Searcharxiv⌕ Search

arXiv subjects

Won-Ki Jeong

Publications and source records attributed to Won-Ki Jeong.

At least 19 recordsLinked to original sources
arXiv2026

LanGuSTE: Language-Guided Coarse-to-Fine Patch Selection for Efficient Whole Slide Image Analysis

Whole slide images (WSIs) in computational pathology pose a major computational challenge due to their gigapixel scale, often requiring tens to hundreds of thousands of high-resolution patches to be processed per slide. In conventional WSI pipelines, exhaustive high-resolution patch processing makes preprocessing far more time-consuming than downstream model training. Existing patch selection methods suffer from a fundamental paradox: all patches must still be extracted and encoded at least during training, and sometimes during both training and inference, before irrelevant ones can be discarded. To address this, we propose LanGuSTE, an efficient patch selection framework that integrates pathology-domain vision-language models (VLMs) and knowledge derived from large language models (LLMs) through two key modules: Cross- Scale Visual Prompt Tuning (CS-VPT) and coarse-to-fine patch selection. CS-VPT aligns low-resolution patches with their spatially corresponding high-resolution patches through contrastive learning, transferring fine-grained diagnostic semantics into low-resolution representations. The patch selection module then leverages VLM representations and LLM-generated pathology-specific descriptions to identify informative regions in a coarse-to-fine manner, encoding only the corresponding high-resolution patches to reduce preprocessing time. Extensive experiments demonstrate that LanGuSTE reduces overall WSI processing time to approximately 3x while achieving diagnostic performance comparable to or better than exhaustive patch processing and recent state-of-the-art patch-selection methods.

cs.CV↗
arXiv2026

ESVR: 3D Ellipsoid-based Sparse Volume Rendering via Structure-aware Primitive Learning and Per-primitive Ray Sampling

Efficient representation and rendering of large-scale sparse volumetric data remain challenging in scientific visualization, as meaningful structures often occupy only a small fraction of the spatial domain. While direct volume rendering (DVR) provides high-quality visualization, its computational and memory costs scale poorly with data size. Recent advances in 3D Gaussian Splatting (3DGS) address this challenge by representing volumetric scenes with compact geometric primitives, enabling efficient, high-fidelity rendering. However, existing 3DGS-based methods learn from DVR rendered images rather than raw volumes, leading to information loss and limiting flexible transfer function control for interactive exploration. To address these limitations, we propose ESVR, an ellipsoid-based sparse volume rendering framework that directly learns and renders volumetric data in 3D space. Our method combines differentiable ellipsoidal primitives with bounded support, structure-aware primitive learning with complementary pruning, and a per-primitive ray sampling strategy for fast and accurate transfer function mapping. To support large-scale datasets, we further introduce a chunk-based optimization scheme with ghost ellipsoids, providing boundary context during training. Across large sparse datasets, ESVR achieves up to four orders of magnitude compression and real-time rendering at 43-223 FPS while maintaining competitive reconstruction quality.

cs.GR↗
arXiv2026

Super-Gaussian: Interactive Scene Editing for 3D Gaussian Splatting and NLI-Based Volume Visualization in Virtual Reality

Despite the promise of virtual reality (VR) for intuitive spatial interaction, volume visualization (VolVis) in VR remains constrained by high rendering costs and motion discomfort. Recent advances have shown that representing volumetric scenes with 3D Gaussian splatting enables high-performance rendering, making this representation well-suited for VR. However, existing Gaussian-based scene editing workflows remain limited by slow offline segmentation and fatigue-inducing manual selection. To address these challenges, we present Super-Gaussian, a novel VolVis framework that enhances scene editing and interaction in VR through intuitive 3D Gaussian selection and natural language interaction (NLI). Our approach groups Gaussian primitives into higher-level units via feature-aware clustering, enabling efficient selection of complex volumetric regions, such as tumors in medical images or filaments in cosmological data, without point-by-point interaction. Building on this, we introduce a hierarchical select-and-refine workflow that combines random-walk-based region propagation, cluster selection, and point refinement, allowing users to progressively specify regions of interest with reduced effort. We further support on-the-fly text labeling of selected regions using NLI, allowing users to semantically query, interpret, and manipulate content within a visualization-perception-action loop. By integrating multimodal interaction, including speech, visual feedback, and spatial manipulation in VR, our framework supports intuitive exploration, editing, and scientific analysis of volumetric data. We demonstrate the effectiveness of Super-Gaussian through four case studies, quantitative selection benchmarks against existing Gaussian-based techniques, and system-level evaluations. Implementation details and experiments can be found on the project page: https://smin0136.github.io/super-gaussian-project/

