Introduction Deep Learning (DL) and Artificial Intelligence (AI) have become widespread due to the advanced technologies and availability of digital data. Supervised learning algorithms have shown human-level performance or even better and are better feature extractor-quantifier than unsupervised learning algorithms. To get huge dataset with good quality control, there is a need of an annotation tool with a customizable feature set. This paper evaluates the viability of having an in house annotation tool which works on a smartphone and can be used in a healthcare setting. Methods We developed a smartphone-based grading system to help researchers in grading multiple retinal fundi. The process consisted of designing the flow of user interface (UI) keeping in view feedback from experts. Quantitative and qualitative analysis of change in speed of a grader over time and feature usage statistics was done. The dataset size was approximately 16,000 images with adjudicated labels by a minimum of 2 doctors. Results for an AI model trained on the images graded using this tool and its validation over some public datasets were prepared. Results We created a DL model and analysed its performance for a binary referrable DR Classification task, whether a retinal image has Referrable DR or not. A total of 32 doctors used the tool for minimum of 20 images each. Data analytics suggested significant portability and flexibility of the tool. Grader variability for images was in favour of agreement on images annotated. Number of images used to assess agreement is 550. Mean of 75.9% was seen in agreement. Conclusion Our aim was to make Annotation of Medical imaging easier and to minimize time taken for annotations without quality degradation. The user feedback and feature usage statistics confirm our hypotheses of incorporation of brightness and contrast variations, green channels and zooming add-ons in correlation to certain disease types. Simulation of multiple review cycles and establishing quality control can boost the accuracy of AI models even further. Although our study aims at developing an annotation tool for diagnosing and classifying diabetic retinopathy fundus images but same concept can be used for fundus images of other ocular diseases as well as other streams of medical science such as radiology where image-based diagnostic applications are utilised.

Background: The second wave of the COVID-19 pandemic in India was associated with an increased incidence of rhino-orbital-cerebral mucormycosis. The objective of this paper was to prospectively explore the epidemiology, management, and results of 18 months follow-up of patients presenting with COVID associated mucormycosis at a tertiary referral centre in India. Methods: Patients presenting with symptoms suggestive of COVID-associated mucormycosis over two months were included in the study. Patients were staged based on the extent of the disease. Surgery was the primary modality of treatment except in those with intracranial spread, altered sensorium, and poor prognosis. A combination of liposomal amphotericin B and posaconazole was used as adjunct medical treatment. Patients were followed up and outcomes at one year of treatment were recorded. Results: Out of a total of 26 patients who were diagnosed with COVID associated mucormycosis, 21 patients underwent bimodality treatment (medical and surgical). The extent of surgery was based on the stage of the disease. Six eyes received retrobulbar injections of Amphotericin B to salvage vision. The overall mortality was 38.46% and 23.8% in those where the intent of treatment was curative. At the end of one year, 16 of 21 operated patients survived with mild to severe sequelae. Conclusions: Mucormycosis is a deadly fungal infection with high mortality. Early diagnosis and prompt, aggressive treatment is paramount in preventing mortality. A multidisciplinary approach is useful for effective management. Continuous follow up is paramount to identifying and treating complications.

Intraocular cysticercosis can be associated with cysts in other areas. High number of patients with neurocysticercosis (80%) in those with intraocular cysticercosis in our study may indicate positive association between the two which needs further investigation.

<p class="abstract">Necrotising fasciitis of the periorbital region is a rare condition where there is destruction of the periorbital soft tissue with potential of rapid spread causing significant morbidity and mortality. It is generally seen in immuno suppressed individuals following trivial trauma. Here we present a case of periorbital necrotising fasciitis in a young immonocompetent lady with emphasis on early identification and aggressive treatment to prevent loss of vision and mortality.</p>

A young female a known case of systemic lupus erythematosus who underwent renal transplantation for end stage lupus nephritis was on long term immunosuppression for her systemic condition. She had an episode of varicella three months before she presented to us with ocular complaints in the right eye. She was diagnosed to have progressive outer retinal necrosis with a differential of cytomegaloviral retinitis in the right eye and treatment was initiated. She had begun to show improvement in visual acuity but within two weeks her systemic condition worsened rapidly and she succumbed to septic shock.The ocular infection in an immunocompromised SLE patient can be a precursor of mortality as seen in our patient.Due consideration is to be given for prophylactic treatment post varicella infection along with a multidisciplinary approach in managing the immunocompromised, to prevent devastating complications or mortality.