Convolutional Neural Network Committees for Melanoma Classification with Classical And Expert Knowledge Based Image Transforms Data Augmentation

Vasconcelos, Cristina Nader; Vasconcelos, Bárbara Nader

doi:10.48550/arxiv.1702.07025

Cited by 5 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whether using transfer or not, works vary widely in their choice of deep-learning architecture, from the relatively shallow (for today's standards) VGG [15], [23], [26], [39], midrange GoogLeNet [12], [16], [35], [37], [39], until the deeper ResNet [4], [9], [16], [24], [27] or Inception [10], [12], [27]. On the one hand, more recent architectures tend to be deeper, and to yield better accuracies; on the other hand, they require more data and are more difficult to parameterize and train.…”

Section: Survey Of Recent Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Data, depth, and design: Learning reliable models for skin lesion analysis

et al. 2020

View full text Add to dashboard Cite

Deep learning fostered a leap ahead in automated skin lesion analysis in the last two years. Those models, however, are expensive to train and difficult to parameterize. Objective: We investigate methodological issues for designing and evaluating deep learning models for skin lesion analysis. We explore ten choices faced by researchers: use of transfer learning, model architecture, train dataset, image resolution, type of data augmentation, input normalization, use of segmentation, duration of training, additional use of Support Vector Machines, and test data augmentation. Methods: We perform two full factorial experiments, for five different test datasets, resulting in 2560 exhaustive trials in our main experiment, and 1280 trials in our assessment of transfer learning. We analyze both with multi-way analyses of variance (ANOVA). We use the exhaustive trials to simulate sequential decisions and ensembles, with and without the use of privileged information from the test set. Results main experiment: Amount of train data has disproportionate influence, explaining almost half the variation in performance. Of the other factors, test data augmentation and input resolution are the most influential. Deeper models, when combined, with extra data, also help. -transfer experiment: Transfer learning is critical, its absence brings huge performance penalties.simulations: Ensembles of models are the best option to provide reliable results with limited resources, without using privileged information and sacrificing methodological rigor. Conclusions and Significance: Advancing research on automated skin lesion analysis requires curating larger public datasets. Indirect use of privileged information from the test set to design the models is a subtle, but frequent methodological mistake that leads to overoptimistic results. Ensembles of models are a cost-effective alternative to the expensive full-factorial and to the unstable sequential designs.

show abstract

Section: Survey Of Recent Techniquesmentioning

confidence: 99%

“…Augmentation provides best performance when applied to both train and test samples, but only the most recent skin lesion analysis works follow that scheme [4], [10], [26]- [29]. Train-only augmentation is still very common [11], [12], [15], [23], [35], [37], [39].…”

Section: Survey Of Recent Techniquesmentioning

confidence: 99%

Data, depth, and design: Learning reliable models for skin lesion analysis

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Despite the novel discovery of the actual power of CNN, its contribution in medical imaging can be referred to the 1990s, when it was applied in digital mammography for computerassisted identification of microcalcifications [22], and computer-assisted diagnosis of lung nodules in CT datasets [23]. CNN has recently been adopted for skin lesion recognition [24], segmentation of pancreas in CT images [25], estimation thickness of carotid intima-media in ultrasound image data [26], segmentation of multimodality isointense infant brain images [27], and neuronal membrane specification in electron microscopy images [28]. Using the Inception v3 model, Esteva et al [29] proposed a method for classifying skin lesions.…”

Section: Deep Learning For Lesion Classificationmentioning

confidence: 99%

Convolutional Neural Network-Based Skin Lesion Classification With Variable Nonlinear Activation Functions

2022

View full text Add to dashboard Cite

One of the worst forms of skin cancer is melanoma which can be curable if it is diagnosed at an early stage. The earlier the cancer is diagnosed, the better is the outcome. The risk of death from melanoma is directly related to the delay in identifying a lesion. A Deep Learning-based computer diagnosing system can be an automated solution in clinical assessments to overcome this problem. Convolutional Neural Network (CNN) can help to improve the classification rate of skin lesions from dermoscopic images without the need for any human assistance. The linear and nonlinear activation functions act as a node placed at hidden layers or output layers of a Neural Network to play a role in deciding whether that node should pass information to the following layer or not. This critical mathematical mechanism influences the accuracy rate of the CNN. To obtain acceptable performance, CNN requires a large amount of training data. This research shows how fast and effective different types of nonlinear activation functions work on a CNN with limited image datasets. Experimental analysis reveals that the proposed CNN model with parameterized Leaky ReLU function outperforms (97.50% accuracy, 98.00% precision, and 98.00% sensitivity) the same network with distinct nonlinear activation functions for the problem of melanoma recognition by classifying skin lesion into three classes. All experimental studies are carried out using images from PH2 (a dermoscopic image database obtained at the Hospital Pedro Hispano Dermatology Service in Matosinhos, Portugal) and International Skin Imaging Collaboration (ISIC) archive datasets.

show abstract

“…The original U-Net architecture does not take advantage of pre-trained classification networks. In order to deal with small amounts of labeled data, the authors made extensive use of Data Augmentation, which has been proven efficient in a many cases (Xu et al, 2016;Vasconcelos and Vasconcelos, 2017;Perez and Wang, 2017;Wong et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Domain adaptation for holistic skin detection

Dourado¹,

Guth²,

Campos³

et al. 2019

Preprint

View full text Add to dashboard Cite

Human skin detection in images is a widely studied topic of Computer Vision for which it is commonly accepted that analysis of pixel color or local patches may suffice. This is because skin regions appear to be relatively uniform and many argue that there is a small chromatic variation among different samples. However, we found that there are strong biases in the datasets commonly used to train or tune skin detection methods. Furthermore, the lack of contextual information may hinder the performance of local approaches. In this paper we present a comprehensive evaluation of holistic and local Convolutional Neural Network (CNN) approaches on in-domain and cross-domain experiments and compare with state-of-theart pixel-based approaches. We also propose a combination of inductive transfer learning and unsupervised domain adaptation methods, which are evaluated on different domains under several amounts of labelled data availability. We show a clear superiority of CNN over pixel-based approaches even without labelled training samples on the target domain. Furthermore, we provide experimental support for the counter-intuitive superiority of holistic over local approaches for human skin detection.

show abstract

Convolutional Neural Network Committees for Melanoma Classification with Classical And Expert Knowledge Based Image Transforms Data Augmentation

Cited by 5 publications

References 8 publications

Data, depth, and design: Learning reliable models for skin lesion analysis

Data, depth, and design: Learning reliable models for skin lesion analysis

Convolutional Neural Network-Based Skin Lesion Classification With Variable Nonlinear Activation Functions

Domain adaptation for holistic skin detection

Contact Info

Product

Resources

About