Performance of a computer-aided digital dermoscopic image analyzer for melanoma detection in 1,076 pigmented skin lesion biopsies

Development and Narrow Validation of Computer Vision Approach to Facilitate Assessment of Change in Pigmented Cutaneous Lesions

The documentation of the change in the number and appearance of pigmented cutaneous lesions over time is critical to the early detection of skin cancers and may provide preliminary signals of efficacy in early-phase therapeutic prevention trials for melanoma. Despite substantial progress in computer-aided diagnosis of melanoma, automated methods to assess the evolution of lesions are relatively undeveloped. This report describes the development and narrow validation of mathematical algorithms to register nevi between sequential digital photographs of large areas of skin and to align images for improved detection and quantification of changes. Serial posterior truncal photographs from a pre-existing database were processed and analyzed by the software, and the results were evaluated by a panel of clinicians using a separate Extensible Markup Language‒based application. The software had a high sensitivity for the detection of cutaneous lesions as small as 2 mm. The software registered lesions accurately, with occasional errors at the edges of the images. In one pilot study with 17 patients, the use of the software enabled clinicians to identify new and/or enlarged lesions in 3‒11 additional patients versus the unregistered images. Automated quantification of size change performed similarly to that of human raters. These results support the further development and broader validation of this technique.

Overdiagnosis of melanoma - causes, consequences and solutions

Malignant melanoma is the skin tumor that causes most deaths in Germany. At an early stage, melanoma is well treatable, so early detection is essential. However, the skin cancer screening program in Germany has been criticized because although melanomas have been diagnosed more frequently since introduction of the program, the mortality from malignant melanoma has not decreased. This indicates that the observed increase in melanoma diagnoses be due to overdiagnosis, i.e. to the detection of lesions that would never have created serious health problems for the patients. One of the reasons is the challenging distinction between some benign and malignant lesions. In addition, there may be lesions that are biologically equivocal, and other lesions that are classified as malignant according to current criteria, but that grow so slowly that they would never have posed a threat to patient's life. So far, these "indolent" melanomas cannot be identified reliably due to a lack of biomarkers. Moreover, the likelihood that an in-situ melanoma will progress to an invasive tumor still cannot be determined with any certainty. When benign lesions are diagnosed as melanoma, the consequences are unnecessary psychological and physical stress for the affected patients and incurred therapy costs. Vice versa, underdiagnoses in the sense of overlooked melanomas can adversely affect patients' prognoses and may necessitate more intense therapies. Novel diagnostic options could reduce the number of over- and underdiagnoses and contribute to more objective diagnoses in borderline cases. One strategy that has yielded promising results in pilot studies is the use of artificial intelligence-based diagnostic tools. However, these applications still await translation into clinical and pathological routine.

[Computer-assisted skin cancer diagnosis : Is it time for artificial intelligence in clinical practice?]

BACKGROUND

Artificial intelligence (AI) is increasingly being used in medical practice. Especially in the image-based diagnosis of skin cancer, AI shows great potential. However, there is a significant discrepancy between expectations and true relevance of AI in current dermatological practice.

OBJECTIVES

This article summarizes promising study results of skin cancer diagnosis by computer-based diagnostic systems and discusses their significance for daily practice. We hereby focus on the analysis of dermoscopic images of pigmented and unpigmented skin lesions.

MATERIALS AND METHODS

A selective literature search for recent relevant trials was conducted. The included studies used machine learning, and in particular "convolutional neural networks", which have been shown to be particularly effective for the classification of image data.

RESULTS AND CONCLUSIONS

In numerous studies, computer algorithms were able to detect pigmented and nonpigmented neoplasms of the skin with high precision, comparable to that of dermatologists. The combination of the physician's assessment and AI showed the best results. Computer-based diagnostic systems are widely accepted among patients and physicians. However, they are still not applicable in daily practice, since computer-based diagnostic systems have only been tested in an experimental environment. In addition, many digital diagnostic criteria that help AI to classify skin lesions remain unclear. This lack of transparency still needs to be addressed. Moreover, clinical studies on the use of AI-based assistance systems are needed in order to prove its applicability in daily dermatologic practice.

