Vitiligo Skin Research Articles

Involvement of interferon γ-producing mast cells in immune responses against melanocytes in vitiligo requires MrgX2 activation.

Increasing evidence indicates that oxidative stress and interferon γ (IFNγ)-driven cellular immune responses are responsible for the pathogenesis of vitiligo. However, the connection between oxidative stress and the local production of IFNγ in early vitiligo remains unexplored. The aim of this study was to identify the mechanism underlying the production of IFNγ by mast cells and its impact on vitiligo pathogenesis. Skin specimens from the central, marginal, and perilesional skin areas of active vitiligo lesions were collected to characterize changes of mast cells, CD8+ T cells, and IFNγ-producing cells. Cell supernatants from hydrogen peroxide (H2O2)-treated keratinocytes (KCs) were harvested to measure levels of soluble stem cell factor (sSCF) and matrix metalloproteinase (MMP)-9. A murine vitiligo model was established using Mas-related G protein-coupled receptor-B2 (MrgB2, mouse ortholog of human MrgX2) conditional knockout (MrgB2-/-) mice to investigate IFNγ production and inflammatory cell infiltrations in tail skin following the challenge with tyrosinase-related protein (Tyrp)-2 180 peptide. Potential interactions between the Tyrp-2 180 peptide and MrgX2 were predicted using molecular docking. The siRNAs targeting MrgX2 and the calcineurin inhibitor FK506 were also used to examine the signaling pathways involved in mast cell activation. IFNγ-producing mast cells were closely aligned with the recruitment of CD8+ T cells in the early phase of vitiligo skin. sSCF released by KCs through stress-enhanced MMP9-dependent proteolytic cleavage recruited mast cells into sites of inflamed skin (Perilesion vs. lesion, 13.00 ± 4.00/HPF vs. 26.60 ± 5.72/HPF, P <0.05). Moreover, IFNγ-producing mast cells were also observed in mouse tail skin following challenge with Tyrp-2 180 (0 h vs. 48 h post-recall, 0.00 ± 0.00/HPF vs. 3.80 ± 1.92/HPF, P <0.05). The IFNγ+ mast cell and CD8+ T cell counts were lower in the skin of MrgB2-/-mice than in those of wild-type mice (WT vs. KO 48 h post-recall, 4.20 ± 0.84/HPF vs. 0.80 ± 0.84/HPF, P <0.05). Mast cells activated by MrgX2 serve as a local IFNγ producer that bridges between innate and adaptive immune responses against MCs in early vitiligo. Targeting MrgX2-mediated mast cell activation may represent a new strategy for treating vitiligo.

Clinical study of Wnt inhibitory factor-1 expression and its association with disease severity in non-segmental vitiligo

BackgroundVitiligo is classified as an acquired chronic depigmentation disorder that includes the destruction of epidermal melanocytes. It affects 0.5–1% of the population all over the world. Wnt signaling pathway is vital in melanocytes differentiation and development. WIF-1 is an antagonist of the Wnt signaling pathway; it hinders Wnt from binding its receptors. The present study aims to detect WIF-1 expression in vitiligo skin and if it relates to the disease's severity.ResultsThis case–control study included 70 subjects: 35 vitiligo patients and 35 healthy controls. Skin WIF-1 expression was estimated using quantitative real-time PCR. Assessment of the vitiligo disease activity score and vitiligo area severity index score was determined. WIF-1 expression showed significant elevation in the skin of vitiligo patients compared to the healthy control group.ConclusionOverexpression of WIF-1 may participate in the pathogenesis of vitiligo; hence, it should be a future therapeutic target.

Vitiligo: From Pathogenesis to Treatment.

