Scalp dermoscopy or trichoscopy

Scalp dermoscopy or `trichoscopy' represents a valuable, noninvasive technique for the evaluation of patients with hair loss that allows for magnified visualization of the hair and scalp skin. It may be performed with a manual dermoscope (×10 magnification) or a videodermoscope (up to ×1,000 magnification). In particular, trichoscopy enhances the diagnosis of androgenetic alopecia, alopecia areata, telogen effluvium, trichotillomania, congenital triangular alopecia, scarring alopecia, tinea capitis and hair shaft disorders. This method is simple, quick and easy to perform, reduces the need for scalp biopsy, is well accepted by patients, and is useful for monitoring treatment and follow-up.

Enhancing classification accuracy utilizing globules and dots features in digital dermoscopy

The interest in image dermoscopy has been significantly increased recently and skin lesion images are nowadays routinely acquired for a number of skin disorders. An important finding in the assessment of a skin lesion severity is the existence of dark dots and globules, which are hard to locate and count using existing image software tools. In this work we present a novel methodology for detecting/segmenting and count dark dots and globules from dermoscopy images. Segmentation is performed using a multi-resolution approach based on inverse non-linear diffusion. Subsequently, a number of features are extracted from the segmented dots/globules and their diagnostic value in automatic classification of dermoscopy images of skin lesions into melanoma and non-malignant nevus is evaluated. The proposed algorithm is applied to a number of images with skin lesions with known histo-pathology. Results show that the proposed algorithm is very effective in automatically segmenting dark dots and globules. Furthermore, it was found that the features extracted from the segmented dots/globules can enhance the performance of classification algorithms that discriminate between malignant and benign skin lesions, when they are combined with other region-based descriptors.

Physiological characterization of skin lesion using non-linear random forest regression model

The current diagnostic technique for melanoma solely relies on the surface level of skin and under-skin information is neglected. Since physiological features of skin such as melanin are closely related to development of melanoma, the non-linear physiological feature extraction model based on random forest regression is proposed. The proposed model characterizes the concentration of eumelanin and pheomelanin from standard camera images or dermoscopic images, which are conventionally used for diagnosis of melanoma. For the validation, the phantom study and the separability test using clinical images were conducted and compared against the state-of-the art non-linear and linear feature extraction models. The results showed that the proposed model outperformed other comparing models in phantom and clinical experiments. Promising results show that the quantitative characterization of skin features, which is provided by the proposed method, can allow dermatologists and clinicians to make a more accurate and improved diagnosis of melanoma.

A Novel Approach to Segment Skin Lesions in Dermoscopic Images Based on a Deformable Model

Dermoscopy is an imaging technique that has been widely used in the diagnosis of skin lesions. However, its accuracy largely depends on the dermatologist's experience; thus, computer-aided diagnosis techniques are required. In this paper, a novel approach based on a deformable model is proposed to handle the segmentation of skin lesions in dermoscopic images. The RGB color space is converted so that the color information contained in the images can be used effectively to differentiate normal skin and skin lesions; and the differences in the color channels are combined together to define the speed function and the stopping criterion of the deformable model. This novel approach is robust against the noise, and provides an effective and flexible segmentation. Two image databases were used to test the performance of the novel approach and the segmentation results obtained were satisfactory. Quantitative analysis on 250 dermoscopic images showed that the novel algorithm outperformed other state-of-the-art algorithms. Also, using comparative data, the reliability and the implementation issues of the approach are discussed in this paper.

Digital dermoscopic follow-up of 1544 melanocytic nevi

The use of dermatoscopy increases melanocytic nevi diagnostic accuracy, and is important for dermoscopic monitoring of atypical lesions, allowing to find significant changes in the earliest stage. Dermoscopic diagnosis of melanocytic nevi type in a group of patients and their follow-up with the assessment of changes occurred during dermoscopic monitoring. Dermoscopically, we followed the nevic size and pattern, the color and pigment distribution. Follow-up visits were scheduled depending on the type of the melanocytic lesions and the patient's compliance. The nevi that have shown significant dermoscopic changes were excised and histopathologically examined. The study was performed on a group of 92 patients, mostly females (56.5%), mean age of 29.1 years. Of the total of 1544 melanocytic nevi examined, 27.4% were atypical and 72.6% common nevi. The average dermoscopic examination interval was 14.1 months. During monitoring, 35.5% atypical nevi and 22.5% common nevi have modified, especially changes in pigmentation and color (31% atypical nevi and 9.9% common nevi) and the appearance of new dermoscopic structures (12.7% atypical nevi and common nevi 8.5%). Of the total nevi monitored, 3% showed significant changes and were excised and examined pathologically, without diagnose of any malignant transformation. In our study, dermoscopic changes appeared in atypical as well as in common nevi. The dermoscopic monitoring of melanocytic-pigmented lesions remains an accessible method of assessment the evolution of nevi and can reduce the risk of appearance of malignant melanoma in the general population.

