Vascular density of histologically benign breast tissue from women with breast cancer: associations with tissue composition and tumor characteristics

Quantifying the tumour vasculature environment from CD-31 immunohistochemistry images of breast cancer using deep learning based semantic segmentation

BACKGROUND

Tumour vascular density assessed from CD-31 immunohistochemistry (IHC) images has previously been shown to have prognostic value in breast cancer. Current methods to measure vascular density, however, are time-consuming, suffer from high inter-observer variability and are limited in describing the complex tumour vasculature morphometry.

METHODS

We propose a method for automatically measuring a range of vascular parameters from CD-31 IHC images, which together provide a detailed description of the vasculature morphology. We first used a U-Net based convolutional neural network, trained and validated using 36 partially annotated whole slide images from 27 patients, to segment vessel structures and tumour regions from which the measurements are taken. The model also segments the vascular smooth muscle, benign epithelium, adipose tissue, stroma, lymphocyte clusters, nerves and CD-31 positive leukocytes, and we applied it to an additional 21 images from 15 patients. Using these segmentations, we investigated the relationship between the various tissue types and the vasculature and studied the relationship of various vascular parameters with clinical parameters. We also performed a 3D histology analysis on a separate tumour sample as a proof of principle, providing a more comprehensive visualization of vasculature morphology compared to the standard 2D cross-section of a tissue sample.

RESULTS

Using two-way cross-validation, we show that vessels were accurately segmented, with Dice scores of 0.875 and 0.856, and were accurately identified, with F1 scores of 0.777 and 0.748. All vascular parameters exhibit strong ( r > 0.7 ) and significant (p<0.001) correlations with measurements taken from the manual ground truth vessel segmentations. A significant relationship between the major/minor axis ratio, a measure of elongation, and the tumour grade was found.

CONCLUSION

Our proposed method shows promise as a tool for studying the tumour vasculature and its relationship with surrounding cells and tissue types. Furthermore, the correlation with tumour grade highlights the clinical relevance of our approach. These findings suggest that our method could have substantial implications for improving prognostic assessments and personalizing therapeutic strategies in breast cancer treatment.

Mammary Microvessels are Sensitive to Menstrual Cycle Sex Hormones

The mammary gland is a highly vascularized organ influenced by sex hormones including estrogen (E2) and progesterone (P4). Beyond whole-organism studies in rodents or cell monocultures, hormonal effects on the breast microvasculature remain largely understudied. Recent methods to generate 3D microvessels on-chip have enabled direct observation of complex vascular processes; however, these models often use non-tissue-specific cell types, such as human umbilical vein endothelial cells (HUVECs) and fibroblasts from various sources. Here, novel mammary-specific microvessels are generated by coculturing primary breast endothelial cells and fibroblasts under optimized culture conditions. These microvessels are mechanosensitive (to interstitial flow) and require endothelial-stromal interactions to develop fully perfusable vessels. These mammary-specific microvessels are also responsive to exogenous stimulation by sex hormones. When treated with combined E2 and P4, corresponding to the four phases of the menstrual cycle (period, follicular, ovular, and luteal), vascular remodeling and barrier function are altered in a phase-dependent manner. The presence of high E2 (ovulation) promotes vascular growth and remodeling, corresponding to high depletion of proangiogenic factors, whereas high P4 concentrations (luteal) promote vascular regression. The effects of combined E2 and P4 hormones are not only dose-dependent but also tissue-specific, as are shown by similarly treating non-tissue-specific HUVEC microvessels.

Remodeling of tumor microenvironment for enhanced tumor chemodynamic/photothermal/chemo-therapy

The anticancer treatment is largely affected by the microenvironment of the tumors, which not only resists the tumors to the thermo/chemo-therapy, but also promotes their growth and invasion. In this work, the angiogenesis factor is balanced by combining with the breathing hyperoxygen, for regulating the tumor microenvironment and also for relieving hypoxia and high tissue interstitial pressure, which promote drug delivery to tumor tissues by increasing the in vivo perfusion and reversing the immunosuppressive tumor. In addition, the designed multifunctional nanoparticles have a great potential for applications to the tumor dual-mode imaging including magnetic resonance (MR) and photoacoustic (PA) imaging. This work proposes a promising strategy to enhance the thermo/chemo-therapy efficacy by remodeling the tumor microenvironment, which would provide an alternative to prolong the lifetime of tumor patients.