Dermatoscopy of Neoplastic Skin Lesions: Recent Advances, Updates, and Revisions

OPINION STATEMENT

Dermatoscopy (dermoscopy) improves the diagnosis of benign and malignant cutaneous neoplasms in comparison with examination with the unaided eye and should be used routinely for all pigmented and non-pigmented cutaneous neoplasms. It is especially useful for the early stage of melanoma when melanoma-specific criteria are invisible to the unaided eye. Preselection by the unaided eye is therefore not recommended. The increased availability of polarized dermatoscopes, and the extended use of dermatoscopy in non-pigmented lesions led to the discovery of new criteria, and we recommend that lesions should be examined with polarized and non-polarized dermatoscopy. The "chaos and clues algorithm" is a good starting point for beginners because it is easy to use, accurate, and it works for all types of pigmented lesions not only for those melanocytic. Physicians, who use dermatoscopy routinely, should be aware of new clues for acral melanomas, nail matrix melanomas, melanoma in situ, and nodular melanoma. Dermatoscopy should also be used to distinguish between different subtypes of basal cell carcinoma and to discriminate highly from poorly differentiated squamous cell carcinomas to optimize therapy and management of non-melanoma skin cancer. One of the most exciting areas of research is the use of dermatoscopic images for machine learning and automated diagnosis. Convolutional neural networks trained with dermatoscopic images are able to diagnose pigmented lesions with the same accuracy as human experts. We humans should not be afraid of this new and exciting development because it will most likely lead to a peaceful and fruitful coexistence of human experts and decision support systems.

Correlation between dermoscopic and histopathological findings of leucoplakia of the tongue: a case report

A 75-year-old Japanese man presented at our outpatient clinic with pain on the right side of his tongue. Comparison of histological and dermoscopic images showed that areas with hyperkeratosis were opaque white, areas above the papillary dermis were reddish, and that the lesion looked whiter on dermoscopy the longer the epithelial rete ridges were. A dermatocope shows structural information from the epidermis as well as the upper dermis, and could improve early diagnosis of oral mucosal squamous carcinoma in situ.

Melanoma recognition in dermoscopy images using lesion's peripheral region information

BACKGROUND AND OBJECTIVES

Melanoma is one of the most dangerous forms of skin cancer, but it has a high survival rate if diagnosed on time. The first diagnostic approach in melanoma recognition is to visually assess the lesion through dermoscopic images. Computer-aided diagnosis systems for melanoma recognition has attracted a lot of attention in the last decade and proved to be helpful in that area. Methods for skin lesions analysis usually involves three main steps: lesion segmentation, feature extraction, and features classification. Extracting highly discriminative features from the lesion has a great impact on the recognition task. In this paper, we are seeking a lesion recognition system that incorporates these highly discriminative features.

METHODS

For segmentation step, we use contour propagation model with a novel two-component speed function. In the feature extraction step, a new set of features based on peripheral information of the lesion are introduced. For this end, the peripheral area of the lesion is mapped to log-polar space using the Daugman's transformation and then a set of texture features are extracted from it. Newly introduced features do not need further segmentation of dermoscopic structures and are robust against lesion's scale, orientation, location, and shape variation. We also design the other global texture features to describe only the information from the lesion area. In the classification step, we evaluated two different schemes to prove the distinction power of the new features, one comprises linear SVM to recognize melanoma vs. nevus and the other scheme uses RUSBoost classifier to recognize melanoma vs. nevus and atypical-nevus. Sequential feature selection algorithm has been utilized in each classification scheme to rank features based on their distinction power.

RESULTS

Cross-validation experiments on the well-known PH² dataset resulted in an average of 97% for sensitivity and 100% for specificity on melanoma vs. nevus recognition task using only four features. Also, in the second classification scheme, we achieved high sensitivity and specificity values of 95% for melanoma vs. nevus and atypical nevus recognition experiments.

CONCLUSION

High values for evaluation metrics show that the proposed melanoma recognition system is superior to the other state-of-the-art algorithms, which proves the high distinction power of the newly introduced features.

