Deep Learning and Handcrafted Method Fusion: Higher Diagnostic Accuracy for Melanoma Dermoscopy Images

Hagerty, Jason; Stanley, R. Joe; Almubarak, Haidar; Lama, Norsang; Kasmi, Reda; Guo, Peng; Drugge, Rhett J.; Rabinovitz, Harold; Oliviero, Margaret; Stoecker, William V.

doi:10.1109/jbhi.2019.2891049

Cited by 162 publications

(111 citation statements)

References 34 publications

Supporting

Mentioning

111

Contrasting

Order By: Relevance

“…Hagerty et al [ 20 ] developed a fusion method where deep features are extracted from images using transfer learning method based on the ResNET-50 Convolutional Neural Network (CNN) architecture. However, the question as to which handcraft features are used in their method is not clear.…”

Section: Literature Surveymentioning

confidence: 99%

Melanoma and Nevus Skin Lesion Classification Using Handcraft and Deep Learning Feature Fusion via Mutual Information Measures

Almaraz-Damian

Ponomaryov

Sadovnychiy

et al. 2020

Entropy

137

View full text Add to dashboard Cite

In this paper, a new Computer-Aided Detection (CAD) system for the detection and classification of dangerous skin lesions (melanoma type) is presented, through a fusion of handcraft features related to the medical algorithm ABCD rule (Asymmetry Borders-Colors-Dermatoscopic Structures) and deep learning features employing Mutual Information (MI) measurements. The steps of a CAD system can be summarized as preprocessing, feature extraction, feature fusion, and classification. During the preprocessing step, a lesion image is enhanced, filtered, and segmented, with the aim to obtain the Region of Interest (ROI); in the next step, the feature extraction is performed. Handcraft features such as shape, color, and texture are used as the representation of the ABCD rule, and deep learning features are extracted using a Convolutional Neural Network (CNN) architecture, which is pre-trained on Imagenet (an ILSVRC Imagenet task). MI measurement is used as a fusion rule, gathering the most important information from both types of features. Finally, at the Classification step, several methods are employed such as Linear Regression (LR), Support Vector Machines (SVMs), and Relevant Vector Machines (RVMs). The designed framework was tested using the ISIC 2018 public dataset. The proposed framework appears to demonstrate an improved performance in comparison with other state-of-the-art methods in terms of the accuracy, specificity, and sensibility obtained in the training and test stages. Additionally, we propose and justify a novel procedure that should be used in adjusting the evaluation metrics for imbalanced datasets that are common for different kinds of skin lesions.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Melanoma and Nevus Skin Lesion Classification Using Handcraft and Deep Learning Feature Fusion via Mutual Information Measures

Almaraz-Damian

Ponomaryov

Sadovnychiy

et al. 2020

Entropy

137

View full text Add to dashboard Cite

show abstract

“…The HAM10000 dataset is a dermoscopic image collected from the Dermatology Department of Vienna Medical University in Austria and the dermatology practice of Cliff Rosendahl in Queensland, Australia [29]. In this study, 18 datasets were collected, including 14 public datasets and 4 self-collected datasets [38], [49], [72], [75]. See Table II for details.…”

Section: A Applied Skin Disease Fieldmentioning

confidence: 99%

Deep Learning in Skin Disease Image Recognition: A Review

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

“…With the introduction of machine learning, artificial intelligence is becoming formal, neural network algorithms are booming, and the emergence of classification models such as Back Propagation (BP) has made image classification technology enter a high-speed development track [20,21]. However, due to its structural characteristics, BP algorithm is difficult to achieve large-scale training sample, and it is even more weak on the problem of multiclassified images, which makes the industry lose confidence in neural networks and makes the research of neural networks in image classification fall into a trough [22][23][24]. The new development of neural networks and the rise of deep learning quickly replaced the status of traditional classification methods, in which Convolutional Neural Network (CNN) in the field of machine vision research and application shines brightly, and is used by major companies [25,26].…”

Section: Introductionmentioning

confidence: 99%

Big Data Image Classification Based on Distributed Deep Representation Learning Model

Zhu

Chen

2020

IEEE Access

View full text Add to dashboard Cite

Traditional image classification technology has become increasingly unable to meet the changing needs of the era of big data. With the open source use of a large number of marked databases and the development and promotion of computers with high performance, deep learning has moved from theory to practice and has been widely used in image classification. This paper takes big data image classification as the research object, selects distributed deep learning tools based on Spark cluster platform, and studies the image classification algorithm based on distributed deep learning. Aiming at the problems that the Labeled Structural Deep Network Embedding (LSDNE) model is applied to the attribute network and generates a large number of hyperparameters and the model complexity is too high, inspired by the Locally Linear Embedding (LLE) algorithm, this paper proposes a semi-supervised network based on the neighbor structure learning model. This model will add the neighbor information of the node at the same time when learning the network representation. Through the node vector reconstruction, the node itself and the neighbor node together constitute the next layer of representation. On the basis of Structural Labeled Locally Deep Nonlinear Embedding (SLLDNE), the node attribute is further added to propose Structural Informed Locally Distributed Deep Nonlinear Embedding (SILDDNE), and how the model combines the structural characteristics of the node with the attribute characteristics is explained in detail. The SVM classifier classifies the known labels, and SILDDNE fuses the network structure, labels, and node attributes into the deep neural network. The experimental results on the CIFAR-10 and CIFAR-100 datasets for image classification standard recognition tasks show that the proposed network achieves good classification performance and has a high generalization ability. Experiments on the CIFAR-10 data set show that the 34layer SLLDNE pruned 40-layer Dense Net compresses about 50% of the parameter amount, increases the computational complexity efficiency by about 8 times, and reduces the classification error rate by 30%. Experiments on the CIFAR-100 data set show that the 34-layer SLLDNE parameter volume is compressed by about 16 times compared to the 19-layer VGG parameter volume, the computational complexity efficiency is increased by about 6 times, and the classification error rate is reduced by 14%. INDEX TERMS image classification; distributed network representation learning; deep learning; neighbor reconstruction.

show abstract

Deep Learning and Handcrafted Method Fusion: Higher Diagnostic Accuracy for Melanoma Dermoscopy Images

Cited by 162 publications

References 34 publications

Melanoma and Nevus Skin Lesion Classification Using Handcraft and Deep Learning Feature Fusion via Mutual Information Measures

Melanoma and Nevus Skin Lesion Classification Using Handcraft and Deep Learning Feature Fusion via Mutual Information Measures

Deep Learning in Skin Disease Image Recognition: A Review

Big Data Image Classification Based on Distributed Deep Representation Learning Model

Contact Info

Product

Resources

About