Non-melanocytic Skin Lesions Research Articles

Computerizing the first step of the two-step algorithm in dermoscopy: A convolutional neural network for differentiating melanocytic from non-melanocytic skin lesions

ImportanceConvolutional neural networks (CNN) have shown performance equal to trained dermatologists in differentiating benign from malignant skin lesions. To improve clinicians’ management decisions, additional classifications into diagnostic categories might be helpful. MethodsA convenience sample of 100 pigmented/non-pigmented skin lesions was used for a cross-sectional two-level reader study including 96 dermatologists (level I: dermoscopy only; level II: clinical close-up images, dermoscopy, and textual information). Dermoscopic images were classified by a binary CNN trained to differentiate melanocytic from non-melanocytic lesions (FotoFinder Systems, Bad Birnbach, Germany). Primary endpoint was the accuracy of the CNN’s classification in comparison with dermatologists reviewing level-II information. Secondary endpoints included dermatologists’ accuracies according to their level of experience and the CNN’s area under the curve (AUC) of receiver operating characteristics (ROC). ResultsThe CNN revealed an accuracy and ROC AUC with corresponding 95 % confidence intervals (CI) of 91.0 % (83.8 % to 95.2 %) and 0.981 (0.962 to 1). In level I, dermatologists showed a mean accuracy of 83.7 % (82.5 % to 84.8 %). With level II information, the accuracy improved to 87.8 % (86.7 % to 88.9 %; p < 0.001). When comparing accuracies of CNN and dermatologists in level II, the CNN’s accuracy was higher (91.0 % versus 87.8 %, p < 0.001). For experts with level II information results were on par with the CNN (91.0 % versus 90.4 %, p = 0.368). ConclusionsThe tested CNN accurately differentiated melanocytic from non-melanocytic skin lesions and outperformed dermatologists. The CNN may support clinicians and could be used in an ensemble approach combined with other CNN models.

Evaluation of Diagnostic Accuracy and Therapeutic Approach of Dermatologists and Plastic Surgeons To Non-Melanocytic Skin Lesions By Using Telemedicine.

IntroductionIn the new circumstances of coronavirus disease 2019 pandemic, tele-dermatology and tele-dermoscopy have become more important in daily practice for departments for which visuality is at the forefront as dermatology and plastic and reconstructive surgery.ObjectivesThis study was aimed to determine diagnostic accuracy and treatment approaches of non-melanocytic skin lesions between 2 clinics by store and forward tele-dermatology method and to evaluate the contribution of tele-dermoscopy to the diagnostic accuracy for dermatologists.MethodsA total of 26 patients with non-melanocytic skin lesions were included in the study. Clinical images of the lesions were sent by email to 3 plastic surgeons and 3 dermatologists. The accuracy of the diagnoses was evaluated by comparing tele-dermatology with histopathology. Diagnosis and treatment approaches were recorded for both clinics. Dermatologists also defined their diagnosis with tele-dermoscopic images.ResultsThe mean percentage of diagnostic accuracy among dermatologists was 74.3% and among plastic surgeons was 61.5%. There was no significant difference in diagnostic accuracy between departments (P = 0.625). There was a statistically significant difference between the departments for diagnostic and treatment approaches (P values respectively P = 0.002, P < 0.001). Plastic surgeons preferred to confirm their pre-diagnosis histopathologically more than dermatologists. Plastic surgeons recommended surgical procedures for 25 lesions (96.2%) while dermatologists for 14 (53.8%) ones. Tele-dermoscopy increased the rate of diagnostic accuracy of dermatologists from 74.3% to 82.0% (P = 0.02).ConclusionsTele-dermatology is an effective method for non-melanocytic skin lesions with high diagnostic accuracy. Adding dermoscopy to tele-dermatology increases diagnostic accuracy of dermatologists on non-melanocytic skin lesions.

