Ambaji S. Jadhav, Pushpa B. Patil and Sunil Biradar
Diabetic retinopathy (DR) is a central root of blindness all over the world. Though DR is tough to diagnose in starting stages, and the detection procedure might be time-consuming…
Abstract
Purpose
Diabetic retinopathy (DR) is a central root of blindness all over the world. Though DR is tough to diagnose in starting stages, and the detection procedure might be time-consuming even for qualified experts. Nowadays, intelligent disease detection techniques are extremely acceptable for progress analysis and recognition of various diseases. Therefore, a computer-aided diagnosis scheme based on intelligent learning approaches is intended to propose for diagnosing DR effectively using a benchmark dataset.
Design/methodology/approach
The proposed DR diagnostic procedure involves four main steps: (1) image pre-processing, (2) blood vessel segmentation, (3) feature extraction, and (4) classification. Initially, the retinal fundus image is taken for pre-processing with the help of Contrast Limited Adaptive Histogram Equalization (CLAHE) and average filter. In the next step, the blood vessel segmentation is carried out using a segmentation process with optimized gray-level thresholding. Once the blood vessels are extracted, feature extraction is done, using Local Binary Pattern (LBP), Texture Energy Measurement (TEM based on Laws of Texture Energy), and two entropy computations – Shanon's entropy, and Kapur's entropy. These collected features are subjected to a classifier called Neural Network (NN) with an optimized training algorithm. Both the gray-level thresholding and NN is enhanced by the Modified Levy Updated-Dragonfly Algorithm (MLU-DA), which operates to maximize the segmentation accuracy and to reduce the error difference between the predicted and actual outcomes of the NN. Finally, this classification error can correctly prove the efficiency of the proposed DR detection model.
Findings
The overall accuracy of the proposed MLU-DA was 16.6% superior to conventional classifiers, and the precision of the developed MLU-DA was 22% better than LM-NN, 16.6% better than PSO-NN, GWO-NN, and DA-NN. Finally, it is concluded that the implemented MLU-DA outperformed state-of-the-art algorithms in detecting DR.
Originality/value
This paper adopts the latest optimization algorithm called MLU-DA-Neural Network with optimal gray-level thresholding for detecting diabetic retinopathy disease. This is the first work utilizes MLU-DA-based Neural Network for computer-aided Diabetic Retinopathy diagnosis.
Details
Keywords
The learning objectives of this case study are based on Bloom’s taxonomy. Upon completion of the case study discussion and exercises, successful students will be able to design a…
Abstract
Learning outcomes
The learning objectives of this case study are based on Bloom’s taxonomy. Upon completion of the case study discussion and exercises, successful students will be able to design a leadership transition and succession plan for non-profit organisations; identify and evaluate critical skills and competencies required in leadership positions; and frame expectations and responsibilities for new and departing executives.
Case overview/synopsis
Apar Gupta co-founded Internet Freedom Foundation (IFF), a digital rights organisation born out of SaveTheInternet – Net Neutrality movement of 2015, credited for urging the Telecom Regulatory Authority of India to uphold net neutrality in India. And ban zero-cost internet services that promoted data discrimination in the country. After working on and winning the net neutrality movement, Gupta identified many areas in technology where democratic rights had not been identified or were yet to be clearly defined (like in the case of net neutrality). There was also a service gap between the existing internet volunteer groups and digital rights organisations, which could IFF fill. This was to provide objective clarity, stakeholder identification, handle policy discussions and, most importantly, arrange resources to support movements over the long term. This prompted him to co-found IFF in 2017, which he later joined as a full-time executive director in 2018. IFF worked at the intersection of technology, democratic rights and government policies and was comparable to some global organisations, such as the Electronic Frontier Foundation in the USA and the Open Rights Group in the UK. Still, none existed in India at the time. After four years as a full-time executive director in 2022, he was convinced that it was finally time for him to act on the pre-defined strategic departure plan and work towards succession for the executive director position. While there were visible gaps in the system, Gupta’s leadership design and plans had helped IFF overcome existential challenges in the past. Also, while digital rights were still at a nascent stage in emerging economies, under Gupta’s leadership, IFF had delivered unmatched value to its beneficiaries in the world’s biggest digital consumer market. However, constant changes in regulations and continuing financial constraints made him nervous about the outcomes of the succession and the overall sustainability of IFF. Gupta wanted to ensure that this phased transition from executive director after two years and then trustee manager after the next four years are carefully communicated to reduce the likelihood of attrition and loss of trust.
Being the co-founder and the first and only executive director IFF had seen, the organisation would also require significant skill and competency mapping to identify the new executive leadership. But with no clear internal successor in sight, the non-profit trust would also need a successor who not only was competent but also would share a passion for the type of work done by IFF, its unique delivery mode, and also would openly inherit its position in society. The other alternative strategic routes present were to look for dual leadership or interim leadership, but then there could be concerns about Gupta’s influence overshadowing any such alternative.
In the case scenario, IFF is planning for succession while navigating the organisation through financial constraints and constant regulatory changes to ensure long- and short-term sustainability.
Complexity academic level
The case study has been written to gain insights into departure-defined successive planning in non-profit organisations. The case study can also be used to gain insights into innovative start-ups and innovative non-profit start-ups, as digital rights are still at nascent stages in emerging markets. The case study will be valuable for courses such as human resource management, strategic human resource management, social entrepreneurial leadership, leadership development, start-up environment, innovation and entrepreneurship, public policy, development studies, cyber security and information technology. The case study also allows students and young professionals to take the perspective of an innovative start-up founder and design a departure-defined succession plan. The case study can also be useful for senior students wanting to undertake an entrepreneurial career by starting or joining a non-profit organisation. While the case study is suitable for postgraduate- and executive-level courses, it can also be used for conducting entrepreneurial workshops and skill training.
Supplementary materials
Teaching notes are available for educators only.
Subject code
CSS 3: Entrepreneurship.