Recent advances in vitiligo have provided promising treatment options, particularly through understanding the immune-mediated mechanisms leading to depigmentation. The inflammatory components in both vitiligo (non-segmental) and segmental vitiligo have similarities. Both are believed to result from an immune-based destruction of melanocytes by anti-melanocyte-specific cytotoxic T cells. The JAK-STAT pathway is activated with IFN-γ as the crucial cytokine and Th1-associated chemokines such as CXCL9 and CXCL10 recruit immune cells towards vitiligo skin. Nonetheless, clear differences are also present, such as the localized nature of segmental vitiligo, likely due to somatic mosaicism and increased presence of poliosis. The differing prevalence of poliosis suggests that the follicular immune privilege, which is known to involve immune checkpoints, may be more important in vitiligo (non-segmental). Immunomodulatory therapies, especially those targeting the JAK-IFNγ pathway, are currently at the forefront, offering effective inhibition of melanocyte destruction by cytotoxic T cells. Although Janus Kinase (JAK) inhibitors demonstrate high repigmentation rates, optimal results can take several months to years. The influence of environmental UV exposure on repigmentation in patients receiving immunomodulating drugs remains largely underexplored. Nonetheless, the combined effect of phototherapy with JAK inhibitors is impressive and suggests a targeted immune-based treatment may still require additional stimulation of melanocytes for repigmentation. Identifying alternative melanocyte stimulants beyond UV light remains crucial for the future management of vitiligo.

Identification of piRNA Expression Profiles in Vitiligo

Objective: Vitiligo is a systemic dermatological disorder characterized by skin depigmentation due to melanocyte damage and dysfunction. The treatment of vitiligo remains a challenging aspect in dermatological practice. PIWI-interacting RNAs (piRNAs), approximately 24–32 nucleotides in length, are crucial in the epigenetic regulation of developmental processes. However, research on piRNA expression profiling in vitiligo is limited. This study aimed to identify and characterize piRNAs in skin tissues from vitiligo patients and healthy controls. Methods: We compared and analyzed piRNA expression profiles of human vitiligo skin by RNA sequencing. Results and Discussion: Our findings revealed a pronounced preference for uridine (U) at the 5′ end of piRNAs, predominantly originating from repeat and other genomic regions. Notably, we detected 73 differentially expressed piRNAs between the patient and control groups, with 40 piRNAs upregulated and 33 downregulated in vitiligo patients. Bioinformatics analysis indicated that the genes responsible for piRNA production were more prevalent in metabolic processes and implicated in regulating the PI3K-Akt and AMPK signaling pathways. Conclusions: The elucidation of piRNA expression profiles enhances our understanding of their functional roles in the pathogenesis of vitiligo.

Mechanism of desuccinylation of G6PD mediated by SIRT7 to promote vitiligo disease progression.

Sirtuin 7 (SIRT7) is pivotal in diverse diseases progression. Importantly, SIRT7 is associated with melanin production. However, whether SIRT7 regulates vitiligo is unclear. Therefore, we aimed to investigate the effects of SIRT7 on pigmentation and the modification of glucose 6-phosphate dehydrogenase (G6PD). After knockdown SIRT7 and G6PD, pigmentation of melanocytes was evaluated using commercial kits, immunofluorescence, and Western blot analysis. The succinylation of G6PD mediated by SIRT7 was analyzed using co-immunoprecipitation, immunofluorescence, Western blot analysis, and cycloheximide-chase experiment. We found that SIRT7 was highly expressed in vitiligo skin lesions. Knockdown of SIRT7 increased tyrosinase activity, melanin content, and the levels of α-melanocyte-stimulating hormone, MITF, TYR, TRP1, and TRP2. Additionally, SIRT7 directly interacted with G6PD. Silenced SIRT7 promoted the succinylation of G6PD and enhanced its protein stability. G6PD knockdown reversed the effect of reduced SIRT7 expression on melanin production. Silencing of SIRT7 promotes pigmentation of melanocytes by succinylating G6PD, suggesting that SIRT7-mediated G6PD desuccinylation may promote vitiligo progression.