cs.HC↗
arXiv2026

LaGuadia: Language-Guided Adaptive Distillation from Pathology Foundation Models

Pathology Foundation Models (PFMs) offer powerful Whole Slide Image (WSI) representations but suffer from massive computational costs. While Knowledge Distillation (KD) can create efficient student models, existing multi-teacher methods often use suboptimal uniform weighting that ignores tissue heterogeneity. We propose LaGuadia (Language-Guided Adaptive DistillAtion), a framework that develops a compact pathology image encoder by dynamically integrating expertise from multiple PFMs under clinical linguistic guidance. Our approach utilizes a multi-stage pipeline: first, extracting visually observable clinical keywords from pathology reports; second, aligning visual features with these keywords via a Vision-Language meta-teacher (MedSigLIP) to provide dense semantic guidance; and finally, performing adaptive KD where teacher contributions are weighted based on their semantic alignment with the clinical narrative. Experiments on WSI captioning, visual question answering, and slide-level classification tasks demonstrate that an 87M parameter LaGuadia student model matches or exceeds foundation-scale models such as GigaPath and UNI, achieving strong factual consistency and robust generalization. These results highlight clinical language as an effective semantic anchor for building efficient and reliable digital pathology systems. Code is available at https://github.com/hvcl/LaGuadia.

cs.CV↗
arXiv2026

LRMIL: Efficient Low-Resolution Multiple Instance Learning via High-Resolution Knowledge Distillation for Whole Slide Image Classification

Multiple instance learning (MIL) has become a standard paradigm for whole slide image (WSI) analysis in digital pathology, as it enables slide-level prediction without dense annotations. Existing MIL methods typically rely on exhaustive extraction and encoding of high-resolution patches. However, this practice suffers from two critical limitations in real-world clinical settings: it struggles to capture global visual cues at lower magnifications, and incurs substantial computational overhead due to the massive number of high-resolution patches per slide. To address these limitations, we propose an efficient low-resolution multiple instance learning (LRMIL) framework that transfers high-resolution knowledge to low-resolution representations. LRMIL adopts a two-stage distillation strategy. First, patch-level cross-resolution distillation aligns low-resolution patch embeddings with high-resolution representations. Second, slide-level knowledge distillation trains a low-resolution student MIL model under both slide-level supervision and teacher guidance. At inference time, LRMIL operates exclusively on low-resolution patches, substantially reducing data preprocessing and computational cost. Extensive experiments on multiple WSI benchmarks demonstrate that LRMIL consistently outperforms state-of-the-art MIL methods while achieving more efficient inference. These results highlight LRMIL as a practical and scalable solution for WSI analysis in clinical pathology.

cs.CV↗
arXiv2026

Zero-shot CT Super-Resolution using Diffusion-based 2D Projection Priors and Signed 3D Gaussians

Computed tomography (CT) is important in clinical diagnosis, but acquiring high-resolution (HR) CT is constrained by radiation exposure risks. While deep learning-based super-resolution (SR) methods have shown promise for reconstructing HR CT from low-resolution (LR) inputs, supervised approaches require paired datasets that are often unavailable. Zero-shot methods address this limitation by operating on single LR inputs; however, they frequently fail to recover fine structural details due to limited LR information within individual volumes. To overcome these limitations, we propose a novel zero-shot 3D CT SR framework that integrates diffusion-based upsampled 2D projection priors into the 3D reconstruction process. Specifically, our framework consists of two stages: (1) LR CT projection SR, training a diffusion model on abundant X-ray data to upsample LR projections, thereby enhancing the scarce information inherent in the LR inputs. (2) 3D CT volume reconstruction, using 3D Gaussian splatting with our novel Negative Alpha Blending (NAB-GS), which models positive and negative Gaussian densities to learn signed residuals between diffusion-generated HR and upsampled LR projections. Our framework demonstrates superior quantitative and qualitative performance on two public datasets, and expert evaluations present the framework's clinical potential at 4x.

eess.IV↗
arXiv2026

Virtual Multiplex Staining for Histological Images using a Marker-wise Conditioned Diffusion Model

