The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Dermatologist-level classification of skin cancer with deep neural networks
Open accessAbstract
Skin cancer, the most common human malignancy, is primarily diagnosed visually, beginning with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy and histopathological examination. Automated classification of skin lesions using images is a challenging task owing to the fine-grained variability in the appearance of skin lesions. Deep convolutional neural networks (CNNs) show potential for general and highly variable tasks across many fine-grained object categories. Here we demonstrate classification of skin lesions using a single CNN, trained end-to-end from images directly, using only pixels and disease labels as inputs. We train a CNN using a dataset of 129,450 clinical images—two orders of magnitude larger than previous datasets—consisting of 2,032 different diseases. We test its performance against 21 board-certified dermatologists on biopsy-proven clinical images with two critical binary classification use cases: keratinocyte carcinomas versus benign seborrheic keratoses; and malignant melanomas versus benign nevi. The first case represents the identification of the most common cancers, the second represents the identification of the deadliest skin cancer. The CNN achieves performance on par with all tested experts across both tasks, demonstrating an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists. Outfitted with deep neural networks, mobile devices can potentially extend the reach of dermatologists outside of the clinic. It is projected that 6.3 billion smartphone subscriptions will exist by the year 2021 (ref. 13) and can therefore potentially provide low-cost universal access to vital diagnostic care.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Esteva et al. [45] found that a DL network has the same ability to diagnose the disease as twenty-one board-certified dermatologists using 129,450 images of 2032 diseases.”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [45]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The CNN achieved a sensitivity of 91.0% and specificity of 88.9% in detecting malignant lesions”
From Revolutionizing dermatopathology using AI in skin diagnostics: scoping review (2026) · cites this paper as [21]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“They showed that the model had comparable diagnostic performance to dermatologists, with a sensitivity of 91% and a specificity of 88.9%.”
From Revolutionizing dermatopathology using AI in skin diagnostics: scoping review (2026) · cites this paper as [21]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This classification aligns algorithm design with validation and implementation requirements and informs regulatory and ethical evaluation [5].”
From Artificial Intelligence in Clinical Decision-Making: A Comprehensive Review of Diagnostic, Prognostic, and Therapeutic Applications, Validation Gaps, Bias, and Deployment Challenges (2026) · cites this paper as [5]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Deep neural networks (LeCun, Bengio, and Hinton 2015) have shown high accuracy at pattern recognition from noisy, complex inputs, including automated detection of diabetic retinopathy from images (Gulshan et al. 2016), skin cancer from mobile phone cameras (Esteva et al. 2017), and the onset of health conditions from electronic medical records (Razavian, Marcus, and Sontag 2016; Lipton et al. 2015”
From DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction (2018) · cites this paper as Esteva et al. 2017
Experimental — accuracy not yet measured
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Artificial intelligence (AI) systems are increasingly used in health, offering the potential to expand access to health information, support clinicians in delivering high-quality care, and help people make better health decisions (Esteva et al., 2017; Gulshan et al., 2016; Beam and Kohane, 2018; Topol, 2019).”
From HealthBench: Evaluating Large Language Models Towards Improved Human Health (2025) · cites this paper as Esteva et al., 2017
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Fusion approaches in other less complex clinical applications also improved performance over single modality models, even those in which single modality models have been widely reported to achieve high performance, such as pixel-based models for automated skin cancer detection43.”
From Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines (2020) · cites this paper as [43]
The cited source says what the claim attributes to it.
In the citing paper
“Although previous research describes the potential of AI/ML systems to outperform human experts on prediction tasks [18, 32, 40]”
From Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision Making (2023) · cites this paper as [18]
The cited source says what the claim attributes to it.
In the citing paper
“Particularly in oncology, success has been reported in machine-learning-based tumour detection3,37, subtyping38, and outcome prediction39”
From Swarm Learning for decentralized and confidential clinical machine learning (2021) · cites this paper as [37]
The cited source says what the claim attributes to it.
In the citing paper
“A prominent demonstration of this was in 2017, when deep CNNs achieved performance comparable with that of dermatologists in classifying images of skin lesions (Esteva et al, 2017).”
From Artificial intelligence–enabled precision medicine for inflammatory skin diseases (2026) · cites this paper as Esteva et al, 2017
The cited source says what the claim attributes to it.
In the citing paper
“Esteva et al. (21) trained their CNN on 129,450 clinical images, which included more than 2,000 skin diseases.”
From Revolutionizing dermatopathology using AI in skin diagnostics: scoping review (2026) · cites this paper as [21]
The cited source says what the claim attributes to it.
In the citing paper
“This highlights the potential for its use in clinical practice.”
From Revolutionizing dermatopathology using AI in skin diagnostics: scoping review (2026) · cites this paper as [21]
The cited source says what the claim attributes to it.
In the citing paper
“Previous work in this area has shown that fine-tuning of a pretrained model, based on Google's Inception v3 architecture on medical data, achieved near human expert performance (16, 17).”
