A novel hybrid approach for automated detection of retinal detachment using ultrasound images

Management, risk factors and treatment outcomes of rhegmatogenous retinal detachment associated with giant retinal tears: scoping review

BACKGROUND

Rhegmatogenous retinal detachment (RRD) is a serious condition that occurs when the retina detaches from its underlying retinal pigment epithelium. RRDs associated with giant retinal tears (GRTs) are caused by retinal tears at least 90° or one-quarter of the circumferential extent. This scoping review systematically identifies and summarizes clinical studies evaluating surgical techniques for the management of GRT-related RRDs, discusses functional and visual outcomes and the risk factors affecting treatment outcomes.

METHODS

This study was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. PubMed, Scopus, Google Scholar, and Springer Link databases were searched for relevant papers (from January 2001 to March 2023). Studies that were published in the English language and reported the risk factors, management, and treatment outcomes of GRT-related RRDs were included in the review. The outcome measures included anatomic success rates, changes in BCVA (logMAR) from baseline to the final follow-up, and adverse events.

RESULTS

A total of 11,982 articles were identified. After the title and abstract review, 71 studies were deemed eligible for full-text review. Thirty-six studies that met the eligibility criteria were included in the final review. Four surgical techniques were identified: pars plana vitrectomy (PPV), combined PPV and scleral buckling, scleral buckling alone, and pneumatic retinopexy. Various types of tamponades, including gas, silicone oil, and air, have been used. PPV was the most commonly used surgical technique in 33.1-100% of patients. Among the 20 studies that used PPV alone, 17 were associated with preoperative PVR. In addition, scleral buckling alone or in combination with PPV was reported as a treatment option in 10 studies, with 2-100% of patients experiencing scleral buckling alone and 13.6-100% experiencing combined PPV and complementary scleral buckling. Primary anatomic success (PAS) was achieved with retinal reattachment via a single operation with no residual tamponade, whereas final anatomic success (FAS) was achieved via more than one operation with no residual tamponade. Reported single surgery anatomic success (SSAS) rates range from 65.51 to 100%. The preoperative best-corrected visual acuity (BCVA) ranged from 0.067 to 2.47 logMAR, whereas the postoperative BCVA ranged from 0.08 to 2.3 logMAR. An improvement in visual acuity was observed in 29 studies. Cataracts (3.9-28.3%) were the most common postoperative complication, followed by high IOP (0.01-51.2%) and PVR (0.8-31.57%).

CONCLUSION

PPV is the most common surgical technique, and currently microincision vitrectomy surgery (MIVS) systems are commonly employed. Silicone oil is the most frequently used tamponade in RRD repair. Risk factors for GRT-related RRD include age, sex, lens status, high myopia status, proliferative vitreoretinopathy (PVR), presenting visual acuity, the extent of the GRT and retinal detachment, and macular involvement. Future research areas include guidelines to reduce variability in the reporting of surgical methodology, choice of tamponades, and reporting of functional and visual outcomes to inform the best therapeutic interventions in GRT-related RRD.

Automated Detection of Epiretinal Membranes in OCT Images Using Deep Learning

INTRODUCTION

Development and validation of a deep learning algorithm to automatically identify and locate epiretinal memberane (ERM) regions in OCT images.

METHODS

OCT images of 468 eyes were retrospectively collected from a total of 404 ERM patients. One expert manually annotated the ERM regions for all images. A total of 422 images (90%) and the remainig 46 images (10%) were used as the training dataset and validation dataset for deep learning algorithm training and validation, respectively. One senior and one junior clinician read the images. The diagnostic results were compared.

RESULTS

The algorithm accurately segmented and located the ERM regions in OCT images. The image-level accuracy was 95.65%, and the ERM region-level accuracy was 90.14%, respectively. In comparison experiments, the accuracies of the junior clinician improved from 85.00% to 61.29% without the assistance of the algorithm to 100.00% and 90.32% with the assistance of the algorithm. The corresponding results of the senior clinician were 96.15%, 95.00% without the assistance of the algorithm, and 96.15%, 97.50% with the assistance of the algorithm.

CONCLUSIONS

The developed deep learning algorithm can accurately segment ERM regions in OCT images. This deep learning approach may help clinicians in clinical diagnosis with better accuracy and efficiency.

Recent Trends in Artificial Intelligence-Assisted Coronary Atherosclerotic Plaque Characterization

Coronary artery disease is a major cause of morbidity and mortality worldwide. Its underlying histopathology is the atherosclerotic plaque, which comprises lipid, fibrous and—when chronic—calcium components. Intravascular ultrasound (IVUS) and intravascular optical coherence tomography (IVOCT) performed during invasive coronary angiography are reference standards for characterizing the atherosclerotic plaque. Fine image spatial resolution attainable with contemporary coronary computed tomographic angiography (CCTA) has enabled noninvasive plaque assessment, including identifying features associated with vulnerable plaques known to presage acute coronary events. Manual interpretation of IVUS, IVOCT and CCTA images demands scarce physician expertise and high time cost. This has motivated recent research into and development of artificial intelligence (AI)-assisted methods for image processing, feature extraction, plaque identification and characterization. We performed parallel searches of the medical and technical literature from 1995 to 2021 focusing respectively on human plaque characterization using various imaging modalities and the use of AI-assisted computer aided diagnosis (CAD) to detect and classify atherosclerotic plaques, including their composition and the presence of high-risk features denoting vulnerable plaques. A total of 122 publications were selected for evaluation and the analysis was summarized in terms of data sources, methods—machine versus deep learning—and performance metrics. Trends in AI-assisted plaque characterization are detailed and prospective research challenges discussed. Future directions for the development of accurate and efficient CAD systems to characterize plaque noninvasively using CCTA are proposed.