Semi-automated total body photography supports robust delivery of skin cancer monitoring services during the SARS-COV2/COVID-19 pandemic.

BACKGROUND: The SARS-CoV-2/COVID-19 pandemic dramatically impacted the delivery of healthcare, including dermatological services. In the initial stages of the pandemic, reduced patient flow produced a dramatic drop in the volume of skin cancer screening. Consistent with COVID-19 precautions, our practice conducted visual skin examinations (VSE) utilizing semi-automated total body photography (TBP). METHODS: A cross-sectional study of patient characteristics and self-reported melanoma risk factors associated with TBP usage was conducted on all patients from May to November 2020 in a single practitioner private dermatology setting. The process and histopathology-confirmed outcomes were compared to those in the same 6-month period in 2019. RESULTS: For the May-November 2020 timeframe, those who opted for the home TBP (35%) compared to clinic TBP were younger, had higher self-reported skin cancer risk, and were more likely to have had previous TBP sessions. Overall, the number of TBP sessions increased, while dermoscopy usage and biopsy number decreased. There was no change in the number and distribution of skin cancer diagnoses compared to the same period in 2019. The Melanoma-In-Situ:Invasive Melanoma (MIS:INV) ratio was above the U.S. ratio reported for 2020 of 0.95:1 (95,710 MIS:100,350 INV). CONCLUSION: Semi-automated TBP was successfully implemented during the pandemic without affecting skin cancer detection.

Melanoma screening using patient self-assessed risk and total body photography.

The current standard of care for high-risk melanoma patients is a two-step process using Total Body Photography (TBP) followed by dermoscopy and is limited to a select group of patients. Methods: A cross-sectional study of patient characteristics and self-reported melanoma risk factors associated with TBP usage and pathology-confirmed outcomes was conducted on a sample of 4,692 patients in a single practitioner private dermatology setting. Results: TBP patients were significantly more likely to be male, partnered, tobacco users, highly educated, and have increased self-reported risk factors (such as fair skin, personal history of skin cancer or melanoma, family history of skin cancer, numerous moles, or previous history of sunburn, P<0.05). Personal history of skin cancer and melanoma, male gender, ?40 moles, Medicare insurance, and increasing age were positively associated with malignancy outcomes, whereas higher education, family history of melanoma, and traditional (private) insurance were associated with reduced prevalence of malignant lesions. Patients' self-assessed skin cancer risk and access to skin detection modalities can result in detection of melanoma at early, curable stages. Higher level of education and partner status may result in a greater awareness of risk factors associated with melanoma.

Deep Learning and Handcrafted Method Fusion: Higher Diagnostic Accuracy for Melanoma Dermoscopy Images.

This paper presents an approach that combines conventional image processing with deep learning by fusing the features from the individual techniques. We hypothesize that the two techniques, with different error profiles, are synergistic. The conventional image processing arm uses three handcrafted biologically inspired image processing modules and one clinical information module. The image processing modules detect lesion features comparable to clinical dermoscopy information-atypical pigment network, color distribution, and blood vessels. The clinical module includes information submitted to the pathologist-patient age, gender, lesion location, size, and patient history. The deep learning arm utilizes knowledge transfer via a ResNet-50 network that is repurposed to predict the probability of melanoma classification. The classification scores of each individual module from both processing arms are then ensembled utilizing logistic regression to predict an overall melanoma probability. Using cross-validated results of melanoma classification measured by area under the receiver operator characteristic curve (AUC), classification accuracy of 0.94 was obtained for the fusion technique. In comparison, the ResNet-50 deep learning based classifier alone yields an AUC of 0.87 and conventional image processing based classifier yields an AUC of 0.90. Further study of fusion of conventional image processing techniques and deep learning is warranted.

Temporal Image Comparison (Serial Imaging) in Assessing Pigmented Lesions.

The large-scale deployment of low-cost, noninvasive mechanisms of early detection are needed to reduce the melanoma burden. A serial 2-step system could power mass screening efforts serving the uninsured and underinsured as well as the rural and remote US counties where melanoma mortality is doubled for lack of access to dermatologists. Furthermore, serial melanoma screening strategies, serial total body photography and serial digital dermatoscopy imaging may be performed as a telehealth service, and thus would be available in any location that can support activity compliant with the Health Insurance Portability and Accountability Act and has appropriate bandwidth.

The pink rim sign: location of pink as an indicator of melanoma in dermoscopic images.

Background. In dermoscopic images, multiple shades of pink have been described in melanoma without specifying location of these areas within the lesion. Objective. The purpose of this study was to determine the statistics for the presence of centrally and peripherally located pink melanoma and benign melanocytic lesions. Methods. Three observers, untrained in dermoscopy, each retrospectively analyzed 1290 dermoscopic images (296 melanomas (170 in situ and 126 invasive), 994 benign melanocytic nevi) and assessed the presence of any shade of pink in the center and periphery of the lesion. Results. Pink was located in the peripheral region in 14.5% of melanomas and 6.3% of benign melanocytic lesions, yielding an odds ratio of 2.51 (95% CI: 1.7-3.8, P < 0.0001). Central pink was located in 12.8% of melanomas and 21.8% of benign lesions, yielding an odds ratio of 0.462 (95% CI: 0.67, P = 0.204). Pink in melanoma in situ tended to be present throughout the lesion (68% of pink lesions). Pink in invasive melanoma was present in 17% of cases, often presenting as a pink rim. Conclusions. The presence of pink in the periphery or rim of a dermoscopic melanocytic lesion image provides an indication of malignancy. We offer the "pink rim sign" as a clue to the dermoscopic diagnosis of invasive melanoma.

