Diagnosis Of Skin Tumors Research Articles

A clinico-histopathological study of cutaneous appendageal tumours

The cutaneous appendageal tumors are an ideal subject for study from clinical and morphological point of view and so ubiquitous that they can affect people of all age group A histopathological study of 100 cases of cutaneous appendageal tumors was carried out at tertiary care hospital over 18 months. A Total 95 cases were benign and 5 cases were malignant tumors, constituting 95.0 % p0.01 respectively. Sweat gland tumors were the most common manifestation (79.0% ) p follicle tumors (20%) and eccrine duct tumors 1(1%). Male and female ratio was 27:73. The commonest affected body site was head and neck region . The mean age was 36.58 1.22 years . Out of 95 cases of benign tumors, syringoma accounted for 48% (48), trichoepithelioma12 p (11) p0.01. Total (39) p clinically and histopathologically. Summing of the results concludes that ,the diagnosis of skin tumors presenting with unique difficulties in correlation with wide variety of tumors . Histopathological study is one of the most valuable means of diagnosis in dermatopathology and the diagnosis of skin tumors can be done by correlating clinical features, gross and histological appearances.

An Adaptive Federated Machine Learning-Based Intelligent System for Skin Disease Detection: A Step toward an Intelligent Dermoscopy Device

The prevalence of skin diseases has increased dramatically in recent decades, and they are now considered major chronic diseases globally. People suffer from a broad spectrum of skin diseases, whereas skin tumors are potentially aggressive and life-threatening. However, the severity of skin tumors can be managed (by treatment) if diagnosed early. Health practitioners usually apply manual or computer vision-based tools for skin tumor diagnosis, which may cause misinterpretation of the disease and lead to a longer analysis time. However, cutting-edge technologies such as deep learning using the federated machine learning approach have enabled health practitioners (dermatologists) in diagnosing the type and severity level of skin diseases. Therefore, this study proposes an adaptive federated machine learning-based skin disease model (using an adaptive ensemble convolutional neural network as the core classifier) in a step toward an intelligent dermoscopy device for dermatologists. The proposed federated machine learning-based architecture consists of intelligent local edges (dermoscopy) and a global point (server). The proposed architecture can diagnose the type of disease and continuously improve its accuracy. Experiments were carried out in a simulated environment using the International Skin Imaging Collaboration (ISIC) 2019 dataset (dermoscopy images) to test and validate the model’s classification accuracy and adaptability. In the future, this study may lead to the development of a federated machine learning-based (hardware) dermoscopy device to assist dermatologists in skin tumor diagnosis.

Nodular Hidradenocarcinoma, Trichelemmal Carcinoma and Squamous Cell Carcinoma with Clear Cell Changes: Pitfalls of Biopsy Diagnosis of Skin and Adnexal Tumours.

Skin and Adnexal tumours are a group of benign and malignant tumours whose basic diagnosis relies on histopathology. A single tumour may show more than 1 appendageal differentiation. Morphologic distinction between benign and its malignant counterpart is of utmost importance as it affects the treatment and prognosis of patient. We have described 3 cases who presented in our university hospital, in which final resection pathological diagnosis differed from initial core biopsy interpretation. The authors have made an attempt to provide a brief overview of diagnostic overlap existing between nodular hidradenocarcinoma and tumours of clear cell histology. Salient morphologic features differentiating cylindroma or trichilemmal carcinoma from squamous cell carcinoma have also been discussed. Final diagnosis is paramount for adjuvant management and prognostication of the patient in a clinical setting.

Progress in the application of reflectance confocal microscopy in dermatology.

Reflectance confocal microscopy (RCM) is abbreviated as skin three-dimensional computed tomography, which can help clearly observe the structure of the epidermis and superficial dermis. It is a non-invasive skin disease examination method and provides fast access to real-time, dynamic skin micro-anatomical images. Therefore, RCM is widely used in the clinical diagnosis of skin diseases. For example, the RCM features of vitiligo are as follows: pigment loss or partial pigment loss in the lesion area, loss of the basal layer pigment ring. The RCM findings of Riehl melanosis are as follows: basal cell liquefaction and degeneration. The RCM results for verruca plana show: the Rose-like structure. The characteristics of psoriasis under RCM include: hyperkeratosis, parakeratosis, thickening of the spinous layer, capillary dilatation and hyperaemia, peripheral inflammatory cell infiltration. Epidermal brain-like structure was observed under RCM of seborrheic keratosis. With RCM, image acquisition and preservation of the skin is convenient, and the technique is convenient for comparing the development of lesions during long-term follow-up observation. Therefore, it helps to understand disease development in real time and dynamically and can be used to evaluate the curative effect. In this article, we briefly review the technical principles, diagnostic criteria for RCM application and RCM-related research progress in the diagnosis of pigmentary diseases, inflammatory diseases, skin tumours, and other common skin diseases.

