No abstract

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.

Introduction: Involvement of teachers is the first and most crucial step in developing health care strategy for the adolescents, however there is paucity of literature in India.Objective: To assess the effect of training on perception and knowledge of the school teachers towards the common health problems among adolescents.Material & methods: An intervention study was conducted in a private school of rural Bangalore in November 2015. A pre-tested open-ended questionnaire containing questions regarding the socio-demographic profile of the teachers and common adolescent health problems was administered to the study subjects before and after one-day workshop for the teachers. Training workshop included sessions on adolescent health issues particularly mental health and life skills. Data was entered in MS-Excel and analyzed with the help of SPSS version 21.Results: A total of 75 teachers participated and their age was 31.07 years. 25 (33%) of them had obtained education till B.Ed. Majority (60; 80%) of teachers were Hindu by religion. After the training perception of the teachers about adolescent health problems improved significantly. 99% of teachers were able to recall common adolescent mental issues particularly depression, anxiety and body image perception disorders after the training. Knowledge scores of the teachers regarding the common adolescent problems for both the genders increased significantly (p <0.05). Conclusion:Training about life skills and on identifying the symptoms related to the common mental disorders should be provided to the teachers on a regular basis.

No abstract