Large-scale extraction of interpretable features provides new insights into kidney histopathology - A proof-of-concept study.

Whole slide images contain a magnitude of quantitative information that may not be fully explored in qualitative visual assessments. We propose: (1) a novel pipeline for extracting a comprehensive set of visual features, which are detectable by a pathologist, as well as sub-visual features, which are not discernible by human experts and (2) perform detailed analyses on renal images from mice with experimental unilateral ureteral obstruction. An important criterion for these features is that they are easy to interpret, as opposed to features obtained from neural networks. We extract and compare features from pathological and healthy control kidneys to learn how the compartments (glomerulus, Bowman's capsule, tubule, interstitium, artery, and arterial lumen) are affected by the pathology. We define feature selection methods to extract the most informative and discriminative features. We perform statistical analyses to understand the relation of the extracted features, both individually, and in combinations, with tissue morphology and pathology. Particularly for the presented case-study, we highlight features that are affected in each compartment. With this, prior biological knowledge, such as the increase in interstitial nuclei, is confirmed and presented in a quantitative way, alongside with novel findings, like color and intensity changes in glomeruli and Bowman's capsule. The proposed approach is therefore an important step towards quantitative, reproducible, and rater-independent analysis in histopathology.

Expression and clinical significance of hypoxia-inducible factor 1α, Snail and E-cadherin in human ovarian cancer cell lines.

The aim of the present study was to investigate the expression and clinical significance of hypoxia-inducible factor 1α (HIF-1α), Snail and E-cadherin in ovarian cancer. The expression levels were assessed in a number of ovarian cancer cell lines and ovarian cancer tissues, and correlations between the expression of the three proteins and clinical pathological factors were analyzed. Transwell assays showed that the invasive ability of the ovarian cancer cell lines SKOV3 and ES­2 were significantly higher than those of TYK and 3AO (P<0.01). Furthermore, the expression levels of HIF­1α and Snail in SKOV3 and ES­2 were significantly higher than those in TYK and 3AO, whereas the expression levels of E­cadherin in SKOV3 and ES­2 were significantly lower than those in TYK and 3AO (P<0.05). In ovarian cancer tissues, the expression levels of HIF­1α, Snail and E­cadherin were correlated with clinical pathological factors (P<0.01); furthermore, there was a positive correlation between the expression levels of HIF­1α and Snail (r=0.231; P=0.021), and a negative correlation between the expression levels of Snail and that of E­cadherin (r=­0.225; P=0.028). HIF­1α was suggested to be able to suppress the expression of E­cadherin by upregulating Snail, thus serving an important role in invasion and metastasis of ovarian cancer.