IMPORTANCE Deep learning convolutional neural networks (CNNs) have shown a performance at the level of dermatologists in the diagnosis of melanoma. Accordingly, further exploring the potential limitations of CNN technology before broadly applying it is of special interest. OBJECTIVE To investigate the association between gentian violet surgical skin markings in dermoscopic images and the diagnostic performance of a CNN approved for use as a medical device in the European market. DESIGN AND SETTING A cross-sectional analysis was conducted from August 1, 2018, to November 30, 2018, using a CNN architecture trained with more than 120 000 dermoscopic images of skin neoplasms and corresponding diagnoses. The association of gentian violet skin markings in dermoscopic images with the performance of the CNN was investigated in 3 image sets of 130 melanocytic lesions each (107 benign nevi, 23 melanomas). EXPOSURES The same lesions were sequentially imaged with and without the application of a gentian violet surgical skin marker and then evaluated by the CNN for their probability of being a melanoma. In addition, the markings were removed by manually cropping the dermoscopic images to focus on the melanocytic lesion. MAIN OUTCOMES AND MEASURES Sensitivity, specificity, and area under the curve (AUC) of the receiver operating characteristic (ROC) curve for the CNN's diagnostic classification in unmarked, marked, and cropped images. RESULTS In all, 130 melanocytic lesions (107 benign nevi and 23 melanomas) were imaged. In unmarked lesions, the CNN achieved a sensitivity of 95.7% (95% CI, 79%-99.2%) and a specificity of 84.1% (95% CI, 76.0%-89.8%). The ROC AUC was 0.969. In marked lesions, an increase in melanoma probability scores was observed that resulted in a sensitivity of 100% (95% CI, 85.7%-100%) and a significantly reduced specificity of 45.8% (95% CI, 36.7%-55.2%, P < .001). The ROC AUC was 0.922. Cropping images led to the highest sensitivity of 100% (95% CI, 85.7%-100%), specificity of 97.2% (95% CI, 92.1%-99.0%), and ROC AUC of 0.993. Heat maps created by vanilla gradient descent backpropagation indicated that the blue markings were associated with the increased false-positive rate. CONCLUSIONS AND RELEVANCE This study's findings suggest that skin markings significantly interfered with the CNN's correct diagnosis of nevi by increasing the melanoma probability scores and consequently the false-positive rate. A predominance of skin markings in melanoma training images may have induced the CNN's association of markings with a melanoma diagnosis. Accordingly, these findings suggest that skin markings should be avoided in dermoscopic images intended for analysis by a CNN. TRIAL REGISTRATION German Clinical Trial Register (DRKS) Identifier: DRKS00013570
Background
Nodular melanoma (NM) is more likely to be fatal compared with other melanoma subtypes, an effect attributed to its greater Breslow thickness.
Methods
Clinicopathological features of NM and superficial spreading melanoma (SSM) diagnosed in 17 centers in Europe (n = 15), the United States, and Australia between 2006 and 2015, were analyzed by multivariable logistic regression analysis, with emphasis on thin (T1 ≤ 1.0 mm) melanomas. Cox analysis assessed melanoma-specific survival. All statistical tests were two sided.
Results
In all, 20 132 melanomas (NM: 5062, SSM: 15 070) were included. Compared with T1 SSM, T1 NM was less likely to have regression (odds ratio [OR] = 0.46, 95% confidence interval [CI] = 0.29 to 0.72) or nevus remnants histologically (OR = 0.60, 95% CI = 0.42 to 0.85), and more likely to have mitoses (OR = 1.97, 95% CI = 1.33 to 2.93) and regional metastasis (OR = 1.77, 95% CI = 1.02 to 3.05). T1 NM had a higher mitotic rate than T1 SSM (adjusted geometric mean = 2.2, 95% CI = 1.9 to 2.5 vs 1.6, 95% CI = 1.5 to 1.7 per mm2, P < .001). Cox multivariable analysis showed a higher risk for melanoma-specific death for NM compared with SSM for T1 (HR = 2.10, 95% CI = 1.24 to 3.56) and T2 melanomas (HR = 1.30, 95% CI = 1.01 to 1.68), and after accounting for center heterogeneity, the difference was statistically significant only for T1 (HR = 2.20, 95% CI = 1.28 to 3.78). The NM subtype did not confer increased risk within each stratum (among localized tumors or cases with regional metastasis).
Conclusions
T1 NM (compared with T1 SSM) was associated with a constellation of aggressive characteristics that may confer a worse prognosis. Our results indicate NM is a high-risk melanoma subtype that should be considered for inclusion in future prognostic classifications of melanoma.
Background Deep learning convolutional neural networks (CNN) may assist physicians in the diagnosis of melanoma. The capacity of a CNN to differentiate melanomas from combined naevi, the latter representing well-known melanoma simulators, has not been investigated. Objective To assess the diagnostic performance of a CNN when used to differentiate melanomas from combined naevi in comparison with dermatologists. Methods In this study, a CNN with regulatory approval for the European market (Moleanalyzer-Pro, FotoFinder Systems GmbH, Bad Birnbach, Germany) was used. We attained a dichotomous classification (benign, malignant) in dermoscopic images of 36 combined naevi and 36 melanomas with a mean Breslow thickness of 1.3 mm. Primary outcome measures were the CNN's sensitivity, specificity and the diagnostic odds ratio (DOR) in comparison with 11 dermatologists with different levels of experience. Results The CNN revealed a sensitivity, specificity and DOR of 97.1% (95% CI [82.7-99.6]), 78.8% (95% CI [62.8-89.1.3]) and 34 (95% CI [4.8-239]), respectively. Dermatologists showed a lower mean sensitivity, specificity and DOR of 90.6% (95% CI [84.1-94.7]; P = 0.092), 71.0% (95% CI [62.6-78.1]; P = 0.256) and 24 (95% CI [11.6-48.4]; P = 0.1114). Under the assumption that dermatologists use the CNN to verify their (initial) melanoma diagnosis, dermatologists achieve an increased specificity of 90.3% (95% CI [79.8-95.6]) at an almost unchanged sensitivity. The largest benefit was observed in 'beginners', who performed worst without CNN verification (DOR = 12) but best with CNN verification (DOR = 98). Conclusion The tested CNN more accurately classified combined naevi and melanomas in comparison with trained dermatologists. Their diagnostic performance could be improved if the CNN was used to confirm/overrule an initial melanoma diagnosis. Application of a CNN may therefore be of benefit to clinicians.
SummaryToday, dermatoscopy is an integral part of every clinical skin examination, as it markedly enhances the early detection of melanocytic and nonmelanocytic skin cancer (NMSC) compared to naked-eye inspection. Besides its diagnostic use, this noninvasive method is increasingly important in the selection of as well as the response assessment to various therapies used for NMSC, including basal cell carcinoma, actinic keratoses, squamous cell carcinoma, and also rare tumors such as Merkel cell carcinoma, angiosarcoma, or dermatofibrosarcoma protuberans. Thus, dermatoscopy is a valid tool for the preoperative assessment of tumor margins in basal cell carcinoma, but also for follow-up of actinic keratoses after topical treatment. The present article presents an overview on the use of dermatoscopy in the diagnosis and therapy of various types of NMSC.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.