in fundus images and compares it to expert-designed models.

METHODS

Ophthalmology trainees without coding experience designed AutoML models using 304 labelled fundus images. We designed a binary model to differentiate OT from normal and an object detection model to visually identify OT lesions.

RESULTS

The AutoML model had an area under the precision-recall curve (AuPRC) of 0.945, sensitivity of 100%, specificity of 83% and accuracy of 93.5% (vs. 94%, 86% and 91% for the bespoke models). The AutoML object detection model had an AuPRC of 0.600 with a precision of 93.3% and recall of 56%. Using a diversified external validation dataset, our model correctly labeled 15 normal fundus images (100%) and 15 OT fundus images (100%), with a mean confidence score of 0.965 and 0.963, respectively.

CONCLUSION

AutoML models created by ophthalmologists without coding experience were comparable or better than expert-designed bespoke models trained on the same dataset. By creatively using AutoML to identify OT lesions on fundus images, our approach brings the whole spectrum of DL model design into the hands of clinicians.

Assessing the medical reasoning skills of GPT-4 in complex ophthalmology cases

BACKGROUND/AIMS

This study assesses the proficiency of Generative Pre-trained Transformer (GPT)-4 in answering questions about complex clinical ophthalmology cases.

METHODS

We tested GPT-4 on 422 Journal of the American Medical Association Ophthalmology Clinical Challenges, and prompted the model to determine the diagnosis (open-ended question) and identify the next-step (multiple-choice question). We generated responses using two zero-shot prompting strategies, including zero-shot plan-and-solve+ (PS+), to improve the reasoning of the model. We compared the best-performing model to human graders in a benchmarking effort.

RESULTS

Using PS+ prompting, GPT-4 achieved mean accuracies of 48.0% (95% CI (43.1% to 52.9%)) and 63.0% (95% CI (58.2% to 67.6%)) in diagnosis and next step, respectively. Next-step accuracy did not significantly differ by subspecialty (p=0.44). However, diagnostic accuracy in pathology and tumours was significantly higher than in uveitis (p=0.027). When the diagnosis was accurate, 75.2% (95% CI (68.6% to 80.9%)) of the next steps were correct. Conversely, when the diagnosis was incorrect, 50.2% (95% CI (43.8% to 56.6%)) of the next steps were accurate. The next step was three times more likely to be accurate when the initial diagnosis was correct (p<0.001). No significant differences were observed in diagnostic accuracy and decision-making between board-certified ophthalmologists and GPT-4. Among trainees, senior residents outperformed GPT-4 in diagnostic accuracy (p≤0.001 and 0.049) and in accuracy of next step (p=0.002 and 0.020).

CONCLUSION

Improved prompting enhances GPT-4's performance in complex clinical situations, although it does not surpass ophthalmology trainees in our context. Specialised large language models hold promise for future assistance in medical decision-making and diagnosis.

Evaluating the Performance of ChatGPT in Ophthalmology: An Analysis of Its Successes and Shortcomings

Purpose

Foundation models are a novel type of artificial intelligence algorithms, in which models are pretrained at scale on unannotated data and fine-tuned for a myriad of downstream tasks, such as generating text. This study assessed the accuracy of ChatGPT, a large language model (LLM), in the ophthalmology question-answering space.

Design

Evaluation of diagnostic test or technology.

Participants

ChatGPT is a publicly available LLM.

Methods

We tested 2 versions of ChatGPT (January 9 "legacy" and ChatGPT Plus) on 2 popular multiple choice question banks commonly used to prepare for the high-stakes Ophthalmic Knowledge Assessment Program (OKAP) examination. We generated two 260-question simulated exams from the Basic and Clinical Science Course (BCSC) Self-Assessment Program and the OphthoQuestions online question bank. We carried out logistic regression to determine the effect of the examination section, cognitive level, and difficulty index on answer accuracy. We also performed a post hoc analysis using Tukey's test to decide if there were meaningful differences between the tested subspecialties.

Main Outcome Measures

We reported the accuracy of ChatGPT for each examination section in percentage correct by comparing ChatGPT's outputs with the answer key provided by the question banks. We presented logistic regression results with a likelihood ratio (LR) chi-square. We considered differences between examination sections statistically significant at a P value of < 0.05.

Results

The legacy model achieved 55.8% accuracy on the BCSC set and 42.7% on the OphthoQuestions set. With ChatGPT Plus, accuracy increased to 59.4% ± 0.6% and 49.2% ± 1.0%, respectively. Accuracy improved with easier questions when controlling for the examination section and cognitive level. Logistic regression analysis of the legacy model showed that the examination section (LR, 27.57; P = 0.006) followed by question difficulty (LR, 24.05; P < 0.001) were most predictive of ChatGPT's answer accuracy. Although the legacy model performed best in general medicine and worst in neuro-ophthalmology (P < 0.001) and ocular pathology (P = 0.029), similar post hoc findings were not seen with ChatGPT Plus, suggesting more consistent results across examination sections.

