A Color and Texture Based Hierarchical K-NN Approach to the Classification of Non-melanoma Skin Lesions

By Lucia Ballerini, Robert B. Fisher, Ben Aldridge, Jonathan Rees. 2013

307 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Oncology

View Paper: https://www.semanticscholar.org/paper/75358062ecd7d8c4e620215f8b25549aa41d7931

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

In Computer Vision and Pattern Recognition

1. Ling Shao
2. P. Heng
3. Jianbing Shen
4. Salman Hameed Khan
5. Qi-Yan Dou
6. Munawar Hayat
7. Lequan Yu
8. Luc Van Gool

In Oncology

1. LinLin Shen
2. Yuexiang Li
3. P. Heng
4. Hao Chen
5. Lequan Yu
6. Balázs Harangi
7. Michal Kosinski

Citations in the corpus

• Skin Lesion Analysis towards Melanoma Detection Using Deep Learning Network (2017, methodology): “ic border detection approach [10] to segment lesion area and then ensemble the extracted features, i.e. shape, texture and color, for melanoma recognition [11]. On the other hand, some investigations [12, 13, 14] attempted to directly employ hand-crafted feature for melanoma recognition without segm”
• Striking the Right Balance With Uncertainty (2019, result): “Similar to [3], we report results with 3-fold cross validation.”
• Disparities in dermatology AI performance on a diverse, curated clinical image set (2021, methodology): “Data sources include ISIC, two datasets sourced from Stanford hospital, Edinburgh Dermofit Library, and open-access data available on the web (Codella et al., 2019; Esteva et al., 2017; Ballerini et al., 2013).”
• Generalizability vs. Robustness: Adversarial Examples for Medical Imaging (2018, methodology): “We use the publicly-available Dermofit [10] image library consisting of 1300 highquality dermatoscopic images, with histologically validated fine grained expert annotations (10 classes) for this task.”
• Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks (2017, background): “Early investigations attempted to apply low-level hand-crafted features to distinguish melanomas from non-melanoma skin lesions, including shape [7], color [8], [9] and texture [10], [11].”
• Data Augmentation with Manifold Exploring Geometric Transformations for Increased Performance and Robustness (2019, methodology): “Datasets ManiFool Augmentation has been validated on two challenging, public, medical imaging classification datasets, namely, Digital Database for Screening Mammography (DDSM) [14], [15] and Dermofit [16].”
• Deep features to classify skin lesions (2016, methodology): “[4], where we randomly split the dataset into three approximately equal sets with approximately the same distribution of class labels.”