Dr Neda Azarmehr

• Qualifications

  • PhD, Computer Science, University of Lincoln, UK 
  • Fellow of FHEA, Fellow of Higher Education of Academy  
  • MSc, Big Data Analytics, Sheffield Hallam University
  • BSc, Health Information Technology, Medical University of Kerman

• Awards

  School of Computing and Engineering, Lecturer of the Year (2024) - Star Awards

  £11,712 2022 - Fellowship exchange program, The University of Sheffield, Yale University - RadioPathomic Integrated Artificial Intelligence System to Predict Salivary Gland Cancers project.

  £1500 2022 - Insigneo Summer Research Programme, Deep learning-based methods for automated radiological detection of jaw lesions project.

• Memberships

  Fellow of Higher Education Academy (FHEA)

  Member of IEEE

  Member of ESDIP (European Society of Digital and Integrative Pathology)

Neda has been lecturing at the undergraduate and postgraduate levels, covering a wide range of courses in Computer Science. Neda is also actively contributing to the Intelligent Sensing and Vision research Lab which has fostered interdisciplinary research by providing a framework for cross-faculty collaborative working.

• Research and publications

  Publications

  • Alajrami, E., Ng, T., Jevsikov, J., Naidoo, P., Fernandes, P., Azarmehr, N., Dinmohammadi, F., Shun-Shin, M.J., Serej, N.D., Francis, D.P. and Zolgharni, M., 2024. Active Learning for Left Ventricle Segmentation in Echocardiography. Computer Methods and Programs in Biomedicine, p.108111. 
  • Jevsikov, J., Ng, T., Lane, E.S., Alajrami, E., Naidoo, P., Fernandes, P., Sehmi, J.S., Alzetani, M., Demetrescu, C.D., Azarmehr, N. and Serej, N.D., Francis, D.P. and Zolgharni, M., 2024. Automated mitral inflow Doppler peak velocity measurement using deep learning. Computers in Biology and Medicine, p.108192.
  • Bashir, R.M.S., Shephard, A.J., Mahmood, H., Azarmehr, N., Raza, S.E.A., Khurram, S.A. and Rajpoot, N.M., 2023. A digital score of peri‐epithelial lymphocytic activity predicts malignant transformation in oral epithelial dysplasia. The Journal of Pathology.
  • Alsanie I, Azarmehr, N., Shephard, A., Rajpoot, N. and Khurram, S.A., 2022.Using Artificial Intelligence for Analysis of Histological and Morphological Diversity in Salivary Gland Tumors, DOI: https://doi.org/10.21203/rs.3.rs-1966782/v1 
  • Azarmehr, N., Ye, X., Howard, J.P., Lane, E.S., Shun-Shin, M.J., Cole, G.D., Bidaut, L., Francis, D.P. and Zolgharni, M., 2021. Neural architecture search of echocardiography view classifiers. Journal of Medical Imaging, 8(3), p.034002. 
  • Lane, E.S., Azarmehr, N., Jevsikov, J., Howard, J.P., Shun-Shin, M.J., Cole, G.D., Francis, D.P. and Zolgharni, M., 2021. Multibeat echocardiographic phase detection using deep neural networks. Computers in Biology and Medicine, 133, p.104373.
  • Azarmehr N, Ye X, Howes J, Docking B, Howard J, Francis D, Zolgharni M 2020- An Optimisation-Based Iterative Approach for Speckle Tracking Echocardiography, Medical & Biological Engineering & Computing, 58, pp.1309-1323. 