Diverse presentations of acral melanoma

BACKGROUND

Acral melanoma (AM) is an uncommon melanoma subtype occurring on the palms, soles and nail apparatus. It often lacks the typical features of primary melanoma resulting in delayed diagnosis.

OBJECTIVE

This article aims to raise awareness of AM and promote a high index of clinical suspicion to enable early diagnosis and improve outcomes for patients with AM.

DISCUSSION

The diagnosis of AM is often delayed because its presentation mimics other benign conditions such as fungal infections and ulcers. When lesions that were thought to be benign fail to respond to appropriate therapies, biopsy is critically important to exclude AM or other malignant pathology. Clinician awareness of the diversity of AM presentations, maintaining AM as part of their differential diagnosis and facilitating early biopsy are essential for early diagnosis and improving outcomes in patients with AM.

A Cloud-Based Infrastructure for Feedback-Driven Training and Image Recognition

Advanced techniques in machine learning combined with scalable "cloud" computing infrastructure are driving the creation of new and innovative health diagnostic applications. We describe a service and application for performing image training and recognition, tailored to dermatology and melanoma identification. The system implements new machine learning approaches to provide a feedback-driven training loop. This training sequence enhances classification performance by incrementally retraining the classifier model from expert responses. To easily provide this application and associated web service to clinical practices, we also describe a scalable cloud infrastructure, deployable in public cloud infrastructure and private, on-premise systems.

Nailfold dermatoscopy in general practice

BACKGROUND

Nailfold capillary examination can assist in distinguishing between primary Raynaud's phenomenon and secondary Raynaud's that is associated with a connective tissue disease. Dermatoscopy is a reliable technique in the evaluation of nailfold capillaries and assists in the diagnosis of connective tissue diseases such as scleroderma.

OBJECTIVE

This article provides an overview of the usefulness of nailfold capillary dermatoscopy in rheumatic and non-rheumatic diseases, and includes the MDAD (morphology, diameter, architecture and density) approach to nailfold dermatoscopy.

DISCUSSION

Dermatoscopes are useful devices in examining nailfold capillaries. Many general practitioners are skilled in dermatoscopy and are well placed to examine nailfold capillaries. The MDAD approach to nailfold dermatoscopy considers capillary morphology, diameter, architecture and density. In Raynaud's phenomenon, nailfold dermatoscopy assists in the diagnosis of an underlying connective tissue disease.

Evolution of melanocytic nevi under vemurafenib, followed by combination therapy with dabrafenib and trametinib for metastatic melanoma

Treatment of advanced melanoma with selective BRAF and MEK inhibitors is associated with a series of mucocutaneous side effects, among which morphological changes in preexisting nevi and the development of new melanocytic lesions, both benign and malignant. Objective was to describe the changes observed in melanocytic nevi under vemurafenib therapy, followed by combination therapy with dabrafenib and trametinib for metastatic melanoma. The melanocytic lesions of a 51-year-old Caucasian male patient diagnosed with stage IV melanoma were monitored both clinically and dermoscopically throughout vemurafenib, followed by combined treatment with dabrafenib and trametinib. The 65 monitored nevi presented different behaviors under vemurafenib treatment: 18 reticular nevi, 9 reticular-homogenous nevi, 3 reticular-globular nevi, and 2 globular nevi showed a diffuse decrease in pigmentation. Ten reticular nevi remained unchanged, while the rest of the nevi, independent of the dermoscopic pattern, presented a gradual increase in pigmentation. On the other hand, under dabrafenib and trametinib treatment 57 of these nevi showed gradual decrease in pigmentation and central involution, while 7 reticular nevi and 1 globular nevus remained unchanged; none of the monitored nevi increased in pigmentation nor presented new globules following this combination therapy. Systematic total body skin examination is mandatory in patients receiving BRAF inhibitors. The divergent course of melanocytic nevi during vemurafenib vs. dabrafenib and trametinib therapy remains to be elucidated by further research.