Analysis of granulysin expression in vitiligo and halo-nevus

Vitiligo and halo nevus are immune-mediated skin diseases that have a similar pathogenesis and involve cellular cytotoxicity mechanisms that are not yet fully understood. In this study, we investigated the expression patterns of the cytolytic molecule granulysin (GNLY) in different cytotoxic cells in skin samples of vitiligo and halo nevus. Skin biopsies were taken from perilesional and lesional skin of ten vitiligo patients, eight patients with halo nevus and ten healthy controls. We analysed the expression of GNLY by immunohistochemistry in CD8+ and CD56+ NK cells. A significantly higher accumulation of GNLY+, CD8+ GNLY+ and fewer CD56+ GNLY+ cells was found in the lesional skin of vitiligo and halo nevus than in the healthy skin. These cells were localised in the basal epidermis and papillary dermis, suggesting that GNLY may be involved in the immune response against melanocytes. Similarly, but to a lesser extent, upregulation of GNLY+ and CD8+ GNLY+ cells was observed in the perilesional skin of vitiligo and halo nevus compared to healthy controls. In this study, we demonstrated for the first time an increased expression of CD8+ GNLY+ T lymphocytes and CD56+ GNLY+ NK cells in lesions of vitiligo and halo nevus, indicating the role of GNLY in the pathogenesis of both diseases.

The relationship between psoriasis and vitiligo: From a comprehensive study.

Both psoriasis and vitiligo are autoimmune skin diseases. Previous observational studies have indicated a relationship between the two conditions, and simultaneous onset of both diseases poses increased health risks to patients. However, limited research has explored the causal relationship between psoriasis and vitiligo. To investigate whether a causal association exists between psoriasis and vitiligo. A case of Chinese patients diagnosed with psoriasis and vitiligo has been reported. Transcriptome sequencing was performed on normal, psoriasis, vitiligo, and co-morbid skin tissues of the patients, and single-cell transcriptome sequencing was conducted on the co-morbid skin tissues. A comprehensive Mendelian randomization analysis of Genome-wide association studies (GWAS) was performed on a cohort of 261 018 European individuals with psoriasis from the IEU Open GWAS Project and vitiligo from the National Institutes of Health (NIH) Database of Genotypes and Phenotypes. Case report and transcriptome results showed that skin tissue with vitiligo combined with psoriasis exhibited both vitiligo and psoriasis. Single-cell transcriptome sequencing results showed that in comparison to normal skin and psoriatic skin, the proportions of CD8+ T cells, natural killer cells, naive T cells, T helper cells 17, regulatory T cells, conventional type 1 dendritic cells, Conventional type 2 dendritic cells, and plasmacytoid dendritic cells were all increased in skin tissue with vitiligo combined with psoriasis. Mendelian randomization analysis included 4510 patients with psoriasis and 4680 patients with vitiligo. The results showed no causal relationship between vitiligo and psoriasis in the forward direction (p=0.192; odds ratio [OR], 1.059; 95% confidence interval [CI], 0.971-1.155) or in the reverse direction (p=0.459; OR, 0.927; 95% CI, 0.757-1.134). This study suggests that the association between psoriasis and vitiligo may be closely related to immunity, however, Mendelian randomization studies do not support a causal relationship. These findings hold significant implications for clinicians aiming to enhance their understanding and treatment approaches for psoriasis and vitiligo.

A Bioinformatics Analysis for Unveiling Novel Long Non-Coding RNAs and their Regulatory Impact on Key Genes Associated with Vitiligo

Vitiligo involves the gradual disappearance of melanocytes, causing skin depigmentation. Long noncoding RNAs (lncRNAs), a type of noncoding RNA, are important for regulating inflammation and immunity. Despite this significance, there needs to be more published research on how lncRNAs are expressed in vitiligo cases and their potential roles in the biology of this skin condition. This study aims to elucidate the molecular landscape of vitiligo by analyzing gene expression profiles of vitiligo skin and normal skin. Two datasets, RNA-seq and microarray, were thoroughly investigated to identify differentially expressed (DE) genes and lncRNAs associated with vitiligo development. Functional enrichment analysis revealed biological processes and pathways influenced by dysregulated genes, highlighting intricate processes such as melanin biosynthesis and melanogenesis, shedding light on the complex regulatory networks involved in pigmentation and immune responses. Protein-protein interaction analysis highlighted significantly downregulated hub genes, including TYRP1, MLANA, MC1R, SLC45A2, PAX3, TYR, DCT, OCA2, PMEL, and SOX10, revealing significant functional relationships among identified hub genes within the network. RNA-seq data analysis uncovered DE-lncRNAs, emphasizing the regulatory role of lncRNAs in vitiligo. Moreover, the correlation analysis between the expression of lncRNAs and key genes associated with melanogenesis (OCA2, TYRP1, and PMEL) unveiled novel upregulated lncRNAs such as CRTC3-AS1, LCMT1-AS1, LINC02178 contributing to vitiligo development. Additionally, lncRNA-gene networks constructed based on key melanocyte-related genes provided insights into the molecular relationships relevant to vitiligo. Overall, this study offers a comprehensive understanding of vitiligo pathogenesis, identifying potential therapeutic targets and laying the foundation for future research in this critical area.

