GP-CNN-DTEL: Global-Part CNN Model With Data-Transformed Ensemble Learning for Skin Lesion Classification

Tang, Peng; Liang, Qiaokang; Yan, Xintong; Shao, Xiang; Zhang, Dan

doi:10.1109/jbhi.2020.2977013

Cited by 94 publications

(40 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparison of SLC-2016. The proposed DermoExpert produces the best results for the AUC by beating the state-of-the-art [70,78]…”

Section: Results Comparisonmentioning

confidence: 99%

“…The proposed DermoExpert produces the best results for the AUC by beating the state-of-the-art [70, 78] with a 10.0 % margin. Concerning the type-II errors (recall), DermoExpert is behind the state-of-the-art [66] by 7.0 %, but the DermoExpert outperforms the FPRPN [66] by a 10.0 % margin concerning the positive predictive value (precision).…”

Section: Resultsmentioning

confidence: 99%

“…Comparison of SLC-2017. For AUC, the DermoExpert wins by defeating the secondhighest [70] by a margin of 2.0 %. DermoExpert has beaten the work of Song et al [66] by the margins of 4.0 %, and 16.0 % with respective precision and AUC although it lost by Song et al [66] in terms of recall.…”

mentioning

confidence: 99%

See 2 more Smart Citations

DermoExpert: Skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation

Mte

2021

Preprint

View full text Add to dashboard Cite

Although automated Skin Lesion Classification (SLC) is a crucial integral step in computer-aided diagnosis, it remains a challenging task due to inconsistency in texture, color, indistinguishable boundaries, and shapes. In this article, we propose an automatic and robust framework for the dermoscopic SLC named Dermoscopic Expert (DermoExpert). The DermoExpert consists of a preprocessing, a hybrid Convolutional Neural Network (hybrid-CNN), and transfer learning. The proposed hybrid-CNN classifier consists of three distinct feature extractors, with the same input images, which are fused to achieve better-depth feature maps of the corresponding lesion. Those distinct and fused feature maps are classified using the different fully connected layers, which are then ensembled to get a final prediction probability. In the preprocessing, we use lesion segmentation, augmentation, and class rebalancing. For boosting the lesion recognition, we have also employed geometric and intensity-based augmentation as well as the class rebalancing by penalizing the loss of the majority class and adding extra images to the minority classes. Additionally, we leverage the knowledge from a pre-trained model, also known as transfer learning, to build a generic classifier, although small datasets are being used. In the end, we design and implement a web application by deploying the weights of our DermoExpert for automatic lesion recognition. We evaluate our DermoExpert on the ISIC-2016, ISIC-2017, and ISIC-2018 datasets, where our DermoExpert has achieved the area under the receiver operating characteristic curve (AUC) of 0.96, 0.95, and 0.97, respectively. The experimental results outperform the recent state-of-the-art by a margin of 10.0 % and 2.0 % respectively for ISIC-2016 and ISIC-2017 datasets in terms of AUC. The DermoExpert also outperforms, in concerning a balanced accuracy, by a margin of 3.0 % for ISIC-2018 dataset. Since our framework can provide better-classification on three different test datasets, even with limited training data, it can lead to better-recognition of melanoma to aid dermatologists. Our source code, and segmented masks, for ISIC-2018 dataset, will be made publicly available for the research community for further improvements.

show abstract

“…Comparison of SLC-2016. The proposed DermoExpert produces the best results for the AUC by beating the state-of-the-art [70,78]…”

Section: Results Comparisonmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

DermoExpert: Skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation

Mte

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Zhang et al [26] proposed a synergic deep learning (SDL) method for skin lesion classification, which employs multiple CNNs to simultaneously learn discriminative feature representations from image pairs. Tang et al [27] designed a global-part CNN (GP-CNN) for skin lesion classification, which consists of a G-CNN and a P-CNN. They trained G-CNN with downscaled images for global dermoscopy image feature extraction, and used multiscale image patches to train P-CNN to capture local fine-grained information.…”

Section: Deep Learning-based Skin Lesion Classificationmentioning

confidence: 99%

Deep metric attention learning for skin lesion classification in dermoscopy images

Wang

Zhao

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

Currently, convolutional neural networks (CNNs) have made remarkable achievements in skin lesion classification because of their end-to-end feature representation abilities. However, precise skin lesion classification is still challenging because of the following three issues: (1) insufficient training samples, (2) inter-class similarities and intra-class variations, and (3) lack of the ability to focus on discriminative skin lesion parts. To address these issues, we propose a deep metric attention learning CNN (DeMAL-CNN) for skin lesion classification. In DeMAL-CNN, a triplet-based network (TPN) is first designed based on deep metric learning, which consists of three weight-shared embedding extraction networks. TPN adopts a triplet of samples as input and uses the triplet loss to optimize the embeddings, which can not only increase the number of training samples, but also learn the embeddings robust to inter-class similarities and intra-class variations. In addition, a mixed attention mechanism considering both the spatial-wise and channel-wise attention information is designed and integrated into the construction of each embedding extraction network, which can further strengthen the skin lesion localization ability of DeMAL-CNN. After extracting the embeddings, three weight-shared classification layers are used to generate the final predictions. In the training procedure, we combine the triplet loss with the classification loss as a hybrid loss to train DeMAL-CNN. We compare DeMAL-CNN with the baseline method, attention methods, advanced challenge methods, and state-of-the-art skin lesion classification methods on the ISIC 2016 and ISIC 2017 datasets, and test its generalization ability on the PH2 dataset. The results demonstrate its effectiveness.

show abstract

“…Melanoma is the most deadly skin cancer, but the 5-year survival rate of early stage melanoma is more than 95%. Therefore, early detection and diagnosis of skin cancer is highly significant and will reduce the mortality rate [2]. Skin cancer is examined visually by clinical experts starting from preliminary screening with the following dermoscopic assessment [3].…”

Section: Introductionmentioning

confidence: 99%

Multiscale ensemble of convolutional neural networks for skin lesion classification

Liu

Wang

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Early detection and treatment of skin cancer can considerably reduce the patient mortality rates. Convolutional neural network (CNN) has been widely applied in the field of computer aided diagnosis. However, for skin lesions, the inconsistent size of lesion regions in dermatoscope images hinders the convolutional neural network precise discrimination. To solve this problem, multiscale ensemble of convolutional neural networks called MECNN is proposed, which involves three branches with different lesion scales as the model input. The first branch locates the lesion region outline by identifying the largest local response point. Then, MECNN reduces the search area of the lesion region and divides the outline into two scales used as the input for the other two branches. A global loss function is defined to control the learning objectives of the three branches and MECNN fuses the branches output as the final classification result. The proposed model is evaluated on the public HAM10000 dataset and achieves a higher classification accuracy than the comparative state-of-the-art methods.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

GP-CNN-DTEL: Global-Part CNN Model With Data-Transformed Ensemble Learning for Skin Lesion Classification

Cited by 94 publications

References 28 publications

DermoExpert: Skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation

DermoExpert: Skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation

Deep metric attention learning for skin lesion classification in dermoscopy images

Multiscale ensemble of convolutional neural networks for skin lesion classification

Contact Info

Product

Resources

About