A Deep Residual Architecture for Skin Lesion Segmentation

Venkatesh, Ganesh; Naresh, Yalagala; Little, Suzanne; O’Connor, Noel E.

doi:10.1007/978-3-030-01201-4_30

Cited by 52 publications

(27 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It achieved a Dice coefficient of 87.40% and IoU scores 79.87% on ISBI2017 dataset. In turn, Venkatesh et al [22] used the U-Net model that is based on multi-scale input with a shortcut connection at each block of the U-Net. The suggested method has evaluated on ISBI2017 dataset, obtaining a Dice coefficient and IoU scores of 85.60% and 76.40%, respectively.…”

Section: B Cnn-based Methodsmentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

Skin lesion segmentation in dermoscopic images is still a challenge due to the low contrast and fuzzy boundaries of lesions. Moreover, lesions have high similarity with the healthy regions in terms of appearance. In this paper, we propose an accurate skin lesion segmentation model based on a modified conditional generative adversarial network (cGAN). We introduce a new block in the encoder of cGAN called factorized channel attention (FCA), which exploits both channel attention mechanism and residual 1-D kernel factorized convolution. The channel attention mechanism increases the discriminability between the lesion and non-lesion features by taking feature channel interdependencies into account. The 1-D factorized kernel block provides extra convolutions layers with a minimum number of parameters to reduce the computations of the higher-order convolutions. Besides, we use a multi-scale input strategy to encourage the development of filters which are scale-variant (i.e., constructing a scale-invariant representation). The proposed model is assessed on three skin challenge datasets: ISBI2016, ISBI2017, and ISIC2018. It yields competitive results when compared to several state-of-the-art methods in terms of Dice coefficient and intersection over union (IoU) score. The codes of the proposed model are publicly available at https://github.com/vivek231/Skin-Project.INDEX TERMS Skin lesion, conditional generative adversarial network, channel attention, factorized kernel, residual convolution.

show abstract

Section: B Cnn-based Methodsmentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Other deep learning networks have also been proposed for lesion segmentation. Venkatesh et al [9] proposed a deep architecture with multi-scale residual connections for lesion segmentation, known as Multi-scale residual U-Net. Their model employed multi-scale residual connections to tackle information loss in the encoding stages in the U-Net.…”

Section: A Image Segmentationmentioning

confidence: 99%

Evolving Ensemble Models for Image Segmentation Using Enhanced Particle Swarm Optimization

et al. 2019

View full text Add to dashboard Cite

In this paper, we propose particle swarm optimization (PSO)-enhanced ensemble deep neural networks and hybrid clustering models for skin lesion segmentation. A PSO variant is proposed, which embeds diverse search actions including simulated annealing, levy flight, helix behavior, modified PSO, and differential evolution operations with spiral search coefficients. These search actions work in a cascade manner to not only equip each individual with different search operations throughout the search process but also assign distinctive search actions to different particles simultaneously in every single iteration. The proposed PSO variant is used to optimize the learning hyper-parameters of convolutional neural networks (CNNs) and the cluster centroids of classical Fuzzy C-Means clustering respectively to overcome performance barriers. Ensemble deep networks and hybrid clustering models are subsequently constructed based on the optimized CNN and hybrid clustering segmenters for lesion segmentation. We evaluate the proposed ensemble models using three skin lesion databases, i.e., PH2, ISIC 2017, and Dermofit Image Library, and a blood cancer data set, i.e., ALL-IDB2. The empirical results indicate that our models outperform other hybrid ensemble clustering models combined with advanced PSO variants, as well as stateof-the-art deep networks in the literature for diverse challenging image segmentation tasks.

show abstract

“…To preserve the initial resolution, the most prevalent architecture termed U-net [18] was proposed, which constructs an encoding path and a symmetric decoding path to reach precise resolution. Given this, studies have shown feasibility of adopting U-net based networks to dermoscopic melanoma A segmentation [19]- [22] and epidermis segmentation [23] from histopathological images. When it comes to melanoma histopathological segmentation, consideration should be taken to accommodate different scenarios because of differentially enriched structures among tissue types.…”

Section: Introductionmentioning

confidence: 99%

Identification of Melanoma From Hyperspectral Pathology Image Using 3D Convolutional Networks

Wang

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Skin biopsy histopathological analysis is one of the primary methods used for pathologists to assess the presence and deterioration of melanoma in clinical. A comprehensive and reliable pathological analysis is the result of correctly segmented melanoma and its interaction with benign tissues, and therefore providing accurate therapy. In this study, we applied the deep convolution network on the hyperspectral pathology images to perform the segmentation of melanoma. To make the best use of spectral properties of three dimensional hyperspectral data, we proposed a 3D fully convolutional network named Hyper-net to segment melanoma from hyperspectral pathology images. In order to enhance the sensitivity of the model, we made a specific modification to the loss function with caution of false negative in diagnosis. The performance of Hyper-net surpassed the 2D model with the accuracy over 92%. The false negative rate decreased by nearly 66% using Hyper-net with the modified loss function. These findings demonstrated the ability of the Hyper-net for assisting pathologists in diagnosis of melanoma based on hyperspectral pathology images.

show abstract

A Deep Residual Architecture for Skin Lesion Segmentation

Cited by 52 publications

References 18 publications

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

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

Evolving Ensemble Models for Image Segmentation Using Enhanced Particle Swarm Optimization

Identification of Melanoma From Hyperspectral Pathology Image Using 3D Convolutional Networks

Contact Info

Product

Resources

About