Past and present of computer-assisted dermoscopic diagnosis: performance of a conventional image analyser versus a convolutional neural network in a prospective data set of 1,981 skin lesions

BACKGROUND

Convolutional neural networks (CNNs) have shown a dermatologist-level performance in the classification of skin lesions. We aimed to deliver a head-to-head comparison of a conventional image analyser (CIA), which depends on segmentation and weighting of handcrafted features, to a CNN trained by deep learning.

METHODS

Cross-sectional study using a real-world, prospectively acquired, dermoscopic dataset of 1981 skin lesions to compare the diagnostic performance of a market-approved CNN (Moleanalyzer-Pro™, developed in 2018) to a CIA (Moleanalyzer-3™/Dynamole™; developed in 2004, all FotoFinder Systems Inc, Germany). As a reference standard, we used histopathological diagnoses (n = 785) or, in non-excised benign lesions (n = 1196), expert consensus plus an uneventful follow-up by sequential digital dermoscopy for at least 2 years.

RESULTS

A total of 281 malignant lesions and 1700 benign lesions from 435 patients (62.2% male, mean age: 52 years) were prospectively imaged. The CNN showed a sensitivity of 77.6% (95% confidence interval [CI]: [72.4%-82.1%]), specificity of 95.3% (95% CI: [94.2%-96.2%]), and receiver operating characteristic (ROC)-area under the curve (AUC) of 0.945 (95% CI: [0.930-0.961]). In contrast, the CIA achieved a sensitivity of 53.4% (95% CI: [47.5%-59.1%]), specificity of 86.6% (95% CI: [84.9%-88.1%]) and ROC-AUC of 0.738 (95% CI: [0.701-0.774]). The data set included melanomas originally diagnosed by dynamic changes during sequential digital dermoscopy (52 of 201, 20.6%), which reduced the sensitivities of both classifiers. Pairwise comparisons of sensitivities, specificities, and ROC-AUCs indicated a clear outperformance by the CNN (all p < 0.001).

CONCLUSIONS

The superior diagnostic performance of the CNN argues against a continued application of former CIAs as an aide to physicians' clinical management decisions.

Advances in Prevention and Surveillance of Cutaneous Malignancies

Skin cancer affects 1 in 5 Americans, resulting in significant morbidity and mortality. Treatment costs and rates of skin cancer and melanoma continue to rise, making preventative measures increasingly important. However, there is conflicting evidence about efficacy of primary and secondary prevention strategies in decreasing incidence and improving early diagnosis. The US Preventative Services Task Force 2016 guidelines did not endorse routine skin cancer screening because of "insufficient evidence." Yet, countries like Australia have shown the feasibility and cost-effectiveness of primary sun safety interventions and secondary prevention measures such as routine skin cancer surveillance. Additional emerging evidence shows that regular skin cancer screening in high-risk populations improves early detection and decreases melanoma mortality. New technology may enhance prevention, promote accurate diagnoses, and improve management of melanoma and nonmelanoma skin cancers. Here, we place rising rates of melanoma within historical context, review costs, efficacy, and evidence for primary and secondary skin cancer prevention and examine the evolving role of novel technologies in the field.

Accuracy of Computer-Aided Diagnosis of Melanoma: A Meta-analysis

IMPORTANCE

The recent advances in the field of machine learning have raised expectations that computer-aided diagnosis will become the standard for the diagnosis of melanoma.

OBJECTIVE

To critically review the current literature and compare the diagnostic accuracy of computer-aided diagnosis with that of human experts.

DATA SOURCES

The MEDLINE, arXiv, and PubMed Central databases were searched to identify eligible studies published between January 1, 2002, and December 31, 2018.

