Pathological Skin Research Articles

A novel CNN-based machine learning approach to identify skin cancers

Skin cancer is the most common type of cancer and includes diagnosis procedures that are costly, time-consuming, inaccurate, and inaccessible to many. The goal of this project was to determine the feasibility of a machine learning algorithm to identify skin cancers and compare the results to the conventional procedures of external visual inspection and biopsies. We used the HAM10000 dataset, a diverse collection of multisource clinical images of cutaneous skin pathologies (based on external appearance) which contained 11,034 unique image files of skin cancers and lesions at the time of this project. We tested and trained a machine learning algorithm with the dataset, and analyzed the accuracy, sensitivity, and runtime of the algorithm for seven skin pathologies, which were either skin cancers or pathologies that could potentially develop into skin cancer. The model was created with AutoKeras to automatically search for and apply the best algorithm. The average accuracy of the model (for each skin pathology type) was 84.05%, which exceeds the accuracy of histopathological diagnoses done by experienced dermatologists by 4.05%. For melanoma, the most fatal form of skin cancer, the model had a 70.63% diagnosis accuracy. Furthermore, the average runtime of the model, 4.9775 seconds, provides a significant advantage when compared to the typical minimum time needed to wait for biopsy results. The increased performance of a machine learning model when compared to conventional methods for identifying skin cancer results makes it a feasible alternative.

Dynamics of the Neural Network Accuracy in the Context of Modernization of the Algorithms of Skin Pathology Recognition.

The lack of objective methodologies and open datasets for the evaluation of the algorithms complicates the objective evaluation by specialists and hinders the widespread use of this technology in health care. The purpose of this study was to estimate the accuracy of Skinive's algorithm 2020 version, then, after an algorithm improvement in 2020-2021, to show a statistically significant decrease in neural network errors in the risk assessment of skin pathologies in 2021. The Skinive neural network uses a machine-learning algorithm to calculate the risk rating of skin pathologies. For this study, we used Skinive's algorithm 2020 and 2021 versions trained on 64,000 and 115,000 images, respectively. Three validation datasets were used to assess the sensitivity of the algorithm: precancer + cancer, viral skin pathology, acne, containing 285 images in each set. The specificity has been calculated on a separate validation set containing 6,000 benign neoplasm cases. The sensitivity of the Skinive neural network in detecting malignant neoplasms was 89.1% and 95.4% in 2020 and 2021, respectively. The specificity of Skinive's neural network in determining benign neoplasms was 95.3% in 2020 and 97.9% in 2021. For all skin neoplasms, in 2020, the sensitivity was 95.3%, and specificity was 93.5%; in 2021, these were 97.9% and 97.1%, respectively. The results of sensitivity and specificity of the Skinive neural network indicate that the algorithm is highly accurate in detecting various neoplasms and skin diseases. After improving the algorithm, we showed a statistically significant decrease in the number of neural network errors in determining the risks of skin pathologies.

The role of inflammasomes in cutaneous pathology.

Inflammasomes are large intracellular multiprotein complexes, which constitute a novel part of the innate immune system. In response to danger signals from pathogens or other harmful agents, inflammasomes assemble resulting in production of the inflammatory cytokines. We discuss recent knowledge of the role of deregulated inflammasome activity in skin pathologies such as autoinflammatory diseases as well as common skin diseases such as psoriasis and atopic dermatitis. We also present an insight into the activation and effector mechanisms of inflammasomes in skin carcinogenesis. The complex influence of inflammasome on cutaneous disorders raises new challenges and opportunities for the treatment of skin diseases.

Analysis of Nursing Effect of Comprehensive Nursing Intervention on Hemodialysis Patients with Uremia.

Uremic pruritus affects 50–90% of hemodialysis patients, making it one of the most frequent medical issues among this group. Pruritus can lead to skin infections, desquamation, pathological skin changes, sleep problems, anxiety, depression, and social problems. The epidemic of uremia pneumonia has put a lot of stress on hemodialysis patients, resulting in negative feelings. As a result, during the prevention and control of uremia, rigorous management and improved nursing intervention are critical. During the uremia disease outbreak, this study will examine and assess the impact of clinically refined nurse intervention on patients receiving maintenance hemodialysis.

