Nahida Akter

Research Title: Automated Detection of Ocular Disease with Artificial Intelligence

Email Address: nahida.akter@student.unsw.edu.au

Linked in: https://www.linkedin.com/in/nahida-akter-6b326b62/?originalSubdomain=au

RESEARCH

Abstract

Currently artificial intelligence (AI), especially deep learning (DL), techniques are revolutionising healthcare for its potential in image-based diagnosis, disease-prognostication, and risk-assessment. In ophthalmology, AI is also becoming common for screening, image-interpretation, early diagnosis and guiding treatment of eye conditions. This project will highlight new research directions and examine the main challenges of machine learning in ophthalmology, such as the “black box” problem which decreases clinical reliability and algorithm transparency of AI in healthcare. This research will devise and evaluate new clinically meaningful metrics for analysing ocular images, implement novel DL algorithms for automatic segmentation, disease detection and progression-classification of eye diseases using both fundus photographs and optical coherence tomography (OCT) images from both healthy subjects and patients undergoing treatment for eye disease.

The project currently focuses on glaucoma as diseases like age-related macular degeneration, retinopathy of prematurity and diabetic retinopathy have well-defined lesions visible on fundus photography and other en face techniques e.g., image analysis and AI spaces. AI has shown great promise in classifying 2D images by distinguishing noticeable features occurring in glaucoma such as enlarged cup-disc-ratio. However, a challenge remains regarding reaching the performance of expert clinicians in a real-world clinical pathway with three-dimensional diagnostic scans and accumulation of patient’s clinical history manifests the AI system more reliable and trustworthy.

We initially aimed to improve our understanding, screening and detection of glaucoma progression using both 2D and 3D fundus, OCT retinal images. Multiple feature extraction techniques, classification methods and DL techniques will then be designed, implemented and tested for the purpose of diagnosis of glaucoma. Finally, the same model will be applied in diagnosing other diseases as well.

BIOGRAPHY

I have 7+ years of experience in the Computer Science Engineering field with a demonstrated history of working in the multinational company and university. I am highly skilled in different data science programming platform of machine learnings, 2D and 3D image processing, statistical software, web design and computer networking. Currently working with Artificial Intelligence as a PhD research student of Optical Imaging and Visualization (OIV) Lab, SOVS, UNSW Sydney, Australia. My professional aim is to develop a career in the academic and research field, where my knowledge, skills and abilities will get the opportunity to flourish.

RECENT PUBLICATIONS

Journal Articles

1. Matsuda K, Yasumoto M, Akter N, Misawa M, López J, Suzuki Y, Takeuchi, Hibino A, Rehman S, Roy M, “A hard x-ray phase contrast microscopy using Gabor hologram without zero-order term”, Applied Optics. https://www.osapublishing.org/ao/abstract.cfm?doi=10.1364/AO.393008
2. Akter N, Nobi A, “Investigation of Financial Stability of S&P500 Using Realized Volatility and Stock Returns Distribution”, Journal of Risk and Financial Management, 2018; 11(2):22. (http://mdpi.com/1911-8074/11/2/22
3. Yeasmin M, Akter N, Kabir MH, Hossain MJ, “Performance evaluation of multi cloud compared to the single cloud under varying Firewall conditions”, Cogent Engineering, 2018; 5: 1471974. (https://tandfonline.com/doi/abs/10.1080/23311916.2018.1471974)
4. Billah MM, Rana SMM, Akter N, Hossain MS, “Analysis of serum electrolyte and lipid profile in young Bangladeshi female with Type II Diabetes” Cogent Biology,2018;4:1431474. https://www.tandfonline.com/doi/full/10.1080/23312025.2018.1431474
5. Shahabuddin AA, Shalu PD, Akter N, “Optimized Process Design of RF Energy Harvesting Circuit for Low Power Devices”, International Journal of Applied Engineering Research, 2018; 13(2): 849-854. https://ripublication.com/ijaer18/ijaerv13n2_05.pdf
6. Akter N, Hossain MB, Kabir MH, Hossain A, Yeasmin M, Sultana S, “Design & Performance Analysis of 10 stage Voltage Doublers RF Energy Harvesting Circuit for Wireless Sensor Network”, Journal of Communications Engineering and Networks, 2014; 2(2): 8491. https://www.semanticscholar.org/paper/Design-and-Performance-Analysis-of-10-Stage-Voltage-Akter-Hossain/c6a05c2247f787083e78dc806967b82886063a42#citing-papers

Education

CONFERENCE ATTENDANCE

1. Akter N, Young J, Lee N, and Roy M, “3D Reconstruction of Retinal Vascular Structure from 2D OCT-A Images for Glaucoma Diagnosis, OSA Optics and Applied Imaging Congress 2020, 22-26 June 2020, Vancouver, British Columbia Canada
2. Akter N, Kayhan D and Roy M, “Evaluation of the Optic Nerve Head with Structural and Functional Features of Glaucoma”, SEMO Meeting 2020, 16-18 April 2020, New Zealand
3. Akter N, Phu J, Perry S, Fletcher J, Kalloniatis M, and Roy M, “Analysis of OCT Images to Optimize Glaucoma Diagnosis”, Imaging and Applied Optics Congress, 24-27 June 2019, Munich, Germany. https://www.osapublishing.org/abstract.cfm?uri=ISA-2019-ITh2B.2
4. Akter N, Li A, Shi R, Phu J, Perry S, Fletcher J, and Roy M, “A feature agnostic based glaucoma diagnosis from OCT images with deep learning technique”, American Academy of Optometry, 23-27 October 2019, Orlando, USA.

https://www.aaopt.org/detail/knowledge-base-article/a-feature-agnostic-based-glaucoma-diagnosis-from-oct-images-with-deep-learning-technique-339277-3238241

AWARDS

AFFILIATIONS AND MEMBERSHIPS

• Assistant Professor, Dept. of Computer Science and Telecommunication Engineering, NSTU, Bangladesh (Study leave)
• IEEE, membership number- 94391677
• American Academy of Optometry, Academy member # 90569