Skin Cancer Lesions Research Articles

Potential of Polymeric Films Loaded with Gold Nanorods for Local Hyperthermia Applications.

Current strategies for the treatment of superficial non-melanoma skin cancer (NMSC) lesions include topical imoquimod, 5-fluorouracil, and photodynamic therapy. Although these treatments are effective, burning pain, blistering, and dermatitis have been reported as frequent side effects, making these therapies far from ideal. Plasmonic materials have been investigated for the induction of hyperthermia and use in cancer treatment. In this sense, the effectiveness of intratumorally and systemically injected gold nanorods (GnRs) in inducing cancer cell death upon near-infrared light irradiation has been confirmed. However, the in vivo long-term toxicity of these particles has not yet been fully documented. In the present manuscript, GnRs were included in a crosslinked polymeric film, evaluating their mechanical, swelling, and adhesion properties; moreover, their ability to heat up neonatal porcine skin (such as a skin model) upon irradiation was tested. Inclusion of GnRs into the films did not affect mechanical or swelling properties. GnRs were not released after film swelling, as they remained entrapped in the polymeric network; moreover, films did not adhere to porcine skin, altogether showing the enhanced biocompatibility of the material. GnR-loaded films were able to heat up the skin model over 40 °C, confirming the potential of this system for non-invasive local hyperthermia applications.

Evaluation for Skin Cancer and Precancer in Patients With Vitiligo Treated With Long-term Narrowband UV-B Phototherapy

Narrowband UV-B (NBUVB) phototherapy has been the mainstay in the treatment of vitiligo, but its long-term safety in terms of photocarcinogenesis has not been established. To investigate the risks of skin cancer and precancerous lesions among patients with vitiligo undergoing NBUVB phototherapy, based on the number of NBUVB phototherapy sessions. This nationwide population-based retrospective cohort study enrolled 60 321 patients with vitiligo 20 years or older between January 1, 2007, and December 31, 2017. Patients and outcomes were identified through nationwide cohort data from the Korean national health insurance claims database, and frequency matching by age and sex was performed. The number of phototherapy sessions each patient received between 2008 and 2017. Patients were classified into 5 groups according to the number of phototherapy sessions (0 sessions, 20 105 patients; 1-49 sessions, 20 106 patients; 50-99 sessions, 9702 patients; 100-199 sessions, 6226 patients; and ≥200 sessions, 4182 patients). We also identifed patients who underwent at least 500 phototherapy sessions (717 patients). Primary outcomes were the development of actinic keratosis, Bowen disease, nonmelanoma skin cancer, or melanoma after enrollment. Among the 60 321 patients with vitiligo in this study (33 617 women; mean [SD] age, 50.2 [14.9] years), the risks of Bowen disease (<50 sessions of phototherapy: hazard ratio [HR], 0.289 [95% CI, 0.060-1.392]; 50-99 sessions: HR, 0.603 [95% CI, 0.125-2.904]; 100-199 sessions: HR, 1.273 [95% CI, 0.329-4.924]; ≥200 sessions: HR, 1.021 [95% CI, 0.212-4.919]), nonmelanoma skin cancer (<50 sessions: HR, 0.914 [95% CI, 0.533-1.567]; 50-99 sessions: HR, 0.765 [95% CI, 0.372-1.576]; 100-199 sessions: HR, 0.960 [95% CI, 0.453-2.034]; ≥200 sessions: HR, 0.905 [95% CI, 0.395-2.073]), and melanoma (<50 sessions: HR, 0.660 [95% CI, 0.286-1.526]; 50-99 sessions: HR, 0.907 [95% CI, 0.348-2.362]; 100-199 sessions: HR, 0.648 [95% CI, 0.186-2.255]; ≥200 sessions: HR, 0.539 [95% CI, 0.122-2.374]) did not increase after phototherapy. The risk of actinic keratosis increased significantly for those who had undergone 200 or more NBUVB phototherapy sessions (HR, 2.269 [95% CI, 1.530-3.365]). A total of 717 patients with vitiligo underwent at least 500 sessions of NBUVB phototherapy; their risks of nonmelanoma skin cancer and melanoma were no greater than those of the patients who did not undergo NBUVB phototherapy (nonmelanoma skin cancer: HR, 0.563 [95% CI, 0.076-4.142]; melanoma: HR, not applicable). Our results suggest that long-term NBUVB phototherapy is not associated with an increased risk of skin cancer in patients with vitiligo and that NBUVB phototherapy may be considered a safe treatment.