Multiplex imaging is revolutionizing pathology by enabling the simultaneous visualization of multiple biomarkers within tissue samples, providing molecular-level insights that traditional hematoxylin and eosin (H&E) staining cannot provide. However, the complexity and cost of multiplex data acquisition have hindered its widespread adoption. Additionally, most existing large repositories of H&E images lack corresponding multiplex images, limiting opportunities for multimodal analysis. To address these challenges, we leverage recent advances in latent diffusion models (LDMs), which excel at modeling complex data distributions by utilizing their powerful priors for fine-tuning to a target domain. In this paper, we introduce a novel framework for virtual multiplex staining that utilizes pretrained LDM parameters to generate multiplex images from H&E images using a conditional diffusion model. Our approach enables marker-by-marker generation by conditioning the diffusion model on each marker, while sharing the same architecture across all markers. To tackle the challenge of varying pixel value distributions across different marker stains and to improve inference speed, we fine-tune the model for single-step sampling, enhancing both color contrast fidelity and inference efficiency through pixel-level loss functions. We validate our framework on two publicly available datasets, notably demonstrating its effectiveness in generating up to 18 different marker types with improved accuracy, a substantial increase over the 2-3 marker types achieved in previous approaches. This validation highlights the potential of our framework, pioneering virtual multiplex staining. Finally, this paper bridges the gap between H&E and multiplex imaging, potentially enabling retrospective studies and large-scale analyses of existing H&E image repositories.

eess.IV↗
arXiv2025

XROps: A Visual Workflow Management System for Dynamic Immersive Analytics

Immersive analytics is gaining attention across multiple domains due to its capability to facilitate intuitive data analysis in expansive environments through user interaction with data. However, creating immersive analytics systems for specific tasks is challenging due to the need for programming expertise and significant development effort. Despite the introduction of various immersive visualization authoring toolkits, domain experts still face hurdles in adopting immersive analytics into their workflow, particularly when faced with dynamically changing tasks and data in real time. To lower such technical barriers, we introduce XROps, a web-based authoring system that allows users to create immersive analytics applications through interactive visual programming, without the need for low-level scripting or coding. XROps enables dynamic immersive analytics authoring by allowing users to modify each step of the data visualization process with immediate feedback, enabling them to build visualizations on-the-fly and adapt to changing environments. It also supports the integration and visualization of real-time sensor data from XR devices, a key feature of immersive analytics, facilitating the creation of various analysis scenarios. We evaluated the usability of XROps through a user study and demonstrate its efficacy and usefulness in several example scenarios. We have released a web platform (https://vience.io/xrops) to demonstrate various examples to supplement our findings.

cs.HC↗
arXiv2025

MC-INR: Efficient Encoding of Multivariate Scientific Simulation Data using Meta-Learning and Clustered Implicit Neural Representations

Implicit Neural Representations (INRs) are widely used to encode data as continuous functions, enabling the visualization of large-scale multivariate scientific simulation data with reduced memory usage. However, existing INR-based methods face three main limitations: (1) inflexible representation of complex structures, (2) primarily focusing on single-variable data, and (3) dependence on structured grids. Thus, their performance degrades when applied to complex real-world datasets. To address these limitations, we propose a novel neural network-based framework, MC-INR, which handles multivariate data on unstructured grids. It combines meta-learning and clustering to enable flexible encoding of complex structures. To further improve performance, we introduce a residual-based dynamic re-clustering mechanism that adaptively partitions clusters based on local error. We also propose a branched layer to leverage multivariate data through independent branches simultaneously. Experimental results demonstrate that MC-INR outperforms existing methods on scientific data encoding tasks.

cs.CV↗
arXiv2025

Synthetic Data Augmentation using Pre-trained Diffusion Models for Long-tailed Food Image Classification

Deep learning-based food image classification enables precise identification of food categories, further facilitating accurate nutritional analysis. However, real-world food images often show a skewed distribution, with some food types being more prevalent than others. This class imbalance can be problematic, causing models to favor the majority (head) classes with overall performance degradation for the less common (tail) classes. Recently, synthetic data augmentation using diffusion-based generative models has emerged as a promising solution to address this issue. By generating high-quality synthetic images, these models can help uniformize the data distribution, potentially improving classification performance. However, existing approaches face challenges: fine-tuning-based methods need a uniformly distributed dataset, while pre-trained model-based approaches often overlook inter-class separation in synthetic data. In this paper, we propose a two-stage synthetic data augmentation framework, leveraging pre-trained diffusion models for long-tailed food classification. We generate a reference set conditioned by a positive prompt on the generation target and then select a class that shares similar features with the generation target as a negative prompt. Subsequently, we generate a synthetic augmentation set using positive and negative prompt conditions by a combined sampling strategy that promotes intra-class diversity and inter-class separation. We demonstrate the efficacy of the proposed method on two long-tailed food benchmark datasets, achieving superior performance compared to previous works in terms of top-1 accuracy.

