Automated decision support in melanocytic lesion management.

An automated melanocytic lesion image-analysis algorithm is described that aims to reproduce the decision-making of a dermatologist. The utility of the algorithm lies in its ability to identify lesions requiring excision from lesions not requiring excision. Using only wavelet coefficients as features, and testing three different machine learning algorithms, a cohort of 250 images of pigmented lesions is classified based on expert dermatologists' recommendations of either excision (165 images) or no excision (85 images). It is shown that the best algorithm utilises the Shannon4 wavelet coupled to the support vector machine, where the latter is used as the classifier. In this case the algorithm, utilising only 22 othogonal features, achieves a 10-fold cross validation sensitivity and specificity of 0.96 and 0.87, resulting in a diagnostic-odds ratio of 261. The advantages of this method over diagnostic algorithms-which make a melanoma/no melanoma decision-are twofold: first, by reproducing the decision-making of a dermatologist, the average number of lesions excised per melanoma among practioners in general can be reduced without compromising the detection of melanoma; and second, the intractable problem of clinically differentiating between many atypical dysplastic naevi and melanoma is avoided. Since many atypical naevi that require excision on clinical grounds will not be melanoma, the algorithm-in contrast to diagnostic algorithms-can aim for perfect specificities without clinical concerns, thus lowering the excision rate of non-melanoma. Finally, the algorithm has been implemented as a smart phone application to investigate its utility in clinical practice and to streamline the assimilation of hitherto unseen tested images into the training set.

Nicotinamide and skin cancer chemoprevention: The jury is still out.

Following the publication of the results of a Phase III trial, the administration of oral nicotinamide has been widely advocated as effective in non-melanoma skin cancer chemoprevention in high-risk individuals. However, I performed a Bayesian analysis of the reported findings and show there is insufficient evidence to demonstrate its efficacy, highlighting the significant probability that the positive conclusions drawn will not be reproducible. Given the potential widespread use of oral nicotinamide, future position statements regarding its efficacy are likely to require higher standards of evidence.

Melanoma screening: Informing public health policy with quantitative modelling.

Australia and New Zealand share the highest incidence rates of melanoma worldwide. Despite the substantial increase in public and physician awareness of melanoma in Australia over the last 30 years-as a result of the introduction of publicly funded mass media campaigns that began in the early 1980s -mortality has steadily increased during this period. This increased mortality has led investigators to question the relative merits of primary versus secondary prevention; that is, sensible sun exposure practices versus early detection. Increased melanoma vigilance on the part of the public and among physicians has resulted in large increases in public health expenditure, primarily from screening costs and increased rates of office surgery. Has this attempt at secondary prevention been effective? Unfortunately epidemiologic studies addressing the causal relationship between the level of secondary prevention and mortality are prohibitively difficult to implement-it is currently unknown whether increased melanoma surveillance reduces mortality, and if so, whether such an approach is cost-effective. Here I address the issue of secondary prevention of melanoma with respect to incidence and mortality (and cost per life saved) by developing a Markov model of melanoma epidemiology based on Australian incidence and mortality data. The advantages of developing a methodology that can determine constraint-based surveillance outcomes are twofold: first, it can address the issue of effectiveness; and second, it can quantify the trade-off between cost and utilisation of medical resources on one hand, and reduced morbidity and lives saved on the other. With respect to melanoma, implementing the model facilitates the quantitative determination of the relative effectiveness and trade-offs associated with different levels of secondary and tertiary prevention, both retrospectively and prospectively. For example, I show that the surveillance enhancement that began in 1982 has resulted in greater diagnostic incidence and reduced mortality, but the reduced mortality carried a significant cost per life saved. I implement the model out to 2028 and demonstrate that the enhanced secondary prevention that began in 1982 becomes increasingly cost-effective over the period 2013-2028. On the other hand, I show that reductions in mortality achieved by significantly enhancing secondary prevention beyond 2013 levels are comparable with those achieved by only modest improvements in late-stage disease survival. Given the ballooning costs of increased melanoma surveillance, I suggest the process of public health policy decision-making-particularly with respect to the public funding of melanoma screening and discretionary mole removal-would be better served by incorporating the results of quantitative modelling.

SBSI: an extensible distributed software infrastructure for parameter estimation in systems biology.

