Syed Rakin Ahmed, PhD

Headshot

Rakin is an M.D.-Ph.D. candidate in a unique, multi-institutional program between Harvard, MIT and Dartmouth, having been born and raised in Dhaka, Bangladesh. Rakin graduated with a Ph.D. in Biophysics at Harvard Medical School in May 2024 (in 3.5 years), having been inducted into Sigma Xi, where he was co-advised by Bruce Rosen [1] and Jayashree Kalpathy-Cramer [2] in the QTIM lab at MIT and the MGH/HST Martinos Center for Biomedical Imaging. His dissertation was titled 'Generating Clinically Translatable AI Models for Cancer Diagnostics' at the intersection of computer science, biophysics, engineering, and medicine; his work resulted in multiple publications, presentations at national and international conferences, as well as several honors and awards [3], including the Mind, Brain. Behavior (MBB) Award.

Before moving to Cambridge, Rakin studied Biomedical Engineering, Applied Math and Economics during his undergrad as a member of the Class of 2018 at Dartmouth on a full-ride scholarship, graduating with High Honors, Phi Beta Kappa, Tau Beta Pi and Magna Cum Laude, and took part in an exchange at the University of Oxford in the UK. His unique MD-PhD program was created via collaboration across all three institutions, and he was accepted via the highly competitive Biomedical Engineering (BME) Early Assurance Program (EAP) as a college sophomore, which waived the MCAT and featured a single streamlined application.

Rakin's clinical and research interests lie at the intersection of AI/deep learning and oncology (radiation-, GU-, neuro- and immuno-oncology), biomedical imaging, cancer genomics and genome editing. Rakin is broadly interested in addressing issues pertaining to AI deployment and model robustness (e.g., repeatability, generalizability), with a long-term goal of integrating deep learning (DL) into oncology workflows to augment the clinician, thereby potentially replacing costly, risky, and invasive tests. Rakin has explored these interests extensively via work and publications generated at the Broad Institute of MIT and Harvard (where he worked with David Liu [4]), Massachusetts General Hospital, HST Martinos Center and Memorial Sloan Kettering Cancer Center, among other institutions.

Alongside his research, clinical and MD-PhD commitments, Rakin also holds a deep passion for residential advising, teaching and student engagement, which is reflected in the multiple residential and teaching roles that he has held throughout his undergraduate and MD-PhD years, including Resident Tutor, Fellow in Values Engagement (Intellectual Vitality Fellow), Proctor, Teaching Fellow, Resident Fellow, Residential Undergraduate Advisor, Live-In Advisor and Program Coordinator, as well as Pre-med, STEM, Senior Common Room (SCR), First-Gen/Low-Income (FGLI) and International Student Advisor.

Recent News (See all posts)

10/2024
My work on assessing generalizability of deep learning models for cancer detection was published in PLOS Digital Health and subsequently featured on an NCI article, while additional work on AI for cervical cancer screening was presented at IPVC 2024. Additionally, four manuscripts from our work on uncertainty and generalizability of AI models were presented in MICCAI 2024, and published in the corresponding journals: MedAGI 2024, UNSURE 2024, PILM-AIPAD 2024, FAIMI-EPIMI 2024.
06/2024
I started clinical rotations as part of the 3rd year of my medical school curriculum and was selected as a Resident Fellow, a residential advising position for undergraduates at Dartmouth College.
05/2024
I graduated Sigma Xi with my PhD in Biophsyics from Harvard, as part of the University Wide Commencement, Harvard Medical School Commencement, and Harvard Graduate School of Arts and Sciences Commencement 2024
03/2024
I successfully defended my doctoral dissertation titled 'Generating Clinically Translatable AI Models for Cancer Diagnostics', after 3.5 years of PhD thesis work at Harvard-MIT as part of my multi-institutional MD-PhD program.
02/2024
I was awarded the Mind Brain Behavior (MBB) Graduate Student Award for 2023-2024, sponsored by the MBB Interfaculty Initiative at Harvard University, as well as the Fellowship in Values Engagement (Intellectual Vitality Fellow) for 2023-2024, sponsored by the Edmond & Lily Safra Center for Ethics at Harvard University, following extremely competitive selection processes.
01/2024
My work on clinically translatable deep learning for cancer diagnosis was published in Nature Scientific Reports, on generalizable deep neural networks for image quality classification was posted to Research Square, on deep learning for immune phenotype prediction from breast cancer histopathology was presented at the 38th Annual AAAI Conference on Artificial Intelligence 2024 and posted to arXiv, and on deep-learning based automated volumetric measurement of meningioma burden was presented at the SNO 28th Annual Meeting and AI Cures Conference 2024.
10/2023
Four manuscripts from my work on AI for cervical cancer screening were published in medRxiv, Cancer Epidemiology, JNCI, and in eLife respectively.
09/2023
I was invited as a featured speaker at the Harvard Biophysics Annual Retreat 2023, and the 3rd Annual Dartmouth Radiation Oncology Research Retreat 2023, presenting a talk titled "Generating clinically translatable models for cancer diagnostics".
08/2023
Five manuscripts and abstracts from my work on AI and computational methods for brain tumor diagnostics were published in Neuro-Oncology, in Volume 26 of the Annual Reviews of Biomedical Engineering, in the Machine Learning for Healthcare Conference (MLHC) 2023, in the Radiological Society of North America (RSNA) Annual Meeting 2023, and in the Society for NeuroOncology 28th Annual Meeting, respectively.
04/2023
My work on algorithmic language lateralization from resting-state functional MRI was published in the Journal of Neuroimaging.