Protein Oxidative Damage in UV-Related Skin Cancer and Dysplastic Lesions Contributes to Neoplastic Promotion and Progression.

The ultraviolet (UV) component of solar radiation is the major driving force of skin carcinogenesis. Most of studies on UV carcinogenesis actually focus on DNA damage while their proteome-damaging ability and its contribution to skin carcinogenesis have remained largely underexplored. A redox proteomic analysis of oxidized proteins in solar-induced neoplastic skin lesion and perilesional areas has been conducted showing that the protein oxidative burden mostly concerns a selected number of proteins participating to a defined set of functions, namely: chaperoning and stress response; protein folding/refolding and protein quality control; proteasomal function; DNA damage repair; protein- and vesicle-trafficking; cell architecture, adhesion/extra-cellular matrix (ECM) interaction; proliferation/oncosuppression; apoptosis/survival, all of them ultimately concurring either to structural damage repair or to damage detoxication and stress response. In peri-neoplastic areas the oxidative alterations are conducive to the persistence of genetic alterations, dysfunctional apoptosis surveillance, and a disrupted extracellular environment, thus creating the condition for transformant clones to establish, expand and progress. A comparatively lower burden of oxidative damage is observed in neoplastic areas. Such a finding can reflect an adaptive selection of best fitting clones to the sharply pro-oxidant neoplastic environment. In this context the DNA damage response appears severely perturbed, thus sustaining an increased genomic instability and an accelerated rate of neoplastic evolution. In conclusion UV radiation, in addition to being a cancer-initiating agent, can act, through protein oxidation, as a cancer-promoting agent and as an inducer of genomic instability concurring with the neoplastic progression of established lesions.

Discrimination between Healthy and Unhealthy Mole Lesions using Artificial Swarm Intelligence

In recent years, occurrence rates of skin melanoma have shown a rapid increase, resulting in enhancements to death rates. Based on the difficulty and subjectivity of human clarification, computer examination of dermoscopy images has thus developed into a significant research field in this area. One the reasons for applying heuristic methods is that good solutions can be developed with only reasonable computational exertion. This paper thus presents an artificial swarm intelligence method with variations and suggestions. The proposed artificial bee colony (ABC) is a more suitable algorithm in comparison to other algorithms for detecting melanoma in the skin tumour lesions, being flexible, fast, and simple, and requiring fewer adjustments. These is characteristics are recognized assisting dermatologists to detect malignant melanoma (MM) at the lowest time and effort cost. Automatic classification of skin cancers by using segmenting the lesion’s regions and selecting of the ABC technique for the values of the characteristic principles allows. Information to be fed into several well-known algorithms to obtain skin cancer categorization: in terms of whether the lesion is suspicious, malignant, benign (healthy and unhealthy nevi). This segmentation approach can further be utilized to develop handling and preventive approaches, thus decreasing the danger of skin cancer lesions. One of the most significant stages in dermoscopy image examination is the segmentation of the melanoma. Here, various PH2 dataset image were utilized along with their masks to estimate the accuracy, sensitivity, and specificity of various segmentation techniques. The results show that a modified automatic based on ABC images have the highest accuracy and specificity compares with the other algorithms. The results show that a modified automatic based on ABC images displayed the highest accuracy and specificity in such testing.

