GHGisu Hwang

Gisu Hwang

*This is an algorithmically generated author record based on publicly available information.

Gisu Hwang has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Comprehensive and reproducible grading of the Updated Sydney System in gastric biopsies using artificial intelligence: multi‐pathologist validation and a reader study

    by Ho Heon Kim, Won Chan Jeong, Yuri Hwang, Gisu Hwang, Kyungeun Kim, Young Sin Ko

    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.


  • Open Access

    SydneyMTL: Interpretable Multi-Task Learning for Complete Sydney System Assessment in Gastric Biopsies

    by Won Chan Jeong, Ho Heon Kim, Yuri Hwang, Gisu Hwang, Kyungeun Kim, Young Sin Ko

    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

    Ranking-Aware Multiple Instance Learning for Histopathology Slide Classification: Development and Validation Study

    by Ho Heon Kim, Gisu Hwang, Won Chan Jeong, Young Sin Ko

    Background: Multiple instance learning (MIL) is widely used for slide-level classification in digital pathology without requiring expert annotations. However, even partial expert annotations offer valuable supervision; few studies have effectively leveraged this information within MIL frameworks. Objective: This study aims to develop and evaluate a ranking-aware MIL framework, called rank induction, that effectively incorporates partial expert annotations to improve slide-level classification performance under realistic annotation constraints. Methods: We developed rank induction, a MIL approach that incorporates expert annotations using a pairwise rank loss inspired by RankNet. The method encourages the model to assign higher attention scores to annotated regions than to unannotated ones, guiding it to focus on diagnostically relevant patches. We evaluated rank induction on 2 public datasets (Camelyon16 and DigestPath2019) and an in-house dataset (Seegene Medical Foundation-stomach; SMF-stomach) and tested its robustness under 3 real-world conditions: low-data regimes, coarse within-slide annotations, and sparse slide-level annotations. Results: Rank induction outperformed existing methodologies, achieving an area under the receiver operating characteristic curve (AUROC) of 0.839 on Camelyon16, 0.995 on DigestPath2019, and 0.875 on SMF-stomach. It remained robust under low-data conditions, maintaining an AUROC of 0.761 with only 60.2% (130/216) of the training data. When using coarse annotations (with 2240-pixel padding), performance slightly declined to 0.823. Remarkably, annotating just 20% (18/89) of the slides was enough to reach near-saturated performance (AUROC of 0.806, vs 0.839 with full annotations). Conclusions: Incorporating expert annotations through ranking-based supervision improves MIL-based classification. Rank induction remains robust even with limited, coarse, or sparsely available annotations, demonstrating its practicality in real-world scenarios.


  • Open Access

    Precise Detection of Peritoneal Metastasis of Gastric and Colorectal Cancer Using Artificial Intelligence of Cytopathologic Whole Slide Images

    by Hyung Kyung Kim, Gisu Hwang, Hongjun Yoon, Daeky Jeong, Won June Cho, Milim Kim, Eunkyung Han, Jeonghyo Lee, Ki Rim Lee, Mohammad Rizwan Alam, et al.

    Kim HK, et al. J Korean Med Sci. 2026 Nov;41:e280. https://doi.org/10.3346/jkms.2026.41.e280

  • Open Access

    Two-Step Ensemble Convolutional Neural Networks for Colonoscopic Biopsy Classification Resembling Pathologists’ Process

    by Hongjun Yoon, Mohammad Rizwan Alam, Nishant Thakur, Sohyun Jeong, Gisu Hwang, Eun Jung Lee, Yosep Chong

    Yoon H, et al. J Korean Med Sci. 2026 Jun;41:e152. https://doi.org/10.3346/jkms.2026.41.e152

  • Open Access

    Ranking-Aware Multiple Instance Learning for Histopathology Slide Classification: Development and Validation Study (Preprint)

    by Ho Heon Kim, Gisu Hwang, Won Chan Jeong, Young Sin Ko

    BACKGROUND Multiple instance learning (MIL) is widely used for slide-level classification in digital pathology without requiring expert annotations. However, even partial expert annotations offer valuable supervision; few studies have effectively leveraged this information within MIL frameworks. OBJECTIVE This study aims to develop and evaluate a ranking-aware MIL framework, called rank induction, that effectively incorporates partial expert annotations to improve slide-level classification performance under realistic annotation constraints. METHODS We developed rank induction, a MIL approach that incorporates expert annotations using a pairwise rank loss inspired by RankNet. The method encourages the model to assign higher attention scores to annotated regions than to unannotated ones, guiding it to focus on diagnostically relevant patches. We evaluated rank induction on 2 public datasets (Camelyon16 and DigestPath2019) and an in-house dataset (Seegene Medical Foundation-stomach; SMF-stomach) and tested its robustness under 3 real-world conditions: low-data regimes, coarse within-slide annotations, and sparse slide-level annotations. RESULTS Rank induction outperformed existing methodologies, achieving an area under the receiver operating characteristic curve (AUROC) of 0.839 on Camelyon16, 0.995 on DigestPath2019, and 0.875 on SMF-stomach. It remained robust under low-data conditions, maintaining an AUROC of 0.761 with only 60.2% (130/216) of the training data. When using coarse annotations (with 2240-pixel padding), performance slightly declined to 0.823. Remarkably, annotating just 20% (18/89) of the slides was enough to reach near-saturated performance (AUROC of 0.806, vs 0.839 with full annotations). CONCLUSIONS Incorporating expert annotations through ranking-based supervision improves MIL-based classification. Rank induction remains robust even with limited, coarse, or sparsely available annotations, demonstrating its practicality in real-world scenarios.