Association between different scale bars in dermoscopic images and diagnostic performance of a market-approved deep learning convolutional neural network for melanoma recognition

Performance of Commercial Dermatoscopic Systems That Incorporate Artificial Intelligence for the Identification of Melanoma in General Practice: A Systematic Review

BACKGROUND

Cutaneous melanoma remains an increasing global public health burden, particularly in fair-skinned populations. Advancing technologies, particularly artificial intelligence (AI), may provide an additional tool for clinicians to help detect malignancies with a more accurate success rate. This systematic review aimed to report the performance metrics of commercially available convolutional neural networks (CNNs) tasked with detecting MM.

METHODS

A systematic literature search was performed using CINAHL, Medline, Scopus, ScienceDirect and Web of Science databases.

RESULTS

A total of 16 articles reporting MM were included in this review. The combined number of melanomas detected was 1160, and non-melanoma lesions were 33,010. The performance of market-approved technology and clinician performance for classifying melanoma was highly heterogeneous, with sensitivity ranging from 16.4 to 100.0%, specificity between 40.0 and 98.3% and accuracy between 44.0 and 92.0%. Less heterogeneity was observed when clinicians worked in unison with AI, with sensitivity ranging between 83.3 and 100.0%, specificity between 83.7 and 87.3%, and accuracy between 86.4 and 86.9%.

CONCLUSION

Instead of focusing on the performance of AI versus clinicians for classifying melanoma, more consistent performance has been obtained when clinicians' work is supported by AI, facilitating management decisions and improving health outcomes.

Artificial intelligence and skin cancer

Artificial intelligence is poised to rapidly reshape many fields, including that of skin cancer screening and diagnosis, both as a disruptive and assistive technology. Together with the collection and availability of large medical data sets, artificial intelligence will become a powerful tool that can be leveraged by physicians in their diagnoses and treatment plans for patients. This comprehensive review focuses on current progress toward AI applications for patients, primary care providers, dermatologists, and dermatopathologists, explores the diverse applications of image and molecular processing for skin cancer, and highlights AI's potential for patient self-screening and improving diagnostic accuracy for non-dermatologists. We additionally delve into the challenges and barriers to clinical implementation, paths forward for implementation and areas of active research.

Basic principles of artificial intelligence in dermatology explained using melanoma

The use of artificial intelligence (AI) continues to establish itself in the most diverse areas of medicine at an increasingly fast pace. Nevertheless, many healthcare professionals lack the basic technical understanding of how this technology works, which severely limits its application in clinical settings and research. Thus, we would like to discuss the functioning and classification of AI using melanoma as an example in this review to build an understanding of the technology behind AI. For this purpose, elaborate illustrations are used that quickly reveal the technology involved. Previous reviews tend to focus on the potential applications of AI, thereby missing the opportunity to develop a deeper understanding of the subject matter that is so important for clinical application. Malignant melanoma has become a significant burden for healthcare systems. If discovered early, a better prognosis can be expected, which is why skin cancer screening has become increasingly popular and is supported by health insurance. The number of experts remains finite, reducing their availability and leading to longer waiting times. Therefore, innovative ideas need to be implemented to provide the necessary care. Thus, machine learning offers the ability to recognize melanomas from images at a level comparable to experienced dermatologists under optimized conditions.

Grundprinzipien der künstlichen Intelligenz in der Dermatologie erklärt am Beispiel des Melanoms

Der Einsatz von künstlicher Intelligenz (KI) setzt sich in den verschiedensten Bereichen der Medizin immer schneller durch. Dennoch fehlt vielen medizinischen Kollegen das technische Grundverständnis für die Funktionsweise dieser Technologie, was ihre Anwendung in Klinik und Forschung stark einschränkt. Daher möchten wir in dieser Übersichtsarbeit die Funktionsweise und Klassifizierung der KI am Beispiel des Melanoms erörtern, um ein Verständnis für die Technologie hinter der KI zu schaffen. Dazu werden ausführliche Illustrationen verwendet, die die Technologie schnell erklären. Bisherige Übersichten konzentrieren sich eher auf die potenziellen Anwendungen der KI und verpassen die Gelegenheit, ein tieferes Verständnis für die Materie herauszuarbeiten, das für die klinische Anwendung so wichtig ist. Das maligne Melanom ist zu einer erheblichen Belastung für die Gesundheitssysteme geworden. Bei frühzeitiger Entdeckung ist eine bessere Prognose zu erwarten, weshalb das Hautkrebs‐Screening immer populärer und von den Krankenkassen unterstützt wird. Die Zahl der Fachärzte ist jedoch begrenzt, was ihre Verfügbarkeit einschränkt und zu längeren Wartezeiten führt. Daher müssen innovative Ideen umgesetzt werden, um die notwendige Versorgung zu gewährleisten. Das maschinelle Lernen bietet die Möglichkeit, Melanome auf Bildern zu erkennen, und zwar auf einem Niveau, das mit dem von erfahrenen Dermatologen – unter optimierten Bedingungen – vergleichbar ist.

Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma

Artificial intelligence (AI) systems have been shown to help dermatologists diagnose melanoma more accurately, however they lack transparency, hindering user acceptance. Explainable AI (XAI) methods can help to increase transparency, yet often lack precise, domain-specific explanations. Moreover, the impact of XAI methods on dermatologists' decisions has not yet been evaluated. Building upon previous research, we introduce an XAI system that provides precise and domain-specific explanations alongside its differential diagnoses of melanomas and nevi. Through a three-phase study, we assess its impact on dermatologists' diagnostic accuracy, diagnostic confidence, and trust in the XAI-support. Our results show strong alignment between XAI and dermatologist explanations. We also show that dermatologists' confidence in their diagnoses, and their trust in the support system significantly increase with XAI compared to conventional AI. This study highlights dermatologists' willingness to adopt such XAI systems, promoting future use in the clinic.

A deep learning fusion network trained with clinical and high-frequency ultrasound images in the multi-classification of skin diseases in comparison with dermatologists: a prospective and multicenter study

Background

Clinical appearance and high-frequency ultrasound (HFUS) are indispensable for diagnosing skin diseases by providing internal and external information. However, their complex combination brings challenges for primary care physicians and dermatologists. Thus, we developed a deep multimodal fusion network (DMFN) model combining analysis of clinical close-up and HFUS images for binary and multiclass classification in skin diseases.

Methods

Between Jan 10, 2017, and Dec 31, 2020, the DMFN model was trained and validated using 1269 close-ups and 11,852 HFUS images from 1351 skin lesions. The monomodal convolutional neural network (CNN) model was trained and validated with the same close-up images for comparison. Subsequently, we did a prospective and multicenter study in China. Both CNN models were tested prospectively on 422 cases from 4 hospitals and compared with the results from human raters (general practitioners, general dermatologists, and dermatologists specialized in HFUS). The performance of binary classification (benign vs. malignant) and multiclass classification (the specific diagnoses of 17 types of skin diseases) measured by the area under the receiver operating characteristic curve (AUC) were evaluated. This study is registered with www.chictr.org.cn (ChiCTR2300074765).

Findings

The performance of the DMFN model (AUC, 0.876) was superior to that of the monomodal CNN model (AUC, 0.697) in the binary classification (P = 0.0063), which was also better than that of the general practitioner (AUC, 0.651, P = 0.0025) and general dermatologists (AUC, 0.838; P = 0.0038). By integrating close-up and HFUS images, the DMFN model attained an almost identical performance in comparison to dermatologists (AUC, 0.876 vs. AUC, 0.891; P = 0.0080). For the multiclass classification, the DMFN model (AUC, 0.707) exhibited superior prediction performance compared with general dermatologists (AUC, 0.514; P = 0.0043) and dermatologists specialized in HFUS (AUC, 0.640; P = 0.0083), respectively. Compared to dermatologists specialized in HFUS, the DMFN model showed better or comparable performance in diagnosing 9 of the 17 skin diseases.

Interpretation

The DMFN model combining analysis of clinical close-up and HFUS images exhibited satisfactory performance in the binary and multiclass classification compared with the dermatologists. It may be a valuable tool for general dermatologists and primary care providers.

Funding

This work was supported in part by the National Natural Science Foundation of China and the Clinical research project of Shanghai Skin Disease Hospital.

Best Practices for Clinical Skin Image Acquisition in Translational Artificial Intelligence Research

Recent advances in artificial intelligence research have led to an increase in the development of algorithms for detecting malignancies from clinical and dermoscopic images of skin diseases. These methods are dependent on the collection of training and testing data. There are important considerations when acquiring skin images and data for translational artificial intelligence research. In this paper, we discuss the best practices and challenges for light photography image data collection, covering ethics, image acquisition, labeling, curation, and storage. The purpose of this work is to improve artificial intelligence for malignancy detection by supporting intentional data collection and collaboration between subject matter experts, such as dermatologists and data scientists.

Recent Advances in Melanoma Diagnosis and Prognosis Using Machine Learning Methods

PURPOSE OF REVIEW

The purpose was to summarize the current role and state of artificial intelligence and machine learning in the diagnosis and management of melanoma.