Changes to skin cancer staging in American Joint Committee on Cancer 8th edition

The American Joint Committee on Cancer (AJCC) has an irreplaceable importance with its guidelines for cancer staging. These staging procedures are carried out with retrospective and prospective analysis studies. In the light of the new data, there may be an increase or decrease in the staging of some skin cancer lesions, while some concepts are completely eliminated. In the 8th Edition of the AJCC Manual, which is published approximately 7 years after the previous edition, changes were made in line with the new data on skin cancers. The most prominent change for squamous cell carcinoma of the skin is the discrimination between “clinical (cN)” and “pathological (pN)” staging. The most prominent change for Merkel cell carcinoma is that “cN” and “pN” distinction has been introduced for both regional lymph node and distant metastasis. In terms of melanoma, it can be said that everything related to a tumor, a regional lymph node, and a distant metastasis have been changed. Given the fact that the next edition will not be released earlier than at least another 7 years, it is necessary to quickly become acquainted with this new edition for the benefit of treating and monitoring patients with skin cancer.

Predictive Value of Preoperative Periocular Skin Cancer Measurements for Final Mohs Defect Size.

To evaluate the relationship between pre-Mohs skin cancer lesion measurements with the post-Mohs defect size in order to most accurately estimate post-Mohs defect size. This is a retrospective analysis of patients who underwent Mohs excision by one of 3 Mohs surgeons followed by reconstruction for basal cell carcinoma or squamous cell carcinoma of the eyelid. The study included all patients from January 2011 to May 2018 operated on by a single oculoplastic surgeon (R.M.) at the University of Texas Southwestern Medical Center. Maximum horizontal and vertical (H/V) dimensions were determined clinically by Mohs surgeons at the time of excision and photographs of the lesion and defect size were analyzed in order to determine the total area of the lesion preoperatively and the defect postoperatively with Image J using H/V dimensions and the area tracing function. Forty-two patients with periocular skin cancers underwent Mohs resection followed by reconstruction. The Mohs defect was overall 4.88 times the size of the preoperative skin cancer measurement using maximum H/V dimensions by Mohs surgeons (p < 0.0001). When using Image J, the area of the Mohs defect was 6.5 times the size of the preoperative lesion (p < 0.0001) using both the maximum H/V dimensions and the area tracing function. There was a statistically significant difference between the Image J area tracing and area determined with H/V dimensions by both the Mohs surgeon and Image J. Postoperative Mohs defect size can be estimated based on maximum H/V dimensions clinically or with Image J technology. Image J digital photograph analysis using the area tracing function more accurately determines the pre-Mohs lesion size and the post-Mohs defect area when compared with standard maximum H/V measurements and digital photographic analysis of maximum H/V measurements with Image J.The preoperative periocular skin cancer measurements can assist in determining the post-Mohs defect size.

Successful application of modified keystone flaps following skin tumor ablation.

Skin cancer and precancerous skin lesions cause significant soft-tissue defects following tumor ablation. Recently, keystone flaps have gained popularity due to their simplicity, versatility, and reliability.We evaluated the efficacy of modified keystone flaps for soft-tissue reconstruction following skin tumor ablation in 2 medical centers.We reviewed the medical records of patients who received modified keystone flaps following the removal of skin tumors from January 2017 to December 2017. The diagnosis, site, flap size, and complications were recorded.Forty-one modified keystone flaps were evaluated, and the wound dimensions ranged from 1 cm × 1 cm to 18 cm × 9.5 cm, with an average size of 9.8 cm × 6.4 cm. With our selection strategy, specific modified keystone flaps were designed for the soft-tissue defects. The flap dimensions ranged from 2.2 cm × 1 cm to 26 cm × 10 cm, with an average size of 14.3 cm × 7.5 cm. Two patients developed minor wound dehiscence (4.9%), and 1 patient developed partial flap loss (2.4%), but all of these patients healed after local wound care without the need for surgical intervention.Our selection strategy for modified keystone flaps is a feasible and reliable option for reconstruction following skin tumor excision.