PIACS: A System for the Automatic Detection, Categorization and Comparison of Scratch-Related Skin Lesions in Dermatology

In the treatment of chronic pruritus-related, scratch-induced skin lesions the categorization, counting and temporal comparison are common methodologies. The observation requires a good memory and expertise in this field to gain comparable findings for this time-consuming process. Digital image processing aims at supporting such manual detections. The objective is to develop a software tool for automatic image detection and comparison. The new photographic setting implies the usage of markers to derive the brightness and size of lesions. MATLAB has been used for the software development. The newly defined setting allows taking standardized images of pruritus-associated cutaneous lesions for detection and comparison. The tool named PIACS (Prurigo Image Analyzing and Comparing System) allows automatically detecting, categorizing and comparing lesions based on digital images.

Solitary trichoepithelioma: clinical, dermatoscopic and histopathological findings

Trichoepithelioma is part of the adnexal carcinomas. It is a benign, small tumor, usually under a centimeter in diameter, which develops in the basal cells of the hair follicle.

CASE REPORT

We present the case of a 30-year-old female patient, from rural area, which was hospitalized in the Clinic of Dermatology, Emergency County Hospital, Craiova, Romania, in March 2015, for the presence of a skin tumor, with round-oval shape, 0.5 cm in diameter, brownish colored, located on the left cervical region. The patient had no past medical history. The skin tumor appeared two years ago, and it was slowly increasing in size. Physical examination was in normal ranges. The dermatoscopic examination reveal a pearly white background covered with tumor islands that were oval shaped, with hyperpigmentation, centered by keratin cysts and surrounded by collagen. During hospitalization, we performed tumor biopsy. The histopathological examination showed microscopic structure of trichoepithelioma. After history taking, physical examination, dermatoscopic examination and histopathological result, our diagnosis was left cervical trichoepithelioma.

CONCLUSIONS

Trichoepithelioma is a rare trichogenic tumor, which appears at any age, including newborns, with potential for local recurrence. Our case report represents a classic dermatoscopic aspect of trichoepithelioma, that can have close resemblance to basal cell carcinoma and other skin adnexal tumors, clinically, dermatoscopic and histopathological.

Hair enhancement in dermoscopic images using dual-channel quaternion tubularness filters and MRF-based multilabel optimization

Hair occlusion is one of the main challenges facing automatic lesion segmentation and feature extraction for skin cancer applications. We propose a novel method for simultaneously enhancing both light and dark hairs with variable widths, from dermoscopic images, without the prior knowledge of the hair color. We measure hair tubularness using a quaternion color curvature filter. We extract optimal hair features (tubularness, scale, and orientation) using Markov random field theory and multilabel optimization. We also develop a novel dual-channel matched filter to enhance hair pixels in the dermoscopic images while suppressing irrelevant skin pixels. We evaluate the hair enhancement capabilities of our method on hair-occluded images generated via our new hair simulation algorithm. Since hair enhancement is an intermediate step in a computer-aided diagnosis system for analyzing dermoscopic images, we validate our method and compare it to other methods by studying its effect on: 1) hair segmentation accuracy; 2) image inpainting quality; and 3) image classification accuracy. The validation results on 40 real clinical dermoscopic images and 94 synthetic data demonstrate that our approach outperforms competing hair enhancement methods.

Integrative analysis of cutaneous skin tumours using ultrasonogaphic criteria. Preliminary results

THE AIM

of this study is to identify the US features of skin tumors, especially morphological and vascular, in order to develop an integrative and differentiating imaging model for benign and malignant skin tumors.

MATERIAL AND METHOD

Twenty three patients with solid skin tumors were included in the study. The diagnostic procedures were clinical examination, dermoscopy, multimodal ultrasonography (US), using high frequency and conventional US, contact elastography, and i.v. contrast enhanced ultrasound (CEUS).

RESULTS

The US characteristics of the basal cell carcinomas were: hypoechoic, inhomogeneous masses, with hyperechoic or anechoic areas, depending on the histological differentiation, increased rigidity, uneven vascularization at Doppler examination, central or mixed type circulatory model, with 1-2 supply vessels, velocity >2 cm/s, intensely inhomogeneous load of the contrast agent (CA) and quick wash out time. The benign tumors were hypoechoic or echoic masses, with inhomogeneous structure, Doppler signal present only in dermofibromas, peripheral circulation model, velocities < 2.00 cm/s, a weak and uneven loading of the CA in the vascular bed, and a slow wash out time. Analysis of the CA dynamics evidenced a significantly higher value for the wash out time in the malignant tumors (38.2s+/- 15.15) as compared to the benign ones (54.2s +/- 8.5). Particularly the tumor thickness examination by HFUS evidences an ultrasound index that may be considered as a statistically significant predictive factor (p<0.05), highly sensitive (r =0.97) for the non-invasive assessment of the histological Breslow index. Elastography did not represent a differentiation examination in the cases studied.

