Artificial Intelligence in Teledermatology

Artificial intelligence in the detection of skin cancer: State of the art

The incidence of melanoma is increasing rapidly. This cancer has a good prognosis if detected early. For this reason, various systems of skin lesion image analysis, which support imaging diagnostics of this neoplasm, are developing very dynamically. To detect and recognize neoplastic lesions, such systems use various artificial intelligence (AI) algorithms. This area of computer science applications has recently undergone dynamic development, abounding in several solutions that are effective tools supporting diagnosticians in many medical specialties. In this contribution, a number of applications of different classes of AI algorithms for the detection of this skin melanoma are presented and evaluated. Both classic systems based on the analysis of dermatoscopic images as well as total body systems, enabling the analysis of the patient's whole body to detect moles and pathologic changes, are discussed. These increasingly popular applications that allow the analysis of lesion images using smartphones are also described. The quantitative evaluation of the discussed systems with particular emphasis on the method of validation of the implemented algorithms is presented. The advantages and limitations of AI in the analysis of lesion images are also discussed, and problems requiring a solution for more effective use of AI in dermatology are identified.

Does the Diagnostic Accuracy and Rates of Face-to-Face Visits Occurring Shortly after an Asynchronized Teledermatology Consultation Justify Its Implementation? An 18-Month Cohort Study

INTRODUCTION

In 2019, Maccabi Health Services (MHS) rolled out the store-and-forward "Dermadetect" teledermatology consultation (TC) application. Study goal was to analyze MHS records of TCs (August 2019-February 2021) for the rate and reasons for face-to-face consultations (FTFC) occurring shortly after a TC with emphasis on FTFCs resulting in a different diagnosis for the same indication.

METHODS

The records of FTFCs held up shortly after TCs were reviewed and classified into cases marked as unsuited for teledermatology, cases in which the indication differed, and cases with the same indication, which were analyzed for concordance of diagnoses.

RESULTS

Dermadetect was used by 12,815 MHS beneficiaries. In 30% of cases, following FTFC occurred within the subsequent 5 months, and 901 of them occurred in the subsequent 2 weeks and were analyzed. Thirty percent were not suited for teledermatology, 15% were held for a different indication, and 55% occurred for the same indication. The diagnosis concordance between the TC and recurrent FTFC for the same indication was 97.4%, with full concordance at 68.1% and partial concordance at 29.3%. Overall, 13 patients (1.4%) of the 901 patients using the application only once had a subsequent FTFC within 2 weeks and received a different diagnosis than the one given in the TC.

CONCLUSIONS

When considering the implementation of store-and-forward TC's, a 30% rate of following FTFC's during the next 5 months should be considered when planning the reimbursement model. Diagnosis discordance may be disregarded due to its low rates.

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.

Stress testing reveals gaps in clinic readiness of image-based diagnostic artificial intelligence models

Artificial intelligence models match or exceed dermatologists in melanoma image classification. Less is known about their robustness against real-world variations, and clinicians may incorrectly assume that a model with an acceptable area under the receiver operating characteristic curve or related performance metric is ready for clinical use. Here, we systematically assessed the performance of dermatologist-level convolutional neural networks (CNNs) on real-world non-curated images by applying computational "stress tests". Our goal was to create a proxy environment in which to comprehensively test the generalizability of off-the-shelf CNNs developed without training or evaluation protocols specific to individual clinics. We found inconsistent predictions on images captured repeatedly in the same setting or subjected to simple transformations (e.g., rotation). Such transformations resulted in false positive or negative predictions for 6.5-22% of skin lesions across test datasets. Our findings indicate that models meeting conventionally reported metrics need further validation with computational stress tests to assess clinic readiness.

Data Augmentation Using Adversarial Image-to-Image Translation for the Segmentation of Mobile-Acquired Dermatological Images

Dermoscopic images allow the detailed examination of subsurface characteristics of the skin, which led to creating several substantial databases of diverse skin lesions. However, the dermoscope is not an easily accessible tool in some regions. A less expensive alternative could be acquiring medium resolution clinical macroscopic images of skin lesions. However, the limited volume of macroscopic images available, especially mobile-acquired, hinders developing a clinical mobile-based deep learning approach. In this work, we present a technique to efficiently utilize the sizable number of dermoscopic images to improve the segmentation capacity of macroscopic skin lesion images. A Cycle-Consistent Adversarial Network is used to translate the image between the two distinct domains created by the different image acquisition devices. A visual inspection was performed on several databases for qualitative evaluation of the results, based on the disappearance and appearance of intrinsic dermoscopic and macroscopic features. Moreover, the Fréchet Inception Distance was used as a quantitative metric. The quantitative segmentation results are demonstrated on the available macroscopic segmentation databases, SMARTSKINS and Dermofit Image Library, yielding test set thresholded Jaccard Index of 85.13% and 74.30%. These results establish a new state-of-the-art performance in the SMARTSKINS database.

Assessment of deep neural networks for the diagnosis of benign and malignant skin neoplasms in comparison with dermatologists: A retrospective validation study

BACKGROUND

The diagnostic performance of convolutional neural networks (CNNs) for diagnosing several types of skin neoplasms has been demonstrated as comparable with that of dermatologists using clinical photography. However, the generalizability should be demonstrated using a large-scale external dataset that includes most types of skin neoplasms. In this study, the performance of a neural network algorithm was compared with that of dermatologists in both real-world practice and experimental settings.