Conclusion

ChatGPT has encouraging performance on a simulated OKAP examination. Specializing LLMs through domain-specific pretraining may be necessary to improve their performance in ophthalmic subspecialties.

Financial Disclosures

Proprietary or commercial disclosure may be found after the references.

Capabilities of GPT-4 in ophthalmology: an analysis of model entropy and progress towards human-level medical question answering

BACKGROUND

Evidence on the performance of Generative Pre-trained Transformer 4 (GPT-4), a large language model (LLM), in the ophthalmology question-answering domain is needed.

METHODS

We tested GPT-4 on two 260-question multiple choice question sets from the Basic and Clinical Science Course (BCSC) Self-Assessment Program and the OphthoQuestions question banks. We compared the accuracy of GPT-4 models with varying temperatures (creativity setting) and evaluated their responses in a subset of questions. We also compared the best-performing GPT-4 model to GPT-3.5 and to historical human performance.

RESULTS

GPT-4-0.3 (GPT-4 with a temperature of 0.3) achieved the highest accuracy among GPT-4 models, with 75.8% on the BCSC set and 70.0% on the OphthoQuestions set. The combined accuracy was 72.9%, which represents an 18.3% raw improvement in accuracy compared with GPT-3.5 (p<0.001). Human graders preferred responses from models with a temperature higher than 0 (more creative). Exam section, question difficulty and cognitive level were all predictive of GPT-4-0.3 answer accuracy. GPT-4-0.3's performance was numerically superior to human performance on the BCSC (75.8% vs 73.3%) and OphthoQuestions (70.0% vs 63.0%), but the difference was not statistically significant (p=0.55 and p=0.09).

CONCLUSION

GPT-4, an LLM trained on non-ophthalmology-specific data, performs significantly better than its predecessor on simulated ophthalmology board-style exams. Remarkably, its performance tended to be superior to historical human performance, but that difference was not statistically significant in our study.

MBT: Model-Based Transformer for retinal optical coherence tomography image and video multi-classification

BACKGROUND AND OBJECTIVE

The detection of retinal diseases using optical coherence tomography (OCT) images and videos is a concrete example of a data classification problem. In recent years, Transformer architectures have been successfully applied to solve a variety of real-world classification problems. Although they have shown impressive discriminative abilities compared to other state-of-the-art models, improving their performance is essential, especially in healthcare-related problems.

METHODS

This paper presents an effective technique named model-based transformer (MBT). It is based on popular pre-trained transformer models, particularly, vision transformer, swin transformer for OCT image classification, and multiscale vision transformer for OCT video classification. The proposed approach is designed to represent OCT data by taking advantage of an approximate sparse representation technique. Then, it estimates the optimal features, and performs data classification.

RESULTS

The experiments are carried out using three real-world retinal datasets. The experimental results on OCT image and OCT video datasets show that the proposed method outperforms existing state-of-the-art deep learning approaches in terms of classification accuracy, precision, recall, and f1-score, kappa, AUC-ROC, and AUC-PR. It can also boost the performance of existing transformer models, including Vision transformer and Swin transformer for OCT image classification, and Multiscale Vision Transformers for OCT video classification.

CONCLUSIONS

This work presents an approach for the automated detection of retinal diseases. Although deep neural networks have proven great potential in ophthalmology applications, our findings demonstrate for the first time a new way to identify retinal pathologies using OCT videos instead of images. Moreover, our proposal can help researchers enhance the discriminative capacity of a variety of powerful deep learning models presented in published papers. This can be valuable for future directions in medical research and clinical practice.

Does real-time artificial intelligence-based visual pathology enhancement of three-dimensional optical coherence tomography scans optimise treatment decision in patients with nAMD? Rationale and design of the RAZORBILL study

BACKGROUND/RATIONALE

Artificial intelligence (AI)-based clinical decision support tools, being developed across multiple fields in medicine, need to be evaluated for their impact on the treatment and outcomes of patients as well as optimisation of the clinical workflow. The RAZORBILL study will investigate the impact of advanced AI segmentation algorithms on the disease activity assessment in patients with neovascular age-related macular degeneration (nAMD) by enriching three-dimensional (3D) retinal optical coherence tomography (OCT) scans with automated fluid and layer quantification measurements.

METHODS

RAZORBILL is an observational, multicentre, multinational, open-label study, comprising two phases: (a) clinical data collection (phase I): an observational study design, which enforces neither strict visit schedule nor mandated treatment regimen was chosen as an appropriate design to collect data in a real-world clinical setting to enable evaluation in phase II and (b) OCT enrichment analysis (phase II): de-identified 3D OCT scans will be evaluated for disease activity. Within this evaluation, investigators will review the scans once enriched with segmentation results (i.e., highlighted and quantified pathological fluid volumes) and once in its original (i.e., non-enriched) state. This review will be performed using an integrated crossover design, where investigators are used as their own controls allowing the analysis to account for differences in expertise and individual disease activity definitions.