Teledermoscopy in the Diagnosis of Melanocytic and Non-Melanocytic Skin Lesions: NurugoTM Derma Smartphone Microscope as a Possible New Tool in Daily Clinical Practice

Background: Due to the COVID-19 pandemic, teledermoscopy has been increasingly used in the remote diagnosis of skin cancers. In a study conducted in 2020, we demonstrated a potential role of an inexpensive device (NurugoTM Derma) as a first triage to select the skin lesions that require a face-to-face consultation with dermatologists. Herein, we report the results of a novel study that aimed to better investigate the performance of NurugoTM. Objectives: (i) verify whether the NurugoTM can be a communication tool between the general practitioner (GP) and dermatologist in the first assessment of skin lesions, (ii) analyze the degree of diagnostic–therapeutic agreement between dermatologists, (iii) estimate the number of potentially serious diagnostic errors. Methods: One hundred and forty-four images of skin lesions were collected at the Dermatology Outpatient Clinic in Novara using a conventional dermatoscope (instrument F), the NurugoTM (instrument N), and the latter with the interposition of a laboratory slide (instrument V). The images were evaluated in-blind by four dermatologists, and each was asked to make a diagnosis and to specify a possible treatment. Results: Our data show that F gave higher agreement values for all dermatologists, concerning the real clinical diagnosis. Nevertheless, a medium/moderate agreement value was obtained also for N and V instruments and that can be considered encouraging and indicate that all examined tools can potentially be used for the first screening of skin lesions. The total amount of misclassified lesions was limited (especially with the V tool), with up to nine malignant lesions wrongly classified as benign. Conclusions: NurugoTM, with adequate training, can be used to build a specific support network between GP and dermatologist or between dermatologists. Furthermore, its use could be extended to the diagnosis and follow-up of other skin diseases, especially for frail patients in emergencies, such as the current pandemic context.

Skin Lesion Image Classification using Convolutional Neural Network

Classification of skin cancer is an important task to detect skin cancer and help with the treatment of skin cancer according to its type. There are many techniques in imaging used to classify skin cancer, one of the superior deep learning (DL) algorithms for classification is the Convolutional Neural Network (CNN). One type of skin cancer is dangerous is melanoma. In this study, CNN is proposed to help classify this type of skin cancer. The dataset consists of 15103 images of skin cancer pigments with 7 different types of skin cancer. These three tests proved malignant skin lesions can be classified with higher accuracy than non-melanocytic skin lesions which is 90% and performance evaluation shows melanocytic and non-melanocytic skin lesions detected with the highest accuracy. The tests conducted in this study grouped several types of skin diseases namely the first tests conducted using a group of melanocytic and non-melanocytic skin disease, second testing using groups of melanoma and melanocytic nevus diseases, and the final testing using malignant and benign. The proposed CNN model achieved significant performance with a best accuracy of 94% on the classification of melanoma and melanocytic nevus.

Dermoscopy pathology correlation in melanoma.

Dermoscopy is a widely used technique whose role in the clinical (and preoperative) diagnosis of melanocytic and non-melanocytic skin lesions has been well established in recent years. The aim of this paper is to clarify the correlations between the "local" dermoscopic findings in melanoma and the underlying histology, in order to help clinicians in routine practice.

Development of A Clinically-Oriented Expert System for Differentiating Melanocytic from Non-melanocytic Skin Lesions

Differentiating melanocytic from non-melanocytic (MnM) skin lesions is the first and important step required by clinical experts to automatically diagnosis pigmented skin lesions (PSLs). In this paper, a new clinically-oriented expert system (COE-Deep) is presented for automatic classification of MnM skin lesions through deep-learning algorithms without focusing on pre- or post-processing steps. For the development of COE-Deep system, the convolutional neural network (CNN) model is employed to extract the prominent features from region-of-interest (ROI) skin images. Afterward, these features are further purified through stack-based autoencoders (SAE) and classified by a softmax linear classifier into categories of melanocytic and non-melanocytic skin lesions. The performance of COE-Deep system is evaluated based on 5200 clinical images dataset obtained from different public and private resources. The significance of COE-Deep system is statistical measured in terms of sensitivity (SE), specificity (SP), accuracy (ACC) and area under the receiver operating curve (AUC) based on 10-fold cross validation test. On average, the 90% of SE, 93% of SP, 91.5% of ACC and 0.92 of AUC values are obtained. It noticed that the results of the COE-Deep system are statistically significant. These experimental results indicate that the proposed COE-Deep system is better than state-of-the-art systems. Hence, the COE-Deep system is able to assist dermatologists during the screening process of skin cancer.