From Fully automated, real-time 3D ultrasound segmentation to estimate first trimester placental volume using deep learning (2018) · cites this paper as [16]
The cited source says what the claim attributes to it.
In the citing paper
“Medical research is no exception, as CNN has achieved expert-level performances in various fields. Gulshan et al. [4], Esteva et al. [5], and Ehteshami Bejnordi et al. [6] demonstrated the potential of deep learning for diabetic retinopathy screening, skin lesion classification, and lymph node metastasis detection, respectively.”
From Convolutional neural networks: an overview and application in radiology (2018) · cites this paper as [5]
The cited source says what the claim attributes to it.
In the citing paper
“While several studies have compared clinician performance with machine learning (ML) models in other fields-such as dermatology [26,27], radiology [28] and pathology [29]-”
From Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches (2025) · cites this paper as [26]
The cited source says what the claim attributes to it.
In the citing paper
“Previous Head-to-Head comparisons of clinician and AI performance-such as in dermatology [26,27], radiology [28], and pathology [29]-have provided valuable insights, but they remained confined to image-based or narrowly defined diagnostic tasks.”
From Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches (2025) · cites this paper as [26]
The cited source says what the claim attributes to it.
In the citing paper
“Los sistemas de diagnóstico basados en aprendizaje profundo han demostrado precisión comparable a la de los especialistas (Esteva et al., 2017), pero la decisión final siempre recae en el juicio clínico humano.”
From Entre Códigos y Corazones: Investigación e Inteligencia Artificial hacia una Tecnología más Humana (2025) · cites this paper as Esteva et al., 2017
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Traditional approaches to assessing segmen- tation quality, such as boundary-based, region-based, and hy- brid metrics, heavily depend on the availability of ground truth data [7], [8], [9].”
From Uncertainty-aware segmentation quality prediction via deep learning Bayesian Modeling: Comprehensive evaluation and interpretation on skin cancer and liver segmentation (2025) · cites this paper as [9]
Experimental — accuracy not yet measuredIn the citing paper
“Esteva et al analysed clinical images to identify skin cancer subtypes.20”
From Artificial intelligence in healthcare: past, present and future (2017) · cites this paper as [20]
In the citing paper
“Esteva et al performed the CNN to identify skin cancer from clinical images.20”
From Artificial intelligence in healthcare: past, present and future (2017) · cites this paper as [20]
In the citing paper
“The proportions of correctly predicted malignant lesions (ie, sensitivity) and benign lesions (ie, specificity) are both over 90%, which indicates the superior performance of the CNN.”
From Artificial intelligence in healthcare: past, present and future (2017) · cites this paper as [20]
In the citing paper
“Recently, the CNN has been successfully implemented in the medical area to assist disease diagnosis.”
From Artificial intelligence in healthcare: past, present and future (2017) · cites this paper as [20]
In the citing paper
“Using large datasets, CV models can acquire many pattern-recognition abilities-from physician-level diagnostics 7 to medical scene perception 8 .”
From Deep learning-enabled medical computer vision (2021) · cites this paper as [7]
In the citing paper
“Given sufficient data, the accuracy often matches or surpasses the level of expert physicians 7,16 .”
From Deep learning-enabled medical computer vision (2021) · cites this paper as [7]
In the citing paper
“These studies have sequentially tested increasing numbers of dermatologists (25-7 57-93 , 157-94 ), consistently demonstrating a sensitivity and specificity in classification that matches or even exceeds physician levels.”
From Deep learning-enabled medical computer vision (2021) · cites this paper as [7]
In the citing paper
“A series of works have demonstrated that CNNs can match the performance of board-certified dermatologists at classifying malignant skin lesions from benign ones 7,93,94 .”
From Deep learning-enabled medical computer vision (2021) · cites this paper as [7]
In the citing paper
“CNNs-trained to classify disease states-have been extensively tested across diseases, and benchmarked against physicians.”
From Deep learning-enabled medical computer vision (2021) · cites this paper as [7]
In the citing paper
“Their performance is typically on par with experts when both are tested on the same image classification task.”
From Deep learning-enabled medical computer vision (2021) · cites this paper as [7]
In the citing paper
“Machine learning algorithms have already shown expert diagnostic performance based on imaging data for conditions including diabetic retinopathy, 1 skin cancer, 2 and pneumonia. 3”
From Clinical applications of machine learning algorithms: beyond the black box (2019) · cites this paper as [2]
In the citing paper
“Similarly, Esteva et al. (78) demonstrated the potential of AI-powered deep learning models in detecting skin cancer, matching the performance of dermatologists.”
From Improving health literacy using the power of digital communications to achieve better health outcomes for patients and practitioners. (2023) · cites this paper as [78]
In the citing paper
“These techniques have been applied to predict cancer prognosis and estimate treatment response based on genomic and clinical data [8–14].”
From Integrating machine learning and artificial intelligence in life-course epidemiology: pathways to innovative public health solutions (2024) · cites this paper as [14]
In the citing paper
“Convolutional neural networks (CNNs), built for spatial data, have demonstrated performance comparable to that of specialists in cancer detection and tumor segmentation [15,16,17,18,19,20].”
