Choi, Yoon-Ho

Background: Tumor immune microenvironment (TIME) organization fundamentally shapes cancer progression and immunotherapy outcomes. Traditional 2D spatial molecular approaches inadequately capture the complex three-dimensional architecture and cellular interactions within TIME. We developed an AI-driven platform integrating multiple spatial molecular datasets, enabling comprehensive 3D visualization for therapeutic discovery and patient selection. Methods: Our platform combines holotomography imaging, providing 3D refractive index maps, with diverse spatial molecular data: in situ molecular imaging, spatial proteomics, multiplex immunohistochemistry, and spatial transcriptomics. AI algorithms align datasets within a unified 3D coordinate system, while Poisson implicit surface reconstruction generates subcellular-resolution models. Platform validation used clinical samples from immunotherapy-treated patients. Results: The platform integrated multimodal spatial data into high-resolution 3D TIME representations, revealing novel relationships between protein expression, transcriptional patterns, and cellular architecture. 3D surface protein analysis with subcellular morphology identified patients with target protein expression outside tight junctions, indicating higher risk for adverse effects from antibody-drug conjugates and cellular therapies. This insight, unavailable through 2D analysis, enabled precise patient selection. Conclusions: This platform provides detailed subcellular-resolution TIME architecture analysis, offering actionable insights for therapeutic targeting, biomarker discovery, and patient selection. AI-driven 3D spatial multimodal TIME analysis advances precision medicine across multiple therapeutic approaches, including immunotherapy, targeted therapy, and drug delivery optimization. AI Disclosure: Original abstract content was written by the authors. Claude was used for editorial assistance and formatting without altering the scientific content or context of the work. Citation Format: Inyeop Jang, Yoonho Choi, Minji Kim, Jeonghwan Park, Jiyeon Sung, Byungsoo Ann, Clemenceau R. Jean, TaeHyun Hwang. AI-enabled 3D multimodal integration platform reveals subcellular architecture of tumor immune microenvironment for therapeutic target and biomarker discovery and patient selection [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 3648.

Abstract Background: Recent studies indicate a correlation between increased stromal composition in tumors and resistance to immune checkpoint inhibitors (ICIs) across various cancer types. Specifically, the extracellular matrix (ECM) within the stromal compartment significantly influence the tumor microenvironment, affecting cancer cell proliferation and immune cell recruitment. However, identifying and quantifying the ECM at the collagen fiber level in whole slide images (WSIs) is challenging due to its inherent heterogeneity and complexity. In this work, we utilized statistical analysis and a deep learning (DL)-based approach to identify and assess collagen in the ECM, examining its characteristics in relation to the ICIs treatment response in gastric cancer. Methods: We analyzed 116 WSIs of hematoxylin and eosin (H&E) stained slides before ICIs treatment from three institutions. Responders were defined as those with a complete response or partial response (N=18); those with stable disease (SD) (N=34) or progressive disease (PD) (N=64) were considered non-responders (N=98). For non-responders, post-treatment H&E slides were available for 21 patients; SD (N=5) and PD (N=16). We applied a DL-based second harmonic generation (SHG) synthesis algorithm to tumor regions identified by a tumor detection model. We then calculated various collagen properties, including volume, fiber orientation and alignment, waviness, straightness, and fiber thickness, based on collagen fiber centerlines extracted from the generated SHG images. An attention-based multiple instance learning (ABMIL) model was trained to automatically predict the treatment response solely based on collagen features. The dataset of 116 pre-treatment slides was divided into training and validation subsets using stratified 3-fold cross-validation. The area under the curve (AUC) was used to assess the performance of the trained models. Results: Collagen fiber features were significantly associated with ICIs response. Notably, ICIs responders have a decrease in collagen waviness and fiber orientation variation (p-value<0.05, by Mann-Whitney U test). Among non-responders, the PD group showed a statistical decrease in waviness after treatment (p-value<0.05, by Mann-Whitney U test). The ABMIL model achieved a mean AUC score of 0.823, with a standard deviation of 0.023. Conclusion: This study provides a comprehensive analysis of collagen in the ECM, and its properties in relation to gastric cancer ICIs response within Tumor Immune Microenvironment. We also developed a model using collagen features and demonstrated high accuracy in predicting treatment response. Citation Format: Minji Kim, Ekaterina Redekop, Yoonho Choi, Sung Hak Lee, Jae-Ho Cheong, Yu Aoki, Kohei Shitara, Tae Hyun Hwang. AI-driven analysis of collagen characteristics in the tumor immune microenvironment predicts immune checkpoint inhibitors treatment responsiveness in gastric cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4262.