Deep learning-based pigment analysis model trained with optical approach and ground truth assistance

This study introduces an integrated training method combining the optical approach with ground truth for skin pigment analysis. Deep learning is increasingly applied to skin pigment analysis, primarily melanin and hemoglobin. While regression analysis is a widely used training method to predict ground truth-like outputs, the input image resolution is restricted by computational resources. The optical approach-based regression method can alleviate this problem, but compromises performance. We propose a strategy to overcome the limitation of image resolution while preserving performance by incorporating ground truth within the optical approach-based learning structure. The proposed model decomposes skin images into melanin, hemoglobin, and shading maps, reconstructing them by solving the forward problem with reference to the ground truth for pigments. Evaluation against the VISIA system, a professional diagnostic equipment, yields correlation coefficients of 0.978 for melanin and 0.975 for hemoglobin. Furthermore, our model can produce pigment-modified images for applications like simulating treatment effects.

Microphthalmia-associated transcription factor up-regulates acetylcholinesterase expression during melanogenesis of murine melanoma cells

Acetylcholinesterase (AChE) hydrolyzes the neurotransmitter acetylcholine in neurons. However, AChE has been proposed to also have nonneuronal functions in different cell types. Here, we report that AChE is expressed in melanocytes and melanoma cells, and that the tetrameric (G4) form is the major AChE isoform in these cells. During melanogenesis of B16F10 murine melanoma cells, AChE levels decreased markedly. The differentiation of melanoma cells led to (i) an increase in melanin and tyrosinase, (ii) a change in intracellular cAMP levels, and (iii) a decrease in microphthalmia-associated transcription factor (MITF). We hypothesized that the regulation of AChE during melanogenesis is mediated by two transcription factors: cAMP-response element-binding protein (CREB) and MITF. In melanoma cells, exogenous cAMP suppressed AChE expression and the promoter activity of the ACHE gene. This suppression was mediated by a cAMP-response element (CRE) located on the ACHE promoter, as mutation of CRE relieved the suppression. In melanoma, MITF overexpression induced ACHE transcription, and mutation of an E-box site in human ACHE promoter blocked this induction. An AChE inhibitor greatly enhanced acetylcholine-mediated responses of melanogenic gene expression levels in vitro; however, this enhancement was not observed in the presence of agonists of the muscarinic acetylcholine receptor. These results indicate that ACHE transcription is regulated by cAMP-dependent signaling during melanogenesis of B16F10 cells, and the effect of this enzyme on melanin production suggests that it has a potential role in skin pigmentation.

Recognizing Latinos' range of skin pigment and phototypes to enhance skin cancer prevention

Latinos in the United States may have the mistaken assumption that their natural pigmentation protects them from developing skin cancer that, effectively, serves as a barrier to Latinos receiving education in primary and secondary prevention of skin cancer. Latino adults of Mexican or Puerto Rican heritage attending community health fairs in the greater Chicago area responded to a culturally informed and sensitive measure for sunburn and tan, which was previously adapted to capture skin irritation with tenderness from the sun occurring in darker skin types (n = 350). By self-reported responses and spectrophotometry assessment of constitutive pigmentation, adapted Fitzpatrick skin types (FST) ranged from skin type I-IV in the Mexican American participants and from II to V in the Puerto Rican participants. The objectively measured proportion of adapted FST II skin type was greater than commonly perceived and demonstrated that many Latinos do indeed have sun-sensitive skin.