Tim K. Lee

Detection and Analysis of Irregular Streaks in Dermoscopic Images of Skin Lesions

Irregular streaks are important clues for Melanoma (a potentially fatal form of skin cancer) diagnosis using dermoscopy images. This paper extends our previous algorithm to identify the absence or presence of streaks in a skin lesions, by further analyzing the appearance of detected streak lines, and performing a three-way classification for streaks, Absent, Regular, and Irregular, in a pigmented skin lesion. In addition, the directional pattern of detected lines is analyzed to extract their orientation features in order to detect the underlying pattern. The method uses a graphical representation to model the geometric pattern of valid streaks and the distribution and coverage of the structure. Using these proposed features of the valid streaks along with the color and texture features of the entire lesion, an accuracy of 76.1% and weighted average area under ROC curve (AUC) of 85% is achieved for classifying dermoscopy images into streaks Absent, Regular, or Irregular on 945 images compiled from atlases and the internet without any exclusion criteria. This challenging dataset is the largest validation dataset for streaks detection and classification published to date. The data set has also been applied to the two-class sub-problems of Absent/Present classification (accuracy of 78.3% with AUC of 83.2%) and to Regular/Irregular classification (accuracy 83.6% with AUC of 88.9%). When the method was tested on a cleaned subset of 300 images randomly selected from the 945 images, the AUC increased to 91.8%, 93.2% and 90.9% for the Absent/Regular/Irregular, Absent/Present, and Regular/Irregular problems, respectively.

Melanoma Epidemiology and Prevention

The epidemiology of melanoma is complex, and individual risk depends on sun exposure, host factors, and genetic factors, and in their interactions as well. Sun exposure can be classified as intermittent, chronic, or cumulative (overall) exposure, and each appears to have a different effect on type of melanoma. Other environmental factors, such as chemical exposures-either through occupation, atmosphere, or food-may increase risk for melanoma, and this area warrants further study. Host factors that are well known to be important are the numbers and types of nevi and the skin phenotype. Genetic factors are classified as high-penetrant genes, moderate-risk genes, or low-risk genetic polymorphisms. Subtypes of tumors, such as BRAF-mutated tumors, have different risk factors as well as different therapies. Prevention of melanoma has been attempted using various strategies in specific subpopulations, but to date optimal interventions to reduce incidence have not emerged.

Assessing incidence rates and secular trends in nonmelanocytic skin cancer: which method is best?

Background: Evaluating the incidence of nonmelanocytic skin cancers in white populations and assessing the direction and strength of secular trends in these cancers have become important issues to dermatologists, oncologists, health policy analysts, and health care funders. Objective: The objective of this paper is to evaluate the three principal methods used to assess incidence rates and secular trends. Conclusions: Each of the three methods has strengths and weaknesses. An understanding of these will enable proper assessment of the value and significance of findings presented in the literature.

Geometry influence on polychromatic speckle contrast

Speckle contrast is widely used in various applications. In this work we develop a simple model to examine the influence of optical geometry on contrast reduction for polychromatic speckle the Fresnel diffraction zone. The model is based on the known fact that the sum of N independent speckle patterns decreases the contrast of the resultant pattern. The model shows how to construct zones in such a way that each zone creates an independent speckle. Theoretical grounds and experimental validation are presented. Practical applications of the derived formulae are discussed. The contrast reduction due to geometry is found to be significant for broad light low-coherent beams.

