Artificial Intelligence in Dermatology: A Primer.

Artificial intelligence (AI) 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 AI technology for image analysis, and discuss its current capabilities, potential failure modes, and challenges surrounding performance assessment and interpretability. We address three primary applications: (1) teledermatology, including triage for referral to dermatologists, (2) augmenting clinical assessment during face-to-face visits, and (3) dermatopathology. We discuss equity and ethical issues related to future clinical adoption and recommend specific standardization of metrics for reporting model performance.

[1]  Michael J. Keiser,et al.  Adversarial Controls for Scientific Machine Learning. , 2018, ACS chemical biology.

[2]  Achim Hekler,et al.  A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task. , 2019, European journal of cancer.

[3]  A. Kalloo,et al.  Computer Algorithms Show Potential for Improving Dermatologists' Accuracy to Diagnose Cutaneous Melanoma; Results of ISIC 2017. , 2020, Journal of the American Academy of Dermatology.

[4]  Maria L. Wei,et al.  Global Saliency: Aggregating Saliency Maps to Assess Dataset Artefact Bias , 2019, ArXiv.

[5]  Andre Esteva,et al.  A guide to deep learning in healthcare , 2019, Nature Medicine.

[6]  Azadeh Sadat Mozafari,et al.  Unsupervised Temperature Scaling: An Unsupervised Post-Processing Calibration Method of Deep Networks , 2019 .

[7]  Kaspar Rufibach,et al.  Use of Brier score to assess binary predictions. , 2010, Journal of clinical epidemiology.

[8]  Eduardo Valle,et al.  (De) Constructing Bias on Skin Lesion Datasets , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[9]  Stephen A. Rains,et al.  Smartphone Internet access and use: Extending the digital divide and usage gap , 2017 .

[10]  Y. Fujisawa,et al.  Deep‐learning‐based, computer‐aided classifier developed with a small dataset of clinical images surpasses board‐certified dermatologists in skin tumour diagnosis , 2018, The British journal of dermatology.

[11]  Jie Xu,et al.  The practical implementation of artificial intelligence technologies in medicine , 2019, Nature Medicine.

[12]  S. Youn,et al.  Dermatologist‐level classification of malignant lip diseases using a deep convolutional neural network , 2020, The British journal of dermatology.

[13]  H. Williams,et al.  Computer-assisted diagnosis techniques (dermoscopy and spectroscopy-based) for diagnosing skin cancer in adults. , 2018, The Cochrane database of systematic reviews.

[14]  Noel C. F. Codella,et al.  Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC) , 2016, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[15]  Andrea C. Radick,et al.  Accuracy of Digital Pathologic Analysis vs Traditional Microscopy in the Interpretation of Melanocytic Lesions , 2018, JAMA dermatology.

[16]  Quoc V. Le,et al.  Self-Training With Noisy Student Improves ImageNet Classification , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Andrea C. Radick,et al.  Assessment of Second-Opinion Strategies for Diagnoses of Cutaneous Melanocytic Lesions , 2019, JAMA network open.

[18]  R. Hofmann-Wellenhof,et al.  Association Between Surgical Skin Markings in Dermoscopic Images and Diagnostic Performance of a Deep Learning Convolutional Neural Network for Melanoma Recognition. , 2019, JAMA dermatology.

[19]  C. Naylor,et al.  On the Prospects for a (Deep) Learning Health Care System , 2018, JAMA.

[20]  Toshihiko Yamasaki,et al.  Interpreting Fine-Grained Dermatological Classification by Deep Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[21]  Brian W. Powers,et al.  Dissecting racial bias in an algorithm used to manage the health of populations , 2019, Science.

[22]  Achim Hekler,et al.  Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task. , 2019, European journal of cancer.

[23]  Kilian Q. Weinberger,et al.  On Calibration of Modern Neural Networks , 2017, ICML.

[24]  Kathy Dallest,et al.  Teledermatology for the Diagnosis and Management of Skin Cancer: A Systematic Review , 2017, JAMA dermatology.

[25]  R. Crawford,et al.  Clinical Recognition of Melanoma in Dermatologists and Nondermatologists , 2016, Journal of cutaneous medicine and surgery.

[26]  A. Enk,et al.  Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images. , 2019, European journal of cancer.

[27]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[28]  Chandan Singh,et al.  Definitions, methods, and applications in interpretable machine learning , 2019, Proceedings of the National Academy of Sciences.

[29]  Cristian Navarrete-Dechent,et al.  Automated Dermatological Diagnosis: Hype or Reality? , 2018, The Journal of investigative dermatology.

[30]  Thomas J. Fuchs,et al.  Clinical-grade computational pathology using weakly supervised deep learning on whole slide images , 2019, Nature Medicine.