Going digital with dermoscopy

Digital dermoscopy refers to the acquisition and storage of digital images from a dermoscopic examination. In this article, we delve into the innovative world of digital dermoscopy with a review of its potential uses as well as some nuances of adapting this technology in a clinical setting, including sequential monitoring, teledermoscopy, and machine learning. We also discuss the acquisition and storage of dermoscopy images in accordance with the Health Insurance Portability and Accountability Act (HIPAA).

Dense Deconvolutional Network for Skin Lesion Segmentation

Automatic delineation of skin lesion contours from dermoscopy images is a basic step in the process of diagnosis and treatment of skin lesions. However, it is a challenging task due to the high variation of appearances and sizes of skin lesions. In order to deal with such challenges, we propose a new dense deconvolutional network (DDN) for skin lesion segmentation based on residual learning. Specifically, the proposed network consists of dense deconvolutional layers (DDLs), chained residual pooling (CRP), and hierarchical supervision (HS). First, unlike traditional deconvolutional layers, DDLs are adopted to maintain the dimensions of the input and output images unchanged. The DDNs are trained in an end-to-end manner without the need of prior knowledge or complicated postprocessing procedures. Second, the CRP aims to capture rich contextual background information and to fuse multilevel features. By combining the local and global contextual information via multilevel feature fusion, the high-resolution prediction output is obtained. Third, HS is added to serve as an auxiliary loss and to refine the prediction mask. Extensive experiments based on the public ISBI 2016 and 2017 skin lesion challenge datasets demonstrate the superior segmentation results of our proposed method over the state-of-the-art methods.

An Improved Skin Lesion Matching Scheme in Total Body Photography

Total body photography is used for early detection of malignant melanoma, primarily as a means of temporal skin surface monitoring. In a prior work, we presented a scanner with a set of algorithms to map and detect changes in pigmented skin lesions, thus demonstrating that it is possible to fully automate the process of total body image acquisition and processing. The key procedure in these algorithms is skin lesion matching that determines whether two images depict the same real lesion. In this paper, we aim to improve it with respect to false positive and negative outcomes. To this end, we developed two novel methods: one based on successive rigid transformations of three-dimensional point clouds and one based on nonrigid coordinate plane deformations in regions of interest around the lesions. In both approaches, we applied a robust outlier rejection procedure based on progressive graph matching. Using the images obtained from the scanner, we created a ground truth dataset tailored to diversify false positive match scenarios. The algorithms were evaluated according to their precision and recall values, and the results demonstrated the superiority of the second approach in all the tests. In the complete interpositional matching experiment, it reached a precision and recall as high as 99.92% and 81.65%, respectively, showing a significant improvement over our original method.

SDI+: A Novel Algorithm for Segmenting Dermoscopic Images

Malignant skin lesions are among the most common types of cancer, and automated systems for their early detection are of fundamental importance. We propose SDI+, an unsupervised algorithm for the segmentation of skin lesions in dermoscopic images. It is articulated into three steps, aimed at extracting preliminary information on possible confounding factors, accurately segmenting the lesion, and post-processing the result. The overall method achieves high accuracy on dark skin lesions and can handle several cases where confounding factors could inhibit a clear understanding by a human operator. We present extensive experimental results and comparisons achieved by the SDI+ algorithm on the ISIC 2017 dataset, highlighting the advantages and disadvantages.

Biologically Inspired QuadTree Color Detection in Dermoscopy Images of Melanoma

This paper presents a QuadTree-based melanoma detection system inspired by dermatologists' color perception. Clinical color assessment in dermoscopy images is challenging because of subtle differences in shades, location-dependent color information, poor color contrast, and wide variation among images of the same class. To overcome these challenges, color enhancement and automatic color identification techniques, based on QuadTree segmentation and modeled after expert color assessments, are developed. The approach presented in this paper is shown to provide an accurate model of expert color assessment. Specifically, the proposed model is shown to: 1) identify significantly more colors in melanomas than in benign skin lesions; 2) identify a higher frequency in melanomas of three colors: blue-gray, black, and pink; and 3) delineate locations of melanoma colors by quintiles, specifically predilection for blue-gray and pink in the periphery and a trend for white and black in the lesion center. Performance of the proposed method is evaluated using four classifiers. The kernel support vector machine classifier is found to achieve the best results, with an area under the receiver operating characteristic (ROC) curve of 0.93, compared to average area under the ROC curve of 0.82 achieved by the dermatologists in this study. The results indicate that the biologically inspired method of automatic color detection proposed in this paper has the potential to play an important role in melanoma diagnosis in the clinic.