A turn-on fluorescence probe for imaging tyrosinase at the wound site in broken tail of zebrafish

Tyrosinase (TYR) is a copper-containing oxidase that affects the synthesis of melanin in the human body, which is regulate to the pigmentation of the skin. Nevertheless, abnormal expression of TYR can lead to albinism, vitiligo and other skin diseases. Excessive accumulation of TYR is a marker of melanoma cancer and an important factor leading to pigmentation during wound healing, freckles and browning of fruits and vegetables. Efficient tracking of TYR is of significance for studying its pathophysiological mechanism. Herein, we synthesized a benzindole-based fluorescent probe Pro-OH to detect TYR in living cells and zebrafish. The probe displayed a high selectivity and sensitivity in distinguishing TYR from other analytes with the low detection limit of 1.024 U/mL. Importantly, Pro-OH was successfully used to imagine TYR at the wound site of broken tail of zebrafish.

Bridging the Gap Between Vitiligo Segmentation and Clinical Scores.

Quantitative evaluation of vitiligo is crucial for assessing treatment response. Dermatologists evaluate vitiligo regularly to adjust their treatment plans, which requires extra work. Furthermore, the evaluations may not be objective due to inter- and intra-assessor variability. Though automatic vitiligo segmentation methods provide an objective evaluation, previous methods mainly focus on patch-wise images, and their results cannot be translated into clinical scores for treatment adjustment. Thus, full-body vitiligo segmentation needs to be developed for recording vitiligo changes in different body parts of a patient and for calculating the clinical scores. To bridge this gap, the first full-body vitiligo dataset with 1740 images, following the international vitiligo photo standard, was established. Compared with patch-wise images, full-body images have more complicated ambient light conditions and larger variances in lesion size and distribution. Additionally, in some hand and foot images, skin can be fully covered by either vitiligo or healthy skin. Previous patch-wise segmentation studies completely ignore these cases, as they assume that the contrast between vitiligo and healthy skin is available in each image for segmentation. To address the aforementioned challenges, the proposed algorithm in this study exploits a tailor-made contrast enhancement scheme and long-range comparison. Furthermore, a novel confidence score refinement module is proposed to manage images fully covered by vitiligo or healthy skin. Our results can be converted to clinical scores and used by clinicians. Compared to the state-of-the-art method, the proposed algorithm reduces the average per-image vitiligo involvement percentage error from 3.69% to 1.81%, and the top 10% per-image errors from 23.17% to 8.29%. Our algorithm achieves 1.17% and 3.11% for the mean and max error for the per-patient vitiligo involvement percentage, which is better than an experienced dermatologist's naked-eye evaluation.

