Deep neural networks are superior to dermatologists in melanoma image classification

Brinker, Titus J.; Hekler, Achim; Enk, Alexander; Berking, Carola; Haferkamp, Sebastian; Hauschild, Axel; Weichenthal, Michael; Klode, Joachim; Schadendorf, Dirk; Holland‐Letz, Tim; Kalle, Christof von; Fröhling, Stefan; Schilling, Bastian; Utikal, Jochen

doi:10.1016/j.ejca.2019.05.023

Cited by 309 publications

(210 citation statements)

References 20 publications

Supporting

Mentioning

195

Contrasting

Unclassified

Order By: Relevance

“…This significance level was sustained for both subgroups. [ 16 ] They had similar findings in two earlier studies in 2019. [ 17 18 ]…”

Section: Current Status Of Ai Application In Dermatologysupporting

confidence: 86%

Use of artificial intelligence in dermatology

Sarda²,

Gupta

et al. 2020

Indian J Dermatol

View full text Add to dashboard Cite

Artificial intelligence (AI) has emerged as a major frontier in computer science research. Although AI has been available for some time and found its application in many fields of medicine, its use in dermatology is comparatively new and limited. A sound understanding of the concepts of AI is essential for dermatologists as skin conditions with their abundant clinical and dermatoscopic data and images can potentially be the next big thing in the application of AI in medicine. There are already a number of artificial intelligence studies focusing on skin disorders, such as skin cancer, psoriasis, atopic dermatitis and onychomycosis. This article presents an overview of AI and new developments relevant to dermatology, examining both its current applications and future potential.

show abstract

“…This significance level was sustained for both subgroups. [ 16 ] They had similar findings in two earlier studies in 2019. [ 17 18 ]…”

Section: Current Status Of Ai Application In Dermatologysupporting

confidence: 86%

Use of artificial intelligence in dermatology

Sarda²,

Gupta

et al. 2020

Indian J Dermatol

View full text Add to dashboard Cite

show abstract

“…The reader study (6) included 804 images with biopsy-verified labels (402 melanoma and 402 nevi), all of which randomly selected from the publicly available database HAM10000 and the ISIC archive (14). These images were sent to dermatologists from nine German university hospitals via six randomly assigned electronic questionnaires, each containing 134 images of either melanoma or nevi.…”

Section: Methodsmentioning

confidence: 99%

“…Deep learning (DL) has revolutionized non-medical image analysis and is starting to change clinical workflows. DL can detect cancer in radiological images (1), can predict molecular changes from histology of cancer (2) and can be used to classify dermatoscopic images (3)(4)(5)(6). Based on a large amount of input data and the corresponding class labels, the parameters of a neural network are optimized during the training phase in such a way that for an unknown input the predicted output ideally corresponds to the true class label.…”

Section: Introductionmentioning

confidence: 99%

Effects of Label Noise on Deep Learning-Based Skin Cancer Classification

et al. 2020

Self Cite

View full text Add to dashboard Cite

Recent studies have shown that deep learning is capable of classifying dermatoscopic images at least as well as dermatologists. However, many studies in skin cancer classification utilize non-biopsy-verified training images. This imperfect ground truth introduces a systematic error, but the effects on classifier performance are currently unknown. Here, we systematically examine the effects of label noise by training and evaluating convolutional neural networks (CNN) with 804 images of melanoma and nevi labeled either by dermatologists or by biopsy. The CNNs are evaluated on a test set of 384 images by means of 4-fold cross validation comparing the outputs with either the corresponding dermatological or the biopsy-verified diagnosis. With identical ground truths of training and test labels, high accuracies with 75.03% (95% CI: 74.39-75.66%) for dermatological and 73.80% (95% CI: 73.10-74.51%) for biopsy-verified labels can be achieved. However, if the CNN is trained and tested with different ground truths, accuracy drops significantly to 64.53% (95% CI: 63.12-65.94%, p < 0.01) on a non-biopsy-verified and to 64.24% (95% CI: 62.66-65.83%, p < 0.01) on a biopsy-verified test set. In conclusion, deep learning methods for skin cancer classification are highly sensitive to label noise and future work should use biopsy-verified training images to mitigate this problem.

show abstract

“…Given the potentially high number of radiomics features created on top of a rising number of clinical variables, powerful algorithms are needed to encompass and make all available data flourish. This is where ML algorithms thrive and have already shown tremendous results for a number of malignancies [42][43][44], but have, for now, barely been explored in ASCC. As an exception, using various ML algorithms including random forest and J48 decision trees, De Bari et al created a model predicting inguinal relapse with respective sensitivity, specificity and accuracy of 86.4%, 50% and 83.1% on the validation dataset (and superior results compared to logistic regression), highlighting the potential of such algorithms for ASCC care [45].…”

Section: Discussionmentioning

confidence: 99%

Radiomics and Machine Learning in Anal Squamous Cell Carcinoma: A New Step for Personalized Medicine?

et al. 2020

View full text Add to dashboard Cite

Anal squamous cell carcinoma (ASCC) is an uncommon yet rising cancer worldwide. Definitive chemo-radiation (CRT) remains the best curative treatment option for non-metastatic cases in terms of local control, recurrence-free and progression-free survival. Still, despite overall good results, with 80% five-year survival, a subgroup of ASCC patients displays a high level of locoregional and/or metastatic recurrence rates, up to 35%, and may benefit from a more aggressive strategy. Beyond initial staging, there is no reliable marker to predict recurrence following CRT. Imaging, mostly positron emission tomography-computed tomography (PET-CT) and magnetic resonance imaging (MRI), bears an important role in the diagnosis and follow-up of ASCC. The routine use of radiomics may enhance the quality of information derived from these modalities. It is thought that including data derived from radiomics into the input flow of machine learning algorithms may improve the prediction of recurrence. Although some studies have shown glimmers of hope, more data is needed before offering practitioners tools to identify high-risk patients and enable extensive clinical application, especially regarding the matters of imaging normalization, radiomics process standardization and access to larger patient databases with external validation in order to allow results extrapolation. The aim of this review is to present a critical overview from this data.

show abstract

Deep neural networks are superior to dermatologists in melanoma image classification

Cited by 309 publications

References 20 publications

Use of artificial intelligence in dermatology

Use of artificial intelligence in dermatology

Effects of Label Noise on Deep Learning-Based Skin Cancer Classification

Radiomics and Machine Learning in Anal Squamous Cell Carcinoma: A New Step for Personalized Medicine?

Contact Info

Product

Resources

About