Dermatologist-level classification of skin cancer with deep neural networks

Published on Feb 2, 2017in Nature42.778
· DOI :10.1038/NATURE21056
Andre Esteva11
Estimated H-index: 11
(Stanford University),
Brett Kuprel4
Estimated H-index: 4
(Stanford University)
+ 4 AuthorsSebastian Thrun152
Estimated H-index: 152
(Stanford University)
Sources
Abstract
An artificial intelligence trained to classify images of skin lesions as benign lesions or malignant skin cancers achieves the accuracy of board-certified dermatologists.
📖 Papers frequently viewed together
34.1k Citations
2014CVPR: Computer Vision and Pattern Recognition
23.9k Citations
2015CVPR: Computer Vision and Pattern Recognition
15.4k Citations
References25
Newest
#1Kenji Suzuki (IIT: Illinois Institute of Technology)H-Index: 53
#2Luping Zhou (UOW: University of Wollongong)H-Index: 19
Last. Qian Wang (SJTU: Shanghai Jiao Tong University)H-Index: 37
view all 3 authors...
7 CitationsSource
Jun 27, 2016 in CVPR (Computer Vision and Pattern Recognition)
#1Kaiming He (Microsoft)H-Index: 77
#2Xiangyu Zhang (Xi'an Jiaotong University)H-Index: 38
Last. Jian Sun (Microsoft)H-Index: 114
view all 4 authors...
Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the...
42.2k CitationsSource
Jun 27, 2016 in CVPR (Computer Vision and Pattern Recognition)
#1Christian Szegedy (Google)H-Index: 28
#2Vincent Vanhoucke (Google)H-Index: 31
Last. Zbigniew Wojna (UCL: University College London)H-Index: 13
view all 5 authors...
Convolutional networks are at the core of most state of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmarks. Although increased model size and computational cost tend to translate to immediate quality gains for most tasks (as long as enough labeled data is provided for training), computational efficiency and low parameter count are still enabling factors for vario...
6,478 CitationsSource
#1David Silver (Google)H-Index: 73
#2Aja Huang (Google)H-Index: 6
Last. Demis Hassabis (Google)H-Index: 66
view all 20 authors...
The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses ‘value networks’ to evaluate board positions and ‘policy networks’ to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-pl...
6,871 CitationsSource
#1Olga Russakovsky (Stanford University)H-Index: 23
#2Jia Deng (UM: University of Michigan)H-Index: 47
Last. Li Fei-Fei (Stanford University)H-Index: 114
view all 12 authors...
The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotat...
17.3k CitationsSource
Oct 5, 2015 in ICML (International Conference on Machine Learning)
#1Noel C. F. Codella (IBM)H-Index: 24
#2Junjie Cai (IBM)H-Index: 9
Last. John R. Smith (IBM)H-Index: 37
view all 6 authors...
This work presents an approach for melanoma recognition in dermoscopy images that combines deep learning, sparse coding, and support vector machine SVM learning algorithms. One of the beneficial aspects of the proposed approach is that unsupervised learning within the domain, and feature transfer from the domain of natural photographs, eliminates the need of annotated data in the target task to learn good features. The applied feature transfer also allows the system to draw analogies between obs...
140 CitationsSource
#1Howard W. Rogers (Norwich University)H-Index: 6
#2Martin A. WeinstockH-Index: 81
Last. Brett M. Coldiron (UC: University of Cincinnati)H-Index: 28
view all 4 authors...
Importance Understanding skin cancer incidence is critical for planning prevention and treatment strategies and allocating medical resources. However, owing to lack of national reporting and previously nonspecific diagnosis classification, accurate measurement of the US incidence of nonmelanoma skin cancer (NMSC) has been difficult. Objective To estimate the incidence of NMSC (keratinocyte carcinomas) in the US population in 2012 and the incidence of basal cell carcinoma (BCC) and squamous cell ...
657 CitationsSource
Jun 7, 2015 in CVPR (Computer Vision and Pattern Recognition)
#1Christian Szegedy (Google)H-Index: 28
#2Wei Liu (UNC: University of North Carolina at Chapel Hill)H-Index: 17
Last. Andrew RabinovichH-Index: 23
view all 9 authors...
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the archite...
15.4k CitationsSource
#1Yann LeCun (NYU: New York University)H-Index: 119
#2Yoshua Bengio (UdeM: Université de Montréal)H-Index: 192
Last. Geoffrey E. Hinton (U of T: University of Toronto)H-Index: 157
view all 3 authors...
Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its inter...
26.8k CitationsSource
#1Volodymyr Mnih (Google)H-Index: 36
#2Koray Kavukcuoglu (Google)H-Index: 78
Last. Demis HassabisH-Index: 66
view all 19 authors...