Oxidative stress-induced hypermethylation and low expression of ANXA2R: Novel insights into the dysfunction of melanocytes in vitiligo

BackgroundVitiligo is a skin disorder with melanocyte destruction caused by complex interplay between multiple genetic and environmental factors. Recent studies have suggested DNA methylation is involved in the melanocyte damage, but the underlying mechanism remains unknown. ObjectiveTo explore the abnormal DNA methylation patterns in vitiligo lesional and nonlesional skin, and the mechanism of DNA methylation involved in vitiligo pathogenesis. MethodsInitially, the genome-wide aberrant DNA methylation profiles in lesional and nonlesional skin of vitiligo were detect via Illumina methylation EPIC 850k Beadchip. Subsequently, a comprehensive analysis was conduct to investigate the genomic characteristics of differentially methylated regions (DMRs). Furthermore, the effects of key aberrant methylated genes on cell apoptosis and function of both melanocytes and keratinocytes were further identified and validated by western bloting, ELISA, and immunofluorescence. ResultsCompared with nonlesional skins, we discovered 79 significantly differentially methylated CpG sites in vitiligo lesions. These DMRs were mainly located in the gene body and the TS1500 region. Annexin A2 receptor (ANXA2R), a crucial gene in cell apoptosis, was hypermethylated in vitiligo lesions. Furthermore, we showed that ANXA2R displayed hypermethylation and low expression levels in both keratinocytes and melanocytes of vitiligo patients, and the hypermethylated-triggered downregulation of ANXA2R under oxidative stress induced melanocyte apoptosis, and inhibited the secretion of stem cell factor (SCF) from keratinocytes thus impaired the survival of melanocytes. ConclusionsOur study illustrates the DNA methylation modification in vitiligo, and further demonstrates the molecular mechanism of hypermethylated ANXA2R in the dysfunction of melanocytes under oxidative stress.

Genome-wide DNA methylation of lesional and peri-lesional skin in vitiligo: a comparative and integrated analysis of multi-omics in Chinese population.

Several studies have emphasized the role of DNA methylation in vitiligo. However, its profile in human skin of individuals with vitiligo remains unknown. Here, we aimed to study the DNA methylation profile of vitiligo using pairwise comparisons of lesions, peri-lesions, and healthy skin. We investigated DNA methylation levels in six lesional skin, six peri-lesional skin, and eight healthy skin samples using an Illumina 850K methylation chip. We then integrated DNA methylation data with transcriptome data to identify differentially methylated and expressed genes (DMEGs) and analyzed their functional enrichment. Subsequently, we compared the methylation and transcriptome characteristics of all skin samples, and the related genes were further studied using scRNA-seq data. Finally, validation was performed using an external dataset. We observed more DNA hypomethylated sites in patients with vitiligo. Further integrated analysis identified 264 DMEGs that were mainly functionally enriched in cell division, pigmentation, circadian rhythm, fatty acid metabolism, peroxidase activity, synapse regulation, and extracellular matrix. In addition, in the peri-lesional skin, we found that methylation levels of 102 DMEGs differed prior to changes in their transcription levels and identified 16 key pre-DMEGs (ANLN, CDCA3, CENPA, DEPDC1, ECT2, DEPDC1B, HMMR, KIF18A, KIF18B, TTK, KIF23, DCT, EDNRB, MITF, OCA2, and TYRP1). Single-cell RNA analysis showed that these genes were associated with cycling keratinocytes and melanocytes. Further analysis of cellular communication indicated the involvement of the extracellular matrix. The expression of related genes was verified using an external dataset. To the best of our knowledge, this is the first study to report a comprehensive DNA methylation profile of clinical vitiligo and peri-lesional skin. These findings would contribute to future research on the pathogenesis of vitiligo and potential therapeutic strategies.

Vitiligo and surgical treatment

Objective: Initial comments on the effectiveness of surgical treatment of vitiligoResearch subjects and methods: A prospective study on 12 cases of vitiligo that were successfully treated with autologous pigment cell transplant surgery. Research period from September 2018 to October 2022 at the Center for Plastic Surgery, Surgery &amp; Regeneration - Le Huu Trac National Burn HospitalResults: 12 patients with an average age of 29, with vitiligo in several locations on the body, received pigment-containing cell transplant surgery. The graft adheres well, ensuring good coverage and assimilating the color of the vitiligo skin area with the surrounding healthy skin after about 12 months.Conclusion: Pigment graft surgery is one of the effective methods of treating vitiligo and can be applied to large areas of the diseased skin.