Prediction of Dermoscopy Patterns for Recognition of both Melanocytic and Non-Melanocytic Skin Lesions

A differentiation between all types of melanocytic and non-melanocytic skin lesions (MnM–SK) is a challenging task for both computer-aided diagnosis (CAD) and dermatologists due to the complex structure of patterns. The dermatologists are widely using pattern analysis as a first step with clinical attributes to recognize all categories of pigmented skin lesions (PSLs). To increase the diagnostic accuracy of CAD systems, a new pattern classification algorithm is proposed to predict skin lesions patterns by integrating the majority voting (MV–SVM) scheme with multi-class support vector machine (SVM). The optimal color and texture features are also extracted from each region-of-interest (ROI) dermoscopy image and then these normalized features are fed into an MV–SVM classifier to recognize seven classes. The overall system is evaluated using a dataset of 350 dermoscopy images (50 ROIs per class). On average, the sensitivity of 94%, specificity of 84%, 93% of accuracy and area under the receiver operating curve (AUC) of 0.94 are achieved by the proposed MnM–SK system compared to state-of-the-art methods. The obtained result indicates that the MnM–SK system is successful for obtaining the high level of diagnostic accuracy. Thus, it can be used as an alternative pattern classification system to differentiate among all types of pigmented skin lesions (PSLs).

Dermoscopy-guided reflectance confocal microscopy of skin using high-NA objective lens with integrated wide-field color camera.

Reflectance Confocal Microscopy, or RCM, is being increasingly used to guide diagnosis of skin lesions. The combination of widefield dermoscopy (WFD) with RCM is highly sensitive (~90%) and specific (~ 90%) for noninvasively detecting melanocytic and non-melanocytic skin lesions. The combined WFD and RCM approach is being implemented on patients to triage lesions into benign (with no biopsy) versus suspicious (followed by biopsy and pathology). Currently, however, WFD and RCM imaging are performed with separate instruments, while using an adhesive ring attached to the skin to sequentially image the same region and co-register the images. The latest small handheld RCM instruments offer no provision yet for a co-registered wide-field image. This paper describes an innovative solution that integrates an ultra-miniature dermoscopy camera into the RCM objective lens, providing simultaneous wide-field color images of the skin surface and RCM images of the subsurface cellular structure. The objective lens (0.9 NA) includes a hyperhemisphere lens and an ultra-miniature CMOS color camera, commanding a 4 mm wide dermoscopy view of the skin surface. The camera obscures the central portion of the aperture of the objective lens, but the resulting annular aperture provides excellent RCM optical sectioning and resolution. Preliminary testing on healthy volunteers showed the feasibility of combined WFD and RCM imaging to concurrently show the skin surface in wide-field and the underlying microscopic cellular-level detail. The paper describes this unique integrated dermoscopic WFD/RCM lens, and shows representative images. The potential for dermoscopy-guided RCM for skin cancer diagnosis is discussed.

Cutaneous Oncology: From Research to Diagnosis and Management

Cutaneous Oncology: From Research to Diagnosis and Management

Computer-assisted melanoma diagnosis: a new integrated system.