RECENT FINDINGS

Deep learning algorithms can identify melanoma from clinical, dermoscopic, and whole slide pathology images with increasing accuracy. Efforts to provide more granular annotation to datasets and to identify new predictors are ongoing. There have been many incremental advances in both melanoma diagnostics and prognostic tools using artificial intelligence and machine learning. Higher quality input data will further improve these models' capabilities.

Assessment of Diagnostic Performance of Dermatologists Cooperating With a Convolutional Neural Network in a Prospective Clinical Study: Human With Machine

Importance

Studies suggest that convolutional neural networks (CNNs) perform equally to trained dermatologists in skin lesion classification tasks. Despite the approval of the first neural networks for clinical use, prospective studies demonstrating benefits of human with machine cooperation are lacking.

Objective

To assess whether dermatologists benefit from cooperation with a market-approved CNN in classifying melanocytic lesions.

Design, Setting, and Participants

In this prospective diagnostic 2-center study, dermatologists performed skin cancer screenings using naked-eye examination and dermoscopy. Dermatologists graded suspect melanocytic lesions by the probability of malignancy (range 0-1, threshold for malignancy ≥0.5) and indicated management decisions (no action, follow-up, excision). Next, dermoscopic images of suspect lesions were assessed by a market-approved CNN, Moleanalyzer Pro (FotoFinder Systems). The CNN malignancy scores (range 0-1, threshold for malignancy ≥0.5) were transferred to dermatologists with the request to re-evaluate lesions and revise initial decisions in consideration of CNN results. Reference diagnoses were based on histopathologic examination in 125 (54.8%) lesions or, in the case of nonexcised lesions, on clinical follow-up data and expert consensus. Data were collected from October 2020 to October 2021.

Main Outcomes and Measures

Primary outcome measures were diagnostic sensitivity and specificity of dermatologists alone and dermatologists cooperating with the CNN. Accuracy and receiver operator characteristic area under the curve (ROC AUC) were considered as additional measures.

Results

A total of 22 dermatologists detected 228 suspect melanocytic lesions (190 nevi, 38 melanomas) in 188 patients (mean [range] age, 53.4 [19-91] years; 97 [51.6%] male patients). Diagnostic sensitivity and specificity significantly improved when dermatologists additionally integrated CNN results into decision-making (mean sensitivity from 84.2% [95% CI, 69.6%-92.6%] to 100.0% [95% CI, 90.8%-100.0%]; P = .03; mean specificity from 72.1% [95% CI, 65.3%-78.0%] to 83.7% [95% CI, 77.8%-88.3%]; P < .001; mean accuracy from 74.1% [95% CI, 68.1%-79.4%] to 86.4% [95% CI, 81.3%-90.3%]; P < .001; and mean ROC AUC from 0.895 [95% CI, 0.836-0.954] to 0.968 [95% CI, 0.948-0.988]; P = .005). In addition, the CNN alone achieved a comparable sensitivity, higher specificity, and higher diagnostic accuracy compared with dermatologists alone in classifying melanocytic lesions. Moreover, unnecessary excisions of benign nevi were reduced by 19.2%, from 104 (54.7%) of 190 benign nevi to 84 nevi when dermatologists cooperated with the CNN (P < .001). Most lesions were examined by dermatologists with 2 to 5 years (96, 42.1%) or less than 2 years of experience (78, 34.2%); others (54, 23.7%) were evaluated by dermatologists with more than 5 years of experience. Dermatologists with less dermoscopy experience cooperating with the CNN had the most diagnostic improvement compared with more experienced dermatologists.

Conclusions and Relevance

In this prospective diagnostic study, these findings suggest that dermatologists may improve their performance when they cooperate with the market-approved CNN and that a broader application of this human with machine approach could be beneficial for dermatologists and patients.

Artificial Intelligence in Dermatology Image Analysis: Current Developments and Future Trends

BACKGROUND

Thanks to the rapid development of computer-based systems and deep-learning-based algorithms, artificial intelligence (AI) has long been integrated into the healthcare field. AI is also particularly helpful in image recognition, surgical assistance and basic research. Due to the unique nature of dermatology, AI-aided dermatological diagnosis based on image recognition has become a modern focus and future trend. Key scientific concepts of review: The use of 3D imaging systems allows clinicians to screen and label skin pigmented lesions and distributed disorders, which can provide an objective assessment and image documentation of lesion sites. Dermatoscopes combined with intelligent software help the dermatologist to easily correlate each close-up image with the corresponding marked lesion in the 3D body map. In addition, AI in the field of prosthetics can assist in the rehabilitation of patients and help to restore limb function after amputation in patients with skin tumors.

