Tiffany So obtained her medical degree from the University of Melbourne, Australia and completed internship and basic training at the Royal Melbourne Hospital. She completed Radiology training at Alfred Health in Melbourne, training in diagnostic radiology with subspecialty training rotations in trauma imaging, neuroradiology, thoracic and lung transplant imaging and body imaging. Dr So is a Fellow of the Royal Australian and New Zealand College of Radiologists and a registered specialist in Diagnostic Radiology in Australia, New Zealand, and Hong Kong. She has a particular interest in neuroimaging, encompassing quantitative and advanced MRI brain imaging, evaluation of structural and functional abnormalities in multiple sclerosis, stroke and cerebrovascular disease diagnosis and assessment, imaging of traumatic head injury, and head and neck imaging. Her research interests also include artificial intelligence (AI) and medical image analysis for image-based detection and diagnosis of disease, development of medical healthcare technologies, and AI in education. She has completed a Master of Medicine in Radiology, with her work centred on traumatic injuries to the dural venous sinuses.

Dr So is currently a Clinical Assistant Professor at The Chinese University of Hong Kong. She is actively involved in undergraduate teaching and postgraduate radiology resident training. She serves as a diagnostic radiologist at the Department of Imaging and Interventional Radiology at the Prince of Wales Hospital, New Territories East Cluster, contributing to clinical services provided by the Hospital Authority. Additionally, she is a part of the neuroradiology team delivering diagnostic neuroimaging services to patients within the New Territories East Cluster.

Dr So is a member of the European Society of Radiology, Radiological Society of North America, The Australian and New Zealand Society of Neuroradiology, American Roentgen Ray Society, and The Medical Image Computing and Computer Assisted Intervention Society.

Current teaching profile includes undergraduate teaching (CUHK 4th and final year medical students), postgraduate radiology resident training (FRCR trainees), and visiting students from international institutions, in the form of lectures, small group and clinical tutorials, flipped classroom teaching, on the job teaching as well as informal tutorials. Dr So is a major contributor in curriculum design in the undergraduate radiology teaching program at CUHK, which incorporates both conventional deliveries and eLearning. Her recent teaching projects are focused on the incorporation of technology, artificial intelligence and game-based learning in education. These projects aim to develop innovative and readily accessible teaching materials to enhance teaching curriculums across several disciplines.

Dr So is actively involved in curriculum planning and the development of courseware material and assessments. She takes an interest in quality improvement in medical education and the techniques and approaches to maintain a quality teaching and student learning experience; in the past year attending several relevant workshops and seminars related to these areas. She also supports collaborative work through actively engaging Students as Partners (SaP) in curriculum and educational material development, working together with other students and staff toward shared educational goals.

Dr So is actively involved in curriculum planning and the development of courseware material and assessments. She takes an interest in quality improvement in medical education and the techniques and approaches to maintain a quality teaching and student learning experience; in the past year attending several relevant workshops and seminars related to these areas.  She also supports collaborative work through actively engaging Students as Partners (SaP) in curriculum and educational material development, working together with other students and staff toward shared educational goals.

Recent Teaching Projects:

Recent major teaching projects include the following:

• eLearning Modules for radiographic assessment of linesand tubes and their potential complications – Implementing artificial intelligence (AI) and game-based learning (Project Lead)

• Interactive interdisciplinary learning of Nasogastric tube assessment (Project Lead) – project encompassing technology in education with implementation of AI deep learning models and game-based learning within an integrated mobile application (app) platform

  • Recipient of Educational Technology Innovation Gold award, Teaching and Learning Innovation Expo, CUHK 2022

  • Awarded best presentation at Tripartite Medical Education Conference – Actualising the Curriculum Continuum 2023

• Curriculum development in Abdominal Ultrasound (Project Lead)

• eLearning in Thoracic Imaging (2019)

Dr So provides clinical radiology service in all areas of diagnostic radiology at the Prince of Wales Hospital. She specializes in neuroimaging and has specialty interest in advanced MRI brain imaging, multiple sclerosis, stroke and cerebrovascular imaging, head and neck imaging and artificial intelligence.

Dr So is actively engaged in interdisciplinary research encompassing neuroimaging, medical artificial intelligence and computer-aided diagnosis. She is particularly interested in the application of advanced imaging techniques to investigate into structural and functional changes in the brain. Harnessing the capabilities of computational approaches, Dr So and her team focus on methods to integrate imaging, clinical and/or molecular data, and artificial intelligence and machine learning into research.

Current Research:

Dr So has recently led and/or contributed to research projects in the following areas:

• Applications of spin-lock imaging, including quantitative T1rho assessment of normal brain and demyelination in multiple sclerosis

• MPF mapping in multiple sclerosis

• Brain intravoxel incoherent motion (IVIM) MRI

• Evaluation of gadolinium- based contrast agent (Gd-CA) effects in brain imaging
• Machine learning and radiomics for brain tumour (glioma and mengingioma) grading, classification and predictive modelling
• Large-scale federated learning (FL) in glioma
• Imaging of nasopharyngeal carcinoma including NPC nodal disease

Recent Service:

• Junior Deputy Editor – European Radiology
• Editorial board member – European Radiology (Neuro Section)
• Program Chair, CLINICCAI, MICCAI 2022 – 25th International Conference on Medical Image Computing and Computer Assisted Intervention
• Program Committee, CLINICCAI, MICCAI 2023 – 26th International Conference on Medical Image Computing and Computer Assisted Intervention
• Editorial board member – BMC Medical Imaging
• Supervisor – MPhil/PhD students supervisor, Examiner – MPhil/PhD students
• Guest Associate Editor- Frontiers in Radiology
• Conference reviewer (e.g RSNA)

Recent publications:

1. Repeatability of quantitative T1rho magnetic resonance imaging in normal brain tissues at 3.0 T.
Wang L, Chen W, Qian Y, So TY*.
Physica Medica. 2023;112:102641.

