FTU-Seek: Foundation Model-Guided Hard-Negative Learning for Sparse Functional Tissue Unit Segmentation
为解决稀疏功能性组织单元自动分割难题，开发了FTU-Seek框架，通过基础模型指导的负样本选择方法提高分割准确性。
0 citationsRead paper
Selected work
Representative Papers
Hierarchical Prototype-based Domain Priors for Multiple Instance Learning in Multimodal Histopathology Analysis
Existing multiple instance learning (MIL) approaches treat whole-slide images as unstructured collections of image patches, thereby neglecting the morphological semantics and spatial geometric relationships inherent in tissue architecture. This limitation renders them susceptible to background noise and misaligned with clinical diagnostic reasoning. To address this, this work proposes the HPDP framework, which introduces a Morphology-Anchored Prototype System (MAPS) to explicitly model histological structural semantics, incorporates sinusoidal positional encoding (SPE) to capture spatial geometry, and designs a Hierarchical Cross-Modal Alignment (HCMA) module that leverages pathology descriptions generated by large language models to achieve image–text semantic alignment. Evaluated across seven cancer cohorts, the proposed method significantly improves diagnostic accuracy, robustness, and interpretability, outperforming current state-of-the-art approaches.
0 citationsRead paper
LGD-Net: Latent-Guided Dual-Stream Network for HER2 Scoring with Task-Specific Domain Knowledge
This work proposes LGD-Net, a novel framework for predicting HER2 status directly from hematoxylin and eosin (H&E)-stained whole-slide images without explicitly generating virtual immunohistochemistry (IHC) images. Addressing the high cost and resource dependency of conventional HER2 IHC testing—and circumventing the computational burden and reconstruction artifacts associated with pixel-level virtual staining—LGD-Net leverages a cross-modal feature hallucination mechanism to map H&E morphological features into the latent space of IHC molecular representations. The architecture integrates teacher-guided distillation, a dual-stream design, and lightweight, domain knowledge–driven auxiliary tasks (e.g., nuclear distribution and membrane staining intensity) to enhance both discriminative power and interpretability. Evaluated on the BCI dataset, the method achieves state-of-the-art HER2 scoring performance using only H&E inputs, significantly outperforming existing baselines.
0 citationsRead paper
Recent publications
Latest Papers
FTU-Seek: Foundation Model-Guided Hard-Negative Learning for Sparse Functional Tissue Unit Segmentation
为解决稀疏功能性组织单元自动分割难题，开发了FTU-Seek框架，通过基础模型指导的负样本选择方法提高分割准确性。
0 citationsRead paper
Hierarchical Prototype-based Domain Priors for Multiple Instance Learning in Multimodal Histopathology Analysis
Existing multiple instance learning (MIL) approaches treat whole-slide images as unstructured collections of image patches, thereby neglecting the morphological semantics and spatial geometric relationships inherent in tissue architecture. This limitation renders them susceptible to background noise and misaligned with clinical diagnostic reasoning. To address this, this work proposes the HPDP framework, which introduces a Morphology-Anchored Prototype System (MAPS) to explicitly model histological structural semantics, incorporates sinusoidal positional encoding (SPE) to capture spatial geometry, and designs a Hierarchical Cross-Modal Alignment (HCMA) module that leverages pathology descriptions generated by large language models to achieve image–text semantic alignment. Evaluated across seven cancer cohorts, the proposed method significantly improves diagnostic accuracy, robustness, and interpretability, outperforming current state-of-the-art approaches.
0 citationsRead paper
LGD-Net: Latent-Guided Dual-Stream Network for HER2 Scoring with Task-Specific Domain Knowledge
This work proposes LGD-Net, a novel framework for predicting HER2 status directly from hematoxylin and eosin (H&E)-stained whole-slide images without explicitly generating virtual immunohistochemistry (IHC) images. Addressing the high cost and resource dependency of conventional HER2 IHC testing—and circumventing the computational burden and reconstruction artifacts associated with pixel-level virtual staining—LGD-Net leverages a cross-modal feature hallucination mechanism to map H&E morphological features into the latent space of IHC molecular representations. The architecture integrates teacher-guided distillation, a dual-stream design, and lightweight, domain knowledge–driven auxiliary tasks (e.g., nuclear distribution and membrane staining intensity) to enhance both discriminative power and interpretability. Evaluated on the BCI dataset, the method achieves state-of-the-art HER2 scoring performance using only H&E inputs, significantly outperforming existing baselines.
0 citationsRead paper