Dermatological and Epidemiological Profiles of Patients with Albinism in São Paulo, Brazil, between 2010 and 2017: A Cross-Sectional Study

Introduction: Oculocutaneous albinism is an autosomal recessive disease caused by complete absence of or decrease in melanin biosynthesis in melanocytes. Due to the reduction or absence of melanin, albinos are highly susceptible to the harmful effects of ultraviolet radiation and are at greater risk of actinic damage and skin cancer. There are no epidemiological data on the incidence of albinism in Brazil. Objective: To analyze the clinical and epidemiological profile of patients with albinism treated by the Pró-Albino Program of the Dermatology Clinic of Santa Casa de Misericórdia from its beginning in 2010 until 2017. Methods: In this cross-sectional study, the records of all consecutive albino patients admitted to the service in the study period were reviewed. Sociodemographic data, family history, and dermatological clinical data were collected. Results: Between March 2010 and April 2017, 191 patients were admitted, of whom 109 were female (57.07%) and the age range was 0–92 years, with >30% under the age of 18 years. Consanguinity among the parents was confirmed by 26% of the patients. Unprotected sun exposure was reported by 109 (57.07%), and 138 (72.25%) had a history of sunburn. Of the 146 records with information, 38 had skin cancer (26%), with a mean age of 47.4 (p < 0.0001); the youngest patient diagnosed with a cutaneous tumor was 23 years old. The prevalence of actinic damage was high. There was information on solar elastosis and actinic keratosis in 148 medical records, of which 96 (64.8%) patients had elastosis and 75 (50.67%) keratoses. Elastosis, keratosis, and skin cancer were significantly associated with age, unprotected sun exposure, and sunburn (p < 0.05). Of the 37 (26% of the sample of 146) patients with a previous or current history of skin cancer, it was possible to identify the histological type in 29 (13 men and 16 women); of these, 18 (62%) were basal cell carcinomas (BCC), 15 (51%) were squamous cell carcinomas (SCC), and 2 (7%) were melanomas. Of these, 4 cases (14%) presented the 2 types of carcinoma (BCC and SCC), and the 2 that had a diagnosis of melanoma also had BCC. Some patients had multiple ulcerated tumors. The tumor site was preferentially in the head and neck (43%), trunk (37%) and limbs (20%). Conclusions: Albinos represent a risk group for skin cancer and other actinic lesions. These lesions were found to be prevalent in the albinos seen by the program and probably reflect the characteristics found in the Brazilian albino population. Access to health care, especially through multidisciplinary programs that enable the diagnosis and early treatment of these lesions, health education, and the use of photoprotective measures can reduce morbidity and mortality and improve the quality of life of patients with this rare genetic condition.

Topical Sunscreen Application Preventing Skin Cancer: Systematic Review

Background: Avoiding extended exposure to direct sunlight and the topical application of sunscreen when exposed are the main techniques used to protect the skin form sunburn, photoaging, and skin cancer risk (melanoma and non-melanoma skin cancer). Preventive strategies could lead to a significant reduction of the excessive health system cost for the treatment of these conditions. Sunscreen employment and efficacy stay controversial despite decades of humane use with health benefits closely related. At the present, few studies still found a connection between the use of sunscreen and not significant long-term benefits from UV induced damages. Objectives: To assess the effects of sunscreens for preventing melanoma, non-melanoma skin cancer (basal or squamous carcinoma and melanoma) and precancerous skin lesions. Method: Published literature (1993–2017) was reviewed and eligible studies that reported the impact of sunscreen use in the prevention of melanoma, non-melanoma skin cancer, or precancerous skin lesion were selected. Result: Starting from 532 sources, a total of seven articles met the inclusion criteria and they have been subjected to a systematic review. All of the included studies suggest that sunscreen use is associated with a reduction in melanoma, squamous cell carcinoma, and precancerous skin lesions; however, the difficulties in evaluating the efficiency of sunscreen were pointed out. Conclusion: The review of the experimental evidence supports the topical application of sunscreen as an effective effort in preventing skin cancer and precancerous skin lesions.

Effect of laser irradiation on the progression of skin cancer using carcinogen among hamsters

Introduction: Skin cancer has been increased day by day, but it can be cured if it diagnosed early. After reviewing the scientific literature about 980 nm diode laser, and its multiple advantages on skin diseases. We studied in this paper the effectiveness of this type of laser on the progression of skin cancer among hamsters which were exposed to carcinogen on the back. Material and Methods: The carcinogenic solution of 9, 10-dime thy 1-1, 2-benzanthracene was applied to the hamsters' skin on the back. A 980 nm Diode laser light with irradiation power of 0.5w and 1.0w and an exposure time of 100 sec were used in order to prevent the harmful thermal effect on surrounding tissue as studied in previous paper [1]. Results: According to the results, only one group of hamsters which was not consistently irradiated by laser gave rise to melanoma tumor. The other groups that were exposed to diode 980nm laser irradiation at different powers (i.e., 0.5w and 1.0w) and an exposure time of 100 sec showed no growth of skin cancer during the experiment. Conclusion: The 980 nm Diode laser has an effect on delaying the onset of cancer and has had a role in the reduction of skin cancer lesions. However, further studies are required to test its inhibitory activities against carcinogenesis.

