Analysis of spatial heterogeneity in normal epithelium and preneoplastic alterations in mouse prostate tumor models

Abstract

Cancer involves histological changes in tissue, which is of primary importance in pathological diagnosis and research. Automated histological analysis requires ability to computationally separate pathological alterations from normal tissue with all its variables. On the other hand, understanding connections between genetic alterations and histological attributes requires development of enhanced analysis methods suitable also for small sample sizes. Here, we set out to develop computational methods for early detection and distinction of prostate cancer-related pathological alterations. We use analysis of features from HE stained histological images of normal mouse prostate epithelium, distinguishing the descriptors for variability between ventral, lateral, and dorsal lobes. In addition, we use two common prostate cancer models, Hi-Myc and Pten+/− mice, to build a feature-based machine learning model separating the early pathological lesions provoked by these genetic alterations. This work offers a set of computational methods for separation of early neoplastic lesions in the prostates of model mice, and provides proof-of-principle for linking specific tumor genotypes to quantitative histological characteristics. The results obtained show that separation between different spatial locations within the organ, as well as classification between histologies linked to different genetic backgrounds, can be performed with very high specificity and sensitivity.

Virtual reality for 3D histology: multi-scale visualization of organs with interactive feature exploration

“…The prostate samples used here have previously been used to develop quantitative histological analysis to computationally study descriptive features and spatial heterogeneity in 2D histological sections [ 33 ]. Here, we computed quantitative histological features and included in the VR to explore them in the 3D context.…”

“…The quantitative hand-crafted features, originally created for use with machine learning algorithms and successfully applied in analysis of mouse prostatic lesions in 2D [ 32 , 33 ], were computed with MATLAB R2017b [ 34 ]. The features include histograms of oriented gradients (HOG) [ 35 ], local binary patterns (LBP) [ 36 ], amount of and distance between nuclei, and intensity features, to name a few.…”

“…The features used in this implementation were pre-computed with MATLAB as previously described [ 32 , 33 ]. MATLAB feature arrays with location information were loaded to Python with scipy module’s loadmat function.…”

3D-Printed Whole Prostate Models with Tumor Hotspots Using Dual-Extruder Printer

“…We can also visualize specific properties computed from data. For example, we can model and print quantified features describing spatial heterogeneity [10]. All of the abovementioned models could also be imported to virtual reality environments to create an immersive experience of walking inside the tissue and viewing pathological lesions and computed features from a new perspective.…”

“…These physical models concretizing tumor locations and prostate anatomical shape can be used for e.g. teaching purposes and to provide complementary insight to quantitative analysis [10]. Even though anatomical models can be visualized and examined digitally, an actual physical model can still give an enhanced understanding of how the organ is formed and how the pathological lesions are situated.…”