Doohyun Park | Research Scientist | Data Science, Computer Vision & Applied AI

Selected Publications

[10] 2026 CVPRW - MMFM-BIOMED Workshop

When Prompts Mislead: Textual Dominance and Diagnostic Bias in MLLMs

Inhyuk Park, Doohyun Park†

† Corresponding author

URL

[09] 2026 ICLR

Frequency-Balanced Retinal Representation Learning with Mutual Information Regularization

Seunghoon Lee, Seongjae Kang, Inhyuk Park, Gitaek Kwon, Jihyeon Baek, Doohyun Park†

† Corresponding author

URL

[08] 2026 ISBI

Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation

Inhyuk Park, Doohyun Park†

† Corresponding author

URL

[07] 2026 ISBI

A Comparative Study of Machine Learning and Deep Learning for Out-of-Distribution Detection

Jihyeon Baek, Seunghoon Lee, Gitaek Kwon, Doohyun Park†

† Corresponding author

URL

[06] 2025 npj Precision Oncology (JCR top 11.7%)

Multimodal AI model for preoperative prediction of axillary lymph node metastasis in breast cancer using whole slide images

Doohyun Park, Yong-Moon Lee, Taejoon Eo, Hee Jung An, Haeyoun Kang, Eunhyang Park, Yoon Jin Cha, Heejung Park, Dohee Kwon, Sun Young Kwon, Hye-Ra Jung, Su-Jin Shin, Hyunjin Park, Yangkyu Lee, Sanghui Park, Ji Min Kim, Sung-Eun Choi, Nam Hoon Cho, Dosik Hwang

URL

[05] 2024 Bioengineering (JCR top 40.7%)

A Comprehensive Review of Performance Metrics for Computer-Aided Detection Systems

Doohyun Park

URL

[04] 2024 Diagnostics (JCR top 17.0%)

Deep Learning-based Slice Thickness Reduction for Computer-Aided Detection of Lung Nodules in Thick Slice CT

Jonghun Jeong*, Doohyun Park*, Jung-Hyun Kang, Myungsub Kim, Hwa-Young Kim, Woosuk Choi, Soo-Youn Ham

* Equally contributed

URL

[03] 2024 European Radiology (JCR top 12.4%)

Weakly-Supervised Deep Learning for Multi-Label Classification of Vertebral Compression Fracture in CT

Euijoon Choi*, Doohyun Park*, Geonhui Son, Seongwon Bak, Taejoon Eo, Daemyung Youn, Dosik Hwang

* Equally contributed

URL

[02] 2023 Scientific Reports (JCR top 18.3%)

Development and Validation of A Hybrid Deep Learning-Machine Learning Approach for Severity Assessment of COVID-19 and Other Pneumonias

Doohyun Park, Ryoungwoo Jang, Myung Jin Chung, Hyun Joon An, Seongwon Bak, Euijoon Choi, Dosik Hwang

URL

[01] 2022 European Radiology (JCR top 11.5%)

Importance of CT Image Normalization in Radiomics Analysis: Prediction of 3-Year Recurrence-Free Survival in Non-Small Cell Lung Cancer

Doohyun Park, Daejoong Oh, MyungHoon Lee, Shin Yup Lee, Kyung Min Shin, Johnson SG Jun, Dosik Hwang

URL

Other Publications

[24] 2026 ISBI, International Symposium on Biomedical Imaging (Abstract)

Prompt-Induced Bias from One-Shot Multimodal Large Language Models Prompting in Medical Imaging

Inhyuk Park, Jihyeon Baek, Doohyun Park

[23] 2026 ISBI, International Symposium on Biomedical Imaging (Abstract)

Prompt Dominance in Medical Multimodal Large Language Models

Inhyuk Park, Jihyeon Baek, Doohyun Park

[22] 2025 npj Digital Medicine

Interpretable Multimodal Transformer for Prediction of Molecular Subtypes and Grades in Adult-type Diffuse Gliomas

Yunsu Byeon, Yae Won Park, Soohyun Lee, Doohyun Park, HyungSeob Shin, Kyunghwa Han, Jong Hee Chang, Se Hoon Kim, Seung-Koo Lee, Sung Soo Ahn, Dosik Hwang

[21] 2025 Preprints

Multi-center Validation of Pulmonary Nodule Classification Model for Lung Cancer Screening

Doohyun Park, Jung-Hyun Kang, Changhyun Park

[20] 2025 MIDL, Medical Imaging with Deep Learning (Short Paper)

Attention-based Interpretable Deep Learning with Radiomic Features for Pulmonary Nodule Classification