2. Federated learning enables big data for rare cancer boundary detection.
Pati S, Baid U, Edwards B, Sheller M, Wang SH, Reina GA, Foley P, Gruzdev A, Karkada D, Davatzikos C, Sako C,… So TY,… Bakas S. Nature communications. 2022;13(1):1-7.

3. Radiomics for Discriminating Benign and Malignant Salivary Gland Tumors; Which Radiomic Feature Categories and MRI Sequences Should Be Used?
Zhang R, Ai QY, Wong LM, Green C, Qamar S, So TY, Vlantis AC, King AD. Cancers. 2022;14(23):5804.

4. Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study.
Dou Q, So TY, Jiang M, Liu Q, Vardhanabhuti V, Kaissis G, Li Z, Si W, Lee HH, Yu K, Feng Z, Dong L, Burian E, Jungmann F, Braren R, Makowski M, Kainz B, Rueckert D, Glocker B, Yu SCH, Heng PA. NPJ digital medicine, 2021;4(1):1-1

5. Machine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph.
Du R, Tsougenis ED, Ho JW, Chan JK, Chiu KW, Fang BX, Ng MY, Leung ST, Lo CS, Wong HF, Lam HY, Chiu LF, So TY, Wong KT, Wong YC, YU K, Yeung YC, Chik T, Pang J, Wai AK, Kuo MD, Lam TP, Khong PL, Cheung NT, Vardhanabhuti V. Scientific reports. 2021;11(1):1-3.

6. Test-retest repeatability of T1rho (T1ρ) MR imaging in the head and neck.
Ai QY, Zhang H, Jiang B, So TY, Mo FK, Qamar S, Chen W, King AD.
European Journal of Radiology. 2021;135:109489.

7. Quantitative T1ρ MRI of the head and neck discriminates carcinoma and benign hyperplasia in the nasopharynx. Ai QY, Chen W, So TY, Lam WK, Jiang B, Poon DM, Qamar S, Mo FK, Blu T, Chan Q, Ma BB. American Journal of Neuroradiology. 2020 Dec 1;41(12):2339-44.

8. Intravoxel incoherent motion diffusion-weighted imaging for discrimination of benign and malignant retropharyngeal nodes.
So TY, Ai QY, Lam WJ, Qamar S, Poon DM, Hui EP, Mo FK, Chan KA, King AD.
2020;16:1-0.

9. Early Detection of Cancer: Evaluation of MR Imaging Grading Systems in Patients with Suspected Nasopharyngeal Carcinoma.
King AD, Woo JK, Ai QY, Mo FK, So TY, Lam WK, Tse IO, Vlantis AC, Yip KW, Hui EP, Ma BB.
American Journal of Neuroradiology. 2020;41(3):515-21.

10. Early intra-treatment diffusion weighted magnetic resonance imaging in patients with recurrent nasopharyngeal carcinoma treated with nivolumab.
So TY, Ai QY, Ma BYB, King AD. International Journal of Otorhinolaryngology and Head and Neck Surgery. 2020; 6(3):568-573.

Recent conference presentations:

1. Macromolecular Proton Fraction Mapping Based on Spin-Lock (MPF-SL) Imaging of the Normal Appearing White Matter (NAWM) and Normal Appearing Grey Matter (NAGM) in Relapsing- Remitting Multiple Sclerosis. Cai Z, Hou J, Wang L, Wong Y, Abrigo J, Lau AY, Choi C, Chen W, So TY*. European Congress of Radiology, 2023.

2. Principles and clinical applications of macromolecular proton fraction (MPF) magnetic resonance imaging (MRI) in clinical brain imaging. Wang L, Hou J, Wong Y, Cai Z, Chen W, So TY*. European Congress of Radiology, 2023.

3. Predictive performance of linear and nonlinear models for meningioma tumor grade prediction based on multiparametric MRI. Cai Z, Wong Y, Wang L, Wong L, So TY*
American Society of Neuroradiology Annual Meeting 2023.

4. Explainable AI for automatic detection of early nasopharyngeal carcinoma on MRI. Wong LM, Ai QH, So TY, Lam JWK, King AD. ISMRM & ISMRT Annual Meeting & Exhibition 2023.

5. Fast Macromolecular Proton Fraction Imaging Based On Spin-Lock
Hou J, Qian Y, Jiang B, Fan X, Chu WCW, So TY, Chen W. ISMRM & ISMRT Annual Meeting & Exhibition 2023.

6. Quantitative T1rho Magnetic Resonance Imaging (MRI): Applications and considerations in neuroradiology. Wang L, Qian Y, Wong Y, Chen W, So TY*. European Congress of Radiology, 2023.

7. High test-retest reliability of T1rho in the brain across serial imaging sessions in healthy subjects. So TY*, Wang L, Qian Y, Chen W. European Congress of Radiology, 2022.

8. Quantitative T1rho MR imaging detects early changes in advanced stage nasopharyngeal carcinoma treated with chemotherapy. Ai, QY, Tsang Y, Yu Z, Wong LM, So TY, Chen W, King AD. European Congress of Radiology, 2022.