Melanoma Classification Using Texture and Wavelet Analysis

Waladi, Akhiyar; Firdaus, Nanda Maulina; Arymurthy, Aniati Murni

doi:10.1109/icaiit.2019.8834545

Cited by 3 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CNN-based model ResNet-50 [44] was used to extract image embeddings from dermoscopy images, which have been extensively used in the literature because it uses residual blocks with shortcut connections to solve performance degradation and vanishing gradient [44]. Although several ResNet variants with different numbers of layers (18,34,50, 101, and 152) have been proposed [44], ResNet-50 was considered because of its proven predictive performance and computational efficiency (as demonstrated in previous studies [9,44]). Transfer learning and fine-tuning techniques were used to improve the extracted textitimage embedding.…”

Section: Image Feature Extractionmentioning

confidence: 99%

Ensemble feature selection and tabular data augmentation with generative adversarial networks to enhance cutaneous melanoma identification and interpretability

Gómez-Martínez,

Chushig-Muzo,

Veierød

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Cutaneous melanoma, the most serious skin cancer, constitutes a considerable health burden in fair-skinned populations. Its increasing incidence highlights the need to develop automated computer-aided approaches that support dermatologists in melanoma detection. Recent advances in artificial intelligence (AI), jointly with the availability of public dermoscopy image datasets, have led to create data-driven models with high predictive performance, thus contributing to dermatology research. Despite these advantages, most image datasets present the class imbalance problem, where a few classes have numerous samples, whereas others are under-represented, impacting the performance of AI-based models. Methods: In this paper, we propose to combine ensemble feature selection (FS) methods and data augmentation with the conditional tabular generative adversarial networks (CTGAN) to enhance melanoma identification in imbalanced datasets. We employed dermoscopy images from two public datasets, PH2 and Derm7pt, which contain melanoma and not-melanoma lesions. To capture intrinsic information from skin lesions, we conduct two feature extraction (FE) approaches, including handcrafted and embedding features. For the former, color, geometric and first-, second-, and higher-order texture features were extracted, while for the latter, embeddings were obtained using ResNet-based models. To alleviate the high-dimensionality in the FE, ensemble FS with filter methods were used and evaluated. For data augmentation, we conducted a progressive analysis of the imbalance ratio (IR), related to the amount of synthetic samples created, and evaluated the impact on the predictive results. To gain interpretability on predictive models, we used SHAP, bootstrap resampling statistical tests and UMAP visualizations. Results: Experimental results showed that the combination of CTGAN and linear models achieved the best predictive results, achieving AUCROC values of 86% (with LASSO and IR=0.8) and 71% (with support vector machine and IR=0.9) for the PH2 and Derm7pt, respectively. We also identified that ‘melanoma’ lesions were mainly characterized by features related to color, while ‘not melanoma’ lesions were characterized by texture features. Conclusions: Our results demonstrated the effectiveness of synthetic data to build generalizable models for melanoma prediction. Our work contributes to skin lesion research, helping in melanoma identification and the interpretation of main characteristics associated with melanoma.

show abstract

Section: Image Feature Extractionmentioning

confidence: 99%

Ensemble feature selection and tabular data augmentation with generative adversarial networks to enhance cutaneous melanoma identification and interpretability

Gómez-Martínez,

Chushig-Muzo,

Veierød

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The performance of the proposed algorithm is evaluated only by accuracy, which mathematically is described as the following [33]: Accuracy = ((TP+TN)) / ((TP+TN+FP+FN)) (4)…”

Section: First: Threshold Entropymentioning

confidence: 99%

The Study of Recognition Methods Based on Wavelet Transform for Melanoma Detection