Doohyun Park, Nahyuk Lee, Sungjoo Lim

[19] 2025 ECR (Oral Presentation), European Congress of Radiology

Foundation Model-based Unsupervised CT Kernel Conversion for Standardizing Emphysema Quantification

Doohyun Park, Jung-Hyun Kang, Jonghun Jeong

[18] 2025 ECR, European Congress of Radiology

Evaluation Metrics for Computer-Aided Detection Systems in Medical AI: What You Need to Know

Doohyun Park

[17] 2025 JRC, Japan Radiology Congress

Deep Learning-based Lesion Segmentation for Patients with Usual Interstitial Pneumonia in High-Resolution CT: A pilot study

Doohyun Park, Jung-Hyun Kang, Jonghun Jeong, Kyoung Min Moon

[16] 2025 JRC, Japan Radiology Congress

Fully Automated Segment-Anything-Model for Robust Lobe Segmentation in Patients with Interstitial Lung Disease

Sungjoo Lim, Doohyun Park, Jonghun Jeong, Changhyun Park, Kyoung Min Moon

[15] 2025 JRC, Japan Radiology Congress

Deep Learning-based Slice Thickness Reduction for Lung Nodule Detection of Thick Slice Chest CT

Jonghun Jeong, Doohyun Park, Jung-Hyun Kang, Myungsub Kim, Hwa-Young Kim, Woosuk Choi, Soo-Youn Ham

[14] 2024 WCLC, World Conference on Lung Cancer

Nodule Type Classification for Lung Cancer Screening with CT

Doohyun Park, Jung-Hyun Kang, Changhyun Park, Jinyoung Kim

[13] 2024 ESTI, European Society of Thoracic Imaging

A Standardized Performance Evaluation Metric for Chest CT Nodule Detection

Doohyun Park, Chanmin Park, Jung-Hyun Kang, Jinyoung Kim

[12] 2024 RSNA, Radiological Society of North America

A Multi-center Retrospective Study of Nodule Type Classification using Artificial Intelligence for Lung-RADS Scoring with CT

Doohyun Park, Jung-Hyun Kang, Changhyun Park, Jonghun Jeong

[11] 2024 RSNA, Radiological Society of North America

Quantity or Certainty: Can Ambiguously Annotated Data Improve Lung Nodule Detection Performance?

Chanmin Park, Jung-Hyun Kang, Doohyun Park, Jonghun Jeong

[10] 2024 MICCAI, Medical Image Computing and Computer Assisted Intervention

LLM-guided Multi-modal Multiple Instance Learning for 5-year Overall Survival Prediction of Lung Cancer

Kyungwon Kim, Yongmoon Lee, Doohyun Park, Taejoon Eo, Daemyung Youn, Hyesang Lee, Dosik Hwang

[09] 2024 ISMRM (Oral Presentation), International Society for Magnetic Resonance in Medicine

Unified Diffusion model for Multi-contrast Ensembling Synthesis

Yeeun Lee, Yejee Shin, Doohyun Park, Geonhui Son, Taejoon Eo, Dosik Hwang

[08] 2024 ISMRM (Oral Presentation), International Society for Magnetic Resonance in Medicine

Deep Learning Algorithm for Prediction of Molecular Subtypes and Grades in Adult-type Diffuse Gliomas: According to the 2021 WHO Updates

Yunsu Byeon, Yae Won Park, Soohyun Lee, Hyungseob Shin, Doohyun Park, Sung Soo Ahn, Seung-Koo Lee, Dosik Hwang

[07] 2024 Diagnostics

Deep Learning-based Joint Effusion Classification in Adult Knee Radiographs: A Multi-Center Prospective Study

Hyeyeon Won, Hye Sang Lee, Daemyung Youn, Doohyun Park, Taejoon Eo, Wooju Kim, Dosik Hwang

[06] 2023 LNCS, Lecture Notes in Computer Science (MICCAI SEG.A Technical Paper)

M3F: Multi-Field-of-View Feature Fusion Network for Aortic Vessel Tree Segmentation in CT Angiography

Yunsu Byeon, Hyeseong Kim, Kyungwon Kim, Doohyun Park, Euijoon Choi, Dosik Hwang

[05] 2023 CICS - Conference on Information and Control Systems

Foundation Models in Healthcare: Applications, Challenges, and Future Directions

Hyeyeon Won, Doohyun Park, Taejoon Eo, Yeeun Lee, Dosik Hwang

[04] 2018 ISMRM, International Society for Magnetic Resonance in Medicine

Iterative Cross-Domain Deep-Learning Approach for Reconstructing Undersampled Radial MRI