CONCLUSIONS

Ultrasound allows a complex, multimodal approach of skin tumors, which completes clinical and histological examinations, orients the therapeutic management and may assess the therapeutic efficacy and the tumoral prognosis.

Understanding visual search patterns of dermatologists assessing pigmented skin lesions before and after online training

The goal of this investigation was to explore the feasibility of characterizing the visual search characteristics of dermatologists evaluating images corresponding to single pigmented skin lesions (PSLs) (close-ups and dermoscopy) as a venue to improve training programs for dermoscopy. Two Board-certified dermatologists and two dermatology residents participated in a phased study. In phase I, they viewed a series of 20 PSL cases ranging from benign nevi to melanoma. The close-up and dermoscopy images of the PSL were evaluated sequentially and rated individually as benign or malignant, while eye position was recorded. Subsequently, the participating subjects completed an online dermoscopy training module that included a pre- and post-test assessing their dermoscopy skills (phase 2). Three months later, the subjects repeated their assessment on the 20 PSLs presented during phase I of the study. Significant differences in viewing time and eye-position parameters were observed as a function of level of expertise. Dermatologists overall have more efficient search than residents generating fewer fixations with shorter dwells. Fixations and dwells associated with decisions changing from benign to malignant or vice versa from photo to dermatoscopic viewing were longer than any other decision, indicating increased visual processing for those decisions. These differences in visual search may have implications for developing tools to teach dermatologists and residents about how to better utilize dermoscopy in clinical practice.

High magnification digital dermoscopy of basal cell carcinoma: a single-centre study on 400 cases

The aim of this study was to assess the frequency of classic dermoscopic basal cell carcinoma (BCC) features and the sensitivity of new descriptors, such as light brown nests (homogeneous and structured) only visible employing a high magnification digital videomicroscope. A retrospective analysis of 2,024 highly magnified digital images referring to 400 BCCs was performed by 3 independent observers, who assessed 11 classic BCC descriptors and the new ones. Light brown nests were detected in 40.5% of BCCs. Homogeneous ones were observable in 17.8%, and structured nests in 32.8%. Light brown nests were visible in 14.3% of non-pigmented lesions, whereas in the pigmented groups these were observed in 42-54% of the cases. We suggest that brown nests described in this study may improve early recognition of superficial BCCs and of non-pigmented or slightly pigmented ones that may lack classic dermoscopic patterns.

Segmentation of skin lesions from digital images using joint statistical texture distinctiveness

Melanoma is the deadliest form of skin cancer. Incidence rates of melanoma have been increasing, especially among non-Hispanic white males and females, but survival rates are high if detected early. Due to the costs for dermatologists to screen every patient, there is a need for an automated system to assess a patient's risk of melanoma using images of their skin lesions captured using a standard digital camera. One challenge in implementing such a system is locating the skin lesion in the digital image. A novel texture-based skin lesion segmentation algorithm is proposed. A set of representative texture distributions are learned from an illumination-corrected photograph and a texture distinctiveness metric is calculated for each distribution. Next, regions in the image are classified as normal skin or lesion based on the occurrence of representative texture distributions. The proposed segmentation framework is tested by comparing lesion segmentation results and melanoma classification results to results using other state-of-art algorithms. The proposed framework has higher segmentation accuracy compared to all other tested algorithms.

Simpler, faster, more accurate melanocytic lesion segmentation through MEDS

We present a new technique for melanocytic lesion segmentation, Mimicking Expert Dermatologists' Segmentations (MEDS), and extensive tests of its accuracy, speed, and robustness. MEDS combines a thresholding scheme reproducing the cognitive process of dermatologists with a number of optimizations that may be of independent interest. MEDS is simple, with a single parameter tuning its “tightness”. It is extremely fast, segmenting medium-resolution images in a fraction of a second even with the modest computational resources of a cell phone-an improvement of an order of magnitude or more over state-of-the-art techniques. And it is extremely accurate: very experienced dermatologists disagree with its segmentations less than they disagree with the segmentations of state-of-the-art techniques, and in fact less than they disagree with the segmentations of dermatologists of moderate experience.