METHODS AND FINDINGS

To demonstrate generalizability, the skin cancer detection algorithm (https://rcnn.modelderm.com) developed in our previous study was used without modification. We conducted a retrospective study with all single lesion biopsied cases (43 disorders; 40,331 clinical images from 10,426 cases: 1,222 malignant cases and 9,204 benign cases); mean age (standard deviation [SD], 52.1 [18.3]; 4,701 men [45.1%]) were obtained from the Department of Dermatology, Severance Hospital in Seoul, Korea between January 1, 2008 and March 31, 2019. Using the external validation dataset, the predictions of the algorithm were compared with the clinical diagnoses of 65 attending physicians who had recorded the clinical diagnoses with thorough examinations in real-world practice. In addition, the results obtained by the algorithm for the data of randomly selected batches of 30 patients were compared with those obtained by 44 dermatologists in experimental settings; the dermatologists were only provided with multiple images of each lesion, without clinical information. With regard to the determination of malignancy, the area under the curve (AUC) achieved by the algorithm was 0.863 (95% confidence interval [CI] 0.852-0.875), when unprocessed clinical photographs were used. The sensitivity and specificity of the algorithm at the predefined high-specificity threshold were 62.7% (95% CI 59.9-65.1) and 90.0% (95% CI 89.4-90.6), respectively. Furthermore, the sensitivity and specificity of the first clinical impression of 65 attending physicians were 70.2% and 95.6%, respectively, which were superior to those of the algorithm (McNemar test; p < 0.0001). The positive and negative predictive values of the algorithm were 45.4% (CI 43.7-47.3) and 94.8% (CI 94.4-95.2), respectively, whereas those of the first clinical impression were 68.1% and 96.0%, respectively. In the reader test conducted using images corresponding to batches of 30 patients, the sensitivity and specificity of the algorithm at the predefined threshold were 66.9% (95% CI 57.7-76.0) and 87.4% (95% CI 82.5-92.2), respectively. Furthermore, the sensitivity and specificity derived from the first impression of 44 of the participants were 65.8% (95% CI 55.7-75.9) and 85.7% (95% CI 82.4-88.9), respectively, which are values comparable with those of the algorithm (Wilcoxon signed-rank test; p = 0.607 and 0.097). Limitations of this study include the exclusive use of high-quality clinical photographs taken in hospitals and the lack of ethnic diversity in the study population.

CONCLUSIONS

Our algorithm could diagnose skin tumors with nearly the same accuracy as a dermatologist when the diagnosis was performed solely with photographs. However, as a result of limited data relevancy, the performance was inferior to that of actual medical examination. To achieve more accurate predictive diagnoses, clinical information should be integrated with imaging information.

The role of technology in melanoma screening and diagnosis

Melanoma presents challenges for timely and accurate diagnosis. Expert panels have issued risk-based screening guidelines, with recommended screening by visual inspection. To assess how recent technology can impact the risk/benefit considerations for melanoma screening, we comprehensively reviewed non-invasive visual-based technologies. Dermoscopy increases lesional diagnostic accuracy for both dermatologists and primary care providers; total body photography and sequential digital dermoscopic imaging also increase diagnostic accuracy, are supported by automated lesion detection and tracking, and may be best suited to use by dermatologists for longitudinal follow-up. Specialized imaging modalities using non-visible light technology have unproven benefit over dermoscopy and can be limited by cost, access, and training requirements. Mobile apps facilitate image capture and lesion tracking. Teledermatology has good concordance with face-to-face consultation and increases access, with increased accuracy using dermoscopy. Deep learning models can surpass dermatologist accuracy, but their clinical utility has yet to be demonstrated. Technology-aided diagnosis may change the calculus of screening; however, well-designed prospective trials are needed to assess the efficacy of these different technologies, alone and in combination to support refinement of guidelines for melanoma screening.

Diagnosis of Skin Lesions Using Photographs Taken With a Mobile Phone: An Online Survey of Primary Care Physicians

Skin conditions are one of the most frequent reasons for visiting a primary health care facility, making it of vital importance that general practitioners (GPs) have the right knowledge and tools to diagnose the most frequent dermatological conditions. Methods: This study evaluates the accuracy of dermatological diagnoses made by 120 GPs based on photographs taken with a smartphone by an anonymous online cross-sectional survey. Results: The study was carried out between August and October 2018. The results show that the majority of the participants are in favor of using mobile phones to communicate with other professionals and use them to consult medical images. The majority (69%) took dermatological photographs and the preferred device was a smartphone (70%). From 22 different images evaluated, in 69% of responses, participants expressed a high degree of confidence in their ability to diagnose the lesion shown and in 72% of the cases, the diagnosis chosen was correct. Conclusions: The study confirms that the use of smartphone to send medical images is growing rapidly and its potential for taking medical images is an opportunity to help primary care teams deal with dermatological problems. The results suggest that GPs need further training in interpreting dermatological images, to increase their diagnostic confidence and to avoid the need for referrals to face-to-face visits.

Artificial Intelligence in Dermatology: A Primer

Artificial intelligence is becoming increasingly important in dermatology, with studies reporting accuracy matching or exceeding dermatologists for the diagnosis of skin lesions from clinical and dermoscopic images. However, real-world clinical validation is currently lacking. We review dermatological applications of deep learning, the leading artificial intelligence technology for image analysis, and discuss its current capabilities, potential failure modes, and challenges surrounding performance assessment and interpretability. We address the following three primary applications: (i) teledermatology, including triage for referral to dermatologists; (ii) augmenting clinical assessment during face-to-face visits; and (iii) dermatopathology. We discuss equity and ethical issues related to future clinical adoption and recommend specific standardization of metrics for reporting model performance.