Doohyun Park, Taejoon Eo, Taeseong Kim, Jinseong Jang, Dosik Hwang

[03] 2018 ISMRM, International Society for Magnetic Resonance in Medicine

Deep Sinogram Learning for Radial MRI: Comparison with k-space and Image Learning

Taeseong Kim, Taejoon Eo, Doohyun Park, Yohan Jun, Dosik Hwang

[02] 2018 Medical Physics

Correction of severe beam‐hardening artifacts via a high‐order linearization function using a prior‐image‐based parameter selection method

Daejoong Oh, Sewon Kim, Doohyun Park, Seungwon Choi, Hundong Song, Yunsu Choi, Seunghyuk Moon, Jongduk Baek, Dosik Hwang

[01] 2017 SPIE Medical Imaging

Beam Hardening Correction Using Length Linearization

Daejoong Oh, Sewon Kim, Doohyun Park, Dosik Hwang

Patents

[13] 2025 US Granted (US12500003B2)

Method of predicting prognosis of patient with adenocarcinoma using image feature

[12] 2025 KR Granted (10-2758775)

Method for Predicting Prognosis in Cancer Patient Using Radiomic Feature

[11] 2024 EPO Application (EP4218032A4)

Method of predicting prognosis of patient with adenocarcinoma using image feature

[10] 2024 KR Application (10-2024-0176698)

Method for outputting segmentation information for an image and device therefor

[09] 2023 US Granted (US11748980B2)

Makeup evaluation system and operating method thereof

[08] 2023 CN Application (CN116325019A)

Method of predicting prognosis of patient with adenocarcinoma using image feature

[07] 2022 CN Granted (CN110235169B)

Cosmetic evaluation system and operation method thereof

[06] 2022 JP Granted (JP7020626B2)

Makeup evaluation system and its operation method

[05] 2021 US Granted (US11113511B2)

Makeup evaluation system and operating method thereof

[04] 2021 KR Granted (10-2305806)

Method for Prodicting Prognosis in Lung Cancer Patient using Clinical Information and Gene Polymorphism Information

[03] 2020 EPO Application (EP3579176A4)

Makeup evaluation system and operation method thereof

[02] 2020 KR Granted (10-2066892)

Make-up evaluation system and operating method thereof

Technology transfer: ₩20,000,000

[01] 2019 KR Granted (10-2039472)

Device and Method for Reconstructing Computed Tomography Image

Projects

SSL · Ophthalmology

Self-Supervised Learning for Retinal Images

Developed a retinal self-supervised learning framework that better preserves clinically important high-frequency structures, improving data efficiency and transfer across multiple downstream tasks.

Multimodal · Pathology

Multimodal Prediction from Whole-Slide Pathology Images

Developed multimodal models that combine whole-slide images with clinical variables to support preoperative prediction, with validation across multiple cohorts for stronger clinical relevance.

Weak Supervision · Radiology

Weakly Supervised Learning for CT Diagnosis

Trained CT diagnostic models with weak supervision to reduce annotation burden while maintaining strong performance at clinically meaningful prediction granularity.

Data-Centric AI· Noisy Labels

Noisy Label Detection for Reliable AI

Developed a task-agnostic noisy-label detection method that produces stable sample-level quality scores, enabling efficient dataset refinement and more reliable model development.

Detection · Evaluation

Performance Metrics for Clinical Detection AI

Reviewed major performance metrics for computer-aided detection systems, clarifying their strengths, limitations, and clinical implications. Proposed practical guidelines for selecting evaluation metrics based on task design, dataset composition, and intended clinical use.

Image Quality Enhancement

Improving Detection from Thick-Slice CT

Developed deep learning methods to enhance thick-slice CT images, improving the visibility of subtle findings and supporting more reliable downstream nodule detection.

Triage · AI/ML

Hybrid AI/ML for CT-Based Severity Assessment

Developed a hybrid severity assessment framework that combines deep learning and machine learning to quantify disease severity from CT images, with external validation across multiple cohorts and pneumonia types.

Robustness · Radiomics

Robust Quantitative Imaging Across Acquisition Settings

Studied how normalization and preprocessing affect radiomic feature stability and predictive performance, improving robustness across heterogeneous CT acquisition settings.

Reliability · OOD

Out-of-Distribution Detection for Reliable Deployment

Evaluated OOD detection approaches for medical imaging pipelines, comparing classical machine learning and deep learning under practical constraints such as accuracy, latency, and simplicity.

Applied Vision · Commercialization

Image-Based Make-up Level Assessment

Developed a image-based method for assessing make-up level from facial photographs, leading to multiple domestic and international patents and technology transfer.