Ultrasound measurements of pathological and physiological skin thickness: a scoping review protocol

IntroductionUltrasound is a quick, safe, and non-invasive imaging method that can be used to measure skin thickness in pathological cutaneous conditions in clinical and research settings. Despite widespread use, there...

Prevalence and Genotyping of Human Papillomavirus among Women in the Departments of Niari and Bouenza, Republic of the Congo

Human papillomaviruses (HPV) are at the origin of many mucosal, benign or malignant skin pathologies. Some so-called high-risk genotypes, especially types 16 and 18, are involved in the genesis of cervical cancer, one of the most common cancers in women. To determine the prevalence of HPV infections and to identify oncogenic genotypes circulating in the departments of Niari and Bouenza. A total of 207 cervical samples collected between 2019 and 2020 were studied. Cervico vaginal smears were performed on all samples for cytological analysis, and HPV DNA detection and genotyping were performed on GeneXpert. The average age of the women who participated in this study was 43.67 ± 12.31 years in Niari and 38.29 ± 10.52 in Bouenza with age intervals ranging from 18 to 80 years. Cytological analysis of these samples reported the following prevalences: Normal diagnosed in 89.58% (186/207) cases, ASCUS in 5.31% (11/207) cases, LSIL in 2.89% (6/207) cases, and ICC in 1.93% (4/207) cases. The prevalence of HPV infection was detected in 83.54% (66/186) of women without lesions, 6.32% (5/11) of ASCUS women and 10.12% (8/10) of women with cytological abnormalities [5.06% (4/6) LSIL, and 5.06% (4/4) ICC]. In total, 79 of the 207 women in our study tested positive for one or more HPV-HR types, or 38.16%. In the department of Niari 37.5% (48/128) women tested positive for HPV, and in the department of Bouenza 39.24% (31/79) tested positive for HPV. Multiple infections ranged from two to more than three strains of HPV. No statistically significant association was observed between socio-demographic characteristics and genotyping (p > 0.05). On the other hand, HPV-HR prevalence varied significantly according to cervical cytology (p = 0.001). The results obtained show the predominance of HPV 16 in women in these two departments of Congo.

MARKETING ANALYSIS OF MEDICINES FOR THE TREATMENT OF WOUNDS AND ULCERS

The availability of medical care to the population at the inpatient and outpatient stages is one of the priorities of the activities of the domestic healthcare system. Treatment of patients with wounds, ulcers, wound infection requires the availability of a drug resource, including both auxiliary and specific drug therapy. A significant number of patients with skin pathologies turn to medical and pharmaceutical organizations. Their treatment is a complex and differentiated process depending on the nature and origin of the wound, as well as the individual characteristics of the victim's body. Currently, there are drugs for the treatment of this pathology on the domestic pharmaceutical market, but the most important for drug therapy for skin injuries is group D – dermatological drugs, which is represented by 21 international nonproprietary names and 283 trade names.

Childhood Maltreatment, Traumatic Experiences, and Posttraumatic Stress in Pathological Skin Picking: An Online Case-Control Study

Childhood Maltreatment, Traumatic Experiences, and Posttraumatic Stress in Pathological Skin Picking: An Online Case-Control Study

Automated segmentation of epidermis in high-frequency ultrasound of pathological skin using a cascade of DeepLab v3+ networks and fuzzy connectedness.

This study proposes a novel, fully automated framework for epidermal layer segmentation in different skin diseases based on 75MHz high-frequency ultrasound (HFUS) image data. A robust epidermis segmentation is a vital first step to detect changes in thickness, shape, and intensity and therefore support diagnosis and treatment monitoring in inflammatory and neoplastic skin lesions. Our framework links deep learning and fuzzy connectedness for image analysis. It consists of a cascade of two DeepLab v3+models with a ResNet-50 backbone and a fuzzy connectedness analysis module for fine segmentation. Both deep models are pre-trained on the ImageNet dataset and subjected to transfer learning using our HFUS database of 580 images with atopic dermatitis, psoriasis and non-melanocytic skin tumors. The first deep model is used to detect the appropriate region of interest, while the second stands for the main segmentation procedure. We use the softmax layer of the latter twofold to prepare the input data for fuzzy connectedness analysis: as a reservoir of seed points and a direct contribution to the input image. In the experiments, we analyze different configurations of the framework, including region of interest detection, deep model backbones and training loss functions, or fuzzy connectedness analysis with parameter settings. We also use the Dice index and epidermis thickness to compare our results to state-of-the-art approaches. The Dice index of 0.919 yielded by our model over the entire dataset (and exceeding 0.93 in inflammatory diseases) proves its superiority over the other methods.