Analysis of patient perceptions of Mohs surgery on social media platforms.

This study assessed social media content to improve understanding of patient experiences with Mohs surgery. An initial search of public Instagram posts and tweets tagged with "#mohssurgery" or "@mohssurgery" identified 1692 Instagram posts and 115 tweets, of which 1390 and 94 were eliminated, respectively, given that they did not directly include a patient's own experience. The team analyzed the posts/tweets for patient gender, timing of post prior to or after their procedure, and classified themes related to patients' experience with Mohs. Analysis showed that 91.4% of Instagram posts and 75.0% of tweets were published post-Mohs surgery, with the majority made by women. The most common theme on Twitter was updating followers on treatment progress (30.0%) and on Instagram, the most common theme was spreading awareness of skin cancer/encouraging others to protect their skin (18.9%). Other common themes included concern of appearance during recovery process, scars after treatment, and healing progress. Social media has the ability to provide a platform for patients to impart their personal experiences with Mohs surgery performed on skin cancer lesions.

Automated Segmentation of Abnormal Tissues in Medical Images.

Nowadays, medical image modalities are almost available everywhere. These modalities are bases of diagnosis of various diseases sensitive to specific tissue type. Usually physicians look for abnormalities in these modalities in diagnostic procedures. Count and volume of abnormalities are very important for optimal treatment of patients. Segmentation is a preliminary step for these measurements and also further analysis. Manual segmentation of abnormalities is cumbersome, error prone, and subjective. As a result, automated segmentation of abnormal tissue is a need. In this study, representative techniques for segmentation of abnormal tissues are reviewed. Main focus is on the segmentation of multiple sclerosis lesions, breast cancer masses, lung nodules, and skin lesions. As experimental results demonstrate, the methods based on deep learning techniques perform better than other methods that are usually based on handy feature engineering techniques. Finally, the most common measures to evaluate automated abnormal tissue segmentation methods are reported

Morphological study of skin cancer lesions through a 3D scanner based on fringe projection and machine learning.

The effective and non-invasive diagnosis of skin cancer is a hot topic, since biopsy is a costly and time-consuming surgical procedure. As skin relief is an important biophysical feature that can be difficult to perceive with the naked eye and by touch, we developed a novel 3D imaging scanner based on fringe projection to obtain morphological parameters of skin lesions related to perimeter, area and volume with micrometric precision. We measured 608 samples and significant morphological differences were found between melanomas and nevi (p<0.001). The capacity of the 3D scanner to distinguish these lesions was supported by a supervised machine learning algorithm resulting in 80.0% sensitivity and 76.7% specificity.

Skin Cancer Diagnostics with an All-Inclusive Smartphone Application

Among the different types of skin cancer, melanoma is considered to be the deadliest and is difficult to treat at advanced stages. Detection of melanoma at earlier stages can lead to reduced mortality rates. Desktop-based computer-aided systems have been developed to assist dermatologists with early diagnosis. However, there is significant interest in developing portable, at-home melanoma diagnostic systems which can assess the risk of cancerous skin lesions. Here, we present a smartphone application that combines image capture capabilities with preprocessing and segmentation to extract the Asymmetry, Border irregularity, Color variegation, and Diameter (ABCD) features of a skin lesion. Using the feature sets, classification of malignancy is achieved through support vector machine classifiers. By using adaptive algorithms in the individual data-processing stages, our approach is made computationally light, user friendly, and reliable in discriminating melanoma cases from benign ones. Images of skin lesions are either captured with the smartphone camera or imported from public datasets. The entire process from image capture to classification runs on an Android smartphone equipped with a detachable 10x lens, and processes an image in less than a second. The overall performance metrics are evaluated on a public database of 200 images with Synthetic Minority Over-sampling Technique (SMOTE) (80% sensitivity, 90% specificity, 88% accuracy, and 0.85 area under curve (AUC)) and without SMOTE (55% sensitivity, 95% specificity, 90% accuracy, and 0.75 AUC). The evaluated performance metrics and computation times are comparable or better than previous methods. This all-inclusive smartphone application is designed to be easy-to-download and easy-to-navigate for the end user, which is imperative for the eventual democratization of such medical diagnostic systems.

