Expert-Level Diagnosis of Nonpigmented Skin Cancer by Combined Convolutional Neural Networks.

Importance: Convolutional neural networks (CNNs) achieve expert-level accuracy in the diagnosis of pigmented melanocytic lesions. However, the most common types of skin cancer are nonpigmented and nonmelanocytic, and are more difficult to diagnose. Objective: To compare the accuracy of a CNN-based classifier with that of physicians with different levels of experience. Design, Setting, and Participants: A CNN-based classification model was trained on 7895 dermoscopic and 5829 close-up images of lesions excised at a primary skin cancer clinic between January 1, 2008, and July 13, 2017, for a combined evaluation of both imaging methods. The combined CNN (cCNN) was tested on a set of 2072 unknown cases and compared with results from 95 human raters who were medical personnel, including 62 board-certified dermatologists, with different experience in dermoscopy. Main Outcomes and Measures: The proportions of correct specific diagnoses and the accuracy to differentiate between benign and malignant lesions measured as an area under the receiver operating characteristic curve served as main outcome measures. Results: Among 95 human raters (51.6% female; mean age, 43.4 years; 95% CI, 41.0-45.7 years), the participants were divided into 3 groups (according to years of experience with dermoscopy): beginner raters (<3 years), intermediate raters (3-10 years), or expert raters (>10 years). The area under the receiver operating characteristic curve of the trained cCNN was higher than human ratings (0.742; 95% CI, 0.729-0.755 vs 0.695; 95% CI, 0.676-0.713; P < .001). The specificity was fixed at the mean level of human raters (51.3%), and therefore the sensitivity of the cCNN (80.5%; 95% CI, 79.0%-82.1%) was higher than that of human raters (77.6%; 95% CI, 74.7%-80.5%). The cCNN achieved a higher percentage of correct specific diagnoses compared with human raters (37.6%; 95% CI, 36.6%-38.4% vs 33.5%; 95% CI, 31.5%-35.6%; P = .001) but not compared with experts (37.3%; 95% CI, 35.7%-38.8% vs 40.0%; 95% CI, 37.0%-43.0%; P = .18). Conclusions and Relevance: Neural networks are able to classify dermoscopic and close-up images of nonpigmented lesions as accurately as human experts in an experimental setting.

Accuracy of dermatoscopy for the diagnosis of nonpigmented cancers of the skin.

BACKGROUND: Nonpigmented skin cancer is common, and diagnosis with the unaided eye is error prone. OBJECTIVE: To investigate whether dermatoscopy improves the diagnostic accuracy for nonpigmented (amelanotic) cutaneous neoplasms. METHODS: We collected a sample of 2072 benign and malignant neoplastic lesions and inflammatory conditions and presented close-up images taken with and without dermatoscopy to 95 examiners with different levels of experience. RESULTS: The area under the curve was significantly higher with than without dermatoscopy (0.68 vs 0.64, P < .001). Among 51 possible diagnoses, the correct diagnosis was selected in 33.1% of cases with and 26.4% of cases without dermatoscopy (P < .001). For experts, the frequencies of correct specific diagnoses of a malignant lesion improved from 40.2% without to 51.3% with dermatoscopy. For all malignant neoplasms combined, the frequencies of appropriate management strategies increased from 78.1% without to 82.5% with dermatoscopy. LIMITATIONS: The study deviated from a real-life clinical setting and was potentially affected by verification and selection bias. CONCLUSIONS: Dermatoscopy improves the diagnosis and management of nonpigmented skin cancer and should be used as an adjunct to examination with the unaided eye.

Non-choroidal yellow melanoma showing positive staining with Sudan Black consistent with the presence of lipofuscin: a case report.

A case of a predominantly yellow primary superficial spreading melanoma arising on the back of a 44-year-old woman is presented. Possible causes of the clinical and dermatoscopic yellow color are discussed. Staining with the histochemical stain, Sudan Black, revealed a differential uptake compared to a closely matched control melanoma. We speculate that the clinical and dermatoscopic yellow color could be due to the presence of increased amounts of the pigment lipofuscin, which is known to produce subtle orange color in some choroidal melanomas.

Total body skin examination for skin cancer screening in patients with focused symptoms.

BACKGROUND: The value of total body skin examination (TBSE) for skin cancer screening is controversial. OBJECTIVE: We sought to determine whether TBSE could be helpful in patients with focused skin symptoms who would not otherwise have undergone TBSE. METHODS: In a prospective, multicenter, cross-sectional study consecutive adult patients were recruited during a period of 18 months. Physicians first inspected problem areas and uncovered areas and then performed TBSE. Equivocal lesions detected in both steps were excised or biopsied. Primary outcomes were the absolute and relative risks of missing skin cancer and the number of patients needed to examine to detect melanoma or another malignancy. A secondary outcome was the proportion of false-positive results obtained by TBSE. RESULTS: We examined 14,381 patients and detected 40 (0.3%) patients with melanoma and 299 (2.1%) with at least one nonmelanoma skin cancer by TBSE. In 195 (1.3%) patients equivocal lesions found by TBSE turned out to be benign. We calculated that 47 patients need to be examined by TBSE to find one skin malignancy and 400 patients to detect one melanoma. The risk of missing one malignancy if not performing TBSE was 2.17% (95% confidence interval 1.25-3.74). Factors significantly increasing the chance to find a skin cancer were age, male gender, previous nonmelanoma skin cancer, fair skin type, skin tumor as the reason for consultation, and presence of an equivocal lesion on problem/uncovered areas. LIMITATIONS: The impact of TBSE on skin cancer mortality was not evaluated. CONCLUSIONS: TBSE improves skin cancer detection in patients with focused skin symptoms and shows a low rate of false-positive results.

Dermoscopy of cutaneous sarcoidosis.

BACKGROUND: The clinical variability of cutaneous sarcoidosis (CS) often makes its correct diagnosis challenging. Although traditionally employed for the diagnosis of skin tumors, during the past years dermoscopy also gained increasing interest as an aid in the clinical diagnosis of inflammatory and infectious skin manifestations in general dermatology. OBJECTIVE: Our purpose was to evaluate the usefulness of dermoscopy in the differential diagnosis of CS. METHODS: This was a retrospective analysis of 7 clinical and dermoscopic images of CS that were collected at dermatology clinics in France and Italy between 2005 and 2009. RESULTS: Retrospective dermoscopic evaluation revealed small grouped, translucent orange globular structures associated with linear vessels of variable diameter in all 7 cases. In 5 cases, additional central scar-like areas were seen. CONCLUSION: Lesions showing dermoscopically translucent yellow to orange globular-like or structureless areas associated with linear vessels should raise the suspicion of a granulomatous skin disease, including CS.

Dermoscopy and entomology (entomodermoscopy).

Although dermoscopy has been primarily designed for aiding the in vivo diagnosis of skin tumors, recent advances indicate it is also useful in the diagnosis of common skin infections and infestations. As such, dermoscopy connects the research fields of dermatology and entomology into one field of "entomodermoscopy". In this article we give an overview on the current applications of entomodermoscopy.