CONCLUSIONS

In order to apply novel AI tools to routine clinical care, their benefit as well as operational feasibility need to be carefully investigated. RAZORBILL will inform on the value of AI-based clinical decision support tools. It will clarify if these can be implemented in clinical treatment of patients with nAMD and whether it allows for optimisation of individualised treatment in routine clinical care.

Accuracy of automated machine learning in classifying retinal pathologies from ultra-widefield pseudocolour fundus images

AIMS

Automated machine learning (AutoML) is a novel tool in artificial intelligence (AI). This study assessed the discriminative performance of AutoML in differentiating retinal vein occlusion (RVO), retinitis pigmentosa (RP) and retinal detachment (RD) from normal fundi using ultra-widefield (UWF) pseudocolour fundus images.

METHODS

Two ophthalmologists without coding experience carried out AutoML model design using a publicly available image data set (2137 labelled images). The data set was reviewed for low-quality and mislabeled images and then uploaded to the Google Cloud AutoML Vision platform for training and testing. We designed multiple binary models to differentiate RVO, RP and RD from normal fundi and compared them to bespoke models obtained from the literature. We then devised a multiclass model to detect RVO, RP and RD. Saliency maps were generated to assess the interpretability of the model.

RESULTS

The AutoML models demonstrated high diagnostic properties in the binary classification tasks that were generally comparable to bespoke deep-learning models (area under the precision-recall curve (AUPRC) 0.921-1, sensitivity 84.91%-89.77%, specificity 78.72%-100%). The multiclass AutoML model had an AUPRC of 0.876, a sensitivity of 77.93% and a positive predictive value of 82.59%. The per-label sensitivity and specificity, respectively, were normal fundi (91.49%, 86.75%), RVO (83.02%, 92.50%), RP (72.00%, 100%) and RD (79.55%,96.80%).

CONCLUSION

AutoML models created by ophthalmologists without coding experience can detect RVO, RP and RD in UWF images with very good diagnostic accuracy. The performance was comparable to bespoke deep-learning models derived by AI experts for RVO and RP but not for RD.

Risk factors for epiretinal membrane formation and peeling following pars plana vitrectomy for primary rhegmatogenous retinal detachment, an OCT guided analysis

Background

To evaluate the rate and risk factors of epiretinal membrane (ERM) formation and need for ERM peeling after pars plana vitrectomy (PPV) for uncomplicated primary rhegmatogenous retinal detachment (RRD).

Methods

Retrospective, single-center, cohort study of 119 consecutive patients (119 eyes) that underwent RRD repair using PPV. The primary outcomes were ERM formation, classified using an optical coherence tomography grading system, and the rate of ERM peeling. Visual acuity, postoperative complications, and risk factors for ERM formation and peeling were also identified.

Results

Postoperative ERM formation occurred in 69 eyes (58.0%); 56 (47.1%) were stage 1, 9 (7.6%) stage 2, 3 (2.5%) stage 3, and 1 (0.8%) stage 4. Only 6 (5.0%) eyes required secondary PPV for a visually significant ERM, with a mean time to reoperation of 488 ± 351 days. Risk factors for ERM formation included intraoperative cryotherapy, more than 1000 laser shots, 360° laser photocoagulation, and choroidal detachment (p < 0.01). Eyes with more than 3 tears had a trend towards increased ERM surgery (p = 0.10).

Conclusions

Visually significant ERM formation following PPV for primary RRD was uncommon in this cohort (5%). Half of the ERMs were detected after the first post-operative year, indicating that this complication may be underreported in studies with only 1-year follow-up.

Deep learning for ultra-widefield imaging: a scoping review

PURPOSE

This article is a scoping review of published and peer-reviewed articles using deep-learning (DL) applied to ultra-widefield (UWF) imaging. This study provides an overview of the published uses of DL and UWF imaging for the detection of ophthalmic and systemic diseases, generative image synthesis, quality assessment of images, and segmentation and localization of ophthalmic image features.

METHODS

A literature search was performed up to August 31st, 2021 using PubMed, Embase, Cochrane Library, and Google Scholar. The inclusion criteria were as follows: (1) deep learning, (2) ultra-widefield imaging. The exclusion criteria were as follows: (1) articles published in any language other than English, (2) articles not peer-reviewed (usually preprints), (3) no full-text availability, (4) articles using machine learning algorithms other than deep learning. No study design was excluded from consideration.

RESULTS

A total of 36 studies were included. Twenty-three studies discussed ophthalmic disease detection and classification, 5 discussed segmentation and localization of ultra-widefield images (UWFIs), 3 discussed generative image synthesis, 3 discussed ophthalmic image quality assessment, and 2 discussed detecting systemic diseases via UWF imaging.

CONCLUSION

The application of DL to UWF imaging has demonstrated significant effectiveness in the diagnosis and detection of ophthalmic diseases including diabetic retinopathy, retinal detachment, and glaucoma. DL has also been applied in the generation of synthetic ophthalmic images. This scoping review highlights and discusses the current uses of DL with UWF imaging, and the future of DL applications in this field.

