A Unified Multi-Modality Fusion Framework for Deep Spatio-Temporal-Spectral Feature Learning in Resting-State fMRI Denoising.

Resting-state functional magnetic resonance imaging (rs-fMRI) is a commonly used functional neuroimaging technique to investigate the functional brain networks. However, rs-fMRI data are often contaminated with noise and artifacts that adversely affect the results of rs-fMRI studies. Several machine/deep learning methods have achieved impressive performance to automatically regress the noise-related components decomposed from rs-fMRI data, which are expressed as the pairs of a spatial map and its associated time series. However, most of the previous methods individually analyze each modality of the noise-related components and simply aggregate the decision-level information (or knowledge) extracted from each modality to make a final decision. Moreover, these approaches consider only the limited modalities making it difficult to explore class-discriminative spectral information of noise-related components. To overcome these limitations, we propose a unified deep attentive spatio-spectral-temporal feature fusion framework. We first adopt a learnable wavelet transform module at the input-level of the framework to elaborately explore the spectral information in subsequent processes. We then construct a feature-level multi-modality fusion module to efficiently exchange the information from multi-modality inputs in the feature space. Finally, we design confidence-based voting strategies for decision-level fusion at the end of the framework to make a robust final decision. In our experiments, the proposed method achieved remarkable performance for noise-related component detection on various rs-fMRI datasets.

Senescent Fibroblast-Derived GDF15 Induces Skin Pigmentation.

Senescent fibroblasts play a role in aging pigmentation. In this study, we found that GDF15 expression levels are increased in UV-irradiated senescent fibroblasts and photoaged hyperpigmented skin. To investigate the effects of GDF15 on melanogenesis, normal human melanocytes were cocultured with fibroblasts infected with the GDF15 lentivirus or GDF15 short hairpin RNA. It was found that GDF15 stimulates melanogenesis in melanocytes through MITF/tyrosinase upregulation via ß-catenin signaling. The stimulatory action of GDF15 during pigmentation was further confirmed in ex vivo cultured skin and in a reconstituted human skin sample. These results suggest that senescent fibroblast-derived GDF15 stimulates skin pigmentation and may play a role in aging-associated pigmentation.

Dasatinib, a second-generation tyrosine kinase inhibitor, induces melanogenesis via ERK-CREB-MITF-tyrosinase signaling in normal human melanocytes.

Dasatinib, a second-generation tyrosine kinase inhibitor, is indicated for the therapy of imatinib-resistant leukemia and also for the treatment of solid cancers. Here, we report a novel effect of dasatinib of inducing differentiation in normal human melanocytes. Treatment with dasatinib significantly increased the melanin content and tyrosinase activity through the up-regulation of MITF and tyrosinase expressions. Consistently, dasatinib had clear stimulatory action in the pigmentation of ex vivo cultured skin. The molecular mechanism underlying the melanogenic effect of dasatinib was associated with the ERK-dependent phosphorylation of CREB. The ERK inhibitor PD98059 not only inhibited the phosphorylation of CREB but also abrogated dasatinib-induced melanocyte differentiation. These results demonstrate for the first time the capacity of dasatinib to induce differentiation in normal human melanocytes depending on the activation of ERK-CREB-MITF-tyrosinase signaling cascades.