In dermatology, attempts at synergy between man and machine have mainly been made to improve melanoma diagnosis. The aim of the present study was to test an 'integrated digital dermoscopy analysis' (i-DDA) system with a series of melanocytic lesions that were benign and malignant in nature, and to evaluate its discriminating power with respect to histological diagnosis. In a retrospective study we used an i-DDA system to evaluate a series of 856 excised, clinically atypical pigmented skin lesions (584 benign and 272 malignant). The system evaluated 48 parameters to be studied as possible discriminant variables, grouped into four categories (geometries, colours, textures and islands of colour) integrated with three personal metadata items (sex, age and site of lesion) and presence/absence of three dermoscopic patterns (regression structures, blue-white veil and polymorphic vascular structures). Stepwise multivariate logistic regression of i-DDA data selected nine variables with the highest possible discriminant power. At the end of the stepwise procedure the percentage of cases correctly classified by i-DDA was 89.2% (100% sensitivity and 40.8% specificity). The limitations of the study included those associated with a retrospective design and the 'a priori' exclusion of nonmelanocytic skin lesions. By incorporating numerical digital features with personal data and some dermoscopic patterns into the learning process, the proposed i-DDA improved the performance of assisted melanoma diagnosis, with the advantage that our results can be objectively repeated in any other clinical setting.

The feasibility of using manual segmentation in a multifeature computer-aided diagnosis system for classification of skin lesions: a retrospective comparative study

ObjectivesTo investigate the feasibility of manual segmentation by users of different backgrounds in a previously developed multifeature computer-aided diagnosis (CADx) system to classify melanocytic and non-melanocytic skin lesions based on...

Computer-Aided Decision Support for Melanoma Detection Applied on Melanocytic and Nonmelanocytic Skin Lesions: A Comparison of Two Systems Based on Automatic Analysis of Dermoscopic Images.

Commercially available clinical decision support systems (CDSSs) for skin cancer have been designed for the detection of melanoma only. Correct use of the systems requires expert knowledge, hampering their utility for nonexperts. Furthermore, there are no systems to detect other common skin cancer types, that is, nonmelanoma skin cancer (NMSC). As early diagnosis of skin cancer is essential, there is a need for a CDSS that is applicable to all types of skin lesions and is suitable for nonexperts. Nevus Doctor (ND) is a CDSS being developed by the authors. We here investigate ND's ability to detect both melanoma and NMSC and the opportunities for improvement. An independent test set of dermoscopic images of 870 skin lesions, including 44 melanomas and 101 NMSCs, were analysed by ND. Its sensitivity to melanoma and NMSC was compared to that of Mole Expert (ME), a commercially available CDSS, using the same set of lesions. ND and ME had similar sensitivity to melanoma. For ND at 95% melanoma sensitivity, the NMSC sensitivity was 100%, and the specificity was 12%. The melanomas misclassified by ND at 95% sensitivity were correctly classified by ME, and vice versa. ND is able to detect NMSC without sacrificing melanoma sensitivity.

Dermoscopic Characteristic Structures of Melanocytic Lesions

Dermoscopy has recorded continuous development in the past decades. Both global and individual features of dermoscopic morphology that play an role in identifying melanomas have enjoyed particular attention by researchers. Dermoscopy has gained an undoubted place in the detection of early melanomas. This paper is a review of data existent in literature that approach of dermoscopic morphology features of melanocytic pigmented skin lesions. This work highlights such situations where these features may be found in non-melanocytic pigmented skin lesions thus inducing confused diagnosis.

Four-class classification of skin lesions with task decomposition strategy.

This paper proposes a new computer-aided method for the skin lesion classification applicable to both melanocytic skin lesions (MSLs) and nonmelanocytic skin lesions (NoMSLs). The computer-aided skin lesion classification has drawn attention as an aid for detection of skin cancers. Several researchers have developed methods to distinguish between melanoma and nevus, which are both categorized as MSL. However, most of these studies did not focus on NoMSLs such as basal cell carcinoma (BCC), the most common skin cancer and seborrheic keratosis (SK) despite their high incidence rates. It is preferable to deal with these NoMSLs as well as MSLs especially for the potential users who are not enough capable of diagnosing pigmented skin lesions on their own such as dermatologists in training and physicians with different expertise. We developed a new method to distinguish among melanomas, nevi, BCCs, and SKs. Our method calculates 828 candidate features grouped into three categories: color, subregion, and texture. We introduced two types of classification models: a layered model that uses a task decomposition strategy and flat models to serve as performance baselines. We tested our methods on 964 dermoscopy images: 105 melanomas, 692 nevi, 69 BCCs, and 98 SKs. The layered model outperformed the flat models, achieving detection rates of 90.48%, 82.51%, 82.61%, and 80.61% for melanomas, nevi, BCCs, and SKs, respectively. We also identified specific features effective for the classification task including irregularity of color distribution. The results show promise for enhancing the capability of the computer-aided skin lesion classification.