Development of a code-free machine learning model for the classification of cataract surgery phases

This study assessed the performance of automated machine learning (AutoML) in classifying cataract surgery phases from surgical videos. Two ophthalmology trainees without coding experience designed a deep learning model in Google Cloud AutoML Video Classification for the classification of 10 different cataract surgery phases. We used two open-access publicly available datasets (total of 122 surgeries) for model training, validation and testing. External validation was performed on 10 surgeries issued from another dataset. The AutoML model demonstrated excellent discriminating performance, even outperforming bespoke deep learning models handcrafter by experts. The area under the precision-recall curve was 0.855. At the 0.5 confidence threshold cut-off, the overall performance metrics were as follows: sensitivity (81.0%), recall (77.1%), accuracy (96.0%) and F1 score (0.79). The per-segment metrics varied across the surgical phases: precision 66.7–100%, recall 46.2–100% and specificity 94.1–100%. Hydrodissection and phacoemulsification were the most accurately predicted phases (100 and 92.31% correct predictions, respectively). During external validation, the average precision was 54.2% (0.00–90.0%), the recall was 61.1% (0.00–100%) and specificity was 96.2% (91.0–99.0%). In conclusion, a code-free AutoML model can accurately classify cataract surgery phases from videos with an accuracy comparable or better than models developed by experts.

Development and ex-vivo validation of 36G polyimide cannulas integrating a guiding miniaturized OCT probe for robotic assisted subretinal injections

We introduced and validated a method to encase guiding optical coherence tomography (OCT) probes into clinically relevant 36G polyimide subretinal injection (SI) cannulas. Modified SI cannulas presented consistent flow capacity and tolerated the typical mechanical stress encountered in clinical use without significant loss of sensitivity. We also developed an approach that uses a micromanipulator, modified SI cannulas, and an intuitive graphical user interface to enable precise SI. We tested the system using ex-vivo porcine eyes and we found a high SI success ratio 95.0% (95% CI: 83.1-99.4). We also found that 75% of the injected volume ends up at the subretinal space. Finally, we showed that this approach can be applied to transform commercial 40G SI cannulas to guided cannulas. The modified cannulas and guiding approach can enable precise and reproducible SI of novel gene and cell therapies targeting retinal diseases.

A Smart Vitrector Equipped by a Fiber-Based OCT Sensor Mitigates Intentional Attempts at Creating Iatrogenic Retinal Breaks During Vitrectomy in Pigs

Purpose

The occurrence of iatrogenic retinal breaks (RB) in pars plana vitrectomy (PPV) is a complication that compromises the overall efficacy of the surgery. A subset of iatrogenic RB occurs when the retina (rather than the vitreous gel) is cut accidentally by the vitrector. We developed a smart vitrector that can detect in real-time potential iatrogenic RB and activate promptly a PPV machine response to prevent them.

Methods

We fabricated the smart vitrectors by attaching a miniaturized fiber-based OCT sensor on commercial vitrectors (25G). The system's response time to an iatrogenic RB onset was measured and compared to the literature reported physiologically limited response time of the average surgeon. Two surgeons validated its ability to prevent simulated iatrogenic RB by performing PPV in pigs. Note that the system is meant to control the PPV machine and requires no visual or audio signal interpretation by the surgeons.

Results

We found that the response time of the system (28.9 ± 6.5 ms) is 11 times shorter compared to the literature reported physiologically limited reaction time of the average surgeon (P < 0.0001). Ex vivo validation (porcine eyes) showed that the system prevents 78.95% (15/19) (95% confidence interval [CI] 54.43–93.95) of intentional attempts at creating RB, whereas in vivo validation showed that the system, prevents 55.68% (30/54) (95% CI 41.40–69.08), and prevents or mitigates 70.37% (38/54) (95% CI 56.39–82.02) of such attempts. A subset of failures was classified as “early stop” (i.e., false positive), having a prevalence of 5.26% (1/19) in ex vivo tests and 24.07% (13/54) in in vivo tests.

Conclusions

Our results indicate the smart vitrector can prevent iatrogenic RB by providing seamless intraoperative feedback to the PPV machine. Importantly, the use of the smart vitrector requires no modifications of the established PPV procedure. It can mitigate a significant proportion of iatrogenic RB and thus improve the overall efficacy of the surgery.

Translational Relevance

Potential clinical adoption of the smart vitrector can reduce the incidence of iatrogenic RB in PPV and thus increase the therapeutic outcome of the surgery.

Evidence-based Canadian guidelines for tele-retina screening for diabetic retinopathy: recommendations from the Canadian Retina Research Network (CR2N) Tele-Retina Steering Committee

OBJECTIVE

The purpose of this report is to develop a consensus for Canadian national guidelines specific to a tele-medicine approach to screening for diabetic retinopathy (DR) using evidence-based and clinical data.

