Kyungeun Kim
Kyungeun Kim has a total of 84 co-authors. Here are the top co-authors by number of shared publications:
- Boram Song
Department of Pathology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, Korea
5 shared publications Hyoun Wook Lee
Sungkyunkwan Univ, Sch Med, Samsung Changwon Hosp, Dept Pathol, Seoul, South Korea
5 shared publications- Jisu Shin
Korea Advanced Institute of Science and Technology
4 shared publications - Mun Yong Yi
Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea
4 shared publications - Sungrae Hong
Korea Advanced Institute of Science and Technology
4 shared publications Chang Hak Yoo
Sungkyunkwan Univ, Sch Med, Kangbuk Samsung Hosp, Dept Surg, Seoul, South Korea
3 shared publications
Latest Publications
- Open Access
- 15 November 2026
- Published by The Korean Society of Pathologists and The Korean Society for Cytopathology in Journal of Pathology and Translational Medicine
- Vol. 60 (6) , 593-610
Digital image analysis–based quantification of p53 immunohistochemistry in gastric cancer: a systematic comparison of three-tier cutoff-derivation strategies in tissue microarrays
Background: p53 immunohistochemistry (IHC) is a common surrogate for TP53 alteration, but in gastric cancer, its concordance is imperfect and depends on a non-standardized cutoff. Digital pathology enables H-score quantification, yet neither its reproducibility nor the choice of cutoff- derivation strategy has been systematically compared. Methods: A semi-automated digital workflow quantified p53 IHC in tissue microarrays from 528 gastric cancer patients. Tumor cells were detected with a deep-learning model (InstanSeg), and nuclear staining was expressed as a continuous H-score (0–300). Reproducibility was assessed at each observer-dependent step. Five thresholding strategies were compared: manual cutoffs, tertiles, log-rank optimization, the extended Youden index, and volume under the receiver operating characteristic surface (VUS). The latter two strategies used the manual three-tier IHC interpretation as the reference standard. Results: Quantification was reproducible: two independent manual interpretations agreed in 91.7% of cores (κ = 0.845). The H-score was robust to the detection algorithm (intraclass correlation coefficient, 0.990) and to repeated threshold determination (0.954). H-scores were right-skewed (median, 45.5), and the strategies yielded distinct cutoffs (8.0–27.6 and 78.6–106.0). Log-rank optimization provided the widest separation but lost significance after multiplicity adjustment (p = .168). The extended Youden and VUS cutoffs were statistically indistinguishable. As a supporting check, all classifications showed nominal overall-survival separation, with low and overexpression faring similarly worse than wild-type. Conclusions: Digital p53 IHC quantification was reproducible at each observer-dependent step. The extended Youden and VUS criteria performed equivalently; therefore, we propose Youden as a reasonable default, pending validation and TP53 correlation.
- 15 November 2026
- Published by The Korean Society of Pathologists and The Korean Society for Cytopathology in Journal of Pathology and Translational Medicine
- Vol. 60 (6) , 593-610
Open AccessDigital image analysis–based quantification of p53 immunohistochemistry in gastric cancer: a systematic comparison of three-tier cutoff-derivation strategies in tissue microarrays
Background: p53 immunohistochemistry (IHC) is a common surrogate for TP53 alteration, but in gastric cancer, its concordance is imperfect and depends on a non-standardized cutoff. Digital pathology enables H-score quantification, yet neither its reproducibility nor the choice of cutoff- derivation strategy has been systematically compared. Methods: A semi-automated digital workflow quantified p53 IHC in tissue microarrays from 528 gastric cancer patients. Tumor cells were detected with a deep-learning model (InstanSeg), and nuclear staining was expressed as a continuous H-score (0–300). Reproducibility was assessed at each observer-dependent step. Five thresholding strategies were compared: manual cutoffs, tertiles, log-rank optimization, the extended Youden index, and volume under the receiver operating characteristic surface (VUS). The latter two strategies used the manual three-tier IHC interpretation as the reference standard. Results: Quantification was reproducible: two independent manual interpretations agreed in 91.7% of cores (κ = 0.845). The H-score was robust to the detection algorithm (intraclass correlation coefficient, 0.990) and to repeated threshold determination (0.954). H-scores were right-skewed (median, 45.5), and the strategies yielded distinct cutoffs (8.0–27.6 and 78.6–106.0). Log-rank optimization provided the widest separation but lost significance after multiplicity adjustment (p = .168). The extended Youden and VUS cutoffs were statistically indistinguishable. As a supporting check, all classifications showed nominal overall-survival separation, with low and overexpression faring similarly worse than wild-type. Conclusions: Digital p53 IHC quantification was reproducible at each observer-dependent step. The extended Youden and VUS criteria performed equivalently; therefore, we propose Youden as a reasonable default, pending validation and TP53 correlation.