Eleven years of itching: a case report of crusted scabies

Crusted scabies is a rare and highly contagious form of scabies that is characterized by uncontrolled proliferation of mites in the skin, extensive hyperkeratotic scaling, crusted lesions, and variable pruritus. We report the case of a 48-year-old man with an 11-year history of pruritic, hyperkeratotic, psoriasiform plaques and widespread erythematous papules that was diagnosed as crusted scabies.

Improving dermoscopy image classification using color constancy

Robustness is one of the most important characteristics of computer-aided diagnosis systems designed for dermoscopy images. However, it is difficult to ensure this characteristic if the systems operate with multisource images acquired under different setups. Changes in the illumination and acquisition devices alter the color of images and often reduce the performance of the systems. Thus, it is important to normalize the colors of dermoscopy images before training and testing any system. In this paper, we investigate four color constancy algorithms: Gray World, max-RGB, Shades of Gray, and General Gray World. Our results show that color constancy improves the classification of multisource images, increasing the sensitivity of a bag-of-features system from 71.0% to 79.7% and the specificity from 55.2% to 76% using only 1-D RGB histograms as features.

Imaging directed photothermolysis through two-photon absorption demonstrated on mouse skin - a potential novel tool for highly targeted skin treatment

One-photon absorption based traditional laser treatment may not necessarily be selective at the microscopic level, thus could result in un-intended tissue damage. Our objective is to test whether two-photon absorption (TPA) could provide highly targeted tissue alteration of specific region of interest without damaging surrounding tissues. TPA based laser treatments (785 nm, 140 fs pulse width, 90 MHz) were performed on ex vivo mouse skin using different average power levels and irradiation times. Reflectance confocal microscopy (RCM) and combined second-harmonic-generation (SHG) and two-photon fluorescence (TPF) imaging channels were used to image before, during, and after each laser treatment. The skin was fixed, sectioned and H & E stained after each experiment for histological assessment of tissue alterations and for comparison with the non-invasive imaging assessments. Localized destruction of dermal fibers was observed without discernible epidermal damage on both RCM and SHG + TPF images for all the experiments. RCM and SHG + TPF images correlated well with conventional histological examination. This work demonstrated that TPA-based light treatment provides highly localized intradermal tissue alteration. With further studies on optimizing laser treatment parameters, this two-photon absorption photothermolysis method could potentially be applied in clinical dermatology.

New trichoscopy findings in trichotillomania: flame hairs, V-sign, hook hairs, hair powder, tulip hairs

Differential diagnosis of trichotillomania is often difficult in clinical practice. Trichoscopy (hair and scalp dermoscopy) effectively supports differential diagnosis of various hair and scalp diseases. The aim of this study was to assess the usefulness of trichoscopy in diagnosing trichotillomania. The study included 370 patients (44 with trichotillomania, 314 with alopecia areata and 12 with tinea capitis). Statistical analysis revealed that the main and most characteristic trichoscopic findings of trichotillomania are: irregularly broken hairs (44/44; 100% of patients), v-sign (24/44; 57%), flame hairs (11/44; 25%), hair powder (7/44; 16%) and coiled hairs (17/44; 39%). Flame hairs, v-sign, tulip hairs, and hair powder were newly identified in this study. In conclusion, we describe here specific trichoscopy features, which may be applied in quick, non-invasive, in-office differential diagnosis of trichotillomania.

Model-based classification methods of global patterns in dermoscopic images

In this paper different model-based methods of classification of global patterns in dermoscopic images are proposed. Global patterns identification is included in the pattern analysis framework, the melanoma diagnosis method most used among dermatologists. The modeling is performed in two senses: first a dermoscopic image is modeled by a finite symmetric conditional Markov model applied to L∗a∗b∗ color space and the estimated parameters of this model are treated as features. In turn, the distribution of these features are supposed that follow different models along a lesion: a Gaussian model, a Gaussian mixture model, and a bag-of-features histogram model. For each case, the classification is carried out by an image retrieval approach with different distance metrics. The main objective is to classify a whole pigmented lesion into three possible patterns: globular, homogeneous, and reticular. An extensive evaluation of the performance of each method has been carried out on an image database extracted from a public Atlas of Dermoscopy. The best classification success rate is achieved by the Gaussian mixture model-based method with a 78.44% success rate in average. In a further evaluation the multicomponent pattern is analyzed obtaining a 72.91% success rate.