AEROBIC – ANAEROBIC CUTANEOUS MICROBIOTA OF HIDRADENITIS SUPPURATIVA. A CASE REPORT

Hidradenitis suppurativa (HS) is a chronic inflammatory disease affecting intertriginous skin areas of young adults. Although HS was historically defined as an infectious disease, the role of microorganisms in its pathogenesis is now controversial. We investigated the lesion microbiota of a recently diagnosed 24-year-old male patient with axillary HS, who shared features of the metabolic syndrome. The microbiological analysis of the patient’s lesion was indicative of colonization with bacteria including aerobes – Staphylococcus (S.) aureus, S. lugdunensis, S. epidermidis, anaerobes – Anaerococcus (A.) octavius, and microaerophiles – Cutibacterium (C.) acnes; this last one was also isolated in monoculture from a patient's healthy skin control sample. In vitro antibiotic susceptibility evaluation revealed Methicillin-resistant S. aureus (MRSA) and highly susceptible S. lugdunensis and S. epidermidis. Profiles of A. octavius and C. acnes showed that both strains were susceptible to Vancomycin, Clindamycin, Doxycycline and Linezolid; the anaerobe was Benzylpenicillin-resistant and Tetracycline and the microaerophile was intrinsically Metronidazole-resistant. We conclude that the intralesional microbial diversity in this case shows low variety of species and similarities to healthy skin microbiota, although the presence of S. aureus, particularly MRSA, S. lugdunensis or C. acnes – frequently involved in chronic skin pathologies – may be relevant for the disease severity. MRSA carriage in the patient’s lesion represents a significant epidemiological risk for the healthcare environment. Antibiotic treatment in the early stages of HS should be administered with caution. Extended studies of HS microbiota could identify relevant colonization patterns for the outcome of the disease and offer important keys for selecting personalised, efficient therapeutic schemes. Keywords: hidradenitis suppurativa, cutaneous microbiome, bacterial pathogens, MRSA, Staphylococcus aureus, Cutibacterium acnes, anaerobes

Methoxy-Monobenzoylmethane Protects Skin from UV-Induced Damages in a Randomized, Placebo Controlled, Double-Blinded Human In Vivo Study and Prevents Signs of Inflammation While Improving the Skin Barrier.

IntroductionSun protection is important in skin care and requires special attention as inefficient protection might trigger skin pathologies including polymorphic light eruption (PLE). The reduce-improve-protect (RIP) concept to avoid the onset of ultraviolet (UV) irradiation-induced diseases or damage to human skin is important. Methoxy-monobenzoylmethane (MeO-MBM), which is neither a UVB nor a UVA filter, converts to the UV filter avobenzone under UV irradiation and further acts as a photoantioxidant during its conversion process and initially as an antioxidant material. The aim of this study was to understand the mechanisms by which MeO-MBM improves the condition of UV-stressed skin through its photoantioxidant properties. The improvement of the skin condition by the activity of MeO-MBM as active ingredient was also investigated.MethodsPotential molecular targets were identified by in silico docking to numerous cellular membrane receptors on the cell surface or nuclear membrane, followed by microarray analysis of 164 genes after MeO-MBM treatment of normal human epidermal keratinocytes (NHEK). We conducted randomized, double-blinded, intra-individual comparison vs. placebo studies on ten volunteers, aged between 34 and 65 years, to assess the effect of MeO-MBM in vivo. The effect after UV-induced inflammation was assessed in a protective and curative set-up with 2% MeO-MBM vs. 1% hydrocortisone and placebo based on the change in blood flow. The barrier function of the skin was assessed by the change in transepidermal water loss (TEWL), skin scaling and skin thickness after the treatment with MeO-MBM. Additionally, the effect of MeO-MBM after UV-induced stress on the activation of ferritin in human explants was determined ex vivo.ResultsA docking simulation of MeO-MBM showed a potential interaction with the retinoic acid receptor gamma and further revealed downregulation of proteins related to inflammation. In the protective treatment set-up, after 24 h MeO-MBM significantly reduced the delta blood flow compared to placebo, while this reduction was more prominent with hydrocortisone. In the curative treatment set-up, a greater reduction in delta blood flow was also observed with MeO-MBM compared to placebo and similar to hydrocortisone. Treatment with MeO-MBM revealed an improvement in skin barrier function as a result of decreased TEWL, reduced skin scaling and increased skin thickness. Immunohistochemistry staining of ferritin on human skin explants further showed that the treatment with MeO-MBM reduced the ferritin expression.ConclusionBased on these results, MeO-MBM is capable of exerting an anti-aging activity via the retinoic acid receptor gamma. Its anti-inflammatory and anti-oxidative activity manifested via the downregulation of multiple anti-inflammatory genes as well as the reduction of ferritin in skin tissue. This study shows that the multidimensional functionality of MeO-MBM offers an effective approach to combat acute and chronic deleterious effects of oxidative UV damage while simultaneously enhancing the skin barrier function.

