A survey, review, and future trends of skin lesion segmentation and classification

Hasan, Md. Kamrul; Ahamad, Md. Asif; Yap, Choon Hwai; Yang, Guang

doi:10.1016/j.compbiomed.2023.106624

Cited by 44 publications

(17 citation statements)

References 278 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, early diagnosis of skin cancer from skin lesions using hybrid models CNN-ANN and CNN-RF is presented [14]. A survey in this direction has been studied in [26]. Several benchmark public datasets are developed by the International Skin Imaging Collaboration (ISIC) for detection and classification of skin cancer, melanoma, and lesions using dermoscopy images [27], [28], [29].…”

Section: Related Workmentioning

confidence: 99%

“…Before the deep learning era, different local shape and texture information including the LBP, geometric properties, shape profiles, bag of words, Scale Invariant Feature Transform (SIFT), colors, and many more have been described in the literature [32], [33], [13], [34], [26], [14], [35], [36]. Most of these conventional feature descriptors are used for recognizing the human faces, emotions, hand-shape, palmprint, skin lesions, and other biometric modality and object categories.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep Neural Networks Fused with Textures for Image Classification

Bera

Bhattacharjee

Nasipuri

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Fine-grained image classification (FGIC) is a challenging task in computer vision for due to small visual differences among inter-subcategories, but, large intra-class variations. Deep learning methods have achieved remarkable success in solving FGIC. In this paper, we propose a fusion approach to address FGIC by combining global texture with local patch-based information. The first pipeline extracts deep features from various fixed-size non-overlapping patches and encodes features by sequential modeling using the long shortterm memory (LSTM). Another path computes image-level textures at multiple scales using the local binary patterns (LBP). The advantages of both streams are integrated to represent an efficient feature vector for image classification. The method is tested on eight datasets representing the human faces, skin lesions, food dishes, marine lives, etc. using four standard backbone CNNs. Our method has attained better classification accuracy over existing methods with notable margins.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Deep Neural Networks Fused with Textures for Image Classification

Bera

Bhattacharjee

Nasipuri

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

show abstract

“…Recently, automatic feature extraction conducted through deep learning algorithms can extract deep features from the skin lesion images better than traditional feature extraction approaches [12], [14], [17]. Previously, there were two types of skin lesion cancer classi cation that have been conducted by researchers, such as binary and multi-class classi cation.…”

Section: Introductionmentioning

confidence: 99%

WELDONNet: Weighted Ensemble DenseNet121, MobileNetV2, and NASNetMobile to improve skin lesion diseases classification

Sutaji

Yıldız

2023

Preprint

View full text Add to dashboard Cite

Skin cancer is classified as an aggressive type of cancer spreading quickly to other organs and tissues. Thus, inappropriate detection of the condition might lead to mortality. Melanoma is the most lethal variety, as it can extend to all human body parts. Early detection by dermatologists is, however, challenging in terms of consistency and timing. Hence, CAD systems have been utilized. Yet, the problems often encountered include class imbalance and noise. Therefore, the present authors propose a new method for detecting multi-class skin lesions by employing weighted ensemble convolutional neural networks (CNN). This study consisted of several steps, firstly, up-sampling and down-sampling of datasets were implemented to overcome the class imbalance problem, and image resizing was performed to scale down the image pixels in order to decrease noise. Secondly, the 20-layered and pre-trained CNN models were introduced. Particularly in the 20-layered model, the three fully connected layers were evaluated before the classification layer. Further, the last block layers were applied for the pre-trained model to obtain more specific features from the skin lesion images. Lastly, the weighted ensemble approach was conducted to improve classification performance. The observed results on the HAM10000 dataset indicate that the proposed strategy has improved an accuracy by 0.43% and 2.99% for 20-layered and pre-trained CNNs, respectively. Furthermore, the proposed WELDONNet model outperformed other CNNs with an accuracy of 99.36%. In sum, the proposed model was applicable to be implemented as a reference for skin cancer early detection systems as well as for prospective further research.

show abstract

“…Current research on PSLs focuses on three main areas: segmentation, 8–12 feature extraction, 13–17 and classification 18–23 . Furthermore, the field of interpretable machine learning or explainable artificial intelligence is expanding to address ethical concerns in the healthcare industry 24 …”

Section: Introductionmentioning

confidence: 99%

“…[18][19][20][21][22][23] Furthermore, the field of interpretable machine learning or explainable artificial intelligence is expanding to address ethical concerns in the healthcare industry. 24 This research will use pretrained CNN for PSL classification with the ISIC-2019 dataset. The main contribution of this research is using augmentation to overcome dataset imbalance and hyper-parameter optimization to improve the model performance.…”

mentioning

confidence: 99%

Boosting the performance of pretrained CNN architecture on dermoscopic pigmented skin lesion classification

Nugroho,

Ardiyanto,

Nugroho

2023

Skin Research and Technology

View full text Add to dashboard Cite

BackgroundPigmented skin lesions (PSLs) pose medical and esthetic challenges for those affected. PSLs can cause skin cancers, particularly melanoma, which can be life‐threatening. Detecting and treating melanoma early can reduce mortality rates. Dermoscopic imaging offers a noninvasive and cost‐effective technique for examining PSLs. However, the lack of standardized colors, image capture settings, and artifacts makes accurate analysis challenging. Computer‐aided diagnosis (CAD) using deep learning models, such as convolutional neural networks (CNNs), has shown promise by automatically extracting features from medical images. Nevertheless, enhancing the CNN models' performance remains challenging, notably concerning sensitivity.Materials and methodsIn this study, we aim to enhance the classification performance of selected pretrained CNNs. We use the 2019 ISIC dataset, which presents eight disease classes. To achieve this goal, two methods are applied: resolution of the dataset imbalance challenge through augmentation and optimization of the training hyperparameters via Bayesian tuning.ResultsThe performance improvement was observed for all tested pretrained CNNs. The Inception‐V3 model achieved the best performance compared to similar results, with an accuracy of 96.40% and an AUC of 0.98.ConclusionAccording to the study, classification performance was significantly enhanced by augmentation and Bayesian hyperparameter tuning.

show abstract

A survey, review, and future trends of skin lesion segmentation and classification

Cited by 44 publications

References 278 publications

Deep Neural Networks Fused with Textures for Image Classification

Deep Neural Networks Fused with Textures for Image Classification

WELDONNet: Weighted Ensemble DenseNet121, MobileNetV2, and NASNetMobile to improve skin lesion diseases classification

Boosting the performance of pretrained CNN architecture on dermoscopic pigmented skin lesion classification

Contact Info

Product

Resources

About