The use of high frequency skin ultrasound in non-melanoma skin cancer

Ultrasound (US) or sonography is the most common diagnostic non-invasive imaging method, which is estimated to account for more than a third of all diagnostic procedures used in medical practice. Traditionally, US frequencies used in diagnostic radiology range from 1 MHz to approximately 16 MHz. Visualization of skin morphology requires US frequencies from 20 to 100 MHz, and is called a “high frequency ultrasound” (HFUS). HFUS has been explored in normal skin and in various skin pathologies. It has been found useful in differentiation diagnosis of infiltrative (perivascular) and exudative inflammation, hypertrophic or normotrophic scars, keloids, and in skin atrophy. Moreover, it has been used to support diagnosis and management of skin tumors. In skin oncology, HFUS can provide essential information on tumors’ size and margins, particularly the depth of invasion. Such information are crucial in deciding on the form of treatment (e.g., photodynamic therapy, radiotherapy, brachytherapy), computed tomography (CT)-based planning treatment (e.g., superficial brachytherapy), and in skin monitoring after treatment, in addition to clinical examination.

Skin Ultrasound as a Diagnostic Approach for Non-melanocytic Benign Skin Tumors

Background. The diagnostic imaging techniques in dermatology, such as skin ultrasound, could improve the diagnosis of non-melanocytic benign tumor lesions, especially those of intradermal and subcutaneous nature. Objective. The general objective of this study was to evaluate the validity and diagnostic safety of high-frequency ultrasound as a diagnostic test for non-melanocytic benign skin tumor detection. The specific objectives were to measure the sensitivity and specificity of ultrasound as a measure of the validity relative to the gold-standard test – diagnostic-therapeutic biopsy. Methods. This study was carried out between January 2017 and June 2019. The patients (n = 641) included in this study comprised of 318 women and 323 men who were between 48 and 74 years. All of them underwent an ultrasound examination of the skin tumor in the dermatology clinic, the removal of the non-melanocytic tumor, and a final histopathological examination. Results. The skin ultrasound has a sensitivity and specificity of 93% and 88%, respectively. Furthermore, the positive and negative predictive values of using skin ultrasound are 84% and 94%, respectively. Conclusion. Skin ultrasound is a diagnostic technique with high sensitivity and specificity in the diagnosis of non-melanocytic skin tumors.

A study of tumours, tumour like lesions and cysts of epidermis and its appendages

Introduction: Skin tumors arise due to proliferation of group of cells having differentiation towards single or multiple components of skin. Based on their primary site of involvement, they can be divided into neoplasms with epithelial differentiation, melanocytic neoplasms, soft tissue neoplasms, neural tumors and tumors of subcutaneous tissue. Aims: 1. To evaluate the demographic and clinico-pathological patterns of tumors, tumor like lesions & cysts of epidermis and its appendages; 2. To compare the profile of patients with appendageal tumors against the total epidermal tumors. Materials and Methods: Prospective study, from July 2012 to November 2014, done at tertiary care center. Results: During the period of three years, there were 306 cases which presented as skin tumors and out of these, 57 happened to be cysts and the remaining 249 were tumors of skin. Out of 249 cases, 205 were diagnosed as benign, 23 were of premalignant and 21 as malignant tumors of skin constituting 82.32%, 9.24% and 8.43% respectively. There was male predominance with male to female ratio of 1.28:1. In this study benign keratinocytic tumors formed majority (49.27%) followed by melanocytic (31.32%) and appendageal tumors (10.44%). Among keratinocytic tumors maximum cases were of seborrheic keratosis (32.19%), among melanocytic tumors maximum cases were of acquired melanocytic nevus (21.40%) while nevus sebaceous (4.87%) formed majority among appendageal tumors. In present study malignant keratinocytic tumors formed majority (95.23%) followed by melanocytic (4.76%). Among keratinocytic tumors maximum cases were of BCC (57.14%). Conclusion: The diagnosis of skin tumors presents unique difficulties due to wide variety of tumors and the complicated nomenclature. The study of the adnexal tumours is interesting, fascinating and challenging because of wide range of differentiation. Keywords: Skin tumours, Benign tumors, Cysts, Benign keratinocytic tumors, Melanocytic tumors, Appendageal tumors