Statistical Detection of Colors in Dermoscopic Images With a Texton-Based Estimation of Probabilities

Color has great diagnostic significance in dermatoscopy. Several diagnosis methods are based on the colors detected within a lesion. Malignant lesions frequently show more than three colors, whereas in benign lesions, three or fewer colors are usually observed. Black, red, white, and blue-gray are found more frequently in melanomas than in benign nevi. In this paper, a method to automatically identify the colors of a lesion is presented. A color label identification problem is proposed and solved by maximizing the posterior probability of a pixel to belong to a label, given its color value and the neighborhood color values. The main contribution of this paper is the estimation of the different terms involved in the computation of this probability. Two evaluations are performed on a database of 200 dermoscopic images. The first one evaluates if all the colors detected in a lesion are indeed present in it. The second analyzes if each pixel within a lesion is assigned the correct color label. The results show that the proposed method performs correctly and outperforms other methods, with an average F-measure of 0.89, an accuracy of 0.90, and a Spearman correlation of 0.831.

Recognition of early melanoma: a monocentric dermoscopy follow-up study comparing de novo melanoma with nevus-associated melanoma

BACKGROUND

The earlier detection of melanomas occurring within preexisting nevi is theoretically possible using sequential dermoscopy. Characterizing the early follow-up changes of nevus-associated melanomas (NAMs) and differentiating them from those observed in de novo melanomas (DNMs) may help the earlier recognition of NAMs.

METHODS

Using descriptive dermoscopic features to detect focal changes, we blindly evaluated retrospectively the baseline and follow-up images of 32 melanomas that were subsequently classified as histopathologically defined NAMs or DNMs.

RESULTS

Correlates of growth, as structureless brown‐black areas or clods, complemented each other for the identification of DNMs at baseline (structureless brown‐black areas: 66.7% DNMs, 15% NAMs, P < 0.01; combined with clods, one or the other being present: 100% DNMs, 30% NAMs, P < 0.01) and when considering their baseline presence or their appearance at follow‐up (100% DNMs, 35% NAMs, P < 0.01). Correlates of fibrosis, as white lines, when considering their baseline presence or their appearance at follow-up, were associated with NAMs (60%, 16.7% DNMs, P = 0.027).

CONCLUSION

Significant differences, distinguishing NAMs from DNMs, were detected particularly when considering both baseline signs and follow-up changes. Earlier identification of NAMs and their subsequent improved histological characterization will help define the subgroup of high-risk patients, for whom comprehensive image monitoring may be beneficial.

Supervised Saliency Map Driven Segmentation of Lesions in Dermoscopic Images

Lesion segmentation is the first step in most automatic melanoma recognition systems. Deficiencies and difficulties in dermoscopic images such as color inconstancy, hair occlusion, dark corners, and color charts make lesion segmentation an intricate task. In order to detect the lesion in the presence of these problems, we propose a supervised saliency detection method tailored for dermoscopic images based on the discriminative regional feature integration (DRFI). A DRFI method incorporates multilevel segmentation, regional contrast, property, background descriptors, and a random forest regressor to create saliency scores for each region in the image. In our improved saliency detection method, mDRFI, we have added some new features to regional property descriptors. Also, in order to achieve more robust regional background descriptors, a thresholding algorithm is proposed to obtain a new pseudo-background region. Findings reveal that mDRFI is superior to DRFI in detecting the lesion as the salient object in dermoscopic images. The proposed overall lesion segmentation framework uses detected saliency map to construct an initial mask of the lesion through thresholding and postprocessing operations. The initial mask is then evolving in a level set framework to fit better on the lesion's boundaries. The results of evaluation tests on three public datasets show that our proposed segmentation method outperforms the other conventional state-of-the-art segmentation algorithms and its performance is comparable with most recent approaches that are based on deep convolutional neural networks.

