Radial matrix constraint influences tissue contraction and promotes maturation of bi-layered skin equivalents.

Human skin equivalents (HSEs) serve as important tools for mechanistic studies with human skin cells, drug discovery, pre-clinical applications in the field of tissue engineering and for skin transplantation on skin defects. Besides the cellular and extracellular matrix (ECM) components used for HSEs, physical constraints applied on the scaffold during HSEs maturation influence tissue organization, functionality, and homogeneity. In this study, we introduce a 3D-printed culture insert that exposes bi-layered HSEs to a static radial constraint through matrix adhesion. We examine the effect of various diameters of the ring-shaped culture insert on the HSE's characteristics and compare them to state-of-the-art unconstrained and planar constrained HSEs. We show that radial matrix constraint of HSEs regulates tissue contraction, promotes fibroblast and matrix organization that is similar to human skin in vivo and improves keratinocyte differentiation, epidermal stratification, and basement membrane formation depending on the culture insert diameter. Together, these data demonstrate that the degree of HSE's contraction is an important design consideration in skin tissue engineering. Therefore, this study can help to mimic various in vivo skin conditions and to increase the control of relevant tissue properties.

Improved Segmentation and Detection Sensitivity of Diffusion-weighted Stroke Lesions with Synthetically Enhanced Deep Learning.

PURPOSE: To compare the segmentation and detection performance of a deep learning model trained on a database of human-labeled clinical stroke lesions on diffusion-weighted (DW) images to a model trained on the same database enhanced with synthetic stroke lesions. MATERIALS AND METHODS: In this institutional review board-approved study, a stroke database of 962 cases (mean patient age ± standard deviation, 65 years ± 17; 255 male patients; 449 scans with DW positive stroke lesions) and a normal database of 2027 patients (mean age, 38 years ± 24; 1088 female patients) were used. Brain volumes with synthetic stroke lesions on DW images were produced by warping the relative signal increase of real strokes to normal brain volumes. A generic three-dimensional (3D) U-Net was trained on four different databases to generate four different models: (a) 375 neuroradiologist-labeled clinical DW positive stroke cases (CDB); (b) 2000 synthetic cases (S2DB); (c) CDB plus 2000 synthetic cases (CS2DB); and (d) CDB plus 40 000 synthetic cases (CS40DB). The models were tested on 20% (n = 192) of the cases of the stroke database, which were excluded from the training set. Segmentation accuracy was characterized using Dice score and lesion volume of the stroke segmentation, and statistical significance was tested using a paired two-tailed Student t test. Detection sensitivity and specificity were compared with labeling done by three neuroradiologists. RESULTS: The performance of the 3D U-Net model trained on the CS40DB (mean Dice score, 0.72) was better than models trained on the CS2DB (Dice score, 0.70; P < .001) or the CDB (Dice score, 0.65; P < .001). The deep learning model (CS40DB) was also more sensitive (91% [95% confidence interval {CI}: 89%, 93%]) than each of the three human readers (human reader 3, 84% [95% CI: 81%, 87%]; human reader 1, 78% [95% CI: 75%, 81%]; human reader 2, 79% [95% CI: 76%, 82%]), but was less specific (75% [95% CI: 72%, 78%]) than each of the three human readers (human reader 3, 96% [95% CI: 94%, 98%]; human reader 1, 92% [95% CI: 90%, 94%]; human reader 2, 89% [95% CI: 86%, 91%]). CONCLUSION: Deep learning training for segmentation and detection of stroke lesions on DW images was significantly improved by enhancing the training set with synthetic lesions.Supplemental material is available for this article.© RSNA, 2020.