Значение нативной аутофлуоресценции протопорфирина в диагностике новообразований век и кожи периорбитальной области

Значение нативной аутофлуоресценции протопорфирина в диагностике новообразований век и кожи периорбитальной области

Comparative analysis of the effectiveness of «Chaos and Clues», «Triage Amalgamated Dermoscopic Algorithm» dermatoscopic algorithms and BLINСK techniques in the diagnosis of melanoma and other skin cancers depending on previous dermatoscopy experience

Aim.Comparison of the results of the use of dermatoscopic algorithms Chaos and Clues, Triage Amalgamated Dermoscopic Algorithm (TADA) and BLINCK technique in the diagnosis of melanoma and other malignant skin tumors depending on the presence of previous dermatoscopy experience.
 Materials and methods.Algorithms were tested on 85 patients with 85 skin formations who visited the polyclinic of Kursk Regional Clinical Oncology Clinic in 20172019. The average age of the patients was 54.8 years old. Dermatoscopy was performed by the non-polarized dermatoscope HEINE mini 3000, photo documentation by the Canon PowerShot SX540 HS camera. Immersion medium ethyl alcohol (conc. 70%). Patients were carefully examined physiologically and clinically. A clinical and epiluminescence pattern of all neoplasms was obtained, their morphological examination was performed. For the research 2 groups of 3 participants were formed based on the criterion of previous dermatoscopy experience. Each algorithm was evaluated by objective (sensitivity, specificity) and subjective (speed, convenience) criteria. The dermatoscopic results obtained by the techniques used were compared to the histological findings.
 Results. Using algorithms by a group having previous dermatoscopy experience, the following results were obtained: in the method Chaos and Clues sensitivity 93.753.3%, specificity 77.44.6%, speed 3 points, convenience 3 points. TADA sensitivity 96.82.2%, specificity 79.24.8%, speed 4 points, convenience 5 points. BLINCK sensitivity 96.82.2% specificity 77.44.6%, speed 4 points, convenience 5 points. In the group with no previous dermatoscopy experience, the results were as follows: in the Chaos and Clues algorithm, sensitivity 93.753.3%, specificity 62.35.7%, speed 3 points, convenience 3 points. TADA sensitivity 84.44.6%, specificity 64.25.8%, speed 4 points, convenience 5 points; BLINCK sensitivity 80.64.4%, specificity 77.44.6%, speed 5 points, convenience 4 points. Thus, these algorithms can be used in the diagnosis of malignant skin neoplasms. At the same time, individuals with no experience of dermatoscopy are encouraged to use the Chaos and Clues algorithm. In a group having experience in dermatoscopy, both the TADA and the BLINCK technique can be used equally.

Validation of a Novel Cutaneous Neoplasm Diagnostic Self-Efficacy Instrument (CNDSEI) for Evaluating User-Perceived Confidence With Dermoscopy.

Accurate medical image interpretation is an essential proficiency for multiple medical specialties, including dermatologists and primary care providers. A dermatoscope, a ×10-×20 magnifying lens paired with a light source, enables enhanced visualization of skin cancer structures beyond standard visual inspection. Skilled interpretation of dermoscopic images improves diagnostic accuracy for skin cancer. Design and validation of Cutaneous Neoplasm Diagnostic Self-Efficacy Instrument (CNDSEI)-a new tool to assess dermatology residents' confidence in dermoscopic diagnosis of skin tumors. In the 2018-2019 academic year, the authors administered the CNDSEI and the Long Dermoscopy Assessment (LDA), to measure dermoscopic image interpretation accuracy, to residents in 9 dermatology residency programs prior to dermoscopy educational intervention exposure. The authors conducted CNDSEI item analysis with inspection of response distribution histograms, assessed internal reliability using Cronbach's coefficient alpha (α) and construct validity by comparing baseline CNDSEI and LDA results for corresponding lesions with one-way analysis of variance (ANOVA). At baseline, residents respectively demonstrated significantly higher and lower CNDSEI scores for correctly and incorrectly diagnosed lesions on the LDA (P = 0.001). The internal consistency reliability of CNDSEI responses for the majority (13/15) of the lesion types was excellent (α ≥ 0.9) or good (0.8≥ α <0.9). The CNDSEI pilot established that the tool reliably measures user dermoscopic image interpretation confidence and that self-efficacy correlates with diagnostic accuracy. Precise alignment of medical image diagnostic performance and the self-efficacy instrument content offers opportunity for construct validation of novel medical image interpretation self-efficacy instruments.