Impact of visible light on skin health: The role of antioxidants and free radical quenchers in skin protection

Until recently, the primary focus of photobiology has centered on the impact of UV radiation on skin health, including DNA damage and oncogenesis; however, the significant effects of visible light (VL) on skin remain grossly underreported. VL has been reported to cause erythema in individuals with light skin (Fitzpatrick skin types [FSTs] I-III) and pigmentary changes in individuals with dark skin types (FSTs IV-VI). These effects have importance in dermatologic diseases and potentially play a role in conditions aggravated by sun exposure, including phototoxicity in patients with FSTs I to III and post-inflammatory hyperpigmentation and melasma in patients with FSTs IV to VI. The induction of free radicals, leading to the generation of reactive species, is one driving mechanism of VL-induced skin pathologies, leading to the induction of melanogenesis and hyperpigmentation. Initial clinical studies have demonstrated the effectiveness of topical sunscreen with antioxidant combinations in inhibiting VL + UV-A1-induced erythema in FSTs I to III and reducing pigmentation in FSTs IV to VI. Antioxidants may help prevent the worsening of pigmentary disorders and can be incorporated into photoprotective strategies. It is essentialthat dermatologists and the public are aware of the impact of VL on skin, especially in patients with skin of color, and understand the available options for VL protection.

Perillyl alcohol inhibits keratinocyte proliferation and attenuates imiquimod-induced psoriasis like skin-inflammation by modulating NF-κB and STAT3 signaling pathways

Psoriasis is a chronic inflammatory and proliferative skin disease characterized by pathological skin lesions which significantly impact the quality of life. Recent studies have been proven that inhibitors of farnesyltransferase enzyme showed significant anti-psoriatic activity. Perillyl alcohol (POH) is one such natural molecule having anti proliferative, anti-inflammatory and anti-oxidant properties by inhibiting farnesyltransferase enzyme which further down regulates NF-κB and STAT3 via Ras/Raf/MAPK pathway. Hence, in the current study we aimed to find the effect of POH on human keratinocytes (HaCat) cells in in-vitro and IMQ induced psoriatic like skin inflammation model in mice. POH significantly decreased the intracellular ROS levels and inhibited the phosphorylation of NF-κB and STAT3 in in-vitro. It was found that POH (200 mg/kg, topical application) has reduced the epidermal hyperplasia, psoriasis area and severity index (PASI) scoring; splenomegaly in imiquimod (IMQ) induced psoriatic mice. Further, POH treatment has decreased the pro-inflammatory serum cytokine levels such as IL-6, IL-12/23, TNF-α and IL-1β and also reduced the expression levels of various inflammatory proteins, COX-2, iNOS, IL-17A, IL-22, NF-кB and STAT3 evidenced by Immunoblotting studies from skin samples. The levels of endogenous antioxidants like glutathione GSH, SOD, Nrf2 were restored to normal levels upon POH treatment. POH downregulated the proteins levels of TLR7, TLR8, CyclinD1 and mRNA expression of Bcl-2 in the skin samples when compared to the IMQ group. POH has ameliorated the hyper-keratosis and acanthosis which was evidenced by histopathology. Collectively, our results suggest that POH has a promising therapeutic application for ameliorating psoriasis-like skin inflammation.

