Sneha Narayan Naik

Computed Tomography Imaging (CT); Cardiac CT Imaging; Lung and Airway disease; Chronic Obstructive Pulmonary Disease (COPD); Computer Vision; Deep Learning; Data Science; Probabilistic Machine Learning

Sneha Naik is a doctoral student with a background in Artificial Intelligence and Medical Physics. She develops deep learning models for studying Long COVID and COPD using CT and MRI; with particular focus on the contributions of airway tree structure to disease risk. Sneha did her Master’s in Artificial Intelligence at Imperial College London as a Google DeepMind scholar, graduating top of her cohort with awards for her thesis, supervised by Dr Elsa Angelini, on AI-based liver disease staging on whole-slide histopathological images. Sneha has an interdisciplinary background, with a first class undergraduate degree in Physics from Cambridge, and two years of investment banking experience where she developed resilience and strong interpersonal skills. She is passionate about empowering women in STEM and has volunteered for the past three years for charity MAGIC (More Active Girls In Computing).

PhD      in Biomedical Engineering, Columbia University,
             Fu Foundation School of Engineering (2022-present)
MSc      in Artificial Intelligence, Imperial College London,
             Department of Computer Science (2020-2021)
BA        in Natural Sciences (Physics),
             Cambridge University, UK St Johns College (2014-2017)

- Abstract scholarship award at American Thoracic Society International Conference 2025, San Francisco, CA (May 2025)
- “Lung Labyrinth Laureate” Poster award granted to a project that embraces collaboration across diverse fields - such as imaging, data science, and clinical practice - demonstrating a multidisciplinary approach to advancing pulmonary research, at the 2025 International Workshop on Pulmonary Imaging, Perelman School of Medicine, University of Pennsylvania, February 2025 (https://www.med.upenn.edu/fmig-workshop-lung/presenters-and-awards )
- Presented at NSF Bio-X summer leadership academy (5% acceptance rate), Crete, Greece, 2024.
- Presented at International Symposium on Biomedical Imaging (ISBI), Athens, Greece, 2024.
- Google DeepMind Scholar at Imperial College London (2020-2021)
- Winton Capital Prize for an outstanding project in applied computing, Imperial College London (https://www.imperial.ac.uk/computing/prospective-students/prizes/postgraduate-accordions/postgraduate-archive/)
- The Corporate Partnership Programme Award for Academic Excellence for top-in cohort exam results, Imperial College London, 2021 (https://www.imperial.ac.uk/computing/prospective-students/prizes/postgraduate-accordions/postgraduate-archive/)
- St John’s College Scholar, 2015 and 2017, United Steels Scholarship 2015, Cambridge University.
- Varsity coxswain (2016 Boat Race), Cambridge University Lightweight Rowing Club (https://en.wikipedia.org/wiki/Cambridge_University_Lightweight_Rowing_Club)

1. Naik SN, Walley SM. The Hall–Petch and inverse Hall–Petch relations and the hardness of nanocrystalline metals. Journal of Materials Science. 2020;55(7):2661-81.
2. Naik SN, Forlano R, Manousou P, Goldin R, Angelini ED. Fibrosis severity scoring on Sirius red histology with multiple-instance deep learning. Biological Imaging. 2023;3:e17.
3. Naik SN, Angelini ED, Barr RG, Allen N, Bertoni A, Hoffman EA, et al. Unsupervised Airway Tree Clustering with Deep Learning: The Multi-Ethnic Study of Atherosclerosis (MESA) Lung Study. arXiv preprint arXiv:240218615. 2024.
4. Smith B, Naik S, Venkatesh B, Zhang X, Shen W, Lovinsky-Desir S, et al. Paired Magnetic Resonance and Computed Tomography Assessment of Dysanapsis. The Subpopulations and Intermediate Outcome Measures in COPD and Heart Failure Study (SPIROMICS HF). A29 WHAT IS YOUR DAMAGE? IMAGING-BASED PHENOTYPES OF COPD: American Thoracic Society; 2024. p. A1255-A.
5. Naik SN, Smith BM, Allen NB, Balte P, Blaha MJ, Budoff MJ, et al. Harmonized Assessment and Quality Control of Quantitative Measures of Lung Structure on Pre-pandemic Cardiac and Lung Computed Tomography (CT) Scans for Large-scale Investigation of Risk of Long COVID-19: The Collaborative Cohort of Cohorts for COVID-19 Research (C4R). Accepted to appear in D30 - GOING WITH THE FLOW: ABNORMALITIES IN RESPIRATORY MECHANICS: American Thoracic Society; 2025.
6. Naik SN, Angelini ED, Hoffman EA, Oelsner EC, Barr RG, Smith BM, et al., editors. Multi-View Transformers for Airway-To-Lung Ratio Inference on Cardiac CT Scans: The C4R Study. International Symposium on Biomedical Imaging (ISBI) 2025; 2025.
7. Naik SN, Angelini ED, Hoffman EA, Sun Y, Allen NB, Bertoni A, et al. Unsupervised Machine-learned Discovery of Quantitative Airway Tree Subtypes and Their Association With Chronic Obstructive Pulmonary Disease Endpoints: The Multi-Ethnic Study of Atherosclerosis Lung Study. Accepted to appear in B99 - IDENTIFYING SIGNATURES OF DYSFUNCTION IN COPD: American Thoracic Society; 2025.
8. Naik SN, Angelini ED, Sun Y, Hoffman EA, Allen NB, Bertoni A, et al. Assessment of Airway-To-Lung Ratio on Cardiac CT: Agreement With Full-lung CT and Validation With Dysanapsis Endpoints: The Collaborative Cohort of Cohorts for COVID-19 Research (C4R) CT Harmonization Study. Accepted to appear in B30 - ADVANCED MODALITIES TO UNCOVER PATHOPHYSIOLOGIC FEATURES IN COPD. American Thoracic Society2025.