LGD-Net: Latent-Guided Dual-Stream Network for HER2 Scoring with Task-Specific Domain Knowledge

• URL: http://arxiv.org/abs/2602.17793v1
• Date: Thu, 19 Feb 2026 19:51:26 GMT
• Title: LGD-Net: Latent-Guided Dual-Stream Network for HER2 Scoring with Task-Specific Domain Knowledge
• Authors: Peide Zhu, Linbin Lu, Zhiqin Chen, Xiong Chen,
• Abstract summary: It is a critical task to evalaute HER2 expression level accurately for breast cancer evaluation and targeted treatment therapy selection.<n> predicting HER2 levels directly from H&E slides has emerged as a potential alternative solution.<n>We propose the Latent-Guided Dual-Stream Network (LGD-Net), a novel framework that employes cross-modal feature hallucination instead of explicit pixel-level image generation.
• Score: 7.483417319910564
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It is a critical task to evalaute HER2 expression level accurately for breast cancer evaluation and targeted treatment therapy selection. However, the standard multi-step Immunohistochemistry (IHC) staining is resource-intensive, expensive, and time-consuming, which is also often unavailable in many areas. Consequently, predicting HER2 levels directly from H&E slides has emerged as a potential alternative solution. It has been shown to be effective to use virtual IHC images from H&E images for automatic HER2 scoring. However, the pixel-level virtual staining methods are computationally expensive and prone to reconstruction artifacts that can propagate diagnostic errors. To address these limitations, we propose the Latent-Guided Dual-Stream Network (LGD-Net), a novel framework that employes cross-modal feature hallucination instead of explicit pixel-level image generation. LGD-Net learns to map morphological H&E features directly to the molecular latent space, guided by a teacher IHC encoder during training. To ensure the hallucinated features capture clinically relevant phenotypes, we explicitly regularize the model training with task-specific domain knowledge, specifically nuclei distribution and membrane staining intensity, via lightweight auxiliary regularization tasks. Extensive experiments on the public BCI dataset demonstrate that LGD-Net achieves state-of-the-art performance, significantly outperforming baseline methods while enabling efficient inference using single-modality H&E inputs.