STUDY SELECTION

Studies that reported on the accuracy of automated systems for melanoma were selected. Search terms included melanoma, diagnosis, detection, computer aided, and artificial intelligence.

DATA EXTRACTION AND SYNTHESIS

Evaluation of the risk of bias was performed using the QUADAS-2 tool, and quality assessment was based on predefined criteria. Data were analyzed from February 1 to March 10, 2019.

MAIN OUTCOMES AND MEASURES

Summary estimates of sensitivity and specificity and summary receiver operating characteristic curves were the primary outcomes.

RESULTS

The literature search yielded 1694 potentially eligible studies, of which 132 were included and 70 offered sufficient information for a quantitative analysis. Most studies came from the field of computer science. Prospective clinical studies were rare. Combining the results for automated systems gave a melanoma sensitivity of 0.74 (95% CI, 0.66-0.80) and a specificity of 0.84 (95% CI, 0.79-0.88). Sensitivity was lower in studies that used independent test sets than in those that did not (0.51; 95% CI, 0.34-0.69 vs 0.82; 95% CI, 0.77-0.86; P < .001); however, the specificity was similar (0.83; 95% CI, 0.71-0.91 vs 0.85; 95% CI, 0.80-0.88; P = .67). In comparison with dermatologists' diagnosis, computer-aided diagnosis showed similar sensitivities and a 10 percentage points lower specificity, but the difference was not statistically significant. Studies were heterogeneous and substantial risk of bias was found in all but 4 of the 70 studies included in the quantitative analysis.

CONCLUSIONS AND RELEVANCE

Although the accuracy of computer-aided diagnosis for melanoma detection is comparable to that of experts, the real-world applicability of these systems is unknown and potentially limited owing to overfitting and the risk of bias of the studies at hand.

Hyperspectral imaging in automated digital dermoscopy screening for melanoma

Objectives

Early melanoma detection decreases morbidity and mortality. Early detection classically involves dermoscopy to identify suspicious lesions for which biopsy is indicated. Biopsy and histological examination then diagnose benign nevi, atypical nevi, or cancerous growths. With current methods, a considerable number of unnecessary biopsies are performed as only 11% of all biopsied, suspicious lesions are actually melanomas. Thus, there is a need for more advanced noninvasive diagnostics to guide the decision of whether or not to biopsy. Artificial intelligence can generate screening algorithms that transform a set of imaging biomarkers into a risk score that can be used to classify a lesion as a melanoma or a nevus by comparing the score to a classification threshold. Melanoma imaging biomarkers have been shown to be spectrally dependent in Red, Green, Blue (RGB) color channels, and hyperspectral imaging may further enhance diagnostic power. The purpose of this study was to use the same melanoma imaging biomarkers previously described, but over a wider range of wavelengths to determine if, in combination with machine learning algorithms, this could result in enhanced melanoma detection.

Methods

We used the melanoma advanced imaging dermatoscope (mAID) to image pigmented lesions assessed by dermatologists as requiring a biopsy. The mAID is a 21‐wavelength imaging device in the 350–950 nm range. We then generated imaging biomarkers from these hyperspectral dermoscopy images, and, with the help of artificial intelligence algorithms, generated a melanoma Q‐score for each lesion (0 = nevus, 1 = melanoma). The Q‐score was then compared to the histopathologic diagnosis.

Results

The overall sensitivity and specificity of hyperspectral dermoscopy in detecting melanoma when evaluated in a set of lesions selected by dermatologists as requiring biopsy was 100% and 36%, respectively.

Conclusion

With widespread application, and if validated in larger clinical trials, this non‐invasive methodology could decrease unnecessary biopsies and potentially increase life‐saving early detection events. Lasers Surg. Med. 51:214–222, 2019. © 2019 The Authors. Lasers in Surgery and Medicine Published by Wiley Periodicals, Inc.