Analysis of Raman spectroscopy data with algorithms based on paraconsistent logic for characterization of skin cancer lesions

Analysis of the Raman data to obtain results in discrimination models is usually done with multivariate statistics based on principal component analysis (PCA). In this work, we present a technique based on a non-classical logic called paraconsistent logic (PL). The aim of this work is to use computational procedures capable of generating efficient expert systems to discriminate cutaneous tissue samples obtained by Raman spectroscopy. First, a set of algorithms originating from PL is presented, and then its application in discrimination analyses is described; the discrimination analysis was conducted using a database of skin tissue samples obtained ex vivo by Raman spectroscopy of spectrum range of 400–1800 cm−1 wavelengths. Data processing, pattern creation, and comparisons were performed using the set of paraconsistent algorithms (SPA-PAL2v). The total number of samples was divided into four histopathological groups, with 115 spectra of basal cell carcinoma (BCC), 21 spectra of squamous cell carcinoma (SCC), 57 spectra of actinic keratosis (AK), and 30 normal skin (NO) spectra. An arrangement type was created for this study, and the samples were randomly selected and analyzed, and the NO group was compared with the group of non-melanoma cancer lesions (BCC + SCC) and the AK tumor lesion. Two analyses were performed. The first (SPA-PAL2v) Mode 1 (no cross-validation) achieved 76% of hits, and the second (SPA-PAL2v) Mode 2 (with cross-validation) achieved 75.78% of hits. These results were compared with discrimination using PCA statistical methods (PCA/DA) and presented superior percentages of hits, which proves the robustness of the SPA-PAL2v, confirming its potential for Raman spectrum data analysis.

Characterization of thermographic images of skin cancer lesions using digital image processing

Skin cancer is the type of cancer with the highest incidence in the world. The alterations of temperature in the skin are organic indicators of the presence of several types of skin cancer, mainly squamous cell carcinomas and melanomas. In this work, thermographic images of lesions of this type were analyzed in order to find indicators of the presence of this neoplasm that allow the future development of a detection algorithm. The digital processing used consists of identification of areas of interest, color segmentation, quantitative discrimination according to color tonality and analysis by histograms. The results showed that lesions with skin cancer have values in the red component above 100 under the RGB color space on a scale of 0 to 255. Also, when segmenting, by the k-means algorithm, a thermography containing a melanoma, the area that contains the lesion has a higher average value in the red component with respect to the other areas. Taking these results into account, a non-invasive tool for prediagnosing skin cancer can be developed that reduces unnecessary clinical procedures and simplifies the diagnosis.

Various Types of Skin Tumors Lesion Medical Imaging (STLMI) of Healthy and Unhealthy Moles a Review and Computational of: Segmentation, Classification, Methods and Algorithms

Over recent decades, updates in the field of the imaging of skin tumor lesions and biomedical sensing at the side of its related clinical implementations have attracted the attention of scientists. The major aim is to develop an artificial bee colony algorithmic and other approaches to propose different types of skin cancer lesion medical imaging, utilizing medical images achieved through different imaging methods. The artificial bee colony is frequently used to get highly accurate analysis, which supports the early detection of that which poses a threat to life, and, this method can be a good area to examine for future research. We compared the achievement of many works that were developed specially to detect the skin tumours lesion of healthy and unhealthy nevi after the use of methods and algorithms to obtain good processing results and discussed the relevant conclusions. The paper presents develop various classification, segmentation, methods and algorithms to recognize benign and malignant nevi to help make an expert decision on dermatology. These methods would allow not just earlier detection of skin cancer cases, however, decreasing of the number of unnecessary of steps in image processing and costly process.