Learning to Detect Blue-White Structures in Dermoscopy Images With Weak Supervision

We propose a novel approach to identify one of the most significant dermoscopic criteria in the diagnosis of cutaneous Melanoma: the blue-white structure (BWS). In this paper, we achieve this goal in a multiple instance learning (MIL) framework using only image-level labels indicating whether the feature is present or not. To this aim, each image is represented as a bag of (nonoverlapping) regions, where each region may or may not be identified as an instance of BWS. A probabilistic graphical model is trained (in MIL fashion) to predict the bag (image) labels. As output, we predict the classification label for the image (i.e., the presence or absence of BWS in each image) and we also localize the feature in the image. Experiments are conducted on a challenging dataset with results outperforming state-of-the-art techniques, with BWS detection besting competing methods in terms of performance. This study provides an improvement on the scope of modeling for computerized image analysis of skin lesions. In particular, it propounds a framework for identification of dermoscopic local features from weakly labeled data.

Performance of a computer-aided digital dermoscopic image analyzer for melanoma detection in 1,076 pigmented skin lesion biopsies

BACKGROUND

Digital dermoscopic image analysis of pigmented skin lesions (PSLs) has become increasingly popular, despite its unclear clinical utility. Unbiased, high-powered studies investigating the efficacy of commercially available systems are limited.

OBJECTIVE

To investigate the diagnostic performance of the FotoFinder Mole-Analyzer in assessing PSLs for cutaneous melanoma.

METHODS

In this 15-year retrospective study, the histopathologies of 1076 biopsied PSLs among a total of 2500 imaged PSLs were collected. The biopsied PSLs were categorized as benign or malignant (cutaneous melanoma) based on histopathology. Analyzer scores (0-1.00) for these PSLs were obtained and grouped according to histopathology.

RESULTS

At an optimized cutoff score of 0.50, a sensitivity of 56% and a specificity of 74% were achieved. The area under the receiver operating characteristics curve was 0.698, indicating poor accuracy as a diagnostic tool.

LIMITATIONS

This study had a retrospective design and involved only a single institution.

CONCLUSION

Our study reveals a low sensitivity of the scoring function of this digital dermoscopic image analyzer for detecting cutaneous melanomas. Physicians must apply keen clinical judgment when using such devices in the screening of suspicious PSLs.

Sclerodermiform basal cell carcinoma: how much can we rely on dermatoscopy to differentiate from non-aggressive basal cell carcinomas? Analysis of 1256 cases

BACKGROUND

The behaviour of each basal cell carcinoma is known to be different according to the histological growth pattern. Among these aggressive lesions, sclerodermiform basal cell carcinomas are the most common type. This is a challenging-to-treat lesion due to its deep tissue invasion, rapid growth, risk of metastasis and overall poor prognosis if not diagnosed in early stages.

OBJECTIVE

To investigate if sclerodermiform basal cell carcinomas are diagnosed later compared to non-sclerodermiform basal cell carcinoma Method: All lesions excised from 2000 to 2010 were included. A pathologist classified the lesions in two cohorts: one with specimens of non-aggressive basal cell carcinoma (superficial, nodular and pigmented), and other with sclerodermiform basal cell carcinoma. For each lesion, we collected patient's information from digital medical records regarding: gender, age when first attending the clinic and the tumor location.

RESULTS

1256 lesions were included, out of which 296 (23.6%) corresponded to sclerodermiform basal cell carcinoma, whereas 960 (76.4%) were non-aggressive subtypes of basal cell carcinoma. The age of diagnosis was: 72.78±12.31 years for sclerodermiform basal cell and 69.26±13.87 years for non-aggressive basal cell carcinoma (P<.0001). Sclerodermiform basal cell carcinomas are diagnosed on average 3.52 years later than non-aggressive basal cell carcinomas. Sclerodermiform basal cell carcinomas were diagnosed 3.40 years and 2.34 years later than non-aggressive basal cell carcinomas in younger and older patients respectively (P=.002 and P=.03, respectively).

STUDY LIMITATIONS

retrospective design.