METHODS

Canadian Tele-Screening Grading Scales for DR and diabetic macular edema (DME) were created primarily based on severity grading scales outlined by the International Clinical Diabetic Retinopathy Disease Severity Scale (ICDR) and the Scottish DR Grading Scheme 2007. Other grading scales used in international screening programs and the clinical expertise of the Canadian Retina Research Network members and retina specialists nationwide were also used in the creation of the guidelines.

RESULTS

National Tele-Screening Guidelines for DR and DME with and without optical coherence tomography (OCT) images are proposed. These outline a diagnosis and management algorithm for patients presenting with different stages of DR and/or DME. General guidelines detailing the requirements for imaged retina fields, image quality, quality control, and follow-up care and the role of visual acuity, pupil dilation, OCT, ultra-wide-field imaging, and artificial intelligence are discussed.

CONCLUSIONS

Tele-retina screening can help to address the need for timely and effective screening for DR, whose prevalence continues to rise. A standardized and evidence-based national approach to DR tele-screening has been proposed, based on DR/DME grading using two 45° image fields or a single widefield or ultra-wide-field image, preferable use of OCT imaging, and a focus on local quality control measures.

Predictive modeling of proliferative vitreoretinopathy using automated machine learning by ophthalmologists without coding experience

We aimed to assess the feasibility of machine learning (ML) algorithm design to predict proliferative vitreoretinopathy (PVR) by ophthalmologists without coding experience using automated ML (AutoML). The study was a retrospective cohort study of 506 eyes who underwent pars plana vitrectomy for rhegmatogenous retinal detachment (RRD) by a single surgeon at a tertiary-care hospital between 2012 and 2019. Two ophthalmologists without coding experience used an interactive application in MATLAB to build and evaluate ML algorithms for the prediction of postoperative PVR using clinical data from the electronic health records. The clinical features associated with postoperative PVR were determined by univariate feature selection. The area under the curve (AUC) for predicting postoperative PVR was better for models that included pre-existing PVR as an input. The quadratic support vector machine (SVM) model built using all selected clinical features had an AUC of 0.90, a sensitivity of 63.0%, and a specificity of 97.8%. An optimized Naïve Bayes algorithm that did not include pre-existing PVR as an input feature had an AUC of 0.81, a sensitivity of 54.3%, and a specificity of 92.4%. In conclusion, the development of ML models for the prediction of PVR by ophthalmologists without coding experience is feasible. Input from a data scientist might still be needed to tackle class imbalance-a common challenge in ML classification using real-world clinical data.

Correlation of ocular rigidity with intraocular pressure spike after intravitreal injection of bevacizumab in exudative retinal disease

BACKGROUND/AIMS

To evaluate the non-invasive measurement of ocular rigidity (OR), an important biomechanical property of the eye, as a predictor of intraocular pressure (IOP) elevation after anti-vascular endothelial growth factor (anti-VEGF) intravitreal injection (IVI).

METHODS

Subjects requiring IVI of anti-VEGF for a pre-existing retinal condition were enrolled in this prospective cross-sectional study. OR was assessed in 18 eyes of 18 participants by measurement of pulsatile choroidal volume change using video-rate optical coherence tomography, and pulsatile IOP change using dynamic contour tonometry. IOP was measured using Tono-Pen XL before and immediately following the injection and was correlated with OR.

RESULTS

The average increase in IOP following IVI was 19±9 mm Hg, with a range of 7-33 mm Hg. The Spearman correlation coefficient between OR and IOP elevation following IVI was 0.796 (p<0.001), showing higher IOP elevation in more rigid eyes. A regression line was also calculated to predict the IOP spike based on the OR coefficient, such that IOP spike=664.17 mm Hg·µL×OR + 4.59 mm Hg.

CONCLUSION

This study shows a strong positive correlation between OR and acute IOP elevation following IVI. These findings indicate that the non-invasive measurement of OR could be an effective tool in identifying patients at risk of IOP spikes following IVI.

A Novel Weakly Supervised Multitask Architecture for Retinal Lesions Segmentation on Fundus Images

Obtaining the complete segmentation map of retinal lesions is the first step toward an automated diagnosis tool for retinopathy that is interpretable in its decision-making. However, the limited availability of ground truth lesion detection maps at a pixel level restricts the ability of deep segmentation neural networks to generalize over large databases. In this paper, we propose a novel approach for training a convolutional multi-task architecture with supervised learning and reinforcing it with weakly supervised learning. The architecture is simultaneously trained for three tasks: segmentation of red lesions and of bright lesions, those two tasks done concurrently with lesion detection. In addition, we propose and discuss the advantages of a new preprocessing method that guarantees the color consistency between the raw image and its enhanced version. Our complete system produces segmentations of both red and bright lesions. The method is validated at the pixel level and per-image using four databases and a cross-validation strategy. When evaluated on the task of screening for the presence or absence of lesions on the Messidor image set, the proposed method achieves an area under the ROC curve of 0.839, comparable with the state-of-the-art.