Melanoma segmentation using bio-medical image analysis for smarter mobile healthcare

Dermoscopy is an excellent method of detecting melanoma in its early stages. Skin is the principal organ of human body. It covers bones, muscles and all parts of the body. Melanoma is rare, but it is the most dangerous form of skin cancer. It is curable if it is detectedin its early stages. Digital dermoscopy help dermatologists in theexamination of cancerous skin lesions. It enables doctors to capture microscopic images of moles by using amobile phone, corresponding application or any handy scope device. Segmentation is used to divide the image into different segments. Segmentation, classification and feature extraction are the three fundamental stages of arecognition system that helps in matching the analysis of skin lesion. Melanoma occurs due to the presence of Melanocytes in the body. With the use of dermoscopy, the dermatologists can examine individual lesions more closely. In our paper, we have proposed an approach that can automatically preprocess the image and then segment the lesion.The gradient magnitude of the image is calculatedto filter the images. We have marked the foreground objects to segment the lesion from background precisely. The proposed technique is tested on European dataset of dermoscopic images. Results of segmented images are compared with other competitors to exhibit the superiority of the recommended approach. Matlab 2016a is used for successful simulation of the experiment.

Dermoscopy diagnosis of cancerous lesions utilizing dual deep learning algorithms via visual and audio (sonification) outputs: Laboratory and prospective observational studies.

BackgroundEarly diagnosis of skin cancer lesions by dermoscopy, the gold standard in dermatological imaging, calls for a diagnostic upscale. The aim of the study was to improve the accuracy of dermoscopic skin cancer diagnosis through use of novel deep learning (DL) algorithms. An additional sonification-derived diagnostic layer was added to the visual classification to increase sensitivity.MethodsTwo parallel studies were conducted: a laboratory retrospective study (LABS, n = 482 biopsies) and a non-interventional prospective observational study (OBS, n = 63 biopsies). A training data set of biopsy-verified reports, normal and cancerous skin lesions (n = 3954), were used to develop a DL classifier exploring visual features (System A). The outputs of the classifier were sonified, i.e. data conversion into sound (System B). Derived sound files were analyzed by a second machine learning classifier, either as raw audio (LABS, OBS) or following conversion into spectrograms (LABS) and by image analysis and human heuristics (OBS). The OBS criteria outcomes were System A specificity and System B sensitivity as raw sounds, spectrogram areas or heuristics.FindingsLABS employed dermoscopies, half benign half malignant, and compared the accuracy of Systems A and B. System A algorithm resulted in a ROC AUC of 0.976 (95% CI, 0.965–0.987). Secondary machine learning analysis of raw sound, FFT and Spectrogram ROC curves resulted in AUC's of 0.931 (95% CI 0.881–0.981), 0.90 (95% CI 0.838–0.963) and 0.988 (CI 95% 0.973–1.001), respectively. OBS analysis of raw sound dermoscopies by the secondary machine learning resulted in a ROC AUC of 0.819 (95% CI, 0.7956 to 0.8406). OBS image analysis of AUC for spectrograms displayed a ROC AUC of 0.808 (CI 95% 0.6945 To 0.9208). By applying a heuristic analysis of Systems A and B a sensitivity of 86% and specificity of 91% were derived in the clinical study.InterpretationAdding a second stage of processing, which includes a deep learning algorithm of sonification and heuristic inspection with machine learning, significantly improves diagnostic accuracy. A combined two-stage system is expected to assist clinical decisions and de-escalate the current trend of over-diagnosis of skin cancer lesions as pathological.FundBostel Technologies.Trial Registration clinicaltrials.gov Identifier: NCT03362138

In Vivo Biomechanical Measurements of Benign and Cancerous Skin Lesions Using Vibrational Oct

Previous literature reports suggest that tissue stiffness is a predictor of cancer and metastatic behavior of lesions. We have used optical coherence tomography and vibrational analysis (VOCT) to characterize normal skin, sca... | Find, read and cite all the research you need on Tech Science Press