Melanoma in situ in a private practice setting 2005 through 2009: location, lesion size, lack of concern.

BACKGROUND: Studies have shown that the incidence of melanoma in situ (MIS) is increasing significantly. OBJECTIVE: This study analyzes selected clinical and demographic characteristics of MIS cases observed in private dermatology practices in the United States. METHODS: This study collected 257 MIS cases from 4 private dermatology practices in the United States from January 2005 through December 2009, recording age, gender, anatomic location, lesion size, patient-reported change in lesion, and concern about lesion. Case totals for invasive melanoma during the same period were recorded. RESULTS: The data collected showed a higher incidence of MIS in sun-exposed areas of older patients, especially men. The median age of patients at the time of MIS detection was 69 years. The most common site for MIS was the head-neck region. The number of MIS cases collected exceeded the number of invasive malignant melanoma cases during the study period, with an observed ratio of 1.35:1. LIMITATIONS: For 136 patients, data were collected retrospectively for lesion size, location, gender, and age. For these patients, patient-reported change in lesion and concern about lesion were not collected. Patients often did not consent to a full body examination, therefore, it is possible that MIS lesions may have been missed in double-clothed areas. CONCLUSION: Careful attention to pigmented lesions, even lesions less than 4 mm, on sun-exposed areas, including scalp, trunk, and feet, will facilitate earlier diagnosis of MIS. As only 30.4% of male patients and 50% of female patients had concern about these lesions, it still falls to the dermatologist to discover MIS.

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.

Clinical pathway for melanoma detection using comprehensive cutaneous analysis with Melanoscan.

The usefulness of a comprehensive cutaneous photography system (Melanoscan) was tested using the following parameters: 1) decision to screen pathway, 2) clinical pathway, 3) clinical outcome, and 4) patient acceptance. The results indicate that 55 percent of those with criteria for scanning were reimbursed by insurance (AMA CTP category 1 code status 96904 for total body photography). In this model of whole body scanning, the ratio of time demand on physicians, patients, and technicians is 1:8:12. In 53 patients, 394 lesions of concern were identified. Of these lesions, 48 (12.31%) were scars, 306 (78.46%) were changed, and 36 (9.23%) were new. The decision to biopsy was made for 18 of the 394 lesions analyzed in the follow-up studies. Sensitivity of the process in determining malignant lesions is 75.00 percent and specificity is 73.70 percent. Preliminary results suggest that change detection analysis reduces the number of biopsies and improves diagnostic accuracy. Assessment of survey results revealed a high degree of patient satisfaction with ease of following Melanoscan directions (81.25%), as well as overall satisfaction with the process (73.44%). These results suggest that whole body screening using the Melanoscan provides a device in which accuracy of lesion tracking, patient confidence in lesion documentation, and clinician time are optimized.

Analysis of globule types in malignant melanoma.

OBJECTIVE: To identify and analyze subtypes of globules based on size, shape, network connectedness, pigmentation, and distribution to determine which globule types and globule distributions are most frequently associated with a diagnosis of malignant melanoma. DESIGN: Retrospective case series of dermoscopy images with globules. SETTING: Private dermatology practices. PARTICIPANTS: Patients in dermatology practices. Intervention Observation only. Main Outcome Measure Association of globule types with malignant melanoma. RESULTS: The presence of large globules (odds ratio [OR], 5.25) and globules varying in size (4.72) or shape (5.37) had the highest ORs for malignant melanoma among all globule types and combinations studied. Classical globules (dark, discrete, convex, and 0.10-0.20 mm) had a higher risk (OR, 4.20) than irregularly shaped globules (dark, discrete, and not generally convex) (2.89). Globules connected to other structures were not significant in the diagnosis of malignant melanoma. Of the different configurations studied, asymmetric clusters have the highest risk (OR, 3.02). CONCLUSIONS: The presence of globules of varying size or shape seems to be more associated with a diagnosis of malignant melanoma than any other globule type or distribution in this study. Large globules are of particular importance in the diagnosis of malignant melanoma.

Melanoma screening with serial whole body photographic change detection using Melanoscan technology.

The use of an automated, whole-body, diffusely lit digital imaging enclosure to produce serial images, which were then compared, using an astrophysics image display method, enabled a private practice dermatologist to detect melanoma at significantly thinner Breslow depths compared to all other clinical detection paradigms examined in this study. The patients were triaged to scanning using a melanoma risk survey system. The system employed a 24 camera semicircular imaging wall, with front and back views. 10,000 whole body photographic scans were obtained. Privacy was maintained with 128-bit image encryption and off-line storage. Image to image comparison of whole body digital photography was combined with a whole body skin exam in order to sensitize a clinical dermatologist to skin changes in individuals at risk for melanoma. Mean depths (Breslow scores) were compiled from six distinct melanoma biopsy cohorts segregated and based on different clinical screening paradigms. The Breslow depth of invasive lesions of the serial screening cohort was significantly less (by at least 0.050 mm) compared to three other clinical screening groups (patient self-detection 0.55 mm, p=0.007; referred by outside non-dermatologist physician 0.73 mm, p=0.03; and serial dermatologic evaluation 0.23 mm, p=0.03) as well as two pathology laboratory cohorts (community hospital laboratory 1.45 mm, p=0.003; dermatopathology laboratory 0.18, p=0.0003). This approach provides a quick and effective method for detection of early melanomas with a significant reduction in the skin area required for lesion examination.