Almarei

Daqrouq

2020

JERR

View full text Add to dashboard Cite

Skin cancer is one of the most cancers occurring in the world. Malignant melanoma is the most skin cancer type causing death around the world. Melanoma could be treated 100% if they are detected at earlier stages. In this paper, various melanoma detection systems were reviewed according to the year of publishing. All reviewed papers were based on feature extraction methods using wavelet transform (WT) in its two versions: Discrete wavelet transform (DWT), and wavelet packet transform (WPT) for melanoma recognition. Our methodology that was based on the WPT feature extraction and probabilistic neural network (PNN) was used for comparison. The ISIC database was used for differentiating between malignant (1110 images) and benign (1110 image) tumors. A (75% training /25% testing) verification system was applied. Many experiments were conducted using different parameters for each experiment. The support vector machine classifier (SVM) was the most common classifier combined with various types of wavelet features that have appeared in many kinds of literature during the last two decades, which achieved relatively the best accuracy ranged between [76% -98.29%]. In this paper, our combination method of the WPT and entropy was proposed and evaluated. Several experiments were conducted for testing. A Almarei and Daqrouq; JERR, 11(3): 46-61, 2020; Article no.JERR.55316 47 comparison manner was used for discussion of the investigation. The proposed method was an excellent detection method for melanoma regarding the complexity, where no preprocessing stage was conducted. Original Research Article

show abstract

Ensemble feature selection and tabular data augmentation with generative adversarial networks to enhance cutaneous melanoma identification and interpretability

Gómez-Martínez,

Chushig-Muzo,

Veierød

et al. 2024

BioData Mining

View full text Add to dashboard Cite

Background Cutaneous melanoma is the most aggressive form of skin cancer, responsible for most skin cancer-related deaths. Recent advances in artificial intelligence, jointly with the availability of public dermoscopy image datasets, have allowed to assist dermatologists in melanoma identification. While image feature extraction holds potential for melanoma detection, it often leads to high-dimensional data. Furthermore, most image datasets present the class imbalance problem, where a few classes have numerous samples, whereas others are under-represented. Methods In this paper, we propose to combine ensemble feature selection (FS) methods and data augmentation with the conditional tabular generative adversarial networks (CTGAN) to enhance melanoma identification in imbalanced datasets. We employed dermoscopy images from two public datasets, PH2 and Derm7pt, which contain melanoma and not-melanoma lesions. To capture intrinsic information from skin lesions, we conduct two feature extraction (FE) approaches, including handcrafted and embedding features. For the former, color, geometric and first-, second-, and higher-order texture features were extracted, whereas for the latter, embeddings were obtained using ResNet-based models. To alleviate the high-dimensionality in the FE, ensemble FS with filter methods were used and evaluated. For data augmentation, we conducted a progressive analysis of the imbalance ratio (IR), related to the amount of synthetic samples created, and evaluated the impact on the predictive results. To gain interpretability on predictive models, we used SHAP, bootstrap resampling statistical tests and UMAP visualizations. Results The combination of ensemble FS, CTGAN, and linear models achieved the best predictive results, achieving AUCROC values of 87% (with support vector machine and IR=0.9) and 76% (with LASSO and IR=1.0) for the PH2 and Derm7pt, respectively. We also identified that melanoma lesions were mainly characterized by features related to color, while not-melanoma lesions were characterized by texture features. Conclusions Our results demonstrate the effectiveness of ensemble FS and synthetic data in the development of models that accurately identify melanoma. This research advances skin lesion analysis, contributing to both melanoma detection and the interpretation of main features for its identification.

show abstract

Melanoma Classification Using Texture and Wavelet Analysis

Cited by 3 publications

References 5 publications

Ensemble feature selection and tabular data augmentation with generative adversarial networks to enhance cutaneous melanoma identification and interpretability

Ensemble feature selection and tabular data augmentation with generative adversarial networks to enhance cutaneous melanoma identification and interpretability

The Study of Recognition Methods Based on Wavelet Transform for Melanoma Detection

Ensemble feature selection and tabular data augmentation with generative adversarial networks to enhance cutaneous melanoma identification and interpretability

Contact Info

Product

Resources

About