Multiple gene-drug prediction tool reveals Rosiglitazone based treatment pathway for non-segmental vitiligo

Vitiligo is a skin disease characterized by selective loss of melanocytes, which seriously affects the appearance and causes great psychological stress to patients. In this study, we performed a comprehensive analysis of two vitiligo microarray datasets from the GEO database using bioinformatics tools to identify 297 up-regulated mRNAs and 186 down-regulated mRNAs, revealing important roles for pathways related to melanin synthesis, tyrosine metabolism, and inflammatory factors, such as “PPAR signaling pathway”, “tyrosine metabolism”, “nonalcoholic fatty liver disease (NAFLD) pathway”, “melanogenesis”, and “IL-17 signaling pathway”. Combining the Search Tool for Interacting Chemicals (STITCH) database 5.0 and the drug-gene interaction database 3.0 (DGIdb), we identified that the PPAR-γ agonist rosiglitazone may promote melanin synthesis via EDNRB. Next, we investigated the mechanism of rosiglitazone and PPAR-γ pathway in promoting melanin production. Consistent with the results of bioinformatics analysis, the expression levels of PPAR-γ, EDNRB, and TYR were significantly reduced in human non-segmental vitiligo skin along with the reduction of MITF, a key gene for epidermal melanogenesis. Meanwhile, rosiglitazone increased melanin synthesis capacity in melanocytes and zebrafish by activating PPAR-γ and upregulating TYR, TYRP-1, and TYRP-2. Conversely, treatment of melanocytes with the PPAR-γ antagonist GW resulted in inhibition of melanin synthesis and expression of melanin-related factors. At the same time, simultaneous treatment of rosiglitazone with GW reversed the inhibitory effect of GW on melanin synthesis. In this study, we identified that rosiglitazone, an important insulin sensitizer, promotes melanin synthesis in melanocytes by increasing PPAR-γ activity and upregulating the expression levels of EDNRB and TYR. These findings may provide new ideas for exploring the pathogenesis and potential therapeutic targets of non-segmental vitiligo.

Decreased ZMIZ1 suppresses melanogenesis in vitiligo by regulating mTOR/AKT/GSK-3β-mediated glucose uptake.

The loss of epidermal melanocytes is a distinguishing feature of vitiligo (VIT), a prevalent and long-lasting skin ailment. While various hypotheses exist to explain the cause of VIT, the precise mechanisms leading to this disease remain unclear. Zinc finger MIZ-type containing 1 (ZMIZ1) has a strong link with the development and occurrence of VIT. However, the exact role of ZMIZ1 and its underlying mechanisms in VIT are not well understood. Our study aims to illustrate that targeting ZMIZ1 is an effective therapeutic and prophylactic strategy for treating VIT. We obtained the RNA expression profile of VIT samples using RNA-seq and determined the locations and expression of ZMIZ1 in these samples via immunochemistry. Glucose uptake was analyzed through immunofluorescence and glucose uptake assay. We evaluated mRNA levels using qPCR and used plasmids transfection to knock down ZMIZ1 in PIG1 and PIG3V cell lines. The activation of the mTOR/AKT/GSK-3β signalling pathway was assessed using Western blotting analysis. We found that ZMIZ1 expression was decreased in VIT samples. Decreased ZMIZ1 expression inhibits the proliferation, migration, and invasion of melanocytes in vitro. Moreover, we revealed that decreased ZMIZ1 could also inhibit the glucose uptake of melanocytes in vitro. Decreased ZMIZ1 expression inhibits the activation of the mTOR/AKT/GSK-3β pathway and the expression of melanin synthesis-related proteins in melanocytes. Finally, we demonstrated that decreased ZMIZ1 may inhibit the cell viability of melanocytes and the synthesis of melanin by mTOR/AKT/GSK-3β-mediated oxidative stress in vitro. In conclusion, our study suggests that decreased ZMIZ1 suppresses melanogenesis in vitiligo by regulating the mTOR/AKT/GSK-3β-mediated glucose uptake in vitro, making ZMIZ1 an attractive therapeutic target for the treatment of VIT.

