Recurrent missense mutations of the PIK3CA oncogene are among the most frequent drivers of human cancers. These often lead to constitutive activation of its product p110α, a phosphatidylinositol 3-kinase (PI3K) catalytic subunit. In addition to causing a broad range of cancers, the H1047R mutation is also found in affected tissues of a distinct set of congenital tumors and malformations. Collectively termed PIK3CA-related disorders (PRDs), these lead to overgrowth of brain, adipose, connective and musculoskeletal tissues and/or blood and lymphatic vessel components. Vascular malformations are frequently observed in PRD, due to cell-autonomous activation of PI3K signaling within endothelial cells. These, like most muscle, connective tissue and bone, are derived from the embryonic mesoderm. However, important organ systems affected in PRDs are neuroectodermal derivatives. To further examine their development, we drove the most common post-zygotic activating mutation of Pik3ca in neural crest and related embryonic lineages. Outcomes included macrocephaly, cleft secondary palate and more subtle skull anomalies. Surprisingly, Pik3ca-mutant subpopulations of neural crest origin were also associated with widespread cephalic vascular anomalies. Mesectodermal neural crest is a major source of non-endothelial connective tissue in the head, but not the body. To examine the response of vascular connective tissues of the body to constitutive Pik3ca activity during development, we expressed the mutation by way of an Egr2 (Krox20) Cre driver. Lineage tracing led us to observe new lineages that had normally once expressed Krox20 and that may be co-opted in pathogenesis, including vascular pericytes and perimysial fibroblasts. Finally, Schwann cell precursors having transcribed either Krox20 or Sox10 and induced to express constitutively active PI3K were associated with vascular and other tumors. These murine phenotypes may aid discovery of new candidate human PRDs affecting craniofacial and vascular smooth muscle development as well as the reciprocal paracrine signaling mechanisms leading to tissue overgrowth.

Background and Objectives: The prognosis of patients undergoing kidney tumor resection or kidney donation is linked to many histological criteria. These criteria notably include glomerular density, glomerular volume, vascular luminal stenosis, and severity of interstitial fibrosis/tubular atrophy. Automated measurements through a Deep Learning approach could save time and provide more precise data. This work aimed to develop a free tool to automatically obtain kidney histological prognostic features. Design, setting, participants, and measurements: Two hundred and forty one samples of healthy kidney tissue were split into 3 independent cohorts. The "Training" cohort (n=65) was used to train two Convolutional Neural Networks: one to detect the cortex and a second one to segment the kidney structures. The "Test" cohort (n=50) assessed their performances by comparing manually outlined regions of interest to predicted ones. The "Application" cohort (n=126) compared prognostic histological data obtained manually or through the algorithm based on the combination of the two Convolutional Neural Networks. Results: In the Test cohort, the networks isolated the cortex and segmented the elements of interest with good performances (more than 90% of the cortex, healthy tubules, glomeruli, and even globally sclerotic glomeruli were detected). In the Application cohort, the expected and predicted prognostic data were significantly correlated. The correlation coefficients r were respectively 0.85 for glomerular volume, 0.51 for glomerular density, 0.75 for interstitial fibrosis, 0.71 for tubular atrophy, and 0.73 for vascular intimal thickness. The algorithm had a good ability to predict significant (> 25%) tubular atrophy and interstitial fibrosis level (ROC curve with an area under the curve 0.92 and 0.91, respectively) or a significant vascular luminal stenosis (> 50%) (area under the curve 0.85). Conclusion: This freely available tool enables the automated segmentation of kidney tissue to obtain prognostic histological data in a fast, objective, reliable and reproducible way.