Accuracy in melanoma detection: a 10-year multicenter survey.

BACKGROUND: Early excision is the only strategy to reduce melanoma mortality, but unnecessary excision of benign lesions increases morbidity and healthcare costs. OBJECTIVE: To assess accuracy in melanoma detection based on number-needed-to-excise (NNE) values over a 10-year period. METHODS: Information was retrieved on all histopathologically confirmed cutaneous melanomas or melanocytic nevi that were excised between 1998 and 2007 at participating clinics. NNE values were calculated by dividing the total number of excised lesions by the number of melanomas. Analyses included changes in NNE over time, differences in NNE between specialized clinical settings (SCS) versus non-specialized clinical settings (NSCS), and patient factors influencing NNE. RESULTS: The participating clinics contributed a total of 300,215 cases, including 17,172 melanomas and 283,043 melanocytic nevi. The overall NNE values achieved in SCS and NSCS in the 10-year period were 8.7 and 29.4, respectively. The NNE improved over time in SCS (from 12.8 to 6.8), but appeared unchanged in NSCS. Most of the effect on NNE in SCS was due to a greater number of excised melanomas. Higher NNE values were observed in patients younger than 40 years and for lesions located on the trunk. LIMITATIONS: No data concerning the use of dermatoscopy and digital monitoring procedures were collected from the participating centers. CONCLUSION: Over the 10-year study period, accuracy in melanoma detection improved only in specialized clinics maybe because of a larger use of new diagnostic techniques such as dermatoscopy.

Automatic detection of basal cell carcinoma using telangiectasia analysis in dermoscopy skin lesion images.

BACKGROUND: Telangiectasia, dilated blood vessels near the surface of the skin of small, varying diameter, are critical dermoscopy structures used in the detection of basal cell carcinoma (BCC). Distinguishing these vessels from other telangiectasia, that are commonly found in sun-damaged skin, is challenging. METHODS: Image analysis techniques are investigated to find vessels structures in BCC automatically. The primary screen for vessels uses an optimized local color drop technique. A noise filter is developed to eliminate false-positive structures, primarily bubbles, hair, and blotch and ulcer edges. From the telangiectasia mask containing candidate vessel-like structures, shape, size and normalized count features are computed to facilitate the discrimination of benign skin lesions from BCCs with telangiectasia. RESULTS: Experimental results yielded a diagnostic accuracy as high as 96.7% using a neural network classifier for a data set of 59 BCCs and 152 benign lesions for skin lesion discrimination based on features computed from the telangiectasia masks. CONCLUSION: In current clinical practice, it is possible to find smaller BCCs by dermoscopy than by clinical inspection. Although almost all of these small BCCs have telangiectasia, they can be short and thin. Normalization of lengths and areas helps to detect these smaller BCCs.

Duration of Loxosceles reclusa venom detection by ELISA from swabs.

BACKGROUND: Diagnosis of Loxosceles reclusa envenomations is currently based upon clinical presentation. An enzyme-linked immunosorbent assay (ELISA) can detect surface Loxosceles venom at the envenomation site, allowing diagnostic confirmation. The length of time that venom on the skin is recoverable non-invasively is unknown. MATERIALS AND METHODS: To investigate duration of recoverable venom antigen, whole venom and fractionated sphingomyelinase D venom aliquots were injected subcutaneously in New Zealand White rabbits. Cotton and Dacron swabs were compared for venom recovery over a 21-day period using a surface swab technique. RESULTS: Significant amounts of Loxosceles reclusa antigen were found on the surface of rabbit skin after experimental injection of whole venom and sphingomyelinase D. The duration of recoverable antigen using this experimental model appears to be at least two weeks and as long as 21 days in some cases. CONCLUSIONS: Because the duration of the recoverable antigen is seen to be at least two weeks, the ELISA venom test appears capable of detecting venom on most patients presenting with Loxosceles envenomations. This detection system will allow the physician more accurate determination of whether the lesion is from a brown recluse spider or some other agent that can cause this type of necrotic ulcer.