- 25 September 2026
- Published by Springer Nature
- p. 572-582
DiagMIL: Uncertainty-Gated Coarse-to-Fine Multi-resolution MIL for WSI Diagnosis
- 25 September 2026
- Published by Springer Nature
- p. 572-582
DiagMIL: Uncertainty-Gated Coarse-to-Fine Multi-resolution MIL for WSI Diagnosis
- 25 September 2026
- Published by Springer Nature
- p. 451-461
RaLMPH: Reliability-Aware Learning for Multi-Pathologist Harmonization in Whole-Slide Image Classification
- 25 September 2026
- Published by Springer Nature
- p. 451-461
RaLMPH: Reliability-Aware Learning for Multi-Pathologist Harmonization in Whole-Slide Image Classification
- Open Access
- 15 August 2026
- Published by Wiley in Histopathology
- Vol. 89 (6) , 1042-1055
Comprehensive and reproducible grading of the Updated Sydney System in gastric biopsies using artificial intelligence: multi‐pathologist validation and a reader study
Aims: The Updated Sydney System is the most widely used framework for histological grading of gastritis, but complete grading in routine gastric biopsies is time‐consuming and subject to interobserver variability. We developed an artificial intelligence (AI) system to support comprehensive and reproducible grading of all five Updated Sydney attributes in gastric biopsies. Methods and results: We developed SydneyMTL, a weakly supervised multi‐task multiple instance learning framework trained on 50,765 whole‐slide images from routine practice. The model jointly predicts mononuclear cell infiltration, neutrophil activity, glandular atrophy, intestinal metaplasia and Helicobacter pylori density, with atrophy including a separate not applicable category when muscularis mucosae is absent. Performance was assessed against routine labels from 24 board‐certified pathologists and against a consensus‐adjudicated Golden dataset. SydneyMTL achieved a mean lenient accuracy of 89.1% across the 24 pathologists, with >80% agreement for 21 of 24 readers on the retrospective dataset. In a two‐reader randomized crossover study, AI assistance improved interobserver agreement and reduced review time by 34.2% for complete Updated Sydney grading. Conclusions: AI can support more reproducible and efficient grading of Updated Sydney histological attributes in gastric biopsies. By combining multi‐pathologist validation, consensus‐based evaluation and explicit handling of non‐assessable atrophy, SydneyMTL provides a clinically realistic decision‐support approach for routine digital pathology.
- 15 August 2026
- Published by Wiley in Histopathology
- Vol. 89 (6) , 1042-1055
Open AccessComprehensive and reproducible grading of the Updated Sydney System in gastric biopsies using artificial intelligence: multi‐pathologist validation and a reader study
Aims: The Updated Sydney System is the most widely used framework for histological grading of gastritis, but complete grading in routine gastric biopsies is time‐consuming and subject to interobserver variability. We developed an artificial intelligence (AI) system to support comprehensive and reproducible grading of all five Updated Sydney attributes in gastric biopsies. Methods and results: We developed SydneyMTL, a weakly supervised multi‐task multiple instance learning framework trained on 50,765 whole‐slide images from routine practice. The model jointly predicts mononuclear cell infiltration, neutrophil activity, glandular atrophy, intestinal metaplasia and Helicobacter pylori density, with atrophy including a separate not applicable category when muscularis mucosae is absent. Performance was assessed against routine labels from 24 board‐certified pathologists and against a consensus‐adjudicated Golden dataset. SydneyMTL achieved a mean lenient accuracy of 89.1% across the 24 pathologists, with >80% agreement for 21 of 24 readers on the retrospective dataset. In a two‐reader randomized crossover study, AI assistance improved interobserver agreement and reduced review time by 34.2% for complete Updated Sydney grading. Conclusions: AI can support more reproducible and efficient grading of Updated Sydney histological attributes in gastric biopsies. By combining multi‐pathologist validation, consensus‐based evaluation and explicit handling of non‐assessable atrophy, SydneyMTL provides a clinically realistic decision‐support approach for routine digital pathology.