cs.CV↗
arXiv2024

Clinical-grade Multi-Organ Pathology Report Generation for Multi-scale Whole Slide Images via a Semantically Guided Medical Text Foundation Model

Vision language models (VLM) have achieved success in both natural language comprehension and image recognition tasks. However, their use in pathology report generation for whole slide images (WSIs) is still limited due to the huge size of multi-scale WSIs and the high cost of WSI annotation. Moreover, in most of the existing research on pathology report generation, sufficient validation regarding clinical efficacy has not been conducted. Herein, we propose a novel Patient-level Multi-organ Pathology Report Generation (PMPRG) model, which utilizes the multi-scale WSI features from our proposed multi-scale regional vision transformer (MR-ViT) model and their real pathology reports to guide VLM training for accurate pathology report generation. The model then automatically generates a report based on the provided key features attended regional features. We assessed our model using a WSI dataset consisting of multiple organs, including the colon and kidney. Our model achieved a METEOR score of 0.68, demonstrating the effectiveness of our approach. This model allows pathologists to efficiently generate pathology reports for patients, regardless of the number of WSIs involved.

cs.CV↗
arXiv2024

Co-synthesis of Histopathology Nuclei Image-Label Pairs using a Context-Conditioned Joint Diffusion Model

In multi-class histopathology nuclei analysis tasks, the lack of training data becomes a main bottleneck for the performance of learning-based methods. To tackle this challenge, previous methods have utilized generative models to increase data by generating synthetic samples. However, existing methods often overlook the importance of considering the context of biological tissues (e.g., shape, spatial layout, and tissue type) in the synthetic data. Moreover, while generative models have shown superior performance in synthesizing realistic histopathology images, none of the existing methods are capable of producing image-label pairs at the same time. In this paper, we introduce a novel framework for co-synthesizing histopathology nuclei images and paired semantic labels using a context-conditioned joint diffusion model. We propose conditioning of a diffusion model using nucleus centroid layouts with structure-related text prompts to incorporate spatial and structural context information into the generation targets. Moreover, we enhance the granularity of our synthesized semantic labels by generating instance-wise nuclei labels using distance maps synthesized concurrently in conjunction with the images and semantic labels. We demonstrate the effectiveness of our framework in generating high-quality samples on multi-institutional, multi-organ, and multi-modality datasets. Our synthetic data consistently outperforms existing augmentation methods in the downstream tasks of nuclei segmentation and classification.

cs.CV↗
arXiv2024

Reference-free Axial Super-resolution of 3D Microscopy Images using Implicit Neural Representation with a 2D Diffusion Prior

Analysis and visualization of 3D microscopy images pose challenges due to anisotropic axial resolution, demanding volumetric super-resolution along the axial direction. While training a learning-based 3D super-resolution model seems to be a straightforward solution, it requires ground truth isotropic volumes and suffers from the curse of dimensionality. Therefore, existing methods utilize 2D neural networks to reconstruct each axial slice, eventually piecing together the entire volume. However, reconstructing each slice in the pixel domain fails to give consistent reconstruction in all directions leading to misalignment artifacts. In this work, we present a reconstruction framework based on implicit neural representation (INR), which allows 3D coherency even when optimized by independent axial slices in a batch-wise manner. Our method optimizes a continuous volumetric representation from low-resolution axial slices, using a 2D diffusion prior trained on high-resolution lateral slices without requiring isotropic volumes. Through experiments on real and synthetic anisotropic microscopy images, we demonstrate that our method surpasses other state-of-the-art reconstruction methods. The source code is available on GitHub: https://github.com/hvcl/INR-diffusion.

eess.IV↗
arXiv2024

Controllable and Efficient Multi-Class Pathology Nuclei Data Augmentation using Text-Conditioned Diffusion Models