Diagnostic performance study on the melanoma automated diagnosis software powered by artificial intelligence technologies

INTRODUCTION: The research evaluates a series of publications on the machine recognition efficacy of cutaneous melanoma dermatoscopic images. Some authors report high sensitivity and specificity of automated diagnostics of skin tumors. Significant differences in the published data can be attributed to the use of different algorithms and groups of skin neoplasms to calculate the accuracy rate.&#x0D; MATERIALS AND METHODS: The diagnostic performance of two automated artificial intelligence systems is compared.&#x0D; RESULTS: The convolutional neural network algorithm improves the overall diagnostic accuracy by 7% compared to the algorithm without deep learning, while the overall accuracy rate was 78%. An initial set of 100 dermatoscopic images used in the study is published online for the assessment of the applicability of the obtained data when introducing existing artificial intelligence systems.&#x0D; CONCLUSION: The main limitations and possible ways to further improve the automated diagnosis of skin tumors based on digital dermatoscopy are outlined.

Dermoscopic diagnostic performance of Japanese dermatologists for skin tumors differs by patient origin: A deep learning convolutional neural network closes the gap.

In the dermoscopic diagnosis of skin tumors, it remains unclear whether a deep neural network (DNN) trained with images from fair-skinned-predominant archives is helpful when applied for patients with darker skin. This study compared the performance of 30 Japanese dermatologists with that of a DNN for the dermoscopic diagnosis of International Skin Imaging Collaboration (ISIC) and Shinshu (Japanese only) datasets to classify malignant melanoma, melanocytic nevus, basal cell carcinoma and benign keratosis on the non-volar skin. The DNN was trained using 12254 images from the ISIC set and 594 images from the Shinshu set. The sensitivity for malignancy prediction by the dermatologists was significantly higher for the Shinshu set than for the ISIC set (0.853 [95% confidence interval, 0.820-0.885] vs 0.608 [0.553-0.664], P<0.001). The specificity of the DNN at the dermatologists' mean sensitivity value was 0.962 for the Shinshu set and 1.00 for the ISIC set and significantly higher than that for the human readers (both P<0.001). The dermoscopic diagnostic performance of dermatologists for skin tumors tended to be less accurate for patients of non-local populations, particularly in relation to the dominant skin type. A DNN may help close this gap in the clinical setting.

Laboratório de Histopatologia Cutânea do Serviço de Dermatologia do Hospital de Santa Maria. Actividade de Doze Anos (2008-2019) - Parte I: Tumores Cutâneos

Introdução: O Laboratório de Histopatologia Cutânea do Serviço de Dermatologia do Hospital de Santa Maria de Lisboa funciona ininterruptamente desde sua criação em 1975.&#x0D; Material e Métodos: Realizámos um estudo retrospetivo através da análise dos exames histológicos da patologia cutânea tumoral diagnosticados no laboratório durante o período de janeiro de 2008 a dezembro de 2019.&#x0D; Resultados: No período 2008-2019 o Laboratório de Histopatologia Cutânea efetuou 60 741 exames histológicos, dos quais 80% foram lesões tumorais. Destes, os tumores malignos representaram cerca de um terço da amostra, essencialmente constituída por basaliomas (53%), carcinomas espinocelulares (23%) e melanomas (8%). Outros tumores malignos documentados foram os linfomas (3%), o sarcoma de Kaposi (1%) e as infiltrações da pele por doenças malignas extracutâneas (2%). Do grupo das neoplasias benignas (68% do número total dos tumores) destacam-se os nevos melanocíticos (50%), as verrugas seborreicas (16%) e os quistos (6%).&#x0D; Conclusão: Em termos comparativos com anteriores casuísticas, tem-se assistido a um aumento constante e regular da actividade geral do Laboratório de Histopatologia Cutânea do Serviço de Dermatologia do Hospital de Santa Maria nos últimos 12 anos. Isto tem sido refletido num aumento no número de diagnósticos de tumores cutâneos malignos. Destacamos a importância do exame histológico como componente central no diagnóstico e subsequente tratamento das condições neoplásicas da pele.

光声成像在皮肤肿瘤中的应用进展

光声成像在皮肤肿瘤中的应用进展

Neurothekeoma in the Axilla Causing Persistent Shoulder Pain: Case Report.