SUMMARY: Complex computational experiments in Systems Biology, such as fitting model parameters to experimental data, can be challenging to perform. Not only do they frequently require a high level of computational power, but the software needed to run the experiment needs to be usable by scientists with varying levels of computational expertise, and modellers need to be able to obtain up-to-date experimental data resources easily. We have developed a software suite, the Systems Biology Software Infrastructure (SBSI), to facilitate the parameter-fitting process. SBSI is a modular software suite composed of three major components: SBSINumerics, a high-performance library containing parallelized algorithms for performing parameter fitting; SBSIDispatcher, a middleware application to track experiments and submit jobs to back-end servers; and SBSIVisual, an extensible client application used to configure optimization experiments and view results. Furthermore, we have created a plugin infrastructure to enable project-specific modules to be easily installed. Plugin developers can take advantage of the existing user-interface and application framework to customize SBSI for their own uses, facilitated by SBSI's use of standard data formats. AVAILABILITY AND IMPLEMENTATION: All SBSI binaries and source-code are freely available from http://sourceforge.net/projects/sbsi under an Apache 2 open-source license. The server-side SBSINumerics runs on any Unix-based operating system; both SBSIVisual and SBSIDispatcher are written in Java and are platform independent, allowing use on Windows, Linux and Mac OS X. The SBSI project website at http://www.sbsi.ed.ac.uk provides documentation and tutorials.

High throughput investigative Dermatology in 2012 and beyond: A new era beckons.

High throughput molecular biology began around the mid-1990s with the introduction of microarrays - a technology that enabled investigators to quantify the cellular expression levels of tens of thousands of mRNA transcripts simultaneously. To date, a large number of microarray experiments have been performed in the investigation of RNA expression signatures in normal and pathological tissues. This review focuses on a next generation tool in high throughput investigation: RNA sequencing or RNA-Seq, highlighting its advantages over traditional microarray investigation and discussing its utility in investigative dermatology. In contrast with the results obtained from microarray experiments, RNA-Seq generates mRNA abundance counts, can identify novel transcripts and splice variants, and provides sequence resolution at the level of single base-pairs. Implementing RNA-Seq in the investigation of skin disease will yield novel insights into the pathogenesis of disease, will facilitate the discovery of new diseases and new mechanisms of disease, and will allow researchers to probe genetic disease in high resolution and with unprecedented efficiency.

A mechanochemical model of striae distensae.

Striae distensae, otherwise known as stretch marks, are common skin lesions found in a variety of clinical settings. They occur frequently during adolescence or pregnancy where there is rapid tissue expansion and in clinical situations associated with corticosteroid excess. Heralding their onset is the appearance of parallel inflammatory streaks aligned perpendicular to the direction of skin tension. Despite a considerable amount of investigative research, the pathogenesis of striae remains obscure. The interpretation of histologic samples - the major investigative tool - demonstrates an association between dermal lymphocytic inflammation, elastolysis, and a scarring response. Yet the primary causal factor in their aetiology is mechanical; either skin stretching due to underlying tissue expansion or, less frequently, a compromised dermis affected by normal loads. In this paper, we investigate the pathogenesis of striae by addressing the coupling between mechanical forces and dermal pathology. We develop a mathematical model that incorporates the mechanical properties of cutaneous fibroblasts and dermal extracellular matrix. By using linear stability analysis and numerical simulations of our governing nonlinear equations, we show that this quantitative approach may provide a realistic framework that may account for the initiating events.

An investigation of striae distensae using reflectance confocal microscopy.

BACKGROUND: Striae distensae, otherwise known as stretch marks, are white or red scar-like streaks on the skin. Although they are not associated with adverse health outcomes, striae are associated with significant cosmetic morbidity. While they have been well characterised histopathologically, a non-invasive method of microscopic lesion assessment of striae would be welcome. METHODS: To gain insight into the small-scale morphological features associated with striae we undertook an in vivo investigation of nine patients with striae alba and one with striae rubra utilising reflectance confocal microscopy (RCM). RESULTS: Here we demonstrate that features known to be present using light microscopy, such as parallel collagen bundles in the dermis, and some features that are not well recognised by light microscopy, including distortion of dermal papillae, are demonstrable using RCM. CONCLUSIONS: Characterising the features of early and established striae distensae with confocal microscopy is an important foundation for future work. The potential ability to reliably identify the earliest pathological changes in skin in early lesions or before clinically manifest striae develop--a task facilitated by our findings--will increase the understanding of their pathogenesis and will have significant practical utility in monitoring the impact of future preventative interventions.

Formal methods for checking the consistency of biological models.