The genome sequence of the Australian filarial nematode, Cercopithifilaria johnstoni.

We present a genome assembly and annotation of an individual female Cercopithifilaria johnstoni, a parasitic filarial nematode that is transmitted by hard ticks (Ixodidae) to infect a broad range of native Australian murid and marsupial hosts. The genome sequence is 76.9 Mbp in length, and although in draft form (N50 = 99 kbp, N50[n] = 232), is largely complete based on universally conserved orthologs (BUSCOs; genome = 94.9%, protein = 96.5%) and relative to other related filarial species. These data represent the first genomic resources for the genus Cercopithifilaria, a group of parasites with a broad host range, and form the basis for comparative analysis with the human-infective parasite, Onchocerca volvulus, both of which are responsible for similar eye and skin pathologies in their respective hosts.

Neural network classifier of hyperspectral images of skin pathologies

The paper presents results of using a neural network classifier to analyze images of malignant skin lesions obtained using a hyper-spectral camera. Using a three-block neural network of VGG architecture, we conducted the classification of a set of two-dimensional images of melanoma, papilloma and basal cell carcinoma, obtained in the range of 530 – 570 and 600 – 606 nm, characterized by the highest absorption of melanin and hemoglobin. The sufficiency of the inclusion in the training set of two-dimensional images of a limited spectral range is analyzed. The results obtained show significant prospects of using neural network algorithms for processing hyperspectral data for the classification of skin pathologies. With a relatively small set of training data used in the study, the classification accuracy for the three types of neoplasms was as high as 96 %.

Skin Aging, Cellular Senescence and Natural Polyphenols.

The skin, being the barrier organ of the body, is constitutively exposed to various stimuli impacting its morphology and function. Senescent cells have been found to accumulate with age and may contribute to age-related skin changes and pathologies. Natural polyphenols exert many health benefits, including ameliorative effects on skin aging. By affecting molecular pathways of senescence, polyphenols are able to prevent or delay the senescence formation and, consequently, avoid or ameliorate aging and age-associated pathologies of the skin. This review aims to provide an overview of the current state of knowledge in skin aging and cellular senescence, and to summarize the recent in vitro studies related to the anti-senescent mechanisms of natural polyphenols carried out on keratinocytes, melanocytes and fibroblasts. Aged skin in the context of the COVID-19 pandemic will be also discussed.

Persistent Facial and Chest Papular and Pustular Eruption in a Stem Cell Transplant Patient.

Demodex folliculitis is a condition caused by inflammation of the pilosebaceous unit due to the Demodex folliculorum mite.1 The mite is a normal inhabitant of the human hair follicle and though they have been found in all areas of human skin, they predominate on the face. The face, with a high density of active sebaceous glands is a desirable home for demodex mites who feed on exfoliated epidermal cells and sebaceous gland secretions. The eruption of demodex folliculitis can mimic many common skin pathologies such as rosacea, acne vulgaris, and bacterial folliculitis.2 When demodex folliculitis occurs with immunocompromised patients, the clinical presentation can be atypical and severe.3 Herein, we report a case of severe demodex folliculitis and review of the literature.

AGNet: Automatic generation network for skin imaging reports

Medical imaging has been increasingly adopted in the process of medical diagnosis, especially for skin diseases, where diagnoses based on skin pathology are extremely accurate. The diagnostic reports of skin pathology images has the distinguishing features of extreme repetitiveness and rigid formatting. However, reports written by inexperienced radiologists and pathologists can have a high error rate, and even experienced clinicians can find the reporting task both tedious and time-consuming. To address this challenge, this paper studies the automatic generation of diagnostic reports based on images of skin pathologies. A novel deep learning-based image caption framework named the automatic generation network (AGNet), which is an effective network for the automatic generation of skin imaging reports, is proposed. The proposed AGNet consists of four parts: (1) the image model that extracts features and classifies images; (2) the language model that codes data and generates words using comprehensible language; (3) the attention module that connects the “tail” of the image model and the “head” of the language model, and computes the relationship between images and captions; (4) the embedding and labeling module that processes the input caption data. In case study, The AGNet is verified on a skin pathological image dataset and compared with several state-of-the-art models. The results show that the AGNet achieves the highest scores of the evaluation metrics of image caption among all comparison models, demonstrating the promising performance of the proposed method.