Related papers

• SDHSI-Net: Learning Better Representations for Hyperspectral Images via Self-Distillation [20.532231645997864]
  Hyperspectral image (HSI) classification presents unique challenges due to its high spectral dimensionality and limited labeled data.<n>Traditional deep learning models often suffer from overfitting and high computational costs.<n>Self-distillation (SD) is a variant of knowledge distillation where a network learns from its own predictions.
  arXiv  Detail & Related papers  (2026-01-12T10:57:24Z)
• Transforming H&E images into IHC: A Variance-Penalized GAN for Precision Oncology [1.0972875392165036]
  This study proposes an advanced deep learning-based image translation framework to generate highfidelity IHC images from H&E-stained tissue samples.<n>By modifying the loss function of pyramid pix2pix, we mitigate mode collapse, a fundamental limitation in generative adversarial networks (GANs)<n>Our model particularly excels in translating HER2-positive (IHC 3+) images, which have remained challenging for existing methods due to their complex morphological variations.
  arXiv  Detail & Related papers  (2025-06-23T07:57:22Z)
• Fast and Accurate Gigapixel Pathological Image Classification with Hierarchical Distillation Multi-Instance Learning [51.525891360380285]
  HDMIL is a hierarchical distillation multi-instance learning framework that achieves fast and accurate classification by eliminating irrelevant patches.<n> HDMIL consists of two key components: the dynamic multi-instance network (DMIN) and the lightweight instance pre-screening network (LIPN)
  arXiv  Detail & Related papers  (2025-02-28T15:10:07Z)
• Leveraging Transfer Learning and Multiple Instance Learning for HER2 Automatic Scoring of H\&E Whole Slide Images [1.0923877073891446]
  This work is to examine the potential of transfer learning on the performance of deep learning models pre-trained on (i) IHC images, (ii) H&E images and (iii) non-medical images. It was found that embedding models pre-trained on H&E images consistently outperformed the others, resulting in an average AUCROC value of $0.622$ across the 4 HER2 scores.
  arXiv  Detail & Related papers  (2024-11-05T09:44:48Z)
• PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation [51.509573838103854]
  We propose a semi-supervised learning framework, termed Progressive Mean Teachers (PMT), for medical image segmentation. Our PMT generates high-fidelity pseudo labels by learning robust and diverse features in the training process. Experimental results on two datasets with different modalities, i.e., CT and MRI, demonstrate that our method outperforms the state-of-the-art medical image segmentation approaches.
  arXiv  Detail & Related papers  (2024-09-08T15:02:25Z)
• Timestep-Aware Diffusion Model for Extreme Image Rescaling [47.89362819768323]
  We propose a novel framework called Timestep-Aware Diffusion Model (TADM) for extreme image rescaling.<n>TADM performs rescaling operations in the latent space of a pre-trained autoencoder.<n>It effectively leverages powerful natural image priors learned by a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-08-17T09:51:42Z)
• UniForensics: Face Forgery Detection via General Facial Representation [60.5421627990707]
  High-level semantic features are less susceptible to perturbations and not limited to forgery-specific artifacts, thus having stronger generalization. We introduce UniForensics, a novel deepfake detection framework that leverages a transformer-based video network, with a meta-functional face classification for enriched facial representation.
  arXiv  Detail & Related papers  (2024-07-26T20:51:54Z)
• StainDiffuser: MultiTask Dual Diffusion Model for Virtual Staining [1.9029890402585894]
  Hematoxylin and Eosin (H&E) staining is widely regarded as the standard in pathology for diagnosing diseases and tracking tumor recurrence.<n>Hematoxylin and Eosin (H&E) staining is widely regarded as the standard in pathology for diagnosing diseases and tracking tumor recurrence.<n>Despite their value, IHC stains require additional time and resources, limiting their utilization in some clinical settings.<n>Recent advances in deep learning have positioned Image-to-Image (I2I) translation as a computational, cost-effective alternative for IHC.<n>We introduce STAINDIFF, a novel multitask diffusion architecture
  arXiv  Detail & Related papers  (2024-03-17T20:47:52Z)
• Towards Accurate Guided Diffusion Sampling through Symplectic Adjoint Method [110.9458914721516]
  We propose Symplectic Adjoint Guidance (SAG), which calculates the gradient guidance in two inner stages. SAG generates images with higher qualities compared to the baselines in both guided image and video generation tasks.
  arXiv  Detail & Related papers  (2023-12-19T10:30:31Z)
• HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging [138.04956118993934]
  We propose a high-resolution dual-domain learning network (HDNet) for HSI reconstruction. On the one hand, the proposed HR spatial-spectral attention module with its efficient feature fusion provides continuous and fine pixel-level features. On the other hand, frequency domain learning (FDL) is introduced for HSI reconstruction to narrow the frequency domain discrepancy.
  arXiv  Detail & Related papers  (2022-03-04T06:37:45Z)
• Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection [54.92703325989853]
  We propose a two-stage Activation-to-Saliency (A2S) framework that effectively generates high-quality saliency cues. No human annotations are involved in our framework during the whole training process. Our framework reports significant performance compared with existing USOD methods.
  arXiv  Detail & Related papers  (2021-12-07T11:54:06Z)
• Exploiting generative self-supervised learning for the assessment of biological images with lack of annotations: a COVID-19 case-study [0.41998444721319217]
  GAN-DL is a Discriminator Learner based on the StyleGAN2 architecture. We show that our technique can be exploited not only for classification tasks, but also to effectively derive a dose response curve.
  arXiv  Detail & Related papers  (2021-07-16T08:36:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.