Formal modeling approaches such as process algebras and Petri nets seek to provide insight into biological processes by using both symbolic and numerical methods to reveal the dynamics of the process under study. These formal approaches differ from classical methods of investigating the dynamics of the process through numerical integration of ODEs because they additionally provide alternative representations which are amenable to discrete-state analysis and logical reasoning. Backed by these additional analysis methods, formal modeling approaches have been able to identify errors in published and widely-cited biological models. This paper provides an introduction to these analysis methods, and explains the benefits which they can bring to ensuring the consistency of biological models.

New insights in naevogenesis: number, distribution and dermoscopic patterns of naevi in the elderly.

BACKGROUND/OBJECTIVES: It is well recognized that the number and patterns of acquired melanocytic naevi vary with age, but little is known about naevus patterns in the elderly. This is a cross-sectional study assessing the prevalence, dermoscopic pattern and anatomical distribution of naevus subtypes in a stratified cohort aged between 60 and 89 years. METHODS: Fifty-nine patients who attended the Queensland Institute of Dermatology were recruited randomly and evenly distributed into three age groups: 60-69 years; 70-79 years; and 80-89 years. For each participant, total naevus count and morphological naevus types were recorded with respect to age, sex and anatomical location. Flat (Clark's) naevi were further subclassified according to the dermoscopic pattern as reticular, globular or structureless. RESULTS: Using non-parametric methods, naevus counts in the elderly decreased due to the disappearance of reticular naevi (P < 0.05). By contrast, structureless and intradermal (Unna's and Miescher's) naevi seemed to persist even into older age. Naevi on the trunk, limbs, head and neck represented 57.6%, 31.0% and 11.3%, respectively. Notably, no reticular naevi were found on the head and neck area. CONCLUSIONS: There is a progressive reduction in total naevus counts with advancing age with respect to a cohort aged greater than 60 years.

Tele-assessment of Psoriasis Area and Severity Index: a study of the accuracy of digital image capture.

BACKGROUND: The implementation of remote Psoriasis Area and Severity Index (PASI) determinations would greatly enhance the delivery of specialist dermatological care to patients with severe psoriasis unable to attend face-to-face dermatological consultations. Here we investigate the feasibility of the remote determination of PASI scores by comparing the results of face-to-face with digital image assessment. METHODS: Twelve patients with confirmed psoriasis were recruited for the study. Initially, two dermatologists scored the PASI at the patients' usual scheduled face-to-face visits, at which time standardized digital images were obtained. PASI scoring based on digital images was then performed on two separate occasions by three dermatologists with a time-interval period between assessments, facilitating an assessment of score reproducibility. Linear weighted kappa statistics were applied to the PASI scores to ascertain agreement between sets of observations. RESULTS: While we found a moderate (κ = 0.51) agreement between the face-to-face scores, there was very good (κ = 0.83) agreement between the first round of telescores and moderate (κ = 0.60) agreement between the second round of telescores. Comparison between the face-to-face and telescores revealed good (κ = 0.67 and 0.63) agreement for the scorers respectively. CONCLUSION: We demonstrate that PASI scores can be determined with moderate to good accuracy by dermatologists using standardized digital images. Our results imply the implementation of a tele-PASI service may be a practical and effective adjunct to the dermatological care of patients with severe psoriasis where incapacity or distance prevent the realisation of face-to-face consultations.

Control strategies for endemic childhood scabies.

Human scabies is a major global public health issue, with an estimated 300 million cases per year worldwide. Prevalence rates are particularly high in many third-world regions and within various indigenous communities in developed countries. Infestation with Sarcoptes Scabiei is associated with group-A streptococcal pyoderma which in turn predisposes to rheumatic fever, acute glomerulonephritis and their respective long-term sequelae: rheumatic heart disease and chronic renal insufficiency. The documented difficulties inherent in achieving scabies control within affected communities have motivated us to develop a network-dependent Monte-Carlo model of the scabies contagion, with the dual aims of gaining insight into its dynamics, and in determining the effects of various treatment strategies. Here we show that scabies burden is adversely affected by increases in average network degree, prominent network clustering, and by a person-to-person transmissibility of greater magnitude. We demonstrate that creating a community-specific model allows for the determination of an effective treatment protocol that can satisfy any pre-defined target prevalence. We find frequent low-density treatment protocols are inherently advantageous in comparison with infrequent mass screening and treatment regimes: prevalence rates are lower when compared with protocols that administer the same number of treatments over a given time interval less frequently, and frequent low-density treatment protocols have economic, practical and public acceptance advantages that may facilitate their long-term implementation. This work demonstrates the importance of stochasticity, community structure and the heterogeneity of individuals in influencing the dynamics of the human scabies contagion, and provides a practical method for investigating the outcomes of various intervention strategies.