CONCLUSION

The diagnostic accuracy and primary clinic conjecture of sclerodermiform basal cell carcinomas is quite low compared to other forms of basal cell carcinoma such as nodular, superficial and pigmented. The dermoscopic vascular patterns, which is the basis for the diagnosis of non-melanocytic nonpigmented skin tumors, may not be particularly useful in identifying sclerodermiform basal cell carcinomas in early stages. As a distinct entity, sclerodermiform basal cell carcinomas show a lack of early diagnosis compared to less-aggressive subtypes of BCC, and thus, more accurate diagnostic tools apart from dermatoscopy are required to reach the goal of early-stage diagnosis of sclerodermiform basal cell carcinomas.

Dermoscopy of inflammatory breast cancer

Inflammatory breast cancer is an aggressive and infiltrative malignancy that is often misdiagnosed as an infection because of its symptoms and signs of inflammation, delaying proper diagnosis and treatment. We report a case of inflammatory breast cancer showing correlation between dermoscopic and histopathological diagnoses. We highlight the utility of dermoscopy for skin biopsy site selection.

Combined Oral Contraception and Bicalutamide in Polycystic Ovary Syndrome and Severe Hirsutism: A Double-Blind Randomized Controlled Trial

CONTEXT

Hirsutism often occurs in women with polycystic ovary syndrome (PCOS). The efficacy of oral contraceptive pill (OCP) plus antiandrogens in the treatment of its severe expression is controversial due to the lack of randomized, double-blind, long-term studies.

OBJECTIVE

The primary outcome was the reduction of hirsutism in PCOS women objectively measured by videodermoscopy on the androgen-sensitive skin areas assessed by the modified Ferriman and Gallwey (mF&G) total score, after 12 months of therapy with OCP + bicalutamide (BC) vs OCP plus placebo (P). The secondary outcomes were to evaluate tolerability of BC and body composition as well as the occurrence of adverse events.

DESIGN

An experimental, phase 3, prospective, multicenter, randomized, double-blind, P-controlled trial. Patients were evaluated at the baseline visit, at 6 and 12 months during treatment, and 6 months' posttreatment.

PARTICIPANTS

Seventy women with classic PCOS (severe hirsutism, oligoanovulation, and ovarian polycystic ovarian morphology).

INTERVENTION

Patients received OCP + BC (50 mg/d) or OCP + P for 12 months.

RESULTS

The repeated measures analysis of variance showed that both treatments were effective in reducing hirsutism: The OCP + BC group had a higher reduction compared with the OCP + P group. No adverse effects were described during treatment except an increase in total cholesterol and low-density lipoprotein in the OCP + BC group.

CONCLUSIONS

The association of OCP + BC is well tolerated and significantly more effective than OCP alone in treating severe hirsutism. We suggest a combined use of the videodermoscopic index and mF&G to evaluate the effects of androgen deprivation therapy for hirsutism.

Dermoscopy in the diagnosis of juvenile xanthogranuloma

Juvenile xanthogranuloma is the most common form of non-Langerhans cell histiocytosis. It manifests clinically as a red-yellow papule, usually showing spontaneous remission. The diagnosis is based on clinical and histological findings. We report the use of dermoscopy ("setting sun" pattern) as an adjuvant tool in the diagnosis of juvenile xanthogranuloma in a female patient presenting with a 2-month history of a pre-auricular papule.

Application of dermoscopy image analysis technique in diagnosing urethral condylomata acuminata

BACKGROUND

In this study, cases with suspected urethral condylomata acuminata were examined by dermoscopy, in order to explore an effective method for clinical.

OBJECTIVE

To study the application of dermoscopy image analysis technique in clinical diagnosis of urethral condylomata acuminata.

METHODS

A total of 220 suspected urethral condylomata acuminata were clinically diagnosed first with the naked eyes, and then by using dermoscopy image analysis technique. Afterwards, a comparative analysis was made for the two diagnostic methods.

RESULTS

Among the 220 suspected urethral condylomata acuminata, there was a higher positive rate by dermoscopy examination than visual observation.

STUDY LIMITATIONS

Dermoscopy examination technique is still restricted by its inapplicability in deep urethral orifice and skin wrinkles, and concordance between different clinicians may also vary.