Selected Publications (See all publications)

Papers

Generating Clinically Translatable AI Models for Cancer Diagnostics
Ahmed SR*
PhD Dissertation (2024)
Generalizable deep neural networks for image quality classification of cervical images.
Ahmed SR, Befano B, Egemen D, et al.
Nature Sci Rep. 2025 Feb 21;15(1):6312.
Assessing generalizability of an AI-based visual test for cervical cancer screening.
Ahmed SR, Egemen D, Befano B, et al.
PLOS Digital Health. 2024 Oct 2;3(10):e0000364
Reproducible and clinically translatable deep neural networks for cervical screening.
Ahmed SR*, Befano B*, Lemay A et al.
Nature Sci Rep. 2023 Dec 8;13(1):21772
Power spectral analysis can determine language laterality from resting-state functional MRI data in healthy controls.
Ahmed SR, Jenabi M, Gene M, Moreno R, Peck K, Holodny A.
J Neuroimaging. 2023 Jul-Aug;33(4):661-670.
Radiotherapy-induced Cherenkov luminescence imaging in a human body phantom.
Ahmed SR, Jia JM, Bruza P, et al.
J Biomed Opt. 2018; 23(3):1-4.
Estimating test performance for AI medical devices under distribution shift with conformal prediction.
Ahmed SR*, Lu C*, Singh P et al
arXiv preprint arXiv:2207.05796. submitted, in-review (2023)
Frequency-Domain Resting State fMRI Analysis Demonstrates Language Lateralization in Healthy Controls.
Ahmed SR, Jenabi M, Gene M, Moreno R, Peck K, Holodny A.
American Society of Neuroradiology (ASNR) 58th Annual Meeting. 2020.
Patient-specific, mechanistic models of tumor growth incorporating artificial intelligence and big data.
Lorenzo G, Ahmed SR, Hormuth D, et al.
Annu Rev Biomed Eng. 2024 Apr 9.
Artificial intelligence applied to musculoskeletal oncology: a systematic review.
Li MD, Ahmed SR, Choy E, Lozano-Calderon SA, Kalpathy-Cramer J, Chang CY
Skeletal Radiol. 2022;51(2):245-256.
Inconsistent Partitioning and Unproductive Feature Associations Yield Idealized Radiomic Models.
Gidwani M, Chang K, Patel J, Hoebel KV, Ahmed SR, et al.
Radiology. 2022: 220715
Opportunities and Challenges for Deep Learning in Brain Lesions.
Patel J, Chang K, Ahmed SR, Jang I, Kalpathy-Cramer J.
In: Crimi, A., Bakas, S. (eds) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2021. Lecture Notes in Computer Science, vol 12962. Springer, Cham.
Systemic coagulation is activated in patients with meningioma and glioblastoma.
Yerrabothala S, Gourley BL, Ford JC, Ahmed SR, et al
J Neurooncol. 2021;155(2):173-180.
Abnormal vascular structure and function within brain metastases is linked to pembrolizumab resistance.
Kim A, Lou K, ..., Ahmed SR, et al.
Neuro Oncol. 2023 Dec 9:noad236
Use of risk-based cervical screening programs in resource-limited settings.
Perkins RB, Smith DL, ..., Ahmed SR et al.
Cancer Epidemiol. 2023 Jun;84:102369.
AI-based image analysis in clinical testing: lessons from cervical cancer screening.
Egemen D, Perkins R, ..., Ahmed SR, et al.
J Natl Cancer Inst. 2023 Sep 27:djad202.
Design of the HPV-Automated Visual Evaluation (PAVE) Study: Validating a Novel Cervical Screening Strategy.
de Sanjose S, Perkins R, ..., Ahmed SR, et al.
eLife (2023). 12:RP91469
Coagulation Activation in Brain Neoplasms
Yerrabothala S, Gourley B, ..., Ahmed SR, et al.
Blood. 2017;130 (Supplement 1).
Addressing catastrophic forgetting by modulating global batch normalization statistics for medical domain expansion
Gupta S, Chang K, ..., Ahmed SR, et al.
In: Proietto Salanitri, F., et al. Artificial Intelligence in Pancreatic Disease Detection and Diagnosis, and Personalized Incremental Learning in Medicine. PILM AIPAD 2024 in conjunction with MICCAI 2024. Lecture Notes in Computer Science, vol 15197. Springer, Cham.
Conformal prediction and Monte Carlo inference for addressing uncertainty in cervical cancer screening
Clark C, Kinder S, ..., Ahmed SR, et al.
In: Sudre, C.H., Mehta, R., Ouyang, C., Qin, C., Rakic, M., Wells, W.M. (eds) Uncertainty for Safe Utilization of Machine Learning in Medical Imaging. UNSURE 2024 in conjunction with MICCAI 2024. Lecture Notes in Computer Science, vol 15167. Springer, Cham.
Cycle-GANs Generated Difference Maps to Interpret Race Prediction from Medical Images.
Rathi L, Nebbia G, ..., Ahmed SR, et al.
In: Puyol-Antón, E., et al. Ethics and Fairness in Medical Imaging. FAIMI EPIMI 2024 in conjunction MICCAI 2024. Lecture Notes in Computer Science, vol 15198. Springer, Cham.

