| Sumario: | Simple Summary: Breast cancer treatment response is influenced not only by cancer cells but also by the surrounding tissue environment. In this preclinical study, we tested whether information contained in immunofluorescence images from a 4T1 mouse breast cancer model could help distinguish therapy responders from non-responders. We analysed 1696 images covering nine tissue-marker panels and compared image-based deep learning with machine learning models trained on quantitative image features. The strongest signal came from extracellular-matrix markers, especially collagen and hyaluronic acid. In animals with matched hypoxia and extracellular-matrix images, collagen and hyaluronic-acid features outperformed hypoxia, and adding hypoxia did not improve prediction. These findings suggest that quantitative tissue architecture is a useful preclinical biomarker source, but the results require validation in independent animal experiments and human tumour tissue before clinical use. Background/Objectives: Histological biomarkers of therapy response remain incompletely defined in preclinical breast cancer models. We evaluated whether quantitative immunofluorescence imaging and multimodal machine learning (ML) could identify image-derived tissue biomarkers associated with response in a 4T1 murine breast cancer therapy-response setting. Methods: We analysed 1696 immunofluorescence images across nine immunofluorescence staining panels: aPDL1, alpha-smooth muscle actin-CD31, alpha-smooth muscle actin-Ki67, CD3-CD31, CD8-Ki67, collagen–hyaluronic acid (HA), granzyme B-CD8, HMGB1, and pimonidazole/hypoxia. A Python image-analysis algorithm extracted 117 RGB-channel, intensity, morphometric, and cross-channel spatial features per image. The modelling framework included image-only deep learning (DL), tabular ML on extracted histological features, and image-plus-tabular gated fusion. Models were evaluated using stratified cross-validation, train-fold-only class balancing, bootstrap confidence intervals, permutation testing, nested feature-selection sensitivity analysis, and grouped leakage controls. Results: Histological staining panels classified treatment-response status across the nine-panel benchmark. Collagen–HA was the strongest staining (AUC 0.954), followed by alpha-smooth muscle actin-Ki67 (AUC 0.851) and hypoxia (AUC 0.837). DL achieved the best performance in eight of nine stainings. In 346 collagen–HA images, combined collagen and HA features achieved AUC 0.848, collagen-only features AUC 0.833, and hyaluronic-acid-only features AUC 0.805. In 104 animals with matched hypoxia and collagen–hyaluronic-acid images, extracellular-matrix features achieved AUC 0.985, hypoxia-only features achieved AUC 0.929, and adding hypoxia did not improve extracellular-matrix-only prediction. Conclusions: Quantitative extracellular-matrix imaging provides a strong preclinical signal for therapy-response stratification in 4T1 breast cancer. The findings are hypothesis-generating and require independent preclinical and human validation before clinical translation.
|
|---|