Extensive lentigo simplex, linear epidermolytic naevus and epidermolytic naevus comedonicus caused by a somatic mutation in KRT10

Somatic Variants of KRT1/KRT10 Identified by Next-generation Sequencing in Patients with Epidermal Nevi

Abstract is missing (Short communication)

Image classification and auxiliary diagnosis system for hyperpigmented skin diseases based on deep learning

Background and aim

Melasma (ML), naevus fusco-caeruleus zygomaticus (NZ), freckles (FC), cafe-au-lait spots (CS), nevus of ota (NO), and lentigo simplex (LS), are common skin diseases causing hyperpigmentation. Deep learning algorithms learn the inherent laws and representation levels of sample data and can analyze the internal details of the image and classify it objectively to be used for image diagnosis. However, deep learning algorithms that can assist clinicians in diagnosing skin hyperpigmentation conditions are lacking.

Methods

The optimal deep-learning image recognition algorithm was explored for the auxiliary diagnosis of hyperpigmented skin disease. Pretrained models, such as VGG-19, GoogLeNet, InceptionV3, ResNet50V2, ResNet101V2, ResNet152V2, InceptionResNetV2, DesseNet201, MobileNet, and NASNetMobile were used to classify images of six common hyperpigmented skin diseases. The best deep learning algorithm for developing an online clinical diagnosis system was selected by using accuracy and area under curve (AUC) as evaluation indicators.

Results

In this research, the parameters of the above-mentioned ten deep learning algorithms were 18333510, 5979702, 21815078, 23577094, 42638854, 58343942, 54345958, 18333510, 3235014, and 4276058, respectively, and their training time was 380, 162, 199, 188, 315, 511, 471, 697, 101, and 144 min respectively. The respective accuracies of the training set were 85.94%, 99.72%, 99.61%, 99.52%, 99.52%, 98.84%, 99.61%, 99.13%, 99.52%, and 99.61%. The accuracy rates of the test set data were 73.28%, 57.40%, 70.04%, 71.48%, 68.23%, 71.11%, 71.84%, 73.28%, 70.39%, and 43.68%, respectively. Finally, the areas of AUC curves were 0.93, 0.86, 0.93, 0.91, 0.91, 0.92, 0.93, 0.92, 0.93, and 0.82, respectively.

Conclusions

The experimental parameters, training time, accuracy, and AUC of the above models suggest that MobileNet provides a good clinical application prospect in the auxiliary diagnosis of hyperpigmented skin.

Post Zygotic, Somatic, Deletion in KERATIN 1 V1 Domain Generates Structural Alteration of the K1/K10 Dimer, Producing a Monolateral Palmar Epidermolytic Nevus

Palmoplantar keratodermas (PPKs) are characterized by thickness of stratum corneum and epidermal hyperkeratosis localized in palms and soles. PPKs can be epidermolytic (EPPK) or non epidermolytic (NEPPK). Specific mutations of keratin 16 (K16) and keratin 1 (K1) have been associated to EPPK, and NEPPK. Cases of mosaicism in PPKs due to somatic keratin mutations have also been described in scientific literature. We evaluated a patient presenting hyperkeratosis localized monolaterally in the right palmar area, characterized by linear yellowish hyperkeratotic lesions following the Blaschko lines. No other relatives of the patient showed any dermatological disease. Light and confocal histological analysis confirmed the presence of epidermolityic hyperkeratosis. Genetic analysis performed demonstrates the heterozygous deletion NM_006121.4:r.274_472del for a total of 198 nucleotides, in KRT1 cDNA obtained by a palmar lesional skin biopsy, corresponding to the protein mutation NP_006112.3:p.Gly71_Gly137del. DNA extracted from peripheral blood lymphocytes did not display the presence of the mutation. These results suggest a somatic mutation causing an alteration in K1 N-terminal variable domain (V1). The deleted sequence involves the ISIS subdomain, containing a lysine residue already described as fundamental for epidermal transglutaminases in the crosslinking of IF cytoskeleton. Moreover, a computational analysis of the wild-type and V1-mutated K1/K10 keratin dimers, suggests an unusual interaction between these keratin filaments. The mutation taster in silico analysis also returned a high probability for a deleterious mutation. These data demonstrate once again the importance of the head domain (V1) of K1 in the formation of a functional keratinocyte cytoskeleton. Moreover, this is a further demonstration of the presence of somatic mutations arising in later stages of the embryogenesis, generating a mosaic phenotype.

Late-Onset Nevus Comedonicus With Follicular Epidermolytic Hyperkeratosis-Case Report and Review of the Literature

Nevus comedonicus is a rare cutaneous follicular hamartoma, characterized by the clustering of papules with firm, blackened horny buffers. It is usually present at birth or during childhood, although few cases of late-onset disease have been described. We present a case of postmenopausal-onset nevus comedonicus in a 55-year-old white woman without relevant medical history. Skin biopsy showed the typical features of several cyst-dilated follicular structures occupied by keratotic material and the peculiar finding of epidermolytic hyperkeratosis of the follicular epithelial walls. A brief review of the clinical and histological features of other similar cases published in the literature is performed.

Epidermal Nevi and Related Syndromes -- Part 1: Keratinocytic Nevi

Epidermal nevi are hamartomatous lesions derived from the epidermis and/or adnexal structures of the skin; they have traditionally been classified according to their morphology. New variants have been described in recent years and advances in genetics have contributed to better characterization of these lesions and an improved understanding of their relationship with certain extracutaneous manifestations. In the first part of this review article, we will look at nevi derived specifically from the epidermis and associated syndromes.