Neurothekeomas, also known as neural sheath myxomas, are rare benign tumors of the neural sheath affecting most commonly the head, arms and shoulder of women in their 2 nd and 3 rd decades of life. Due to the low prevalence and undefined clinical picture, they are hardly considered in the initial differential diagnosis of skin tumors. We report the case of a 24 year-old woman who was seen in 2016 reporting > 1 year of moderate pain and limited mobility of her left shoulder. Clinical evaluation revealed restricted mobility of the affected shoulder and nuclear magnetic resonance imaging showed a T2-weighted contrast-enhanced multilobular mass in the quadrilateral area apparently invading the adjacent humeral cortical region. Histopathology of a needle sample material revealed loose fibroconnective tissue with no signs of invasion, mitosis or atypical figures. Successful surgical excision was performed and the diagnosis of neurothekeoma was confirmed after detailed histopathology, including immunohistochemistry. The patient was asymptomatic at 18 months of follow-up, with full recovery of shoulder movement and no signs of relapse.

Dermatoscopic and morphological features of some clinical variants of seborrheic keratosis

Objective — to determine medical tactics, trace the relationship and supplement the correlation information between clinical manifestations, dermatoscopic patterns and histological picture of typical and flat variants of seborrheic keratosis (SK).Materials and methods. The studies were conducted in Zaporizhzhya Regional Dermatovenerological Clinical Hospital of Zaporizhzhya Regional Council. 20 persons with seborrheic keratosis were monitored — 14 (70 %) women and 6 (30 %) men aged 41 to 87. The screening included a general, dermatoscopic and pathomorphological examination of the patient.Results and discussion. More often, lesions were localized on the skin of the body — in 10 persons, on face and scalp — in 5, on lateral neck — in 3, less often on upper limbs — in 2 patients. Fitzpatrick’s І phototype was detected in 3 (15 %) persons, ІІ phototype — in 13 (65 %), ІІІ phototype — in 4, which equals to 20 %. Histologically, the acanthotic type of seborrheic keratosis was identified in 14 (70 %), papillomatous and reticular in — 5 and 1 patients, respectively. The dermatoscopic picture of the acanthotic variant is represented by the following criteria: milia­like cysts— in 10 cases, comedo­like openings— in 4, «convoluted cerebriform pattern» — in 5, «moth­eaten» border — in 2, verrucous surface — in 1, papillomatous SK with verrucous, papillary surface — in 1, keratoma with patterns of «finger print» type — in 3 cases. The reticular (adenoid) variant is represented by a symmetrical lesion of dark brown color and round shape up to 0.5 cm in diameter with moth-­eaten borders and milia­-like cysts around the periphery. Conclusions. The variability of the clinical, dermatoscopic, and pathomorphological manifestations of seborrheic keratosis needs further search for new algorithms of therapy and differential diagnosis of malignant skin tumors.

Prospects of screening skin neoplasms in servicemen of the Armed Forces of Ukraine

Objective — to improve the methods of diagnosis of skin neoplasms and to optimize the management of patients-service­men.Materials and methods. A literature review and analysis of the results of clinical and instrumental studies of military personnel with skin neoplasms are presented.Results and discussion. Management of diagnosis and treatment of skin neoplasms is a difficult task, especially for the early detection of skin neoplasms and the provision of medical care in accordance with international recommendations and guidelines, particularly in the Armed Forces. An important issue is that the examination and management of patients with skin neoplasms are not accompanied by photodocumentation of dermatoscopic images (namely, this situation exists in the real outpatient practice of the vast majority of Ukrainian dermatovenereologists and cosmetologists) since it is difficult to compare the results of the current and previous examinations when observing a patient, especially if they conducted by different specialists. This is due to the fact that specialists do not have a standardized protocol for detection, examination and fixation of dermatoscopic signs using a certain sequence and unified terminology of their description. In addition, there are a number of issues requiring further development in relation to the provision of medical care to military patients with skin neoplasms. The Dermatological Service of Ukraine is currently in a state of reform, which significantly reduces the possibility of early patient visits to the dermatologist and, accordingly, worsens the early diagnosis of skin tumors, especially in conscripts. A complicating factor is also the insufficient regulation of the algorithm and route of the patient with skin neoplasms in order to verify or exclude their malignant nature.Conclusions. Modern views on the diagnosis and treatment of dermatovenerological neoplasms need to be changed in order to early detect skin neoplasms and provide medical care in accordance with international recommendations and guidelines, especially in the ranks of the Armed Forces of Ukraine. In Ukraine, the identification and care of military patients with skin neoplasms is an issue that needs further development.