An artificial agent is developed that learns to play a diverse range of classic Atari 2600 computer games directly from sensory experience, achieving a performance comparable to that of an expert human player; this work paves the way to building general-purpose learning algorithms that bridge the divide between perception and action.
10.3k CitationsSource
Cited By3982
Newest
Abstract null null A depth slice image that is computationally reconstructed from an integral imaging system consists of focused and out of focus areas. The unfocused areas affect three-dimensional (3D) image analyses and visualization including 3D object detection, extraction, and tracking. In this work, we present a deep learning integral imaging system that can reconstruct a 3D image without the out of focus areas and can accomplish target detection and segmentation at the same time. A Mask-R...
Source
Summary null null Artificial intelligence (AI) allows analysis of “big data” combining clinical, environmental and laboratory based objective measures to allow a deeper understanding of sleep and sleep disorders. This development has the potential to transform sleep medicine in coming years to the betterment of patient care and our collective understanding of human sleep. This review addresses the current state of the field starting with a broad definition of the various components and analytic ...
Source
#1Jordan OttH-Index: 13
Last. Pierre BaldiH-Index: 116
view all 7 authors...
Source
#1Shahin Ali (Islamic University)H-Index: 3
#1Md. Shahin Ali (Islamic University)
Last. Md. Khairul Islam (Islamic University)H-Index: 4
view all 5 authors...
Abstract Skin cancer is one of the top three perilous types of cancer caused by damaged DNA that can cause death. This damaged DNA begins cells to grow uncontrollably and nowadays it is getting increased speedily. There exist some researches for the computerized analysis of malignancy in skin lesion images. However, analysis of these images is very challenging having some troublesome factors like light reflections from the skin surface, variations in color illumination, different shapes, and siz...
1 CitationsSource
#1Guanghui FuH-Index: 1
#2Jianqiang LiH-Index: 27
Last. Yueda ChenH-Index: 1
view all 5 authors...
Abstract Diagnose brain diseases by brain CT images is one of the most common ways. But, it usually takes several ( > 7 ) years to train a professional doctor because it is very challenging to diagnose brain diseases correctly. The study on automated assistance of brain CT diagnosis is still limited. In this paper, we research the challenges of this task and propose a method by simulating human doctor diagnosis habits. Our method analyzes a full slice of brain CT images, instead of every single ...
Source
Abstract null null Fairness emerged as an important requirement to guarantee that Machine Learning (ML) predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given the inherent subjectivity of viewing the concept of fairness, several notions of fairness have been introduced in the literature. This paper is a survey that illustrates the subtleties between fairness notions through a large number of examples and scenarios. In addit...
Source
#1Juan Manuel Durán (TU Delft: Delft University of Technology)H-Index: 6
Abstract Explanatory AI (XAI) is on the rise, gaining enormous traction with the computational community, policymakers, and philosophers alike. This article contributes to this debate by first distinguishing scientific XAI (sXAI) from other forms of XAI. It further advances the structure for bona fide sXAI, while remaining neutral regarding preferences for theories of explanations. Three core components are under study, namely, i) the structure for bona fide sXAI, consisting in elucidating the e...
Source
#1Yuheng WangH-Index: 1
#2Daniel C. LouieH-Index: 4
Last. Tim K. LeeH-Index: 26
view all 7 authors...
Abstract Polarization speckle is a growing research field, especially for the purposes of biomedical imaging and diagnostics. The statistical uniformity of speckle creates novel opportunities for AI methods to analyze speckle patterns, as they are difficult for a human to interpret. We employed deep learning and traditional machine learning methods (Support Vector Machine, K Nearest Neighbor, and Random Forests) to analyze polarization speckle images generated from the general categories of mali...
Source
#1Hang YuH-Index: 4
#2Laurence T. YangH-Index: 80
Last. M. Jamal DeenH-Index: 35
view all 5 authors...
Abstract Convolutional neural networks, are one of the most representative deep learning models. CNNs were extensively used in many aspects of medical image analysis, allowing for great progress in computer-aided diagnosis in recent years. In this paper, we provide a survey on convolutional neural networks in medical image analysis. First, we review the commonly used CNNs in medical image processing, including AlexNet, GoogleNet, ResNet, R-CNN, and FCNN. Then, we present an overview of the use o...
2 CitationsSource
#1Jin Bu (Peking Union Medical College)H-Index: 6
#2Yu LinH-Index: 1
Last. Erxia Shen (Guangzhou Medical University)H-Index: 8
view all 0 authors...
With the development of artificial intelligence, technique improvement of the classification of skin disease is addressed. However, few study concerned on the current classification system of International Classification of Diseases, Tenth Revision (ICD)-10 on Diseases of the skin and subcutaneous tissue, which is now globally used for classification of skin disease. This study was aimed to develop a new taxonomy of skin disease based on cytology and pathology, and test its predictive effect on ...
Source