CONCLUSION

Dermoscopy image analysis technique features a high sensitivity, quick and accurate diagnosis and is non-invasive, and we recommend its use.

Recognition of pigment network pattern in dermoscopy images based on fuzzy classification of pixels

BACKGROUND AND OBJECTIVE

One of the most relevant dermoscopic patterns is the pigment network. An innovative method of pattern recognition is presented for its detection in dermoscopy images.

METHODS

It consists of two steps. In the first one, by means of a supervised machine learning process and after performing the extraction of different colour and texture features, a fuzzy classification of pixels into the three categories present in the pattern's definition ("net", "hole" and "other") is carried out. This enables the three corresponding fuzzy sets to be created and, as a result, the three probability images that map them out are generated. In the second step, the pigment network pattern is characterised from a parameterisation process -derived from the system specification- and the subsequent extraction of different features calculated from the combinations of image masks extracted from the probability images, corresponding to the alpha-cuts obtained from the fuzzy sets.

RESULTS

The method was tested on a database of 875 images -by far the largest used in the state of the art to detect pigment network- extracted from a public Atlas of Dermoscopy, obtaining AUC results of 0.912 and 88%% accuracy, with 90.71%% sensitivity and 83.44%% specificity.

CONCLUSION

The main contribution of this method is the very design of the algorithm, highly innovative, which could also be used to deal with other pattern recognition problems of a similar nature. Other contributions are: 1. The good performance in discriminating between the pattern and the disturbing artefacts -which means that no prior preprocessing is required in this method- and between the pattern and other dermoscopic patterns; 2. It puts forward a new methodological approach for work of this kind, introducing the system specification as a required step prior to algorithm design and development, being this specification the basis for a required parameterisation -in the form of configurable parameters (with their value ranges) and set threshold values- of the algorithm and the subsequent conducting of the experiments.

Dense deconvolution net: Multi path fusion and dense deconvolution for high resolution skin lesion segmentation

BACKGROUND

Dermoscopy imaging has been a routine examination approach for skin lesion diagnosis. Accurate segmentation is the first step for automatic dermoscopy image assessment.

OBJECTIVE

The main challenges for skin lesion segmentation are numerous variations in viewpoint and scale of skin lesion region.

METHODS

To handle these challenges, we propose a novel skin lesion segmentation network via a very deep dense deconvolution network based on dermoscopic images. Specifically, the deep dense layer and generic multi-path Deep RefineNet are combined to improve the segmentation performance. The deep representation of all available layers is aggregated to form the global feature maps using skip connection. Also, the dense deconvolution layer is leveraged to capture diverse appearance features via the contextual information. Finally, we apply the dense deconvolution layer to smooth segmentation maps and obtain final high-resolution output.

RESULTS

Our proposed method shows the superiority over the state-of-the-art approaches based on the public available 2016 and 2017 skin lesion challenge dataset and achieves the accuracy of 96.0% and 93.9%, which obtained a 6.0% and 1.2% increase over the traditional method, respectively.

CONCLUSIONS

By utilizing Dense Deconvolution Net, the average time for processing one testing images with our proposed framework was 0.253 s.

Association of Clinical, Dermoscopic, and Histopathologic Findings With Gene Expression in Patients With Balloon Cell Melanoma

Importance

Balloon cell melanoma is a rare subtype of melanoma that is underrecognized clinically and is challenging to diagnose on histologic studies.

Objective

To further characterize the clinical, dermoscopic, and histopathologic features of balloon cell melanomas and their correlation to gene expression.

Design, Setting, and Participants

Case series of 2 patients with balloon cell melanoma whose medical records were retrieved from the database of Thomas Jefferson University Dermatopathology Center in Philadelphia, Pennsylvania. Both cases had been referred to the institution's dermatopathology laboratory and provided complete data on clinical, dermoscopic, and histopathologic findings and gene-expression profiles.

Main Outcomes and Measures

Dermoscopic findings, histopathologic findings, and results of gene expression tests.

