Enhanced Skin Condition Prediction Through Machine Learning Using Dynamic Training and Testing Augmentation

Putra, Tryan Aditya; Rufaida, Syahidah Izza; Leu, Jenq-Shiou

doi:10.1109/access.2020.2976045

Cited by 45 publications

(18 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the main types of ensemble learning is called stacking or stacked generalization [26][27][28]. Stacking has been successfully implemented in regression, density estimations, distance learning, and classification, and has been used in many medical applications [29][30][31]. This technique works because it allows multiple algorithms to collaborate to solve the same problem; the various solutions can be aggregated into one better final solution.…”

Section: Proposed Efficientnet-b3-gap-ensemble Methodsmentioning

confidence: 99%

CNN Ensemble Approach to Detect COVID-19 from Computed Tomography Chest Images

Haikel¹

2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In January 2020, the World Health Organization declared a global health emergency concerning the spread of a new coronavirus disease, which was later named COVID-19. Early and fast diagnosis and isolation of COVID-19 patients have proven to be instrumental in limiting the spread of the disease. Computed tomography (CT) is a promising imaging method for fast diagnosis of COVID-19. In this study, we develop a unique preprocessing step to resize CT chest images to a fixed size (256 × 256 pixels) that preserves the aspect ratio and reduces image loss. Then, we present a deep learning (DL) method to classify CT chest images based on the light-weight pre-trained EfficientNet-B3 CNN model and ensemble techniques. The proposed method, which we refer to as EfficientNet-B3-GAP-Ensemble, comprises an ensemble of a modified version of the EfficientNet-B3. We build the ensemble using multiple runs and multiple training epochs. We test the EfficientNet-B3-GAP-Ensemble on two common benchmark datasets, i.e., the COVID19-CT and SARS-CoV-2-CT datasets. The proposed method has outperformed state-ofthe-art methods for both datasets. For the COVID19-CT dataset, it achieved 88.18% sensitivity, 88.29% precision, 88.18% accuracy, an F1-score of 88.15%, and AUC of 92.10%. With the SARS-CoV-2-CT dataset, we tested the proposed method under different train-test splits, i.e., 20%-80%, 50%-50%, and 80%-20%. For the latter split, the proposed method achieved 99.72% accuracy, 99.80% sensitivity, precision, and F1-scores, and an AUC score of 99.99%.

show abstract

Section: Proposed Efficientnet-b3-gap-ensemble Methodsmentioning

confidence: 99%

CNN Ensemble Approach to Detect COVID-19 from Computed Tomography Chest Images

Haikel¹

2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…In 2019, Tan et al proposed a series of lightweight DCNN models named EfficientNets [19]. Owing to their outstanding performance in many classification tasks, they have been adopted as a backbone in the latest skin lesion classification tasks [49,54,55]. Recently, Radosavovic et al proposed RegNets that perform better and up to 5x faster on GPUs compared with EfficientNets of similar FLOPs and parameters [18].…”

Section: A Dcnn Modelsmentioning

confidence: 99%

Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classification

Yao

Shen

et al. 2022

IEEE Trans. Med. Imaging

114

View full text Add to dashboard Cite

Deep convolutional neural network (DCNN) models have been widely explored for skin disease diagnosis and some of them have achieved the diagnostic outcomes comparable or even superior to those of dermatologists. However, broad implementation of DCNN in skin disease detection is hindered by small size and data imbalance of the publically accessible skin lesion datasets. This paper proposes a novel data augmentation strategy for single model classification of skin lesions based on a small and imbalanced dataset. First, various DCNNs are trained on this dataset to show that the models with moderate complexity outperform the larger models. Second, regularization DropOut and DropBlock are added to reduce overfitting and a Modified RandAugment augmentation strategy is proposed to address the defects of sample underrepresentation in the small dataset. Finally, a novel Multi-Weighted Focal Loss function is introduced to overcome the challenge of uneven sample size and classification difficulty. By combining Modified RandAugment and Multi-weighted Focal Loss in a single DCNN model, we have achieved the classification accuracy comparable to those of multiple ensembling models on the ISIC 2018 challenge test dataset. Our study shows that this method is able to achieve a high classification performance at a low cost of computational resources and inference time, potentially suitable to implement in mobile devices for automated screening of skin lesions and many other malignancies in low resource settings.

show abstract

“…Data augmentation is a way to expand the training dataset by transforming input images without having to collect new datasets for model training, thus avoiding the overfitting issue that might occur during the training process when a small amount of training data is used. These papers use data augmentation for performance enhancement: [25], [26], [34]- [36], [40], [41], [46], [46], [47], [49], [50], [52], [56], [58], [60], [60], [61], [64], [67], [68], [85], [88], [90], [91], [98], [105], [107], [109], [115], [116], [122], [124]- [127], [130], [151], [152], [154], [155], [158], [159], [162]- [166], [168]- [170], [180]- [186]. The literature includes several w...…”

Section: Data Augmentationmentioning

confidence: 99%

Recent Advances in Diagnosis of Skin Lesions Using Dermoscopic Images Based on Deep Learning

et al. 2022

View full text Add to dashboard Cite

Skin cancer is one of the most threatening cancers, which spreads to the other parts of the body if not caught and treated early. During the last few years, the integration of deep learning into skin cancer has been a milestone in health care, and dermoscopic images are right at the center of this revolution. This review study focuses on the state-of-the-art automatic diagnosis of skin cancer from dermoscopic images based on deep learning. This work thoroughly explores the existing deep learning and its application in diagnosing dermoscopic images. This study aims to present and summarize the latest methodology in melanoma classification and the techniques to improve this. We discuss advancements in deep learningbased solutions to diagnose skin cancer, along with some challenges and future opportunities to strengthen these automatic systems to support dermatologists and enhance their ability to diagnose skin cancer. INDEX TERMSSkin cancer, Dermoscopy images, Deep learning, Classification, Literature review.FIGURE 1: Global heat map showing estimated agestandardized incidence rates, in 2020, of melanoma of the skin in all sexes, all ages. The map shows melanoma incidence in all parts of the world, except Greenland in the Arctic Circle. The regions most affected by skin melanoma globally are Europe, the United States, Canada, and Australia [2].microscopy-based tool to improve non-invasive diagnostic discrimination of skin lesions based on color and structure analysis [5]. This paper focuses on dermoscopy images. Because dermoscopic structures have direct histopathologic correlates, dermoscopic images help the dermatologist select management and treatment options for particular types of skin cancers [6]. In addition, dermoscopy can be useful for

show abstract

Enhanced Skin Condition Prediction Through Machine Learning Using Dynamic Training and Testing Augmentation

Cited by 45 publications

References 29 publications

CNN Ensemble Approach to Detect COVID-19 from Computed Tomography Chest Images

CNN Ensemble Approach to Detect COVID-19 from Computed Tomography Chest Images

Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classification

Recent Advances in Diagnosis of Skin Lesions Using Dermoscopic Images Based on Deep Learning

Contact Info

Product

Resources

About