Tick-borne febrile illnesses lacking specific symptoms.

We report here one case of tularemia, one case of human monocytic ehrlichiosis, and one case of febrile illness most consistent with tularemia with titers suggestive of Rocky Mountain spotted fever in residents of three south-central Missouri counties. All three cases had with nonspecific symptoms of a febrile illness. All three patients had a history of a tick bite, common in south-central Missouri, but only two patients reported the tick bite when first seen. In these three cases, the severity of the illness provided a clue that led to a diagnosis of tick-borne febrile illnesses by confirmatory serology in two cases. It is very important that physicians be aware of these diseases in the spring and summer months.

Systemic loxoscelism confirmation by bite-site skin surface: ELISA.

We report here a case of systemic loxoscelism, confirmed by bite-site skin surface swab. Features of systemic loxoscelism present in this case included debilitating symptoms, a classic local bite-site reaction, hemolysis causing loss of approximately 15% of the blood volume within 72 hours, and a symptomatic exanthem. A skin surface ELISA test was used to confirm the presence of venom. This test enables confirmation of cases of loxoscelism for which no spider is found.

Detection of granularity in dermoscopy images of malignant melanoma using color and texture features.

Granularity, also called peppering and multiple blue-grey dots, is defined as an accumulation of tiny, blue-grey granules in dermoscopy images. Granularity is most closely associated with a diagnosis of malignant melanoma. This study analyzes areas of granularity with color and texture measures to discriminate granularity in melanoma from similar areas in non-melanoma skin lesions. The granular areas in dermoscopy images of 74 melanomas and 14 melanomas in situ were identified and manually selected. For 200 non-melanoma dermoscopy images, those areas which most closely resembled granularity in color and texture were similarly selected. Ten texture and twenty-two color measures were studied. The texture measures consisted of the average and range of energy, inertia, correlation, inverse difference, and entropy. The color measures consisted of absolute and relative RGB averages, absolute and relative RGB chromaticity averages, absolute and relative G/B averages, CIE X, Y, Z, X/Y, X/Z and Y/Z averages, R variance, and luminance. These measures were calculated for each granular area of the melanomas and the comparable areas in the non-melanoma images. Receiver operating characteristic (ROC) curve analysis showed that the best separation of melanoma images from non-melanoma images by granular area features was obtained with a combination of color and texture measures. Comparison of ROC results showed greater separation of melanoma from benign lesions using relative color than using absolute color. Statistical analysis showed that the four most significant measures of granularity in melanoma are two color measures and two texture measures averaged over the spots: relative blue, relative green, texture correlation, and texture energy range. The best feature set, utilizing texture and relative color measures, achieved an accuracy of 96.4% based on area under the receiver operating characteristic curve.

Concentric decile segmentation of white and hypopigmented areas in dermoscopy images of skin lesions allows discrimination of malignant melanoma.

Dermoscopy, also known as dermatoscopy or epiluminescence microscopy (ELM), permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. White areas, prominent in early malignant melanoma and melanoma in situ, contribute to early detection of these lesions. An adaptive detection method has been investigated to identify white and hypopigmented areas based on lesion histogram statistics. Using the Euclidean distance transform, the lesion is segmented in concentric deciles. Overlays of the white areas on the lesion deciles are determined. Calculated features of automatically detected white areas include lesion decile ratios, normalized number of white areas, absolute and relative size of largest white area, relative size of all white areas, and white area eccentricity, dispersion, and irregularity. Using a back-propagation neural network, the white area statistics yield over 95% diagnostic accuracy of melanomas from benign nevi. White and hypopigmented areas in melanomas tend to be central or paracentral. The four most powerful features on multivariate analysis are lesion decile ratios. Automatic detection of white and hypopigmented areas in melanoma can be accomplished using lesion statistics. A neural network can achieve good discrimination of melanomas from benign nevi using these areas. Lesion decile ratios are useful white area features.