Chronic telogen effluvium is due to a reduction in the variance of anagen duration.

BACKGROUND/OBJECTIVES: Chronic telogen effluvium and diffuse cyclical hair loss in women are well-described clinical entities characterized by chronic and fluctuating increases in hair shedding without loss of hair volume. We sought to investigate the follicular dynamics of chronic telogen effluvium and diffuse cyclical hair loss using a previously validated computer simulation known as the follicular automaton. METHODS: Using our model, we were able to simulate reductions in both the mean and variance of anagen duration and thus investigate their consequences with respect to both hair volume and hair shedding. RESULTS: We showed that reducing the mean anagen duration results in a loss of hair volume without prominent fluctuations in hair fall: findings that reproduced the key features in androgenetic alopecia. In contrast, a reduction in the variance of anagen duration generated follicular dynamics that accurately reproduced the known key features of chronic telogen effluvium and diffuse cyclical hair loss: acute exacerbations, periodicity and only minimal reductions in long-term hair volume. CONCLUSIONS: We provide evidence that suggests chronic telogen effluvium may be secondary to a reduction in the variance of anagen and suggest this pathological state represents a new functional type of recurrent hair shedding.

A support vector machine for decision support in melanoma recognition.

The early diagnosis of melanoma is critical to achieving reduced mortality and increased survival. Although clinical examination is currently the method of choice for melanocytic lesion assessment, difficulties may arise in the diagnosis of atypical lesions. From both the naked eye and dermoscopic perspective, dysplastic naevi often exhibit a prominent heterogeneity of structure that renders their clinical distinction from melanoma difficult. To address these problems in diagnosis, there exists a heightened interest among researchers regarding the utility of machine learning techniques in computerised image analysis. Here we report on the utility, for dermatologists, of support vector machine (SVM) technology in melanoma diagnosis, using an archive of 199 digital dermoscopic images of excised atypical melanocytic lesions. Our best validation models achieved an average sensitivity and specificity for melanoma diagnosis of 0.86 and 0.72, respectively. Applying the best model to our test set yielded a sensitivity of 0.89, a diagnostic odds ratio of 14.09 and an area under the receiver operated characteristic curve (AUC) of 0.76. Advantages of the procedure implemented are the simplicity of feature extraction and the computationally cheap and efficient nature of SVMs. The derived model generalises well with outcomes that compare favourably with competing algorithms and expert assessment. In line with the concept of the utility of decision support systems in clinical practice, we propose that to reduce the risk of missed melanomas, both the dermatologists' assessment and the SVM diagnosis be incorporated into the clinical decision-making process.

Patterns in naevoid skin disease: development, disease and modelling.

The aetiology of pattern-formation in human naevoid skin disease remains unknown. However, it is likely that the majority of previously proposed mechanisms - those that simply rely on passive clonal trafficking in embryogenesis - are incomplete. A more comprehensive explanation for pattern-formation in naevi invokes the principle of self-organization. We define two types of patterning: anatomical and functional. Anatomical patterning is where the abnormal clone is limited to regions of pathologic skin, while functional patterning is where the abnormal clone and pathologic skin are spatially uncorrelated. From a theoretical perspective self-organized naevoid patterns may be either secondary to local interactions between normal and aberrant genotypes or due to the interaction between aberrant genotypes and the presence of normal embryonic patterning cues. The latter possibility suggests the critical observation and analysis of patterns in naevoid skin disease may lead to unique insights into key aspects of early human embryogenesis.

Lacunarity analysis: a promising method for the automated assessment of melanocytic naevi and melanoma.

The early diagnosis of melanoma is critical to achieving reduced mortality and increased survival. Although clinical examination is currently the method of choice for melanocytic lesion assessment, there is a growing interest among clinicians regarding the potential diagnostic utility of computerised image analysis. Recognising that there exist significant shortcomings in currently available algorithms, we are motivated to investigate the utility of lacunarity, a simple statistical measure previously used in geology and other fields for the analysis of fractal and multi-scaled images, in the automated assessment of melanocytic naevi and melanoma. Digitised dermoscopic images of 111 benign melanocytic naevi, 99 dysplastic naevi and 102 melanomas were obtained over the period 2003 to 2008, and subject to lacunarity analysis. We found the lacunarity algorithm could accurately distinguish melanoma from benign melanocytic naevi or non-melanoma without introducing many of the limitations associated with other previously reported diagnostic algorithms. Lacunarity analysis suggests an ordering of irregularity in melanocytic lesions, and we suggest the clinical application of this ordering may have utility in the naked-eye dermoscopic diagnosis of early melanoma.