Recognition of Cutaneous Melanoma on Digitized Histopathological Slides via Artificial Intelligence Algorithm.

Increasing incidence of skin cancer combined with a shortage of dermatopathologists has increased the workload of pathology departments worldwide. In addition, the high intraobserver and interobserver variability in the assessment of melanocytic skin lesions can result in underestimated or overestimated diagnosis of melanoma. Thus, the development of new techniques for skin tumor diagnosis is essential to assist pathologists to standardize diagnoses and plan accurate patient treatment. Here, we describe the development of an artificial intelligence (AI) system that recognizes cutaneous melanoma from histopathological digitalized slides with clinically acceptable accuracy. Whole-slide digital images from 100 formalin-fixed paraffin-embedded primary cutaneous melanoma were used to train a convolutional neural network (CNN) based on a pretrained Inception-ResNet-v2 to accurately and automatically differentiate tumoral areas from healthy tissue. The CNN was trained by using 60 digital slides in which regions of interest (ROIs) of tumoral and healthy tissue were extracted by experienced dermatopathologists, while the other 40 slides were used as test datasets. A total of 1377 patches of healthy tissue and 2141 patches of melanoma were assessed in the training/validation set, while 791 patches of healthy tissue and 1122 patches of pathological tissue were evaluated in the test dataset. Considering the classification by expert dermatopathologists as reference, the trained deep net showed high accuracy (96.5%), sensitivity (95.7%), specificity (97.7%), F1 score (96.5%), and a Cohen’s kappa of 0.929. Our data show that a deep learning system can be trained to recognize melanoma samples, achieving accuracies comparable to experienced dermatopathologists. Such an approach can offer a valuable aid in improving diagnostic efficiency when expert consultation is not available, as well as reducing interobserver variability. Further studies in larger data sets are necessary to verify whether the deep learning algorithm allows subclassification of different melanoma subtypes.

Biomedical Data Analysis Systems for the Diagnosis of Skin Neoplasms

Introduction. The effectiveness of the diagnosis of malignant neoplasms of the skin remains unsatisfactory due to the complex process of interpretation of clinical features. On the other hand, in the last two decades, noninvasive optical diagnostic methods have been actively developed, for example, digital dermatoscopy for visualization of surface neoplasms and Optical Coherence Tomography (OCT) for obtaining spatial scans. Recent advances in the study of non-invasive diagnostic tools makes this area very promising for research in a clinical condition. Aim. Developing of software modules based on the mathematical framework of texture analysis for biomedical data systems designed for the diagnosis of skin malignant neoplasms. Materials and methods. Algorithms of software modules developed for optical systems of our own design are presented. Algorithms for a dermatoscopic module are based on the Haar transform, Local Binary Patterns and color features. Algorithms for OCT are based on the texture features of Haralick, Tamura, fractal dimension, complex directional field and Markov random field. Studies were conducted on sets of 106 dermatoscopic and 1008 OCT images of various classes of pathologies, including melanoma and Basal Cell Carcinoma (BCC). Results. The values of sensitivity and specificity for the dermatoscopic system and OCT were experimentally obtained. Conclusion. The sensitivity of the dermatoscopic system is 90 % versus 93 % for other authors, as well as the specificity is 86 % versus 80 %. One of the factors of the increase can be considered the introduction of a personalized mode - the addition of comparative features evaluating a difference between a tumor and a normal tissue in the software analysis module. The improved accuracy of OCT is up to 97 % for the diagnosis of melanoma and up to 96 % for the diagnosis of BCC.

Comparing the capabilities of transfer learning models to detect skin lesion in humans.

Effective diagnosis of skin tumours mainly relies on the analysis of the characteristics of the lesion. Automatic detection of malignant skin lesion has become a mandatory task to reduce the risk of human deaths and increase their survival. This article proposes a study of skin lesion classification using transfer learning approach. The transfer learning model uses four different state-of-the-art architectures, namely Inception v3, Residual Networks (ResNet 50), Dense Convolutional Networks (DenseNet 201) and Inception Residual Networks (Inception ResNet v2). These models are trained under the dataset comprising seven different classes of skin lesions. The skin lesion images are pre-processed using image quantization, grayscaling and the Wiener filter before final training step. These models are compared for performance evaluation on different metrics. The present study shows the efficacy of the methodology for automated classification of lesion images.