Stokes polarimetry probe for skin lesion evaluation – preliminary results

This paper reports on the design of a prototype in-vivo Stokes polarimetry probe for skin lesion evaluation, and preliminary results from skin phantom and clinical trials of this device. The probe releases a single millisecond-long pulse from a laser diode with either linear or circular polarization. It then captures the resulting backscattered far-field polarization speckle and calculates the Stokes parameters. This probe was designed with three novel innovations in mind. First, the Stokes vector is captured quickly, using low-cost components without the use of moving parts. Second, a compact collimated laser diode was used as the light source. Third, the device and detector geometry were designed to produce and capture a uniform speckle field. In the first clinical trial of this device, measurements were taken from a variety of skin lesions, both cancerous and benign. The Stokes vector was measured and used to calculate the degree of polarization (DOP), the azimuth angle, and the ellipticity angle of the polarization ellipse for two input light polarizations. Among other findings, the DOP for circular polarized input light was consistently lower than the DOP for linear polarized input light. These findings indicate the potential for a fast and low-cost in-vivo skin cancer screening tool, and encourages the continuing development of this probe’s techniques.

Automatic detection of basal cell carcinoma using vascular-extracted features from dermoscopy images

Basal cell carcinoma (BCC) is the most common type of skin cancer. Timely diagnosis of BCC is an important factor in the prognosis of the disease. A key to BCC diagnosis are vascular structures of the lesion. Detection and recognition of cutaneous vasculature provide critical information on diagnosis accuracy and assessment precision. In this paper, we present an effective method to extract vascular information towards lesion diagnosis. Given a dermoscopy image, we first segment vascular structures of the lesion by decomposing the image using independent component analysis into melanin and hemoglobin components and further applying shape filters at different scales. A vessel mask is generated as a result of global thresholding. A set of vascular features are then extracted from the final vessel image of the lesion and fed into a Random Forest classifier. The method demonstrates performance of 90.3% in terms of AUC in differentiating BCC from benign lesions.

Changing image of correlation optics: Introduction

This feature issue of Applied Optics contains a series of selected papers reflecting recent progress of correlation optics and illustrating current trends in vector singular optics, internal energy flows at light fields, optical science of materials, and new biomedical applications of lasers.

Coherence and polarization of polarization speckle generated by depolarizers and their changes through complex ABCD matrix

Recent research work on speckle patterns indicates a variation of the polarization state during propagation and its nonuniformly spatial distribution. The preliminary step for the investigation of this polarization speckle is the generation of the corresponding field. In this paper, a kind of special depolarizer: the random roughness birefringent screen (RRBS) is introduced to meet this requirement. The statistical properties of the field generated by the depolarizer is investigated and illustrated in terms of the 2x2 beam coherence and polarization matrix (BCPM) with the corresponding degree of coherence (DoC) η and degree of polarization (DoP) P . The changes of the coherence and polarization when the speckle field propagates through any optical system are analysed within the framework of the complex ABCD-matrix theory.

Polychlorinated biphenyls (PCB), UV radiation, and cutaneous malignant melanoma

Several older epidemiologic studies have suggested that exposure to polychlorinated biphenyls (PCBs) may increase risk of cutaneous malignant melanoma (CMM). These investigations, however, have not been able to control for sun exposure, and sun sensitivity, which are major risk factors for this cancer. We conducted a pilot study to examine the possible association between plasma levels of PCBs and risk of CMM, controlling for sun exposure and sun sensitivity. Our case-control study compared levels of 14 PCB congeners in the plasma of 80 Caucasian CMM patients, and 310 Caucasian controls frequency matched by age group and gender. Assays were conducted using gas chromatography and values were lipid-adjusted. Data concerning sun exposure history, sun sensitivity, and host pigmentation variables such as skin, eye and hair colour were also collected using standardized questionnaires. Odds ratios and 95% confidence intervals were calculated for total PCBs, dioxin-like and non-dioxin like PCBs, as well as individual congeners using unconditional logistic regression. A strong association was seen between melanoma risk and plasma levels of total PCBs, (OR highest quartile: 6.02; 95% CI = 2.00-18.17); non-dioxin-like PCBs (OR highest quartile:7.02; 95%CI = 2.30-21.43); and many of the single congeners. These associations persisted after adjustment for recreational sun exposure, sun sensitivity and pigmentation factors. Although the study results will require independent confirmation in larger case-control or cohort investigations, they suggest that potential environmental factors other than UV radiation may be involved in melanoma.