Primary rhegmatogenous retinal detachment with inferior retinal breaks postoperative prone positioning results: 1 day versus 7 days

Background

To compare the primary anatomical outcome of pars plana vitrectomy, 360° peripheral endolaser, and 15% octafluoropropane C₃F₈ gas tamponade in patients with uncomplicated rhegmatogenous detachment and inferior retinal breaks, after 24-h postoperative prone positioning to similar patients with 1 week postoperative prone positioning.

Methods

Records of 5500 patients who underwent pars plana vitrectomy between 2008 and 2015 were retrieved. Collected data included age, gender, number of retinal quadrants with retinal breaks, number of retinal breaks, macula status on presentation (attached or detached), phakic status (phakic, pseudophakic, or aphakic), and primary anatomical outcome (at 1 and 3 months post-operative).

Results

270 patients met the study inclusion criteria (78 females, and 192 males). In the 24-h positioning arm (183 patients), the overall anatomical success rate was 96.2% at 1 month and 83.6% at 3 months. In the 1-week positioning group (87 patients), the overall anatomical success rate was 93% at 1 month and 79% at 3 months. Both positioning groups did not show statistical difference in outcome at 1 month (p-value = 0.7) or at 3 months (p-value = 0.39). Logistic regression analysis found that the number of retinal breaks correlates with the postoperative anatomical success at 3 months (odd ratio 0.8, p-value = 0.016).

Conclusion

This short term retrospective study demonstrated that patients with uncomplicated rhegmatogenous retinal detachment due to inferior retinal breaks, who underwent pars plana vitrectomy, 360° endolaser, 15% C₃F₈ gas, and limited (24-h) prone positioning did not show statistical difference in the anatomical outcome (at 1, and 3 months) when compared with 1 week postoperative positioning. Larger prospective studies are warranted to further elucidate positioning role.

Vitrectomy surgery for primary retinal detachment

Small-gauge pars plana vitrectomy has emerged as one of the leading approaches to the management of primary retinal detachment in recent years. Developments in technology and instrumentation have improved this procedure and given surgeons a wide variety of tools to tackle this pathology. In this chapter, the techniques utilized in the management of primary retinal detachments are discussed.

Maternal Stress during Pregnancy, ADHD Symptomatology in Children and Genotype: Gene-Environment Interaction

OBJECTIVE

Case control studies suggest a relationship between maternal stress during pregnancy and childhood ADHD. However, maternal smoking, parenting style and parental psychiatric disorder are possible confounding factors. Our objective was to control for these factors by using an intra-familial design, and investigate gene-environment interactions.

METHODS

One hundred forty two children, ages 6 to 12, (71 with ADHD, and their 71 non-ADHD siblings) participated in the intra-familial study design. A larger sample of ADHD children (N=305) was genotyped for DAT1 and DRD4 to examine gene-environment interactions. Symptom severity was evaluated using the Child Behavior Checklist (CBCL) and the Conners' Global Index for Parents (CGI-P). The Kinney Medical and Gynecological Questionnaire was used to report stressful events during pregnancies.

RESULTS

LOGISTIC REGRESSION INDICATED THAT MOTHERS WERE MORE LIKELY TO HAVE EXPERIENCED HIGH STRESS DURING PREGNANCY OF THEIR ADHD CHILD COMPARED TO THAT OF THE UNAFFECTED SIBLING (OR: 6.3, p=.01). In the larger sample, DRD4 7/7 genotype was associated with increased symptom severity in the high stress pregnancy (p=.01).

CONCLUSIONS

Maternal stress during pregnancy was associated with the development of ADHD symptomatology after controlling for family history of ADHD and other environmental factors. This association could partly be mediated through the DRD4 genotype.

Acquired myelinated nerve fibers in association with optic disk drusen

Myelinated retinal nerve fibers are a well-recognized anomaly of the ocular fundus associated with many ocular and systemic conditions. Myelination is almost always congenital and stable, but progression has been documented in rare cases. Optic disk drusen are the result of a degenerative process at the optic nerve head and are often found incidentally on ophthalmologic examination. To our knowledge, optic disk drusen have only been reported once in association with acquired and progressive myelinated retinal nerve fibers. We present 2 such cases and consider the implications for the pathogenesis of myelinated nerve fibers.

Recurrent anterior uveitis after trabeculectomy with mitomycin C

OBJECTIVE

To report 4 cases of recurrent anterior uveitis occurring 1-11 months after trabeculectomy with mitomycin C.

DESIGN

Observational case series.

PARTICIPANTS

Four patients in whom recurrent uveitis developed after trabeculectomy with mitomycin C, followed at Maisonneuve-Rosemont Hospital in Montreal, Quebec.

METHODS

Retrospective review of the medical records.

RESULTS

One to 11 months after trabeculectomy with mitomycin C, noninfectious, recurrent anterior uveitis developed in 4 patients with no prior history of uveitis. Topical and intravitreal corticosteroids were effective in reducing acute inflammation, yet 2 patients went on to have chronic anterior uveitis.

