Hyun Do Jung

정현도

Building trustworthy AI for computational pathology

I am a Ph.D. student in Artificial Intelligence at Yonsei University, advised by Prof. Hwiyoung Kim and Prof. Yujin Oh. I study how to make computational pathology models not only accurate but also interpretable and robust — especially when labeled data is limited or the data distribution shifts across institutions.

Specifically, I work on multiple instance learning (MIL), self-supervised pre-training, and concept-based reasoning for whole slide image (WSI) analysis. Most of my recent work asks: given a gigapixel pathology slide, can a model point to which regions drove its prediction, and can we trust those explanations in real clinical settings?

Computational Pathology Multiple Instance Learning Self-supervised Learning Explainable AI Weakly Supervised Learning Medical Image Analysis

I am currently looking for research internship opportunities in industry. If my work resonates with yours, I would be glad to connect.

Publications

Selected Papers

Are Compact Rationales Free? Measuring Tile Selection Headroom in Frozen WSI-MIL
Hyun Do Jung, Jungwon Choi, Soojung Choi, Yujin Oh, Hwiyoung Kim

Under Review
ReaMIL: Reasoning- and Evidence-Aware Multiple Instance Learning for Whole-Slide Histopathology
Hyun Do Jung, Jungwon Choi, Hwiyoung Kim

WACV 2026 Workshop ★ Oral Presentation arXiv
Comparing Adaptation Strategies Across Pathology Foundation Models: Model- and Data-Dependent Performance on Cross-Domain Breast Cancer Cohorts
Hyun Do Jung*, Soojung Choi*, Suk Jun Lee, Seho Park, Hwiyoung Kim

Under Review at Medical Image Analysis

* Equal contribution
A Feasibility Study: Assessing the Use of a Pre-Trained Detection-Free Model on Cytologic Whole Slide Images for Efficient Prediction of Breast Cancer Recurrence Risk
Hyun Do Jung, Suk Jun Lee, Seho Park, Hwiyoung Kim

EMBC 2024 Poster

Clinical Collaborations

Multivariable Radiomics Model for Predicting Programmed Death-Ligand 1 Expression After Neoadjuvant Chemoradiotherapy in Esophageal Squamous Cell Carcinoma
Hyun Do Jung*, Tae Hoon Lee*, Byoung Hyuck Kim*, Hye Seung Lee, Jaeman Son, Hwiyoung Kim, Hak Jae Kim

Under Review at Cancer Medicine

* Equal contribution
Deep Learning for Multi-Label Plaque Classification in Intravascular OCT: Ensuring Cross-Site Generalization through External Calibration
Hyun Do Jung*, Seul-gee Lee*, Dongcho Park, Hwiyoung Kim, Jung-Sun Kim

Submitted to Artificial Intelligence in Medicine

* Equal contribution
Prediction of Pathological Complete Response after Neoadjuvant Chemoradiation in Esophageal Squamous Cell Carcinoma Using Delta Radiomics-Based Machine Learning
Hyun Do Jung, Tae Hoon Lee, Byoung Hyuck Kim, Hak Jae Kim, Hwiyoung Kim

AACR-KCA 2023 Poster

Talks & Teaching

Instructor

Hands-on Workshop on Medical AI for Developers: Cancer MRI Analysis
Korean Society of Artificial Intelligence in Medicine (대한의료인공지능학회) · Oct 2024

Co-author

A Complete Guide to Medical Imaging AI, Part I: From Environment Setup to Machine Learning Model Development
Online educational book (의료영상 인공지능의 모든 것) · WikiDocs · 2025

Presentation

Transfer Learning with a Pre-trained Model on Cytologic WSIs for Breast Cancer Recurrence Prediction
Institute for Innovation in Digital Healthcare 2024 Symposium, Yonsei University Health System · Nov 2024

Mentor

Project Mentor
Likelion AI School, 6th Cohort (멋쟁이사자처럼) · 2022

Awards

Excellence Award (First Place)
AI+Healthcare Research Training Program · Seoul AI Hub × Seoul National University Hospital × KAIST · Dec 2024

Education

Yonsei University
Ph.D. in Artificial Intelligence (Integrated M.S./Ph.D.) · Sep 2021 – Present
University of Illinois at Urbana-Champaign (UIUC)
B.S. in Computer Engineering · Aug 2012 – Dec 2020
University of Southern California (USC)
International Education Program · Summer 2024