A methodological approach to the classification of dermoscopy images

By M. Emre Celebi, Hassan A. Kingravi, Bakhtiyar Uddin, Hitoshi Iyatomi, Y. Aslandogan, William Van Stoecker, Randy H. Moss. Comput. Medical Imaging Graph., 2007

712 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cell Biology, Oncology

View Paper: https://www.semanticscholar.org/paper/e457cdcd7769b81f6da854a12fff65f7310237ce

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Balázs Harangi
2. P. Heng
3. Qi-Yan Dou
4. Hao Chen
5. Jing Qin
6. Yuexiang Li
7. LinLin Shen
8. Lequan Yu

In Cell Biology

1. Balázs Harangi

In Oncology

1. Balázs Harangi
2. LinLin Shen
3. Yuexiang Li
4. Adel Al-Jumaily
5. Ammara Masood
6. P. Heng
7. Hao Chen
8. Lequan Yu

Citations in the corpus

• PH2 - A dermoscopic image database for research and benchmarking (2013, methodology): “system proposed in [12] uses a set of shape, color, and texture related features and a support vector machine (SVM)”
• A Color and Texture Based Hierarchical K-NN Approach to the Classification of Non-melanoma Skin Lesions (2013, methodology): “Classification methods range from discriminant analysis to neural networks and support vector machines [55, 41, 15].”
• Skin Lesion Analysis towards Melanoma Detection Using Deep Learning Network (2017, background): “Celebi et al. extracted several features, including color and texture from segmented lesion region for skin lesion classification [21].”
• Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard Distance (2017, background): “Automatically segmenting melanoma from the surrounding skin is an essential step in computerized analysis of dermoscopic images [6], [7].”
• Skin lesion detection based on an ensemble of deep convolutional neural network (2017, methodology): “The methods proposed in [13], [14], [15] and [16] to classify skin lesion images use traditional handcrafted feature sets; however, the dominance of the powerful, self-extracted, deep convolutional neural network-based features is hardly questionable in these days.”
• Supporting Skin Lesion Diagnosis with Content-Based Image Retrieval (2021, background): “Aided Diagnosis (CAD) systems for the automated melanoma recognition have been proposed [16], [17], [18], [19].”
• Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks (2017, background): “Dermoscopy is a non-invasive dermatology imaging technique for the in vivo observation of pigmented skin lesions [3] and plays an important role in the early diagnosis of malignant melanoma [2].”
• Computer Aided Diagnostic Support System for Skin Cancer: A Review of Techniques and Algorithms (2013, methodology): “Some researchers [61, 117, 118, 134, 135] used GLCM-based texture features [136– 138] like dissimilarity, contrast, energy, maximum probability, correlation, entropy, and so forth.”
• Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks (2017, background): “Some researchers further proposed to employ feature selection algorithms to select proper features and utilized combinations of these low-level features to improve the recognition performance [12], [13].”
• A Systematic Review on Imbalanced Data Challenges in Machine Learning (2019, background): “Celebi et al. (2007) proposed issue of imbalanced data while classifying the dermoscopy images.”
• Overview of Advanced Computer Vision Systems for Skin Lesions Characterization (2009, methodology): “The support vector machine (SVM) is a popular algorithm for data classification in two classes [75]– [77], [36].”
• Two Systems for the Detection of Melanomas in Dermoscopy Images Using Texture and Color Features (2014, methodology): “Most of these works use global methods to classify skin lesions [16]–[20], [22], [24].”