Loading
Ai in Cancer Detection / HER2/EGFR in Cancer Research · Journal article
Diagnostic Pathology · August 11, 2026
Early or partial results. Treat as a signal, not a conclusion.
This is a single-centre retrospective study developing a deep learning model to predict HER2-low status from H&E-stained breast cancer images using ResNet50 and CLAM architecture. The model achieved mean AUC of 0.613 on validation and 0.608 on test sets, with interpretable attention heatmaps, but performance is modest and no external validation or clinical outcome correlation is reported.
Single-centre retrospective diagnostic study with deep learning. Invasive breast carcinoma diagnosed at Affiliated Hospital of Zunyi Medical University, China, between January 2019 and April 2023.. Intervention: Deep learning model (ResNet50 + CLAM) applied to H&E whole-slide images for HER2-low status prediction.. n = 776. Single centre: Affiliated Hospital of Zunyi Medical University, China..
Mean AUC 0.613 ± 0.118 on validation set Mean AUC 0.608 ± 0.104 on test set Attention heatmap visualization provided biologically plausible explanations for predictions
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
This model shows promise for providing decision-support to pathologists in assessing HER2-low status, but modest diagnostic accuracy (AUC ~0.61) and lack of external validation or clinical outcome data limit current clinical utility. Independent validation in other populations and comparison with standard IHC interpretation are needed before deployment.
Single-centre retrospective study with moderate diagnostic accuracy (AUC ~0.61) on a surrogate imaging endpoint; model performance is modest and requires external validation before clinical use.
As stated by the source record.
Quoted from the source exactly as published.
This model shows promise for providing decision-support to pathologists in assessing HER2-low status, but modest diagnostic accuracy (AUC ~0.61) and lack of external validation or clinical outcome data limit current clinical utility. Independent validation in other populations and comparison with standard IHC interpretation are needed before deployment.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
The development and clinical application of novel HER2-targeted antibody-drug conjugates (ADCs) have significantly improved outcomes for breast cancer patients with HER2-low expression. The efficacy of such therapies critically depends on accurate assessment of HER2-low status. However, immunohistochemical (IHC) interpretation of HER2-low breast cancer faces multiple challenges due to tumor heterogeneity and interobserver variability among pathologists. This study aimed to develop a deep learning-based framework for analyzing hematoxylin and eosin (H&E) stained whole-slide images (WSIs) of breast cancer to achieve precise prediction of HER2-low status while providing interpretable evidence. We retrospectively collected 776 cases of invasive breast carcinoma diagnosed at the Affiliated Hospital of Zunyi Medical University between January 2019 and April 2023 to construct a HER2-low expression dataset. Leveraging an ImageNet-pretrained ResNet50 model for feature extraction and a CLAM (Clustering-constrained Attention Multiple Instance Learning) model with 10-fold cross-validation, our framework demonstrated robust performance on both validation and test sets. Critical HER2-low predictive regions were visualized using attention heatmaps to enhance model interpretability. The mean AUC of the model was 0.613 ± 0.118 on the validation set, and 0.608 ± 0.104 on the test set. The attention heatmap visualization provided biologically plausible explanations for model predictions, offering reliable decision-support tools for pathologists.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.