From Artificial Intelligence in Clinical Oncology: From Productivity Enhancement to Creative Discovery (2025) · cites this paper as [18]
In the citing paper
“most notably evidenced by a 2017 publication demonstrating neural network performance on par with human experts across large image datasets2”
From Large language models and multimodal foundation models for precision oncology (2024) · cites this paper as [2]
In the citing paper
“Algorithmic-based healthcare services (medical 'artificial intelligence' (AI)) are cost-effective and scalable and provide expert-level accuracy in applications ranging from the detection of skin cancer 5 and emergency department triage 6,7 to diagnoses of COVID-19 from chest X-rays 8 .”
From Understanding, explaining, and utilizing medical artificial intelligence (2021) · cites this paper as [5]
In the citing paper
“Several algorithms incorporating artificial intelligence (AI) have been developed to help interpret both clinical11,12,13,14,15 and dermoscopic16,17,18,19,20,21,22,23 images for a variety of skin conditions”
In the citing paper
“The applications of DL techniques based on transfer learning have reported performance comparable to that of the human experts 5 , , 6 or better 7 ., 8”
From The need for uncertainty quantification in machine-assisted medical decision making (2019) · cites this paper as [6]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“Deep learning algorithms, powered by advances in computation and very large datasets 25 , have recently been shown to exceed human performance in visual tasks such as playing Atari games 26 , strategic board games like Go 27 and object recognition 6 .”
MethodGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
(2008) · Journal of Machine Learning Research · Cited by 33,051
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · cited 1×
“Deep learning algorithms, powered by advances in computation and very large datasets 25 , have recently been shown to exceed human performance in visual tasks such as playing Atari games 26 , strategic board games like Go 27 and object recognition 6 .”
MethodPan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387
Research works printed but not linked: 4
- LeCun, Y. & Bengio, Y. In The Handbook of Brain Theory and Neural Networks (ed. Arbib, M. A. ) 3361.10 (MIT Press, 1995)
- Gutman, D. et al. Skin lesion analysis toward melanoma detection. International Symposium on Biomedical Imaging (ISBI), (International Skin Imaging Collaboration (ISIC), 2016)
- Menzies, S. W. et al. In Skin Cancer and UV Radiation (eds Altmeyer, P., Hoffmann, K. & Stücker, M. ) 1064–1070 (Springer, 1997)
- Ballerini, L. et al. In Color Medical Image Analysis. (eds, Celebi, M. E. & Schaefer, G. ) 63–86 (Springer, 2013)
Cited by
Sorted by citations
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332
A survey on Image Data Augmentation for Deep Learning
Shorten, C., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0197-0 · Cited by 13,203
High-performance medicine: the convergence of human and artificial intelligence
Topol, E. J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0300-7 · Cited by 10,450
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
A guide to deep learning in healthcare
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., & Dean, J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0316-z · Cited by 5,312
Self-citation
Metadata
- Authors
- Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S.
- Affiliations
- Stanford University (US)
- Stanford Medicine (US)
- VA Palo Alto Health Care System (US)
- Institute for Stem Cell Biology and Regenerative Medicine (US)
- Corresponding author
- Esteva, Andre
- Kuprel, Brett
- Novoa, Roberto A.
- Thrun, Sebastian
- Venue
- Nature
- Published
- 2017-01-25
- Volume
- 542
- Issue
- 7639
- Pages
- 115-118
- ISSN
- 0028-0836 (ISSN-L)
- 1476-4687
- PMC
- PMC8382232
- OpenAlex
- W2581082771
- Semantic Scholar
- e1ec11a1cb3d9745fb18d3bf74247f95a6663d08
- Cited by
- 14,362
- References
- 26
- Citations by year
- 2026: 1681 · 2025: 2079 · 2024: 1706 · 2023: 1544 · 2022: 1495 · 2021: 1739 · 2020: 1647 · 2019: 1324 · 2018: 862 · 2017: 266
- FWCI
- 490.95
- Type
- journal article
- Language
- en
- Update notices
- erratum (2017-06-29)
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Nature (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Funders
- National Institutes of Health (UL1TR001085)
- National Institute on Aging (R01AG009521, R21AG044815, R01AG020961)
- National Institute of Neurological Disorders and Stroke (R01NS089533)
- National Institute of Arthritis and Musculoskeletal and Skin Diseases (R01AR063963)
- National Center for Advancing Translational Sciences
- Topics
- Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- skin cancer classification, skin lesion images, deep convolutional neural networks, melanoma, non-melanoma skin cancer, seborrheic keratosis, benign nevi, mobile phone imaging, clinical screening, fine-grained image classification
- MeSH terms
- Dermatologists, Automation, Humans, Melanoma, Nevus, Photography, Skin Neoplasms, Reproducibility of Results, Keratinocytes, Neural Networks, Computer, Keratosis, Seborrheic, Cell Phone, Datasets as Topic
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