Extension of automated melanoma screening for non-melanocytic skin lesions

In this paper, we present an automated melanoma screening system that supports not only melanocytic skin lesions (MSLs) but also non-melanocytic skin lesions (NoMSLs). Melanoma is known as the most fatal skin cancer. Therefore, early detection is highly desired. However, melanoma diagnosis is not easy even for expert dermatologists. Several researchers have developed automated methods for melanoma detection but they mostly focused only on MSLs while NoMSLs have been almost neglected. To expand the scope to NoMSLs, we developed two melanoma classification models, namely the single-shot model and the double-shot model. The single-shot model differentiates melanomas from all the other skin lesions including NoMSLs. The double-shot model divides the task into two subtasks. Firstly, it differentiates MSLs from NoMSLs and then differentiates melanomas from the other MSLs. The single-shot achieved a sensitivity (SE) of 92.9% and a specificity (SP) of 83.9%, while the double-shot achieved an SE of 97.6% and an SP of 87.7% with ten image features. Through a detailed data analysis, we confirmed that the double-shot can exploit effective image features more than the single-shot as a result of its task decomposition method.

Computer-Aided Diagnosis of Skin Lesions Using Conventional Digital Photography: A Reliability and Feasibility Study

BackgroundComputer-aided diagnosis (CADx) software that provides a second opinion has been widely used to assist physicians with various tasks. In dermatology, however, CADx has been mostly limited to melanoma or melanocytic skin cancer diagnosis. The frequency of non-melanocytic skin cancers and the accessibility of regular digital macrographs have raised interest in developing CADx for broader applications.ObjectivesTo investigate the feasibility of using CADx to diagnose both melanocytic and non-melanocytic skin lesions based on conventional digital photographic images.MethodsThis study was approved by an institutional review board, and the requirement to obtain informed consent was waived. In total, 769 conventional photographs of melanocytic and non-melanocytic skin lesions were retrospectively reviewed and used to develop a CADx system. Conventional and new color-related image features were developed to classify the lesions as benign or malignant using support vector machines (SVMs). The performance of CADx was compared with that of dermatologists.ResultsThe clinicians' overall sensitivity, specificity, and accuracy were 83.33%, 85.88%, and 85.31%, respectively. New color correlation and principal component analysis (PCA) features improved the classification ability of the baseline CADx (p = 0.001). The estimated area under the receiver operating characteristic (ROC) curve (Az) of the proposed CADx system was 0.949, with a sensitivity and specificity of 85.63% and 87.65%, respectively, and a maximum accuracy of 90.64%.ConclusionsWe have developed an effective CADx system to classify both melanocytic and non-melanocytic skin lesions using conventional digital macrographs. The system's performance was similar to that of dermatologists at our institute. Through improved feature extraction and SVM analysis, we found that conventional digital macrographs were feasible for providing useful information for CADx applications. The new color-related features significantly improved CADx applications for skin cancer.

Electrical impedance spectroscopy as a potential adjunct diagnostic tool for cutaneous melanoma