News

Education

Selected Publications

When Prompts Mislead: Textual Dominance and Diagnostic Bias in MLLMs

Frequency-Balanced Retinal Representation Learning with Mutual Information Regularization

Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation

A Comparative Study of Machine Learning and Deep Learning for Out-of-Distribution Detection

Multimodal AI model for preoperative prediction of axillary lymph node metastasis in breast cancer using whole slide images

A Comprehensive Review of Performance Metrics for Computer-Aided Detection Systems

Deep Learning-based Slice Thickness Reduction for Computer-Aided Detection of Lung Nodules in Thick Slice CT

Weakly-Supervised Deep Learning for Multi-Label Classification of Vertebral Compression Fracture in CT

Development and Validation of A Hybrid Deep Learning-Machine Learning Approach for Severity Assessment of COVID-19 and Other Pneumonias

Importance of CT Image Normalization in Radiomics Analysis: Prediction of 3-Year Recurrence-Free Survival in Non-Small Cell Lung Cancer

Other Publications

Prompt-Induced Bias from One-Shot Multimodal Large Language Models Prompting in Medical Imaging

Prompt Dominance in Medical Multimodal Large Language Models

Interpretable Multimodal Transformer for Prediction of Molecular Subtypes and Grades in Adult-type Diffuse Gliomas

Multi-center Validation of Pulmonary Nodule Classification Model for Lung Cancer Screening

Attention-based Interpretable Deep Learning with Radiomic Features for Pulmonary Nodule Classification

Foundation Model-based Unsupervised CT Kernel Conversion for Standardizing Emphysema Quantification

Evaluation Metrics for Computer-Aided Detection Systems in Medical AI: What You Need to Know

Deep Learning-based Lesion Segmentation for Patients with Usual Interstitial Pneumonia in High-Resolution CT: A pilot study

Fully Automated Segment-Anything-Model for Robust Lobe Segmentation in Patients with Interstitial Lung Disease

Deep Learning-based Slice Thickness Reduction for Lung Nodule Detection of Thick Slice Chest CT

Nodule Type Classification for Lung Cancer Screening with CT

A Standardized Performance Evaluation Metric for Chest CT Nodule Detection

A Multi-center Retrospective Study of Nodule Type Classification using Artificial Intelligence for Lung-RADS Scoring with CT

Quantity or Certainty: Can Ambiguously Annotated Data Improve Lung Nodule Detection Performance?

LLM-guided Multi-modal Multiple Instance Learning for 5-year Overall Survival Prediction of Lung Cancer

Unified Diffusion model for Multi-contrast Ensembling Synthesis

Deep Learning Algorithm for Prediction of Molecular Subtypes and Grades in Adult-type Diffuse Gliomas: According to the 2021 WHO Updates

Deep Learning-based Joint Effusion Classification in Adult Knee Radiographs: A Multi-Center Prospective Study

M3F: Multi-Field-of-View Feature Fusion Network for Aortic Vessel Tree Segmentation in CT Angiography

Foundation Models in Healthcare: Applications, Challenges, and Future Directions

Iterative Cross-Domain Deep-Learning Approach for Reconstructing Undersampled Radial MRI

Deep Sinogram Learning for Radial MRI: Comparison with k-space and Image Learning

Correction of severe beam‐hardening artifacts via a high‐order linearization function using a prior‐image‐based parameter selection method

Beam Hardening Correction Using Length Linearization

Patents

Patents

Method of predicting prognosis of patient with adenocarcinoma using image feature

Method for Predicting Prognosis in Cancer Patient Using Radiomic Feature

Method of predicting prognosis of patient with adenocarcinoma using image feature

Method for outputting segmentation information for an image and device therefor

Makeup evaluation system and operating method thereof

Method of predicting prognosis of patient with adenocarcinoma using image feature

Cosmetic evaluation system and operation method thereof

Makeup evaluation system and its operation method

Makeup evaluation system and operating method thereof

Method for Prodicting Prognosis in Lung Cancer Patient using Clinical Information and Gene Polymorphism Information

Makeup evaluation system and operation method thereof

Make-up evaluation system and operating method thereof

Device and Method for Reconstructing Computed Tomography Image

Projects

Self-Supervised Learning for Retinal Images

Multimodal Prediction from Whole-Slide Pathology Images

Weakly Supervised Learning for CT Diagnosis

Noisy Label Detection for Reliable AI

Performance Metrics for Clinical Detection AI

Improving Detection from Thick-Slice CT

Hybrid AI/ML for CT-Based Severity Assessment

Robust Quantitative Imaging Across Acquisition Settings

Out-of-Distribution Detection for Reliable Deployment

Image-Based Make-up Level Assessment

Curriculum Vitae

Contact

Email

Location

Affiliation