FCA-Net: Adversarial Learning for Skin Lesion Segmentation Based on Multi-Scale Features and Factorized Channel Attention

Singh, Vivek Kumar; Abdel-Nasser, Mohamed; Rashwan, Hatem A.; Akram, Farhan; Pandey, Nidhi; Lalande, Alain; Presles, Benoît; Romaní, Santiago; Puig, Domènec

doi:10.1109/access.2019.2940418

Cited by 59 publications

(42 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, there is a noteworthy phenomenon in Table 2 to 6 that a method on mJI is usually better than other methods while its mAC score is relatively poor than them, although better mAC and better mJI both indicate a better performance. This phenomenon does not merely occur in our experimental results, extensively existing in many previous works such as FCA-Net [15], SkinNet [34] and iMSCGnet [37], and there has been no reasonable explanation for it in community. It is known that the metrics mJI and mAC were both introduced in the official ISIC 2017 [21] and mJI was the finally decisive metric adopted, and the official had not explained the specific reasons.…”

Section: F Comparison With State Of the Artsmentioning

confidence: 57%

“…In the International Skin Imaging Collaboration (ISIC) 2017 Challenge [21] and 2018 Challenge [33] at the International Symposium on Biomedical Imaging (ISBI), most of top ranked participants took advantage of various dominated DCNN methods such as the FCNs model [8], Mask R-CNN [11] or their variations. In addition, some DCNN-based methods such as FCA-Net [15], SkinNet [34], PA-Net [35], FrCN [36], iMSCGnet [37] and Slsdeep [38] were proposed as well in recent years. These efforts were mainly based on some single model resolving the lesion segmentation problem on the global level upon whole training dataset.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Inferring Skin Lesion Segmentation With Fully Connected CRFs Based on Multiple Deep Convolutional Neural Networks

et al. 2020

View full text Add to dashboard Cite

This paper presents a method to infer skin lesion segmentation based on multiple deep convolutional neural network (DCNN) models by employing fully connected conditional random fields (CRFs). This method is on the strength of the synergism between ensemble learning which is responsible for introducing diversity from multiple DCNN models and CRFs inference which is in charge of probabilistic inference based on random fields over dermoscopy images. Contrasting to single DCNN models, the proposed method can gain better segmentation by comprehensively utilizing the advances and performance preferences of multiple different DCNN models. In comparison with simple ensemble schemes, it can effectively and precisely refine the fuzzy lesion boundary by utilizing the information in test images to maximize label agreement between similar pixels. Further, an engineering bonus is the feasibility of parallelization for the heavy operation, predicting on multiple DCNN models. In experiments, we tested the effectiveness and robustness of the proposed method on the mainstream datasets ISIC 2017 and PH2, and the results were competitive with the state-of-art methods. we also confirmed that the proposed method can capture the local information in fuzzy dermoscopy images being able to find more accurate lesion borders with a good boost on Boundary Recall (BR) metric. Moreover, since the hyper-parameters in CRFs are explainable, it is possible to adjust them manually to reach better results case by case, being attractive in practice. This work is of value on integration between the deep learning technologies and probabilistic inference in resolving lesion segmentation, and has great potential to be applied in similar tasks.

show abstract

Section: F Comparison With State Of the Artsmentioning

confidence: 57%

Section: Related Workmentioning

confidence: 99%

Inferring Skin Lesion Segmentation With Fully Connected CRFs Based on Multiple Deep Convolutional Neural Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…However, these methods require an expert dermatologist. In recent years, dermatologists have used dermoscopy and microscopic images for diagnosing skin cancer [ 10 ]. The microscopic images have a low resolution and can be seen through mobile cameras.…”

Section: Introductionmentioning

confidence: 99%

Skin Lesion Segmentation and Multiclass Classification Using Deep Learning Features and Improved Moth Flame Optimization

et al. 2021

View full text Add to dashboard Cite

Manual diagnosis of skin cancer is time-consuming and expensive; therefore, it is essential to develop automated diagnostics methods with the ability to classify multiclass skin lesions with greater accuracy. We propose a fully automated approach for multiclass skin lesion segmentation and classification by using the most discriminant deep features. First, the input images are initially enhanced using local color-controlled histogram intensity values (LCcHIV). Next, saliency is estimated using a novel Deep Saliency Segmentation method, which uses a custom convolutional neural network (CNN) of ten layers. The generated heat map is converted into a binary image using a thresholding function. Next, the segmented color lesion images are used for feature extraction by a deep pre-trained CNN model. To avoid the curse of dimensionality, we implement an improved moth flame optimization (IMFO) algorithm to select the most discriminant features. The resultant features are fused using a multiset maximum correlation analysis (MMCA) and classified using the Kernel Extreme Learning Machine (KELM) classifier. The segmentation performance of the proposed methodology is analyzed on ISBI 2016, ISBI 2017, ISIC 2018, and PH2 datasets, achieving an accuracy of 95.38%, 95.79%, 92.69%, and 98.70%, respectively. The classification performance is evaluated on the HAM10000 dataset and achieved an accuracy of 90.67%. To prove the effectiveness of the proposed methods, we present a comparison with the state-of-the-art techniques.

show abstract

“…The aforementioned problems make skin lesion segmentation a challenging task. To address these problems, literature works that deploy different CNN architectures with multi-scale information [ 11 , 13 , 14 ], or multi-task learning framework [ 15 , 16 ] have been proposed for skin lesion segmentation. The core idea of these methods can be regarded as trying to use as much information as possible to make robust predictions.…”

Section: Introductionmentioning

confidence: 99%

Skin Lesion Segmentation Using Deep Learning with Auxiliary Task

2021

View full text Add to dashboard Cite

Skin lesion segmentation is a primary step for skin lesion analysis, which can benefit the subsequent classification task. It is a challenging task since the boundaries of pigment regions may be fuzzy and the entire lesion may share a similar color. Prevalent deep learning methods for skin lesion segmentation make predictions by ensembling different convolutional neural networks (CNN), aggregating multi-scale information, or by multi-task learning framework. The main purpose of doing so is trying to make use of as much information as possible so as to make robust predictions. A multi-task learning framework has been proved to be beneficial for the skin lesion segmentation task, which is usually incorporated with the skin lesion classification task. However, multi-task learning requires extra labeling information which may not be available for the skin lesion images. In this paper, a novel CNN architecture using auxiliary information is proposed. Edge prediction, as an auxiliary task, is performed simultaneously with the segmentation task. A cross-connection layer module is proposed, where the intermediate feature maps of each task are fed into the subblocks of the other task which can implicitly guide the neural network to focus on the boundary region of the segmentation task. In addition, a multi-scale feature aggregation module is proposed, which makes use of features of different scales and enhances the performance of the proposed method. Experimental results show that the proposed method obtains a better performance compared with the state-of-the-art methods with a Jaccard Index (JA) of 79.46, Accuracy (ACC) of 94.32, SEN of 88.76 with only one integrated model, which can be learned in an end-to-end manner.

show abstract

FCA-Net: Adversarial Learning for Skin Lesion Segmentation Based on Multi-Scale Features and Factorized Channel Attention

Cited by 59 publications

References 37 publications

Inferring Skin Lesion Segmentation With Fully Connected CRFs Based on Multiple Deep Convolutional Neural Networks

Inferring Skin Lesion Segmentation With Fully Connected CRFs Based on Multiple Deep Convolutional Neural Networks

Skin Lesion Segmentation and Multiclass Classification Using Deep Learning Features and Improved Moth Flame Optimization

Skin Lesion Segmentation Using Deep Learning with Auxiliary Task

Contact Info

Product

Resources

About