In the field of computational pathology, deep learning algorithms have made significant progress in tasks such as nuclei segmentation and classification. However, the potential of these advanced methods is limited by the lack of available labeled data. Although image synthesis via recent generative models has been actively explored to address this challenge, existing works have barely addressed label augmentation and are mostly limited to single-class and unconditional label generation. In this paper, we introduce a novel two-stage framework for multi-class nuclei data augmentation using text-conditional diffusion models. In the first stage, we innovate nuclei label synthesis by generating multi-class semantic labels and corresponding instance maps through a joint diffusion model conditioned by text prompts that specify the label structure information. In the second stage, we utilize a semantic and text-conditional latent diffusion model to efficiently generate high-quality pathology images that align with the generated nuclei label images. We demonstrate the effectiveness of our method on large and diverse pathology nuclei datasets, with evaluations including qualitative and quantitative analyses, as well as assessments of downstream tasks.

cs.CV↗
arXiv2023

Evaluation and improvement of Segment Anything Model for interactive histopathology image segmentation

With the emergence of the Segment Anything Model (SAM) as a foundational model for image segmentation, its application has been extensively studied across various domains, including the medical field. However, its potential in the context of histopathology data, specifically in region segmentation, has received relatively limited attention. In this paper, we evaluate SAM's performance in zero-shot and fine-tuned scenarios on histopathology data, with a focus on interactive segmentation. Additionally, we compare SAM with other state-of-the-art interactive models to assess its practical potential and evaluate its generalization capability with domain adaptability. In the experimental results, SAM exhibits a weakness in segmentation performance compared to other models while demonstrating relative strengths in terms of inference time and generalization capability. To improve SAM's limited local refinement ability and to enhance prompt stability while preserving its core strengths, we propose a modification of SAM's decoder. The experimental results suggest that the proposed modification is effective to make SAM useful for interactive histology image segmentation. The code is available at \url{https://github.com/hvcl/SAM_Interactive_Histopathology}

cs.CV↗
arXiv2023

Reference-Free Isotropic 3D EM Reconstruction using Diffusion Models

Electron microscopy (EM) images exhibit anisotropic axial resolution due to the characteristics inherent to the imaging modality, presenting challenges in analysis and downstream tasks.In this paper, we propose a diffusion-model-based framework that overcomes the limitations of requiring reference data or prior knowledge about the degradation process. Our approach utilizes 2D diffusion models to consistently reconstruct 3D volumes and is well-suited for highly downsampled data. Extensive experiments conducted on two public datasets demonstrate the robustness and superiority of leveraging the generative prior compared to supervised learning methods. Additionally, we demonstrate our method's feasibility for self-supervised reconstruction, which can restore a single anisotropic volume without any training data.

cs.CV↗
arXiv2023

CGAM: Click-Guided Attention Module for Interactive Pathology Image Segmentation via Backpropagating Refinement

Tumor region segmentation is an essential task for the quantitative analysis of digital pathology. Recently presented deep neural networks have shown state-of-the-art performance in various image-segmentation tasks. However, because of the unclear boundary between the cancerous and normal regions in pathology images, despite using modern methods, it is difficult to produce satisfactory segmentation results in terms of the reliability and accuracy required for medical data. In this study, we propose an interactive segmentation method that allows users to refine the output of deep neural networks through click-type user interactions. The primary method is to formulate interactive segmentation as an optimization problem that leverages both user-provided click constraints and semantic information in a feature map using a click-guided attention module (CGAM). Unlike other existing methods, CGAM avoids excessive changes in segmentation results, which can lead to the overfitting of user clicks. Another advantage of CGAM is that the model size is independent of input image size. Experimental results on pathology image datasets indicated that our method performs better than existing state-of-the-art methods.

cs.CV↗
arXiv2023

Histopathology Image Classification using Deep Manifold Contrastive Learning

Contrastive learning has gained popularity due to its robustness with good feature representation performance. However, cosine distance, the commonly used similarity metric in contrastive learning, is not well suited to represent the distance between two data points, especially on a nonlinear feature manifold. Inspired by manifold learning, we propose a novel extension of contrastive learning that leverages geodesic distance between features as a similarity metric for histopathology whole slide image classification. To reduce the computational overhead in manifold learning, we propose geodesic-distance-based feature clustering for efficient contrastive loss evaluation using prototypes without time-consuming pairwise feature similarity comparison. The efficacy of the proposed method is evaluated on two real-world histopathology image datasets. Results demonstrate that our method outperforms state-of-the-art cosine-distance-based contrastive learning methods.

cs.CV↗