A Benchmark for Automatic Visual Classification of Clinical Skin Disease Images

Sun, Xiaoxiao; Yang, Jufeng; Sun, Ming; Wang, Kai

doi:10.1007/978-3-319-46466-4_13

Cited by 132 publications

(118 citation statements)

References 39 publications

Supporting

Mentioning

117

Contrasting

Order By: Relevance

“…Works employing DNNs for melanoma screening either train a network from scratch [6,7,9], or transfer knowledge from ImageNet [4,5,8,10,11] the choice of DNN architecture and implementation frameworkthe most common framework is Caffe [4,8,11], and the most common architectures are ResNet [10], DRN-101 [11], AlexNet [5], and VGG-16 [8]. Schemes for artificially augmenting training data, and for transferring learned knowledge also vary.…”

Section: Introductionmentioning

confidence: 99%

“…Schemes for artificially augmenting training data, and for transferring learned knowledge also vary. Segmenting the lesion before feature extraction is a common choice for melanoma screening [8,11], although DNNs generally allow forgoing it [1,4,5,8,10,14]. In this paper we forgo all preprocessing steps, like lesion segmentation, or artifacts/hair removal.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Knowledge transfer for melanoma screening with deep learning

Menegola

Fornaciali

Pires

et al. 2017

2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)

164

View full text Add to dashboard Cite

Knowledge transfer impacts the performance of deep learning -the state of the art for image classification tasks, including automated melanoma screening. Deep learning's greed for large amounts of training data poses a challenge for medical tasks, which we can alleviate by recycling knowledge from models trained on different tasks, in a scheme called transfer learning. Although much of the best art on automated melanoma screening employs some form of transfer learning, a systematic evaluation was missing. Here we investigate the presence of transfer, from which task the transfer is sourced, and the application of fine tuning (i.e., retraining of the deep learning model after transfer). We also test the impact of picking deeper (and more expensive) models. Our results favor deeper models, pretrained over ImageNet, with fine-tuning, reaching an AUC of 80.7% and 84.5% for the two skin-lesion datasets evaluated.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Knowledge transfer for melanoma screening with deep learning

Menegola

Fornaciali

Pires

et al. 2017

2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)

164

View full text Add to dashboard Cite

show abstract

“…The performance of deep learning model heavily relies on the properties of dataset, under the current technology level. Yang et al 26 presented medical representations inspired by dermatological criteria for diagnosing clinical skin lesions based on proposed dataset 27 with superior performance, which was collected from Derm101. Many other innovative researches 16,17,28 are also attributed to these publicly available datasets, although not all of them are pathologically supported like our purposed dataset.…”

Section: Discussionmentioning

confidence: 99%

Smart identification of psoriasis by images using convolutional neural networks: a case study in China

Zhao

Xie

et al. 2019

Acad Dermatol Venereol

View full text Add to dashboard Cite

Background Psoriasis is a chronic inflammatory skin disease, which holds a high incidence in China. However, professional dermatologists who can diagnose psoriasis early and correctly are insufficient in China, especially in the rural areas. A smart approach to identify psoriasis by pictures would be highly adaptable countrywide and could play a useful role in early diagnosis and regular treatment of psoriasis. Objectives Design and evaluation of a smart psoriasis identification system based on clinical images (without relying on a dermatoscope) that works effectively similar to a dermatologist. Methods A set of deep learning models using convolutional neural networks (CNNs) was explored and compared in the system for automatic identification of psoriasis. The work was carried out on a standardized dermatological dataset with 8021 clinical images of 9 common disorders including psoriasis along with full electronic medical records of patients built over the last 9 years in China. A two‐stage deep neural network was designed and developed to identify psoriasis. In the first stage, a multilabel classifier was trained to learn the visual patterns for each individual skin disease. In the second stage, the output of the first stage was utilized to distinguish psoriasis from other skin diseases. Results The area under the curve (AUC) of the two‐stage model reached 0.981 ± 0.015, which outperforms a single‐stage model. And, the classifier showed superior performance (missed diagnosis rate: 0.03, misdiagnosis rate: 0.04) than 25 Chinese dermatologists (missed diagnosis rate: 0.19, misdiagnosis rate: 0.10) in the diagnosis of psoriasis on 100 clinical images. Conclusions Using clinical images to identify psoriasis is feasible and effective based on CNNs, which also builds a solid technical base for smart care of skin diseases especially psoriasis using mobile/tablet applications for teledermatology in China.

show abstract

“…The dataset in [8] has 44 classes containing 2,309 images. Another two datasets are proposed in [6]: SD-128, which has 128 classes and 5,619 1 https://isic-archive.com/ images, and SD-198, which has 198 classes and 6,584 images. They achieve the classification accuracy of 52.15% on SD-128 and 50.27% on SD-198.…”

Section: A Skin Disease Datasetsmentioning

confidence: 99%

Computer-Aided Clinical Skin Disease Diagnosis Using CNN and Object Detection Models

Liu

et al. 2019

2019 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Skin disease is one of the most common types of human diseases, which may happen to everyone regardless of age, gender or race. Due to the high visual diversity, human diagnosis highly relies on personal experience; and there is a serious shortage of experienced dermatologists in many countries. To alleviate this problem, computer-aided diagnosis with stateof-the-art (SOTA) machine learning techniques would be a promising solution. In this paper, we aim at understanding the performance of convolutional neural network (CNN) based approaches. We first build two versions of skin disease datasets from Internet images: (a) Skin-10, which contains 10 common classes of skin disease with a total of 10,218 images; (b) Skin-100, which is a larger dataset that consists of 19,807 images of 100 skin disease classes. Based on these datasets, we benchmark several SOTA CNN models and show that the accuracy of skin-100 is much lower than the accuracy of skin-10. We then implement an ensemble method based on several CNN models and achieve the best accuracy of 79.01% for Skin-10 and 53.54% for Skin-100. We also present an object detection based approach by introducing bounding boxes into the Skin-10 dataset. Our results show that object detection can help improve the accuracy of some skin disease classes.

show abstract

A Benchmark for Automatic Visual Classification of Clinical Skin Disease Images

Cited by 132 publications

References 39 publications

Knowledge transfer for melanoma screening with deep learning

Knowledge transfer for melanoma screening with deep learning

Smart identification of psoriasis by images using convolutional neural networks: a case study in China

Computer-Aided Clinical Skin Disease Diagnosis Using CNN and Object Detection Models

Contact Info

Product

Resources

About