Choroidal vascularity index and choroidal thickness assessment in vitiligo

ABSTRACT Clinical relevance Vitiligo is a skin disease characterised by depigmentation and loss of melanocytes. Melanocyte loss may not be limited to the skin in vitiligo, and various abnormalities may occur in the choroid, which is dense in melanocytes. Background To evaluate structural changes in the choroid by measuring choroidal thickness and vascularity index using optical coherence tomography in patients with vitiligo and comparing them to healthy subjects. Methods This study included 168 participants: 84 with vitiligo (30 females, 54 males) and 84 controls (36 females, 48 males). Choroidal thickness and vascularity index were measured using the enhanced depth imaging mode in spectral-domain optical coherence tomography. The choroidal thickness was measured at the following five points; subfoveal (SF), 500 μm (NCT1) and 1000 μm (NCT2) nasal to the fovea; and 500 μm (TCT1) and 1000 μm (TCT2) temporal to the fovea. The choroidal vascularity index was calculated using the ImageJ software. Results SF (p < 0.001), NCT1 (p < 0.001), NCT2 (p = 0.021), TCT1 (p = 0.001), and TCT2 (p < 0.006) choroidal thicknesses were significantly smaller in the vitiligo group than in the control group. Total choroidal (p < 0.001) and stromal (p < 0.001) areas were significantly smaller in the vitiligo group than in the control group. Choroidal vascularity indices were significantly higher in the vitiligo group than in the control group (p < 0.001). However, luminal areas did not differ significantly between groups (p = 0.935). Conclusion Patients with vitiligo should be regularly monitored for choroidal alterations and, if necessary, referred to an ophthalmologist.

Response to Venables and Levell

Response to Venables and Levell

222 New perspectives on immune checkpoint inhibitor-induced vitiligo-like depigmentation in melanoma: a comparative study with classical vitiligo and healthy skin

222 New perspectives on immune checkpoint inhibitor-induced vitiligo-like depigmentation in melanoma: a comparative study with classical vitiligo and healthy skin

Novel real-time visualization of functional vitiligo skin lymphocytes attracting melanocytes in autologous cultured epidermis.

Novel real-time visualization of functional vitiligo skin lymphocytes attracting melanocytes in autologous cultured epidermis.

Deep Learning based Model for Detection of Vitiligo Skin Disease using Pre-trained Inception V3

Skin diseases are commonly identified problems all over the world. There are various kinds of skin diseases, such as skin cancer, vulgaris, ichthyosis, and eczema. Vitiligo is one of the skin diseases that can occur in any area of the body, including the inner part of the mouth. This type of skin can have immense negative impacts on the human body, involving memory issues, hypertension, and mental health problems. Conventionally, dermatologists use biopsy, blood tests, and patch testing to identify the presence of skin diseases and provide medications to patients. However, these treatments don't always provide results due to the transformation of a macule into a patch. Various machine learning (ML) and deep learning (DL) models have been developed for the early identification of macules to avoid delays in treatments. This work has implemented a DL-based model for predicting and classifying vitiligo skin disease in healthy skin. The features from the images have been extracted using a pre-trained Inception V3 model and substituted for each classifier, namely, naive Bayes, convolutional neural network (CNN), random forest, and decision tree. The results have been determined as accuracy, recall, precision, area under the curve (AUC), and F1-score for Inception V3 with naive Bayes as 99.5%, 0.995, 0.995, 0.997, and 0.995, respectively. The Inception V3 with CNN has achieved 99.8% accuracy, 0.998 recall, 0.998 precision, 1.00 AUC, and 0.998 F1-score. Further, Inception V3 with random forest shows 99.9% accuracy, 0.999 recall, 0.999 precision, 1.00 AUC, and 0.999 F1-score values whereas, Inception V3 with decision tree classifier shows an accuracy value of 97.8%, 0.978 recall, 0.977 precision, 0.969 AUC, and 0.977 F1-score. Results exhibit that Inception V3 with a random forest classifier outperforms in terms of accuracy, recall, precision, and F1-score, whereas for the AUC metric, Inception V3 with a random forest and Inception V3 with CNN have shown the same outcomes of 1.00.