Presentations and Symposia

A deep learning framework enables non-invasive detection of tumor mutational burden in brain metastases.
Ahmed SR, Brahmavar S, Bridge C, et al.
Radiological Society of North America (RSNA) 2023 Annual Meeting.
A deep learning-based framework for joint image registration and segmentation of brain metastases on magnetic resonance imaging.
Patel J, Ahmed SR, Chang K, et al.
Machine Learning for Healthcare (MLHC) 2023
Focal loss improves clinical deployability of deep learning models.
Ahmed SR, Lemay A, Hoebel K, Kalpathy-Cramer J.
Radiological Society of North America (RSNA) 2022 Annual Meeting; Program pp 456, 461
Estimating test performance for AI medical devices under distribution shift with conformal prediction.
Ahmed SR*, Lu C*, Singh P, Kalpathy-Cramer J.
International Conference on Machine Learning (ICML) 2022: Principles of Distribution Shift (PODS) Workshop, Baltimore, MD, US.
Focal loss improves repeatability of deep learning models.
Ahmed SR, Lemay A, Hoebel K, Kalpathy-Cramer J.
Medical Imaging with Deep Learning (MIDL) 2022, ETH, Zurich, Switzerland.
Frequency-Domain Resting State fMRI Analysis to Investigate Language and Handmotor Cortices in Healthy Controls.
Ahmed SR, Jenabi M, Gene M, Moreno R, Peck K, Holodny A.
MSK Medical Student Summer Fellowship Research Symposium 2019, MSKCC, New York, NY, US
Making the Most of Limited Data with Self-Supervised Learning for Breast Cancer Screening.
Clark C, Kinder S, Ahmed SR, et al.
27th MICCAI 2024 conference (MedAGI Workshop), Marrakesh, Morocco.
Deep learning-based non-invasive molecular profiling of brain metastases from MR imaging.
Bhat S, Goncalves T, Ahmed SR, et al.
The 21st International Symposium on Biomedical Imaging (ISBI) 2024, Athens, Greece
Deep learning-based prediction of breast cancer tumor and immune phenotypes from digitized histopathology.
Goncalves T, Kim A, ..., Ahmed SR, et al.
The 38th Annual AAAI Conference on Artificial Intelligence (2024).
A deep learning algorithm for fully automated volumetric measurement of meningioma burden.
Cleveland M, Kim A, ..., Ahmed SR, et al.
Society for NeuroOncology 28th Annual Meeting (2023) and MIT/MGB AI Cures Conference 2024.
Coagulation Activation in Brain Neoplasms.
Yerrabothala S, Gourley BL, Ford JC, Ahmed SR, et al.
59th American Society of Hematology (ASH) Annual Meeting and Exposition 2017, Atlanta, GA, US.