Inhibition of BRD4 inhibits proliferation and promotes apoptosis of psoriatic keratinocytes

BackgroundPsoriasis is a common chronic recurrent inflammatory skin disease. The pathogenesis of psoriasis, such as other autoimmune diseases, is still unclear, which brings great difficulties to the treatment. This study aimed to investigate the role of bromine domain protein 4 (BRD4) in affecting the psoriatic keratinocytes.MethodsImiquimod-induced psoriasis mice model and TNF-α or IL-17A induced HaCAT cells, an experimental model in vitro for psoriasis, were constructed. The pathological skin changes at the back of mice were observed by hematoxylin and eosin (H&E) assay and evaluated by psoriasis area and severity index (PASI). KI67 expression and keratinocyte apoptosis at the skin tissues were, respectively, detected by Immunohistochemical analysis and TUNEL assay. The inflammatory factors in mice serum and culture supernatant were determined by ELISA assay. The related proteins expression of proliferation, apoptosis and MAPK pathway were detected by Western blot analysis.ResultsBRD4 expression was upregulated in injured skin on the back of imiquimod-induced mice and (+)-JQ1 relieved the skin injury by suppressing the inflammation and promoting apoptosis of keratinocytes. Consistently, BRD4 expression was also increased in TNF-α or IL-17A induced HaCAT cells. (+)-JQ1 suppressed the viability and inflammation, and promoted apoptosis of TNF-α or IL-17A induced HaCAT cells. In addition, the MAPK signaling pathway was inhibited by (+)-JQ1 whether in mice or HaCAT cells.ConclusionsInhibition of BRD4 inhibited proliferation and inflammation and promoted apoptosis of psoriatic keratinocytes.

Pathological Skin Picking: Phenomenology and Associations With Emotions, Self-Esteem, Body Image, and Subjective Physical Well-Being.

Pathological skin picking (PSP) refers to the repetitive manipulation of the skin causing wounds, scars, emotional distress, and social impairment. Skin picking disorder was first recognized as a distinct disorder in the DSM-5 and is still understudied in terms of phenomenology, etiology, and associated consequences. However, the body-related pathology suggests that the relation to the own body might be a crucial factor in PSP. Previous studies provided first insights that affected individuals show a more negative body image and lower self-esteem than healthy individuals. The present study sought to investigate skin picking phenomenology, related emotions as well as associations with self-esteem, body image, and subjective physical well-being. The study was conducted as an open online study, and recruitment was generally targeted to individuals of full age and in addition specifically to individuals with PSP. A total of 363 individuals (82.9% female; age: M = 32.6, SD = 13.92) participated and answered various self-report measures. Nearly half of the sample exceeded the cutoff score for pathological skin picking (N = 163; 44.9%). The results suggest that boredom, bodily tension and strong negative feelings often precede PSP episodes. During the episode most individuals seem to experience a loss of control, trance and positive feelings. After the PSP episode, shame, guilt, anger and anger toward themselves are most prominent. As expected, skin picking severity was positively associated with body image disturbances and negatively with self-esteem, and subjective physical well-being. When controlling for depressive symptoms, all associations were reduced, but those with body image disturbances (r = 0.44; p < 0.001), self-esteem (r = −0.27; p < 0.001), subjective physical well-being (r = −0.22; p < 0.001), and peace of mind (r = 0.30; p < 0.01) remained significant. Moreover, greater skin damage due to skin picking was moderately associated with higher body image disturbances. The results indicate that PSP severity is associated with a negative body image and low self-esteem, and suggest that it may be warranted to consider these aspects in the development of future interventions for PSP. However, relations with body image and self-esteem should be examined in longitudinal studies investigating causal relationships between body image, self-esteem and skin picking. Moreover, PSP phenomenology and the role of specific emotions should be investigated in more detail.