[31]  S. Han,et al.  Keratinocytic Skin Cancer Detection on the Face Using Region-Based Convolutional Neural Network. , 2019, JAMA dermatology.

[32]  H. Williams,et al.  Algorithm based smartphone apps to assess risk of skin cancer in adults: systematic review of diagnostic accuracy studies , 2020, BMJ.

[33]  Julianna D. Ianni,et al.  Tailored for Real-World: A Whole Slide Image Classification System Validated on Uncurated Multi-Site Data Emulating the Prospective Pathology Workload , 2019, Scientific Reports.

[34]  Dawn Song,et al.  Natural Adversarial Examples , 2019, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Tim Verbelen,et al.  Quantifying Uncertainty of Deep Neural Networks in Skin Lesion Classification , 2019, UNSURE/CLIP@MICCAI.

[36]  Kishore L Jayakumar,et al.  Trends in the dermatology residency match from 2007 to 2018: Implications for the dermatology workforce , 2019, Journal of the American Academy of Dermatology.

[37]  Majid Razmara,et al.  Diagnostic accuracy of content‐based dermatoscopic image retrieval with deep classification features† , 2018, The British journal of dermatology.

[38]  Woohyung Lim,et al.  Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network , 2018, PloS one.

[39]  S. Han,et al.  Classification of the Clinical Images for Benign and Malignant Cutaneous Tumors Using a Deep Learning Algorithm. , 2018, The Journal of investigative dermatology.

[40]  Anna Choromanska,et al.  Towards Automated Melanoma Detection With Deep Learning: Data Purification and Augmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[41]  John Paoli,et al.  Expert-Level Diagnosis of Nonpigmented Skin Cancer by Combined Convolutional Neural Networks , 2019, JAMA dermatology.

[42]  P. Tschandl,et al.  Accuracy of Computer-Aided Diagnosis of Melanoma: A Meta-analysis. , 2019, JAMA dermatology.

[43]  R. Hofmann-Wellenhof,et al.  Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic study. , 2019, The Lancet. Oncology.

[44]  H. Haenssle,et al.  Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists , 2018, Annals of oncology : official journal of the European Society for Medical Oncology.

[45]  E. Wilmer,et al.  Most common dermatologic conditions encountered by dermatologists and nondermatologists. , 2014, Cutis.

[46]  Tim Holland-Letz,et al.  Superior skin cancer classification by the combination of human and artificial intelligence. , 2019, European journal of cancer.

[47]  Maria L. Wei,et al.  Artificial Intelligence in Teledermatology , 2019, Current Dermatology Reports.

[48]  Sharath Pankanti,et al.  Deep learning ensembles for melanoma recognition in dermoscopy images , 2016, IBM J. Res. Dev..

[49]  Rainer Hofmann-Wellenhof,et al.  A deep learning system for differential diagnosis of skin diseases , 2019, Nature Medicine.

[50]  A. Adamson,et al.  Machine Learning and Health Care Disparities in Dermatology. , 2018, JAMA dermatology.

[51]  Giuseppe Argenziano,et al.  Assessment of Accuracy of an Artificial Intelligence Algorithm to Detect Melanoma in Images of Skin Lesions , 2019, JAMA network open.

[52]  A. Kalloo,et al.  Results of the 2016 International Skin Imaging Collaboration International Symposium on Biomedical Imaging challenge: Comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images , 2018, Journal of the American Academy of Dermatology.

[53]  Jesús Bescós,et al.  Accurate Segmentation and Registration of Skin Lesion Images to Evaluate Lesion Change , 2019, IEEE Journal of Biomedical and Health Informatics.

[54]  A. Enk,et al.  Systematic outperformance of 112 dermatologists in multiclass skin cancer image classification by convolutional neural networks. , 2019, European journal of cancer.

[55]  R. Hofmann-Wellenhof,et al.  Man against machine reloaded: performance of a market-approved convolutional neural network in classifying a broad spectrum of skin lesions in comparison with 96 dermatologists working under less artificial conditions. , 2020, Annals of oncology : official journal of the European Society for Medical Oncology.

[56]  P. Sopory,et al.  Does integral affect influence intentions to use artificial intelligence for skin cancer screening? A test of the affect heuristic , 2019, Psychology & health.

[57]  Tim Holland-Letz,et al.  Deep neural networks are superior to dermatologists in melanoma image classification. , 2019, European journal of cancer.

[58]  Achim Hekler,et al.  Comparing artificial intelligence algorithms to 157 German dermatologists: the melanoma classification benchmark. , 2019, European journal of cancer.

[59]  C. Garbe,et al.  Diagnostic Performance of a Support Vector Machine for Dermatofluoroscopic Melanoma Recognition: The Results of the Retrospective Clinical Study on 214 Pigmented Skin Lesions , 2019, Diagnostics.

[60]  E. Topol,et al.  A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. , 2019, The Lancet. Digital health.