Skin lesion classification on dermatoscopic images using effective data augmentation and pre-trained deep learning approach

Bozkurt, Ferhat

doi:10.1007/s11042-022-14095-1

Cited by 22 publications

(7 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To elaborate, Li, Zhang, Wei, Qian, Tang, Hu, Huang, Xia, Zhang, Cheng, Yu, Zhang, Dan, Liu, Ye, He, Jiang, Liu, Fan, Song, Zhou, Wang, Zhang and Lv [53] combined images and medical records to diagnose skin diseases, while El Saleh, Chantaf and Nait-ali [90] focused on facial skin diseases, using images captured under various conditions. Bozkurt [91] emphasized data augmentation to address dataset limitations. This approach highlighted the importance of enhancing data quality and quantity for training more robust AI models in dermatology.…”

Section: Dataset Utilizationmentioning

confidence: 99%

SkinLiTE: Lightweight Supervised Contrastive Learning Model for Enhanced Skin Lesion Detection and Disease Typification in Dermoscopic Images

Alzahrani

2024

Preprint

View full text Add to dashboard Cite

This study introduces SkinLiTE, a lightweight supervised contrastive learning model, tailored to enhance the detection and typification of skin lesions in dermoscopic images. The core of SkinLiTE lies in its unique integration of supervised and contrastive learning approaches, which leverages labeled data to learn generalizable representations. This approach is particularly adept at handling the complexities and imbalances inherent in skin lesions datasets. The methodology encompasses a two-phase learning process. In the first phase, SkinLiTE utilizes an encoder network and a projection head to transform and project dermoscopic images into a feature space where contrastive loss is applied, focusing on minimizing intra-class variations while maximizing inter-class differences. The second phase freezes the encoder's weights, leveraging the learned representations for classification through a series of dense and dropout layers. The model was evaluated using three datasets from Skin Cancer ISIC 2019-2020, covering a wide range of skin conditions. SkinLiTE demonstrated superior performance across various metrics—accuracy, AUC , and F1 score—particularly when compared with traditional supervised learning models. Notably, SkinLiTE achieved an accuracy of 0.9087 using AugMix augmentation for binary classification of skin lesions. It also showed comparable results with the state-of-the-art approaches of ISIC challenge without relying on external data, underscoring its efficacy and efficiency. The results highlight the potential of SkinLiTE as a significant step forward in the field of dermatological AI, offering a robust, efficient, and accurate tool for skin lesion detection and classification. Its lightweight architecture and ability to handle imbalanced datasets make it particularly suited for integration into Internet of Medical Things environments, paving the way for enhanced remote patient monitoring and diagnostic capabilities. This research contributes to the evolving landscape of AI in healthcare, demonstrating the impact of innovative learning methodologies in medical image analysis.

show abstract

Section: Dataset Utilizationmentioning

confidence: 99%

SkinLiTE: Lightweight Supervised Contrastive Learning Model for Enhanced Skin Lesion Detection and Disease Typification in Dermoscopic Images

Alzahrani

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Bozkurt (11) proposed a pre-trained deep-learning approach known as Inception-Resnet-v2 for skin lesion classification. The research specifically investigated the impact of data augmentation techniques on the performance of the skin cancer classification system.…”

Section: Related Workmentioning

confidence: 99%

Convolutional Neural Network-Based Approach For Skin Lesion Classification

Oumoulylte,

Omari Alaoui,

Farhaoui

et al. 2023

Data and Metadata

View full text Add to dashboard Cite

Skin cancer represents one of the primary forms of cancer arising from various dermatological disorders. It can be further categorized based on morphological characteristics, coloration, structure, and texture. Given the rising incidence of skin cancer, its significant mortality rates, and the substantial costs associated with medical treatment, the imperative lies in early detection to promptly diagnose symptoms and initiate appropriate interventions. Traditionally, skin cancer diagnosis and detection involve manual screening and visual examination conducted by dermatologists. these techniques are complex, error-prone, and time-consuming. Machine learning algorithms, particularly deep learning approaches, have been applied to analyze images of skin lesions, detect potential cancerous growths, and provide predictions regarding the likelihood of malignancy. In this paper, we have developed an optimized deep convolutional neural network (DCNN) specifically tailored for classifying skin lesions into benign and malignant categories. Thereby, enhancing the precision of disease diagnosis. Our study encompassed the utilization of a dataset comprising 3,297 dermoscopic images. To enhance the model's performance, we applied rigorous data preprocessing techniques and softmax activation algorithms. The suggested approach employs multiple optimizers, including Adam, RMSProp, and SGD, all configured with a learning rate of 0.0001. The outcomes of our experiments reveal that the Adam optimizer outperforms the others in distinguishing benign and malignant skin lesions within the ISIC dataset, boasting an accuracy score of 84%, a loss rate of 32%, a recall rating of 85%, a precision score of 85%, a f1-score of 85%, and a ROC-AUC of 83%.

show abstract

“…These methods rebalance a dataset by either generating new minority samples (oversampling approaches) or discarding the majority samples (undersampling approaches) [21]. Recent studies [22,23] have tackled the CIP in skin image datasets, primarily employing data augmentation techniques such as rotation, blurring, and cropping to achieve class balance and increase the dataset size.…”

Section: Introductionmentioning

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

Skin lesion classification on dermatoscopic images using effective data augmentation and pre-trained deep learning approach

Cited by 22 publications

References 51 publications

SkinLiTE: Lightweight Supervised Contrastive Learning Model for Enhanced Skin Lesion Detection and Disease Typification in Dermoscopic Images

SkinLiTE: Lightweight Supervised Contrastive Learning Model for Enhanced Skin Lesion Detection and Disease Typification in Dermoscopic Images

Convolutional Neural Network-Based Approach For Skin Lesion Classification

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

Contact Info

Product

Resources

About