THE AIM OF THE STUDY

For the benefit of patients, dermatologists have an obligation to explore the opportunities, risks and limitations of AI applications. This study focuses on the application of emerging AI in dermatology to aid clinical diagnosis and treatment, analyzes the current state of the field and summarizes its future trends and prospects so as to help dermatologists realize the impact of new technological innovations on traditional practices so that they can embrace and use AI-based medical approaches more quickly.

[Artificial intelligence-based classification for the diagnostics of skin cancer]

Convolutional neural networks (CNN) achieve a level of performance comparable or even superior to dermatologists in the assessment of pigmented and nonpigmented skin lesions. In the analysis of images by artificial neural networks, images on a pixel level pass through various layers of the network with different graphic filters. Based on excellent study results, a first deep learning network (Moleanalyzer pro, Fotofinder Systems GmBH, Bad Birnbach, Germany) received market approval in Europe. However, such neural networks also reveal relevant limitations, whereby rare entities with insufficient training images are classified less adequately and image artifacts can lead to false diagnoses. Best results can ultimately be achieved in a cooperation of "man with machine". For future skin cancer screening, automated total body mapping is evaluated, which combines total body photography, automated data extraction and assessment of all relevant skin lesions.

Model soups improve performance of dermoscopic skin cancer classifiers

BACKGROUND

Image-based cancer classifiers suffer from a variety of problems which negatively affect their performance. For example, variation in image brightness or different cameras can already suffice to diminish performance. Ensemble solutions, where multiple model predictions are combined into one, can improve these problems. However, ensembles are computationally intensive and less transparent to practitioners than single model solutions. Constructing model soups, by averaging the weights of multiple models into a single model, could circumvent these limitations while still improving performance.

OBJECTIVE

To investigate the performance of model soups for a dermoscopic melanoma-nevus skin cancer classification task with respect to (1) generalisation to images from other clinics, (2) robustness against small image changes and (3) calibration such that the confidences correspond closely to the actual predictive uncertainties.

METHODS

We construct model soups by fine-tuning pre-trained models on seven different image resolutions and subsequently averaging their weights. Performance is evaluated on a multi-source dataset including holdout and external components.

RESULTS

We find that model soups improve generalisation and calibration on the external component while maintaining performance on the holdout component. For robustness, we observe performance improvements for pertubated test images, while the performance on corrupted test images remains on par.

CONCLUSIONS

Overall, souping for skin cancer classifiers has a positive effect on generalisation, robustness and calibration. It is easy for practitioners to implement and by combining multiple models into a single model, complexity is reduced. This could be an important factor in achieving clinical applicability, as less complexity generally means more transparency.

Monitoring patients at risk for melanoma: May convolutional neural networks replace the strategy of sequential digital dermoscopy?

BACKGROUND

Sequential digital dermoscopy (SDD) is applied for early melanoma detection by uncovering dynamic changes of monitored lesions. Convolutional neural networks (CNN) are capable of high diagnostic accuracies similar to trained dermatologists.

OBJECTIVES

To investigate the capability of CNN to correctly classify melanomas originally diagnosed by mere dynamic changes during SDD.

METHODS

A retrospective cross-sectional study using image quartets of 59 high-risk patients each containing one melanoma diagnosed by dynamic changes during SDD and three nevi (236 lesions). Two validated CNN classified quartets at baseline or after SDD follow-up at the time of melanoma diagnosis. Moreover, baseline quartets were rated by 26 dermatologists. The main outcome was the number of quartets with correct classifications.

RESULTS

CNN-1 correctly classified 9 (15.3%) and CNN-2 8 (13.6%) of 59 baseline quartets. In baseline images, CNN-1 attained a sensitivity of 25.4% (16.1%-37.8%) and specificity of 92.7% (87.8%-95.7%), whereas CNN-2 of 28.8% (18.8%-41.4%) and 75.7% (68.9%-81.4%). Expectedly, after SDD follow-up CNN more readily detected melanomas resulting in improved sensitivities (CNN-1: 44.1% [32.2%-56.7%]; CNN-2: 49.2% [36.8%-61.6%]). Dermatologists were told that each baseline quartet contained one melanoma, and on average, correctly classified 24 (22-27) of 59 quartets. Correspondingly, accepting a baseline quartet to be appropriately classified whenever the highest malignancy score was assigned to the melanoma within, CNN-1 and CNN-2 correctly classified 28 (47.5%) and 22 (37.3%) of 59 quartets, respectively.

CONCLUSIONS

The tested CNN could not replace the strategy of SDD. There is a need for CNN capable of integrating information on dynamic changes into analyses.