• Conferences

  • Neda Azarmehr, (April 2023) Automated Echocardiographic Image Interpretation Using Artificial Intelligence, delivered a talk to IEEE Early Career Talks, organised by the IEEE WIE UK 
  • Jevsikov, J., Lane, E.S., Alajrami, E., Naidoo, P., Serej, N.D., Azarmehr, N., Aleshaiker, S., Stowell, C.C., Shun-shin, M.J., Francis, D.P. and Zolgharni, M., 2023, June. Automated Analysis of Mitral Inflow Doppler Using Deep Neural Networks. In International Conference on Functional Imaging and Modeling of the Heart (pp. 394-402). Cham: Springer Nature Switzerland. 
  • Alajrami, E., Naidoo, P., Jevsikov, J., Lane, E., Pordoy, J., Serej, N.D., Azarmehr, N., Dinmohammadi, F., Shun-shin, M.J., Francis, D.P. and Zolgharni, M., 2023, June. Deep Active Learning for Left Ventricle Segmentation in Echocardiography. In International Conference on Functional Imaging and Modeling of the Heart (pp. 283-291). Cham: Springer Nature Switzerland. 
  • Azarmehr, N., Shephard, A., Mahmood, H., Rajpoot, N. and Khurram, S.A., 2022. A Neural Architecture Search Based Framework for Segmentation of Epithelium, Nuclei and Oral Epithelial Dysplasia Grading. In Annual Conference on Medical Image Understanding and Analysis (pp. 357-370). Springer, Cham. 
  • Azarmehr, N., Shephard, A., Mahmood, H., Rajpoot, N. and Khurram, S.A., 2022. Automated Oral Epithelial Dysplasia Grading Using Neural Networks and Feature Analysis. International Conference on Medical Imaging with Deep Learning (MIDL) 
  • Shephard, A., Azarmehr, N., Bashir, R.M.S., Raza, S.E.A., Mahmood, H., Khurram, S.A. and Rajpoot, N., 2022. A Fully Automated Multi-Scale Pipeline for Oral Epithelial Dysplasia Grading and Outcome Prediction. International Conference on Medical Imaging with Deep Learning (MIDL)
  • Azarmehr, N., Shephard, A., Mahmood, H., Rajpoot, N. and Khurram, S.A., 2022, Application of neural architecture search technique in nuclear and epithelium segmentation in digital pathology images of oral dysplasia, the 18th European Congress on Digital Pathology (ECDP) 
  • Adam J Shephard, R M Saad Bashir, Neda Azarmehr, Hanya Mahmood, Shan Raza, Syed Ali Khurram, Nasir M Rajpoot, 2022, Fully Automated Attention based Multiple Instance Learning Predicts the Presence of Oral Epithelial Dysplasia in Whole Slide Images, the 18th European Congress on Digital Pathology (ECDP) 
  • Azarmehr N, Shephard A, Rajpoot N, Khurram S A (2021) An Optimal Architecture for Semantic Segmentation in Multi-Gigapixel Images of Oral Dysplasia, 35th Conference on Neural Information Processing Systems (NeurIPS 2021) 
  • Lane, E.S., Azarmehr, N., Jevsikov, J., Howard, J.P., Shun-shin, M., Francis, D.P. and Zolgharni, M., (2021). Echocardiographic Phase Detection Using Neural Networks, International Conference on Medical Imaging with Deep Learning (MIDL) 
  • Lab R, Vrettos, A., Azarmehr, N., Howard, J.P., Shun-shin, M.J., Cole, G.D., Francis, D.P. and Zolgharni, M., (2020). Automated Assessment of Image Quality in 2D Echocardiography Using Deep Learning, International Conference on Radiology, Medical Imaging and Radiation Oncology ICRMIRO 
  • Azarmehr N, Ye X, Janan F, Howard P, Francis D, Zolgharni M, (2019) Automated Segmentation of Left Ventricle in 2D echocardiography using deep learning, International Conference on Medical Imaging with Deep Learning (MIDL) 
  • Azarmehr N, Ye X, Sacchi S, Howard J, Francis D, Zolgharni M, (2019) Segmentation of Left Ventricle in 2D echocardiography using deep learning, Medical Image Understanding and Analysis (MIUA) 

• Research degree supervision

  PI supervision:

  • May Hlaing Kyi- May Deep Learning for Precision Detection of Mitosis and Perineural Invasion in Digital Pathology images 

  Co-supervised:

  • Patricia Fernandes- Real-time echocardiographic image quality analysis using deep learning
  • Preshen Naidoo- Self-supervised learning in Echocardiography

  Available PhD projects:

  Title: Application of Deep Learning in Perineural Invasion Detection

  This project aims to develop an AI-based tool for automatically identifying cancerous cells that have spread around nerves in head and neck cancers. Head and neck cancer ranks among the top ten most common cancers globally, with approximately 12,400 new cases reported annually in the UK alone, equating to 34 cases per day (2016-2018). The high frequency of occurrence and poor survival rates in head and neck cancer patients are often linked to perineural invasion (PNI), a process in which cancer cells spread within, around, and through nerves. Detecting PNI is crucial, as patients with PNI may require more aggressive treatment. Traditionally, PNI assessment relies on histological examination of tissues, which is labour-intensive and time-consuming, leading to inconsistent diagnoses among clinicians. This underscores the necessity for more accurate and efficient diagnostic tools. AI-based approaches offer promise in addressing these challenges. However, research on PNI is limited and there is room for improvement. This project aims to use a novel AI, deep-learning tool to detect and predict the presence of PNI.

  Impact of project: The proposed project has the potential to enhance the early and accurate detection of PNI, thereby facilitating precise prognostic assessments and personalised treatment plans for patients. 

  • Expected start date: January, May and September of each academic year.
  • Duration: This is a three-year position. 
  • PhD applicants for this project must have previous experience in AI projects, proficiency in Python programming, as well as hands-on experience with TensorFlow or PyTorch.