- 4 June 2026
- Published by Springer Nature
- p. 91-100
Priority-Aware Clinical Pathology Hierarchy Training for Multiple Instance Learning
- 4 June 2026
- Published by Springer Nature
- p. 91-100
Priority-Aware Clinical Pathology Hierarchy Training for Multiple Instance Learning
- Open Access
SydneyMTL: Interpretable Multi-Task Learning for Complete Sydney System Assessment in Gastric Biopsies
Summary: The Updated Sydney System (USS) provides a standardized framework for grading gastritis and stratifying gastric cancer risk. However, subjective observer variability and labor-intensive workflows impede its routine clinical use. To address these challenges, we developed SydneyMTL, a multi-task deep learning framework that uses Multiple Instance Learning (MIL) with task-specific attention pooling to predict severity grades across all five USS attributes simultaneously. Trained on an unprecedented cohort of 50,765 whole-slide images (WSIs), SydneyMTL generates interpretable histologic evidence for clinical practice. In retrospective evaluations against 24 board-certified pathologists, the model achieved an overall mean lenient accuracy of 89.1%, with 22 pathologists exhibiting >80% agreement with the model. When evaluated on an expert-adjudicated “Golden dataset,” the model’s performance improved to 90.2%, demonstrating its capacity to align with multi-expert consensus and filter individual annotator noise. Latent space analysis confirmed that SydneyMTL captures the ordinal structure of the USS, by representing disease severity as a continuous biological spectrum rather than as disjoint categories. Finally, a randomized crossover reader study showed that AI-assisted review significantly reduced interpretation time and improved inter-observer agreement, establishing SydneyMTL as a scalable tool for supporting standardized gastric cancer risk stratification. Graphical Highlights: SydneyMTL is the first unified framework to simultaneously predict the full 4-tier severity grades across all five Updated Sydney System attributes. Trained on a massive cohort of 50,765 whole slide images, the model aligns with multi-expert consensus on a rigorous “Golden dataset”. AI assistance significantly reduces pathologist reading time and harmonizes inter-observer variability in real-world clinical workflows. Latent space analysis confirms that SydneyMTL preserves the biological ordinality of disease severity without explicit ordinal constraints. The bigger picture: Gastritis is among the most frequent diagnoses in gastrointestinal pathology, and its histologic severity is central to gastric cancer prevention. In routine practice, pathologists convert subtle mucosal changes into semi-quantitative, ordinal grades using the Updated Sydney System, which evaluates five co-existing histologic dimensions. While this framework provides a shared language, grading is labor intensive and inherently dependent on reader-specific thresholds, creating variability that affects risk stratification and surveillance. A key concept motivating our study is that gastritis is not defined by a single finding but by multiple criteria that co-occur and interact. This suggests that computational models should learn these criteria jointly – capturing their biological correlations and the continuum of severity – rather than treating each grade as an isolated classification task. SydneyMTL implements this perspective through a unified multi-task, weakly supervised approach that learns directly from a massive cohort of 50,765 routine whole-slide images. Beyond diagnostic accuracy, our work reveals that the model preserves the ordinality of severity in its representation space, supporting the biological view that discrete clinical categories approximate an underlying continuous biological spectrum. Its attention-based explanations also connect model outputs to interpretable tissue evidence, enhancing clinical trust. Crucially, by harmonizing inter-observer variability, SydneyMTL provides a more reliable foundation for gastric cancer risk assessment, ensuring that premalignant changes are captured with greater consistency. More broadly, our findings reposition AI for gastritis from narrow detection toward scalable, evidence-based decision support that can standardize grading practices and reduce cognitive burden on the global pathology workforce.