CONCLUSIONS

Recurrent anterior uveitis presenting later than 3 weeks postoperatively may be associated with trabeculectomy with mitomycin C. It should be included in the differential diagnosis of a nonresolving blebitis.

Interrelationships of quality of life, compliance, clinical outcomes and life satisfaction: a cross-sectional study on hypertensive geriatrics

OBJECTIVE

(i) To assess quality of life (QoL) profiles in hypertensive geriatrics with SF-36; (ii) to assess the compliance of geriatrics to medications; (iii) to estimate clinical outcomes (reduction in systolic and diastolic blood pressure); (iv) to assess life satisfaction and (v) to explore the interrelationships of QoL, compliance, clinical outcomes and life satisfaction in hypertensive geriatrics.

METHOD

Fifty-nine hypertensive geriatric patients in cardiology and 65 Plus clinics in West Virginia Hospitals were studied.

RESULTS

Age showed a significant negative correlation with physical functioning (r = 0.339, P< or =0.0127) and physical role (r=0.335, P< or =0.0148). The physical role facet of SF-36 is correlated with life satisfaction in geriatrics (r = 0.316, P < or =0.0219). A regression analysis (backward stepwise) not including bodily pain (BP) and general health (GH) resulted in a model explaining 22.3% of variance (n = 54, F = 2.252, P < or = 0.0543). Physical role (P < or = 0.0084) and mental health facets (P< or = 0.0184) of SF-36 emerged as the predictors of life satisfaction in elderly hypertensive patients. Emotional role functioning (P < or = 0.0257) and social functioning (P < or = 0.0033) scores predicted levels of diastolic blood pressure in elderly hypertensive patients. However, all eight concepts of SF-36 failed to predict compliance behaviour in geriatrics (n = 53, P < or = 0.6913, R2= 0.110).

AZT inhibits Visna/maedi virus -induced apoptosis

Visna/maedi virus (VMV) causes severe encephalitis and a progressive demyelinating disease in sheep. Previous in vitro studies have demonstrated that VMV-infection leads to apoptosis in sheep choroid plexus cells (SCPC) via induction of both intrinsic and extrinsic pathways with subsequent activation of caspases. 3' azido-2',3'-deoxythymidine (AZT) is a potent and selective Human immunodeficiency virus 1 (HIV-1) reverse transcriptase inhibitor, widely used in antiretroviral therapy; however its effects on retrovirus-induced apoptosis are unknown. Using diverse strategies to detect apoptosis, we analysed the broad range effect of AZT treatment on inhibition of VMV-induced apoptosis. First, we found that AZT treatment inhibited the appearance of characteristic apoptotic morphologic changes documented by DAPI staining and oligonucleosomal DNA laddering. Secondly, AZT treatment inhibited caspase cascade and resulted in (i) diminished caspase-3, -8 and -9 activities and (ii) no fluorescein isothiocynate-[VAD]-fluoromethylketone (FITC-VAD-FMK) in situ labelling in VMV-infected cells treated with AZT. Finally, immunocytochemistry indicated that VMV-infection of SCPC induced the subsequent release of apoptosis inducing factor (AIF), whereas AZT treatment inhibited AIF leakage. Consequently, the anti-apoptotic effects of AZT are not restricted, since AZT treatment blocks all the apoptotic pathways induced during VMV-infection.

Semisynthesis of heterocyclic analogues of squamocin, a cytotoxic annonaceous acetogenin, by an unusual oxidative decarboxylation reaction

In addition to two expected pyrazin derivatives, two imidazole analogues of squamocin 1 have been semisynthetised from squamocin derived alpha-ketoesters/alpha-ketoacid, via an unusual condensation-oxidative decarboxylation reaction with 1,2 diamines in presence of acetic acid and oxygen as the key step. Some of these analogues exhibited potent, although significantly reduced cytotoxicities relatively to squamocin 1. In addition, benzimidazole 8 possessed in comparison with the natural acetogenin some interesting cell cycle effects.

Implication of caspases during maedi-visna virus-induced apoptosis

Maedi-visna virus (MVV) causes encephalitis, pneumonia and arthritis in sheep. In vitro, MVV infection and replication lead to strong cytopathic effects characterized by syncytia formation and subsequent cellular lysis. It was demonstrated previously that MVV infection in vitro induces cell death of sheep choroid plexus cells (SCPC) by a mechanism that can be associated with apoptotic cell death. Here, the relative implication of several caspases during acute infection with MVV is investigated by employing diverse in vitro and in situ strategies. It was demonstrated using specific pairs of caspase substrates and inhibitors that, during in vitro infection of SCPC by MVV, the two major pathways of caspase activation (i.e. intrinsic and extrinsic pathways) were stimulated: significant caspase-9 and -8 activities, as well as caspase-3 activity, were detected. To study the role of caspases during MVV infection in vitro, specific, cell-permeable, caspase inhibitors were used. First, these results showed that both z-DEVD-FMK (a potent inhibitor of caspase-3-like activities) and z-VAD-FMK (a broad spectrum caspase inhibitor) inhibit caspase-9, -8 and -3 activities. Second, both irreversible caspase inhibitors, z-DEVD-FMK and z-VAD-FMK, delayed MVV-induced cellular lysis as well as virus growth. Third, during SCPC in vitro infection by MVV, cells were positively stained with FITC-VAD-FMK, a probe that specifically stains cells containing active caspases. In conclusion, these data suggest that MVV infection in vitro induces SCPC cell death by a mechanism that is strongly dependent on active caspases.

