Heejong Kim

Instructor

About

I am an Instructor at Weill Cornell Medicine, Department of Radiology, working with Mert Sabuncu. My research sits at the intersection of medical image analysis and artificial intelligence, developing computational methods that extract clinically meaningful insight from medical data — from predicting diagnosis, progression, and treatment outcomes to building better image processing models. I earned my Ph.D. at NYU under Guido Gerig.

Recent Updates

[07.2026] Our paper on self-supervised subject-wise super-resolution, co-led by Abhishek Thanki, is accepted at MICCAI 2026 (Paper/Code).

[01.2026] Our paper on a deep survival model for predicting Alzheimer's disease using longitudinal data, led by Batuhan Karamen, is accepted at Big Data Mining and Analytics 2026 (Paper).

[07.2025] Knockout, a simple way to handle missing inputs, led by Minh Nguyen, is published at Transactions on machine learning research 2025 (Paper/Code).

[06.2025] I was invited to give a talk at The Artificial Intelligence and Machine-Learning (AIMS) working group of the North American Imaging in MS (NAIMS).

Past Updates: See All Updates.

Publications

Single-Subject Multi-View MRI Super-Resolution via Implicit Neural Representations

H Kim^∗, A Thanki^∗, R van Herten, D Margolis , MR Sabuncu

MICCAI, 2026.

[ Code |^∗Equal contribution ]

A Deep Survival Model for Predicting Alzheimer's Diagnosis Based on Multi-Modal Longitudinal Data

BK Karaman, M Nguyen, H Kim, MR Sabuncu

Big Data Mining and Analytics, 2026.

Knockout: A simple way to handle missing inputs

M Nguyen, BK Karaman, H Kim, AQ Wang, F Liu, MR Sabuncu

TMLR, 2025.

[ Code ]

BrainMorph: A Foundational Keypoint Model for Robust and Flexible Brain MRI Registration

AQ Wang, R Sagluja, H Kim, X He, A Dalca, MR Sabuncu

MELBA, 2025.

[ Code ]

Learning-based inference of longitudinal image changes: Applications in embryo development, wound healing, and aging brain

H Kim, BK Karaman, Q Zhao, AQ Wang, MR Sabuncu, and for the Alzheimer's Disease Neuroimaging Initiative

PNAS, 2025.

[ Code | News1 | News2 ]

Effective Segmentation of Post-Treatment Gliomas Using Simple Approaches: Artificial Sequence Generation and Ensemble Models

H Kim^∗, L Milecki^∗, MC Moghadam^∗, F Liu^∗, M Nguyen^∗, E Qiu^∗, A Thanki^∗, MR Sabuncu

MICCAI: BraTS Challenge, 2024.

[ Challenge Runner-Up |^∗Equal contribution ]

Adapting to Shifting Correlations with Unlabeled Data Calibration

M Nguyen, AQ Wang, H Kim, MR Sabuncu

ECCV: European Conference on Computer Vision, 2024.

Robust Learning via Conditional Prevalence Adjustment

M Nguyen, AQ Wang, H Kim, MR Sabuncu

WACV: Winter Conference on Applications of Computer Vision, 2024.

[ Code ]

A Framework for Interpretability in Machine Learning for Medical Imaging

AQ Wang, BK Karaman, H Kim, J Rosenthal, R Saluja, SI Young, MR Sabuncu

IEEE Access, 2024.

Empirical Analysis of a Segmentation Foundation Model in Prostate Imaging

H Kim, VI Butoi, AV Dalca, DJA Margolis, MR Sabuncu

MICCAI Workshop MedAGI: Foundation Models for General Medical AI, 2023.

The role of AI in prostate MRI quality and interpretation: Opportunities and challenges

H Kim, SW Kang, J Kim, H Nagar, MR Sabuncu, DJA Margolis, CK Kim

European Journal of Radiology, 2023

Learning to Compare Longitudinal Images

H Kim, MR Sabuncu

MIDL: Medical Imaging with Deep Learning, 2023

[ Code | Webpage | Oral presentation ]

Pulse Sequence Dependence of a Simple and Interpretable Deep Learning Method for Detection of Clinically Significant Prostate Cancer Using Multiparametric MRI

H Kim, DJA Margolis, H Nagar, MR Sabuncu

Academic Radiology, 2022

[ Code ]

Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRI

M Ren^∗, H Kim^∗, N Dey, G Gerig

MICCAI: Medical Image Computing and Computer Assisted Intervention, 2021.

[ Code | Webpage | Oral presentation | ^∗Equal contribution ]

Equivariant Spherical Deconvolution: Learning Sparse Orientation Distribution Functions from Spherical Data

A Elaldi, N Dey, H Kim, G Gerig

IPMI: Information Processing in Medical Imaging, 2021.

[ Code ]

Microparticle-based Biochemical Sensing Using Optical Coherence Tomography and Deep Learning

S Shah, CN Yu, M Zheng, H Kim, MS Eggleston

ACS Nano, 2021.

Hierarchical Geodesic Modeling on the Diffusion Orientation Distribution Function for Longitudinal DW-MRI Analysis

H Kim, S Hong, M Styner, J Piven, K Botteron, G Gerig

MICCAI: Medical Image Computing and Computer Assisted Intervention, 2020.

A framework to construct a longitudinal dw-mri infant atlas based on mixed effects modeling of dodf coefficients

H Kim, M Styner, J Piven, G Gerig

MICCAI CDMRI: Computational Diffusion MRI, 2020.

[ Oral presentation | Best oral presentation award ]

Longitudinal structural connectivity in the developing brain with projective non-negative matrix factorization

H Kim, J Piven, G Gerig

SPIE Medical Imaging, 2019.

[ Oral presentation | Best paper finalist ]

Using individualized brain network for analyzing structural covariance of the cerebral cortex in alzheimer's patients

HJ Kim, JH Shin, CE Han, HJ Kim, DL Na, SW Seo, JK Seong, and the ADNI

Frontiers in neuroscience, 2016.

Tract-specific correlates of neuropsychological deficits in patients with subcortical vascular cognitive impairment

NY Jung, CE Han, HJ Kim, SW Yoo, HJ Kim, EJ Kim, DL Na, SN Lockhart, WJ Jagust, JK Seong, SW Seo

Journal of Alzheimer's Disease, 2016.