Open AccessSydneyMTL: Interpretable Multi-Task Learning for Complete Sydney System Assessment in Gastric Biopsies
Summary: The Updated Sydney System (USS) provides a standardized framework for grading gastritis and stratifying gastric cancer risk. However, subjective observer variability and labor-intensive workflows impede its routine clinical use. To address these challenges, we developed SydneyMTL, a multi-task deep learning framework that uses Multiple Instance Learning (MIL) with task-specific attention pooling to predict severity grades across all five USS attributes simultaneously. Trained on an unprecedented cohort of 50,765 whole-slide images (WSIs), SydneyMTL generates interpretable histologic evidence for clinical practice. In retrospective evaluations against 24 board-certified pathologists, the model achieved an overall mean lenient accuracy of 89.1%, with 22 pathologists exhibiting >80% agreement with the model. When evaluated on an expert-adjudicated “Golden dataset,” the model’s performance improved to 90.2%, demonstrating its capacity to align with multi-expert consensus and filter individual annotator noise. Latent space analysis confirmed that SydneyMTL captures the ordinal structure of the USS, by representing disease severity as a continuous biological spectrum rather than as disjoint categories. Finally, a randomized crossover reader study showed that AI-assisted review significantly reduced interpretation time and improved inter-observer agreement, establishing SydneyMTL as a scalable tool for supporting standardized gastric cancer risk stratification. Graphical Highlights: SydneyMTL is the first unified framework to simultaneously predict the full 4-tier severity grades across all five Updated Sydney System attributes. Trained on a massive cohort of 50,765 whole slide images, the model aligns with multi-expert consensus on a rigorous “Golden dataset”. AI assistance significantly reduces pathologist reading time and harmonizes inter-observer variability in real-world clinical workflows. Latent space analysis confirms that SydneyMTL preserves the biological ordinality of disease severity without explicit ordinal constraints. The bigger picture: Gastritis is among the most frequent diagnoses in gastrointestinal pathology, and its histologic severity is central to gastric cancer prevention. In routine practice, pathologists convert subtle mucosal changes into semi-quantitative, ordinal grades using the Updated Sydney System, which evaluates five co-existing histologic dimensions. While this framework provides a shared language, grading is labor intensive and inherently dependent on reader-specific thresholds, creating variability that affects risk stratification and surveillance. A key concept motivating our study is that gastritis is not defined by a single finding but by multiple criteria that co-occur and interact. This suggests that computational models should learn these criteria jointly – capturing their biological correlations and the continuum of severity – rather than treating each grade as an isolated classification task. SydneyMTL implements this perspective through a unified multi-task, weakly supervised approach that learns directly from a massive cohort of 50,765 routine whole-slide images. Beyond diagnostic accuracy, our work reveals that the model preserves the ordinality of severity in its representation space, supporting the biological view that discrete clinical categories approximate an underlying continuous biological spectrum. Its attention-based explanations also connect model outputs to interpretable tissue evidence, enhancing clinical trust. Crucially, by harmonizing inter-observer variability, SydneyMTL provides a more reliable foundation for gastric cancer risk assessment, ensuring that premalignant changes are captured with greater consistency. More broadly, our findings reposition AI for gastritis from narrow detection toward scalable, evidence-based decision support that can standardize grading practices and reduce cognitive burden on the global pathology workforce.
- Open Access
- 1 January 2026
- Published by XMLink in Journal of Gastric Cancer
- Vol. 26 (2) , 247-259
Tumor-Associated Macrophage Infiltration and PD-L1 Expression in Gastric Cancer According to a Modified TCGA-Based Classification
Song B, et al. J Gastric Cancer. 2026 Apr;26(2):247-259. https://doi.org/10.5230/jgc.2026.26.e3
- 1 January 2026
- Published by XMLink in Journal of Gastric Cancer
- Vol. 26 (2) , 247-259
Open AccessTumor-Associated Macrophage Infiltration and PD-L1 Expression in Gastric Cancer According to a Modified TCGA-Based Classification
Song B, et al. J Gastric Cancer. 2026 Apr;26(2):247-259. https://doi.org/10.5230/jgc.2026.26.e3
- Open Access
Multimodal Approach for Identification and Validation of Hepatocellular Carcinoma Targets for Radiotheranostics
Identifying tumor selective targets is critical for the development of precision diagnostic and therapeutic agents in oncology. Despite advances in precision oncology elsewhere, there are no FDA-approved hepatocellular carcinoma (HCC)-selective treatments. HCC is the most common type of liver cancer and accounts for significant morbidity and mortality worldwide. Here, we sought to integrate bulk (371 cases) and single cell RNA sequencing (scRNAseq, n =2 datasets, 34 cases, 102,956 cells) of patient samples to enrich for molecules that are overexpressed in HCC, which could serve as HCC-selective targets. To guide definitions of tumor and normal cell clusters with higher fidelity, we also imported a normal liver scRNAseq dataset. Using this integrated approach, we identified several HCC-selective plasma membrane molecules. To validate these targets, we performed immunohistochemical staining of HCC and normal tissue microarrays and confirmed HCC-selective staining of identified targets. Next, we verified the presence of these targets in several commercially available HCC cell lines by flow cytometry and western blot. Finally, we designed, engineered, and tested novel antibody-based positron emission tomography (immunoPET) agents to these targets in various murine models of liver cancer. Our findings confirm that we can leverage this multimodal approach to identify and validate of HCC-selective targets, which can be used to develop tumor-selective diagnostic and therapeutic radiopharmaceuticals, or radiotheranostics, and other precision oncology agents. One Sentence Summary: A multimodal pipeline defines and validates tumor-selective surface targets for radiotheranostic use in hepatocellular carcinoma.
