SLSNet: Skin lesion segmentation using a lightweight generative adversarial network

Sarker, Md. Mostafa Kamal; Rashwan, Hatem A.; Akram, Farhan; Singh, Vivek Kumar; Banu, Syeda Furruka; Chowdhury, Forhad Uddin Hasan; Choudhury, Kabir Ahmed; Chambon, Sylvie; Radeva, Petia; Puig, Domènec; Abdel-Nasser, Mohamed

doi:10.1016/j.eswa.2021.115433

Cited by 50 publications

(32 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 3 shows various performance measures found in this survey research. In cases, Brain: Retina: [39][40][41][42][43][44][45][46][47][48][49][50][51][52][53][54] Microscopic: [55][56][57][58][59][60][61][62][63][64] Multi-Organs: [65][66][67][68][69][70][71] Liver: [72][73][74][75][76][77] Skin: [78][79][80][81][82][83] Orthopedic: [84][85][86][87] Cardiac: [88]…”

Section: Performance Metricsmentioning

confidence: 99%

“…We have also noticed that l mse function is also utilized in 6 different studies followed by l mae , the function being used in 2 studies only. [20,22,44,45,48,51,58,62,72,76,79,84,85], [86, 92, 94, 96-98, 117, 125, 150, 151] The binary cross-entropy loss function evaluates each projected probability against the actual class outcome, which is either 0 or 1 L4 l dice [27, 51, 64, 66, 67, 90, 94, 95, 117, 120, 122][130, 141, 144, 145, 149] The term dice loss comes from the Sørensen-Dice coefficient, a statistic created in the 1940s to determine the similarity of two samples L5 l cyc [106]. [140] The element-wise loss is employed to ensure self-similarity during cyclic transformation when an unaligned training pair is provided L6 l r p [22] Regional perceptual loss function L7 l image [91] The element-wise data fidelity loss in the image domain is used to validate structure similarity to the target when an aligned training pair is provided [101] Perceptual loss function L9 l tvl1 [101] The loss function is based on TVL1 algorithm L10 l al [89] The multiple paths of loss are penalized differently in an asymmetric loss function L11 l acc [89] The function is based on achieved accuracy from the confusion matrix L12 l f l [77] The focal loss function is utilized to address class imbalance issues during the network training L13 l mse [48,66,68,69,81,1...…”

Section: Loss Functionsmentioning

confidence: 99%

See 1 more Smart Citation

Generative adversarial networks and its applications in the biomedical image segmentation: a comprehensive survey

Iqbal

Sharif

Yasmin

et al. 2022

Int J Multimed Info Retr

View full text Add to dashboard Cite

Recent advancements with deep generative models have proven significant potential in the task of image synthesis, detection, segmentation, and classification. Segmenting the medical images is considered a primary challenge in the biomedical imaging field. There have been various GANs-based models proposed in the literature to resolve medical segmentation challenges. Our research outcome has identified 151 papers; after the twofold screening, 138 papers are selected for the final survey. A comprehensive survey is conducted on GANs network application to medical image segmentation, primarily focused on various GANs-based models, performance metrics, loss function, datasets, augmentation methods, paper implementation, and source codes. Secondly, this paper provides a detailed overview of GANs network application in different human diseases segmentation. We conclude our research with critical discussion, limitations of GANs, and suggestions for future directions. We hope this survey is beneficial and increases awareness of GANs network implementations for biomedical image segmentation tasks.

show abstract

Section: Performance Metricsmentioning

confidence: 99%

Section: Loss Functionsmentioning

confidence: 99%

Generative adversarial networks and its applications in the biomedical image segmentation: a comprehensive survey

Iqbal

Sharif

Yasmin

et al. 2022

Int J Multimed Info Retr

View full text Add to dashboard Cite

show abstract

“…It would also be interesting to explore the segmentation of lungs in the healthy patients using the AI model trained on COVID-19 patients. Other neural network techniques such as generative adversarial networks (GANs) [80] or transfer learning and loss schemes [38,44,81] can also be adapted. A big data framework can be used to integrate comorbidity factors [82] in the AI models.…”

