Computational Pathology Detection of Hypoxia-Induced Morphologic Changes in Breast Cancer

Abstract

Understanding the tumor hypoxic microenvironment is crucial for grasping tumor biology, clinical progression, and treatment responses. This study presents a novel application of artificial intelligence in computational histopathology to evaluate hypoxia in breast cancer. Weakly supervised deep learning models can accurately detect morphologic changes associated with hypoxia in routine hematoxylin and eosin (H&E)-stained whole slide images (WSIs). The HypOxNet model was trained on H&E-stained WSIs from breast cancer primary sites (n = 1016) at ×40 magnification using data from The Cancer Genome Atlas. Hypoxia Buffa signature was used to measure hypoxia scores, which ranged from -43 to 47, and stratified the samples into hypoxic and normoxic based on these scores. This stratification represented the weak labels associated with each WSI. HypOxNet achieved an average area under the curve of 0.82 on test sets, identifying significant differences in cell morphology between hypoxic and normoxic tissue regions. Importantly, once trained, the HypOxNet model required only the readily available H&E-stained slides, making it especially valuable in low-resource settings where additional gene expression assays are not available. These artificial intelligence-based hypoxia detection models can potentially be extended to other tumor types and seamlessly integrated into pathology workflows, offering a fast, cost-effective alternative to molecular testing.

Graphical abstract

Figure 1

Hypoxia prediction neural network (HypOxNet). A: Approach. Whole slide images (WSIs) of breast biopsies from The Cancer Genome Atlas database are first divided into small tiles. Bags of tiles are passed through a multiple instance learning convolutional neural network with an attention pooling layer. The network is trained to classify the bags of tiles as hypoxic or normoxic, according to their hypoxia signature.B: Hypoxia score distribution. Samples with a positive score were considered as hypoxic, whereas the remaining ones were considered as normoxic. C: Average areas under the receiver operating characteristic curve (AUROCs) on the left-out test set for all (Buffa score >0), low (20 > Buffa score > 0), and high (Buffa score >20). D: Additional performance metrics on the test sets. Performance on the training sets is shown in Supplemental Figure S2. n = 253 (with 3 random train-test splits; C). Original magnification, ×40 (A).

Figure 2

Tile-level texture analysis. A and D: Examples of tiles classified by HypOxNet as normoxic. B and E: Examples of tiles classified by HypOxNet as hypoxic. C and F: Corresponding class activation maps overlayed on the hypoxic tiles. G–I: Gray-level co-occurrence matrix–based texture feature box plots of individual tiles (size = 512 × 512) classified as hypoxic (orange) and normoxic (blue). Additional texture feature comparison can be found in Supplemental Figure S4. n = 576 (G–I). ∗∗∗∗P < 0.0001. Original magnification, ×40 (A–F).

Figure 3

Cell-level shape analysis of epithelial cells from the MoNuSaC annotated data set.A: Example of tiles containing epithelial cells classified by HypOxNet as normoxic. B and C: Examples of tiles classified by HypOxNet as hypoxic. D–F: Corresponding class activation maps overlayed on the tiles. G–I: Box plots of binary shape descriptors of epithelial cells in tiles classified as normoxic (blue) and hypoxic (orange) by the deep learning model. Shape descriptors were computed using the implementation available (https://scikit-image.org/docs/stable/api/skimage.measure.html#skimage.measure.regionprops, last accessed December 9, 2024). Additional shape feature comparison can be found in Supplemental Figure S5. n = 2560 (G–I). ∗∗∗∗P < 0.0001. Original magnification, ×40 (A–F).

Figure 4

Cell-level shape analysis of macrophae cells from the MoNuSaC annotated data set.A: Example of tiles containing macrophages classified by HypOxNet as normoxic. B and C: Examples of tiles classified by HypOxNet as hypoxic. D–F: Corresponding class activation maps overlayed on the tiles. G–I: Box plots of binary shape descriptors of epithelial cells in tiles classified as normoxic (blue) and hypoxic (orange) by the deep learning model. Shape descriptors were computed using the implementation available (https://scikit-image.org/docs/stable/api/skimage.measure.html#skimage.measure.regionprops, last accessed December 9, 2024). Additional shape feature comparison can be found in Supplemental Figure S6. n = 96 (G–I). ∗∗∗P < 0.001, ∗∗∗∗P < 0.0001. Original magnification, ×40 (A–F).