Results

In the 2 patients included, translucent hypopigmented areas on gross examination and a translucent white-gray veil and dull yellow globules on dermoscopic examination correlated with the balloon cell melanocytic region demonstrated on histologic studies with hematoxylin-eosin stain. Specifically, dull yellow globules corresponded to the balloon cell melanocytic nests. Both lesions presented with a second, morphologically distinct population of melanocytes, common in balloon cell melanocytic neoplasms. In both cases, a prominent junctional component that consisted of cells demonstrating ample clear-to-granular cytoplasm and a central nucleus were present. Cytologic atypia was minimal to lacking in both cases, and architectural disorder served as a better clue to the diagnosis. Findings of a gene expression profiling test corroborated the diagnosis in both cases.

Conclusions and Relevance

Balloon cell melanomas may present with characteristic clinical and dermoscopic findings, and a gene expression profiling test may provide additional useful diagnostic information in cases that are difficult to interpret.

Texture based skin lesion abruptness quantification to detect malignancy

BACKGROUND

Abruptness of pigment patterns at the periphery of a skin lesion is one of the most important dermoscopic features for detection of malignancy. In current clinical setting, abrupt cutoff of a skin lesion determined by an examination of a dermatologist. This process is subjective, nonquantitative, and error-prone. We present an improved computational model to quantitatively measure abruptness of a skin lesion over our previous method. To achieve this, we quantitatively analyze the texture features of a region within the lesion boundary. This region is bounded by an interior border line of the lesion boundary which is determined using level set propagation (LSP) method. This method provides a fast border contraction without a need for extensive boolean operations. Then, we build feature vectors of homogeneity, standard deviation of pixel values, and mean of the pixel values of the region between the contracted border and the original border. These vectors are then classified using neural networks (NN) and SVM classifiers.

RESULTS

As lower homogeneity indicates sharp cutoffs, suggesting melanoma, we carried out our experiments on two dermoscopy image datasets, which consist of 800 benign and 200 malignant melanoma cases. LSP method helped produce better results than Kaya et al., 2016 study. By using texture homogeneity at the periphery of a lesion border determined by LSP, as a classification results, we obtained 87% f1-score and 78% specificity; that we obtained better results than in the previous study. We also compared the performances of two different NN classifiers and support vector machine classifier. The best results obtained using combination of RGB color spaces with the fully-connected multi-hidden layer NN.

CONCLUSIONS

Computational results also show that skin lesion abrupt cutoff is a reliable indicator of malignancy. Results show that computational model of texture homogeneity along the periphery of skin lesion borders based on LSP is an effective way of quantitatively measuring abrupt cutoff of a lesion.

Comparison of computer systems and ranking criteria for automatic melanoma detection in dermoscopic images

Melanoma is the deadliest form of skin cancer, and early detection is crucial for patient survival. Computer systems can assist in melanoma detection, but are not widespread in clinical practice. In 2016, an open challenge in classification of dermoscopic images of skin lesions was announced. A training set of 900 images with corresponding class labels and semi-automatic/manual segmentation masks was released for the challenge. An independent test set of 379 images, of which 75 were of melanomas, was used to rank the participants. This article demonstrates the impact of ranking criteria, segmentation method and classifier, and highlights the clinical perspective. We compare five different measures for diagnostic accuracy by analysing the resulting ranking of the computer systems in the challenge. Choice of performance measure had great impact on the ranking. Systems that were ranked among the top three for one measure, dropped to the bottom half when changing performance measure. Nevus Doctor, a computer system previously developed by the authors, was used to participate in the challenge, and investigate the impact of segmentation and classifier. The diagnostic accuracy when using an automatic versus the semi-automatic/manual segmentation is investigated. The unexpected small impact of segmentation method suggests that improvements of the automatic segmentation method w.r.t. resemblance to semi-automatic/manual segmentation will not improve diagnostic accuracy substantially. A small set of similar classification algorithms are used to investigate the impact of classifier on the diagnostic accuracy. The variability in diagnostic accuracy for different classifier algorithms was larger than the variability for segmentation methods, and suggests a focus for future investigations. From a clinical perspective, the misclassification of a melanoma as benign has far greater cost than the misclassification of a benign lesion. For computer systems to have clinical impact, their performance should be ranked by a high-sensitivity measure.