Visna virus-induced cytopathic effect in vitro is caused by apoptosis

Visna-Maedi virus (VMV), an ungulate lentivirus, causes a natural infection in sheep. In vitro, VMV infection and replication lead to strong cytopathic effects with subsequent death of host cells. We investigated, in vitro, the relative contribution of apoptosis or programmed cell death (PCD) to cell killing during acute infection with VMV, by employing diverse strategies to detect its common end-stage alterations. We demonstrated that VMV-infection in sheep choroid plexus cells (SCPC), is associated with apoptosis, characterized by morphological changes such as condensation of chromatin and the appearence of apoptotic bodies. DNA fragmentation was documented by TUNEL assay. Although the mechanism by which VMV activates this cell suicide program is not known, we examined the activation of caspases, the family of death-inducing proteases that resulted in cleavage of several cellular substrates. To study the role of caspases in VMV-induced apoptosis, we focused on several protease targets: procaspase-3 and procaspase-1. During VMV-infection, SCPC display active caspase-3 and no caspase-1 activity. In conclusion, our results suggest that VMV infection, in vitro, induces cell death of SCPC by a mechanism that can be characterized by many of the properties most closely associated with apoptotic cell death.

Enantioseparation of aminoglutethimide and thalidomide by high performance liquid chromatography or supercritical fluid chromatography on mono-2 and mono-6-O-pentenyl-beta-cyclodextrin-based chiral stationary phases

Mono-2 and mono-6-O-pentenyl-beta-cyclodextrin (mono-2-pent-beta-CD and mono-6-pent-beta-CD), covalently linked to mercaptopropylsilica gel (thiol-Si) through thioether or sulfone linkage, reveal differentiated enantioselectivities in the separation of piperidine-2,6-dione-related drugs, namely aminoglutethimide and thalidomide, in supercritical fluid conditions. Supercritical fluid chromatographic resolution on completely defined mono-cyclodextrin derivative-based chiral stationary phases (CSP) is a method of choice for the separation of aminoglutethimide but not effective for thalidomide. For both high performance liquid chromatography (HPLC) and supercritical fluid chromatography (SFC) conditions, the impact of the position, imposed to be 2 or 6 in our synthetic pathway, of the pentenyl moiety on one of the glucopyranosidics of the CD cage is of crucial importance in the chiral discrimination phenomenon. Additionally, the nature of the heteroatom present in the spacer arm between the CD and the silica gel, in this case thioether or sulfone functionality, is also essential for the chiral recognition mechanism(s) for the solute enantiomer.

Synthesis of two optically active calcium channel antagonists labelled with carbon-11 for in vivo cardiac PET imaging

(+/-)-S11568 (1, 3-ethyl-5-methyl-(+/-)-2-[(2-(2-aminoethoxy)ethoxy) methyl]-4-(2,3-dichlorophenyl)-6-methyl-1,4-dihydropyridine-3, 5-dicarboxylate), has an in vitro profile of high potency and of high selectivity for the low-voltage dependent. L-type calcium channel. In in vitro binding studies, it displaced specifically bound (-)-[3H]PN 200-110 (isradipine (2), the reference molecule for in vitro studies) from cardiac and vascular smooth muscle preparations with potencies of 5.6 and 51 nM, respectively. It also appears as a pure pharmacological antagonist acting at a single channel L-type and free of any interaction at the benzothiazepine binding site such as amlodipine (3). Both enantiomers of S11568 have in vitro activities, the dextro isomer S12967 ((+)-1) being 6 to 18-fold less potent than the levo one S12968 ((-)-1). Two couples of optically active labelling precursors of S11568, ((-)-10/(+)-10 and (-)-14/(+)-14) have been synthesized using a modified Hantzsch's dihydropyridine synthesis. In both cases, the enantiomers were separated by preparative chiral HPLC. They both have been independently labelled with carbon-11, using [11C]diazomethane or [11C]iodomethane to give multimilliCurie quantities of (-)-1 (S12968) and (+)-1 (S12967) with high specific activities (500-1000 mCi/mumol, 18.5-37.0 GBq/mumol). Both enantiomers appear suitable for PET experiments: their myocardial concentration increases after a bolus injection to reach a maximum in 2 min and then remains on a plateau with a slight downslope while the blood concentration falls rapidly. Myocardial uptake was threefold higher than lung uptake, leading to a good contrast on PET images. The present preliminary biological results obtained in Beagle dogs showed that both enantiomers have similar myocardial kinetics and in vivo affinity for the left ventricular myocardium.