Previous studies have shown statistically significant differences in electrical impedance between various cutaneous lesions. Electrical impedance spectroscopy (EIS) may therefore be able to aid clinicians in differentiating between benign and malignant skin lesions. The aim of the study was to develop a classification algorithm to distinguish between melanoma and benign lesions of the skin with a sensitivity of at least 98% and a specificity approximately 20 per cent higher than the diagnostic accuracy of dermatologists. A total of 1300 lesions were collected in a multicentre, prospective, non-randomized clinical trial from 19 centres around Europe. All lesions were excised and subsequently evaluated independently by a panel of three expert dermatopathologists. From the data two classification algorithms were developed and verified. For the first classification algorithm, approximately 40% of the data were used for calibration and 60% for testing. The observed sensitivity for melanoma was 98.1% (101/103), non-melanoma skin cancer 100% (25/25) and dysplastic nevus with severe atypia 84.2% (32/38). The overall observed specificity was 23.6% (66/280). For the second classification algorithm, approximately 55% of the data were used for calibration. The observed sensitivity for melanoma was 99.4% (161/162), for non-melanoma skin cancer was 98.0% (49/50) and dysplastic nevus with severe atypia was 93.8% (60/64). The overall observed specificity was 24.5% (116/474). EIS has the potential to be an adjunct diagnostic tool to help clinicians differentiate between benign and malignant (melanocytic and non-melanocytic) skin lesions. Further studies are needed to confirm the validity of the automatic assessment algorithm.

Different expression of cyclooxygenase-2 (COX-2) in selected nonmelanocytic human cutaneous lesions

The aim of our study was to elucidate the possible involvement of COX-2 in the development and/or progression of nonmelanocytic skin lesions. To evaluate the usefulness of that enzyme as a potential molecular marker, we examined the intensity and spatial distribution of COX-2 expression in selected types of such tumors using the same immunohistochemical procedure as in our earlier studies of melanocytic cancers. We examined 20 benign epithelial lesions, 11 precancerous lesions, 21 basal cell carcinomas (BCC), 14 squamous cell carcinomas (SCC) and eight fibromas. The levels of COX-2 expression detected in benign lesions and in normal skin were comparable. Elevated expression of this protein may play a role in the development of SCC, as indicated by strong immunostaining both in SCCs and precancerous lesions. Significantly stronger staining in SCCs compared to BCCs may indicate a role of COX-2 in cancer malignancy and serve as an indicator useful for differential diagnostics of the two types of cancer. Strong staining in all skin layers of SCC may help in detecting cancer cells infiltrating surrounding skin layers.

Three‐phase general border detection method for dermoscopy images using non‐uniform illumination correction

Computer-aided diagnosis of dermoscopy images has shown great promise in developing a quantitative, objective way of classifying skin lesions. An important step in the classification process is lesion segmentation. Many studies have been successful in segmenting melanocytic skin lesions (MSLs), but few have focused on non-melanocytic skin lesions (NoMSLs), as the wide variety of lesions makes accurate segmentation difficult. We developed an automatic segmentation program for detecting borders of skin lesions in dermoscopy images. The method consists of a pre-processing phase, general lesion segmentation phase, including illumination correction, and bright region segmentation phase. We tested our method on a set of 107 NoMSLs and a set of 319 MSLs. Our method achieved precision/recall scores of 84.5% and 88.5% for NoMSLs, and 93.9% and 93.8% for MSLs, in comparison with manual extractions from four or five dermatologists. The accuracy of our method was competitive or better than five recently published methods. Our new method is the first method for detecting borders of both non-melanocytic and melanocytic skin lesions.

Concordance of Frozen and Permanent Sections for the Diagnosis of Skin Lesions

There has been little written concerning the use of frozen sections to diagnose skin lesions. To compare the concordance between frozen and permanent sections of the same diagnostic skin biopsy specimen. Over 3 months, all non-melanocytic skin lesions that were biopsied in a skin cancer clinic were examined using frozen and permanent sections. Diagnoses from a dermatologist and dermatopathologist were recorded for each specimen and later examined for concordance. There was rare (0.5% of specimens) disagreement recorded between interpretations of the dermatologist and dermatopathologist. Permanent and frozen section pathology agreed with one another 90.4% of the time. Specimen processing was the most probable cause of discordance. Most discordance was not clinically relevant, although the patient was clinically affected in 35 of 2009 specimens (1.7%). Although there is a high concordance rate between diagnostic frozen and permanent sections, there are significant quality assurance and patient care advantages to following up initial diagnostic frozen sections with permanent sections of the same specimen.