Section: Strengths Weakness and Extensionsmentioning

confidence: 99%

Inter-Variability Study of COVLIAS 1.0: Hybrid Deep Learning Models for COVID-19 Lung Segmentation in Computed Tomography

Suri¹,

Agarwal²,

Elavarthi³

et al. 2021

Diagnostics

View full text Add to dashboard Cite

Background: For COVID-19 lung severity, segmentation of lungs on computed tomography (CT) is the first crucial step. Current deep learning (DL)-based Artificial Intelligence (AI) models have a bias in the training stage of segmentation because only one set of ground truth (GT) annotations are evaluated. We propose a robust and stable inter-variability analysis of CT lung segmentation in COVID-19 to avoid the effect of bias. Methodology: The proposed inter-variability study consists of two GT tracers for lung segmentation on chest CT. Three AI models, PSP Net, VGG-SegNet, and ResNet-SegNet, were trained using GT annotations. We hypothesized that if AI models are trained on the GT tracings from multiple experience levels, and if the AI performance on the test data between these AI models is within the 5% range, one can consider such an AI model robust and unbiased. The K5 protocol (training to testing: 80%:20%) was adapted. Ten kinds of metrics were used for performance evaluation. Results: The database consisted of 5000 CT chest images from 72 COVID-19-infected patients. By computing the coefficient of correlations (CC) between the output of the two AI models trained corresponding to the two GT tracers, computing their differences in their CC, and repeating the process for all three AI-models, we show the differences as 0%, 0.51%, and 2.04% (all < 5%), thereby validating the hypothesis. The performance was comparable; however, it had the following order: ResNet-SegNet > PSP Net > VGG-SegNet. Conclusions: The AI models were clinically robust and stable during the inter-variability analysis on the CT lung segmentation on COVID-19 patients.

show abstract

“…Dosovitskiy et al removed the CNN-based encoder and replaced it with the vision transformer to improve the image recognition performance of the network [23]. Sarker et al proposed a SLSNet network that reduces the computational cost by using 1-D core factor deep learning networks for sensitive skin lesion segmentation with minimal resources [24]. Wu et al [25] proposed a new feature adaptive transformer network based on the classical encoder-decoder architecture called FAT-Net.…”

Section: Introductionmentioning

confidence: 99%

Skin Lesion Segmentation Based on Edge Attention Vnet with Balanced Focal Tversky Loss

Ocal

Alhudhaif

Polat

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Segmentation of skin lesions from dermoscopic images plays an essential role in the early detection of skin cancer. However, skin lesion segmentation is still challenging due to artifacts such as indistinguishability between skin lesion and normal skin, hair on the skin, and reflections in the obtained dermoscopy images. In this study, an edge attention network (ET-Net) combining edge guidance module (EGM) and weighted aggregation module is added to the 2D volumetric convolutional neural network (Vnet 2D) to maximize the performance of skin lesion segmentation. In addition, the proposed fusion model presents a new fusion loss function by combining balanced binary cross-entropy (BBCE) and focal Tversky loss (FTL). The proposed model has been tested on the ISIC 2018 Task 1 Lesion Boundary Segmentation Challenge dataset. The proposed model outperformed the state-of-the-art studies as a result of the tests.

show abstract

SLSNet: Skin lesion segmentation using a lightweight generative adversarial network

Cited by 50 publications

References 21 publications

Generative adversarial networks and its applications in the biomedical image segmentation: a comprehensive survey

Generative adversarial networks and its applications in the biomedical image segmentation: a comprehensive survey

Inter-Variability Study of COVLIAS 1.0: Hybrid Deep Learning Models for COVID-19 Lung Segmentation in Computed Tomography

Skin Lesion Segmentation Based on Edge Attention Vnet with Balanced Focal Tversky Loss

Contact Info

Product

Resources

About