Open AccessMultimodal Approach for Identification and Validation of Hepatocellular Carcinoma Targets for Radiotheranostics
Identifying tumor selective targets is critical for the development of precision diagnostic and therapeutic agents in oncology. Despite advances in precision oncology elsewhere, there are no FDA-approved hepatocellular carcinoma (HCC)-selective treatments. HCC is the most common type of liver cancer and accounts for significant morbidity and mortality worldwide. Here, we sought to integrate bulk (371 cases) and single cell RNA sequencing (scRNAseq, n =2 datasets, 34 cases, 102,956 cells) of patient samples to enrich for molecules that are overexpressed in HCC, which could serve as HCC-selective targets. To guide definitions of tumor and normal cell clusters with higher fidelity, we also imported a normal liver scRNAseq dataset. Using this integrated approach, we identified several HCC-selective plasma membrane molecules. To validate these targets, we performed immunohistochemical staining of HCC and normal tissue microarrays and confirmed HCC-selective staining of identified targets. Next, we verified the presence of these targets in several commercially available HCC cell lines by flow cytometry and western blot. Finally, we designed, engineered, and tested novel antibody-based positron emission tomography (immunoPET) agents to these targets in various murine models of liver cancer. Our findings confirm that we can leverage this multimodal approach to identify and validate of HCC-selective targets, which can be used to develop tumor-selective diagnostic and therapeutic radiopharmaceuticals, or radiotheranostics, and other precision oncology agents. One Sentence Summary: A multimodal pipeline defines and validates tumor-selective surface targets for radiotheranostic use in hepatocellular carcinoma.
- Open Access
- 17 September 2025
- Published by Elsevier in Journal of Pathology Informatics
- Vol. 19
Evaluating the robustness of slide-level AI predictions on out-of-focus whole slide images: A retrospective observational study
- 17 September 2025
- Published by Elsevier in Journal of Pathology Informatics
- Vol. 19
Open AccessEvaluating the robustness of slide-level AI predictions on out-of-focus whole slide images: A retrospective observational study
- Open Access
Priority-Aware Clinical Pathology Hierarchy Training for Multiple Instance Learning
Multiple Instance Learning (MIL) is increasingly being used as a support tool within clinical settings for pathological diagnosis decisions, achieving high performance and removing the annotation burden. However, existing approaches for clinical MIL tasks have not adequately addressed the priority issues that exist in relation to pathological symptoms and diagnostic classes, causing MIL models to ignore priority among classes. To overcome this clinical limitation of MIL, we propose a new method that addresses priority issues using two hierarchies: vertical inter-hierarchy and horizontal intra-hierarchy. The proposed method aligns MIL predictions across each hierarchical level and employs an implicit feature re-usability during training to facilitate clinically more serious classes within the same level. Experiments with real-world patient data show that the proposed method effectively reduces misdiagnosis and prioritizes more important symptoms in multiclass scenarios. Further analysis verifies the efficacy of the proposed components and qualitatively confirms the MIL predictions against challenging cases with multiple symptoms.
Open AccessPriority-Aware Clinical Pathology Hierarchy Training for Multiple Instance Learning
Multiple Instance Learning (MIL) is increasingly being used as a support tool within clinical settings for pathological diagnosis decisions, achieving high performance and removing the annotation burden. However, existing approaches for clinical MIL tasks have not adequately addressed the priority issues that exist in relation to pathological symptoms and diagnostic classes, causing MIL models to ignore priority among classes. To overcome this clinical limitation of MIL, we propose a new method that addresses priority issues using two hierarchies: vertical inter-hierarchy and horizontal intra-hierarchy. The proposed method aligns MIL predictions across each hierarchical level and employs an implicit feature re-usability during training to facilitate clinically more serious classes within the same level. Experiments with real-world patient data show that the proposed method effectively reduces misdiagnosis and prioritizes more important symptoms in multiclass scenarios. Further analysis verifies the efficacy of the proposed components and qualitatively confirms the MIL predictions against challenging cases with multiple symptoms.