Skin Lesion Segmentation with Improved Convolutional Neural Network

Öztürk, Şaban; Özkaya, Umut

doi:10.1007/s10278-020-00343-z

Cited by 96 publications

(45 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hajabdollahi et al (2020) developed a pruning framework to reduce the burden of the network for feature extraction through the selection of most informative color channels and simplification of the network. Ozturk and Ozkaya (2020) proposed improved FCN (iFCN) architecture for the segmentation of full-resolution skin lesion images without any pre-or post-processing. It is to support the residual structure of the FCN architecture with spatial information.…”

Section: Related Workmentioning

confidence: 99%

Skin Lesion Segmentation Using Local Binary Convolution-Deconvolution Architecture

Salih

Viriri

2020

Image Anal Stereol

View full text Add to dashboard Cite

Deep learning techniques such as Deep Convolutional Networks have achieved great success in skin lesion segmentation towards melanoma detection. The performance is however restrained by distinctive and challenging features of skin lesions such as irregular and fuzzy border, noise and artefacts presence and low contrast between lesions. The methods are also restricted with scarcity of annotated lesion images training dataset and limited computing resources. Recent research in convolutional neural network (CNN) has provided a variety of new architectures for deep learning. One interesting new architecture is the local binary convolutional neural network (LBCNN), which can reduce the workload of CNNs and improve the classification accuracy. The proposed framework employs the local binary convolution on U-net architecture instead of the standard convolution in order to reduced-size deep convolutional encoder-decoder network that adopts loss function for robust segmentation. The proposed framework replaced the encoder part in U-net by LBCNN layers. The approach automatically learns and segments complex features of skin lesion images. The encoder stage learns the contextual information by extracting discriminative features while the decoder stage captures the lesion boundaries of the skin images. This addresses the issues with encoder-decoder network producing coarse segmented output with challenging skin lesions appearances such as low contrast between healthy and unhealthy tissues and fine grained variability. It also addresses issues with multi-size, multi-scale and multi-resolution skin lesion images. The deep convolutional network also adopts a reduced-size network with just five levels of encoding-decoding network. This reduces greatly the consumption of computational processing resources. The system was evaluated on publicly available dataset of ISIC and PH2. The proposed system outperforms most of the existing state-of-art.

show abstract

Section: Related Workmentioning

confidence: 99%

Skin Lesion Segmentation Using Local Binary Convolution-Deconvolution Architecture

Salih

Viriri

2020

Image Anal Stereol

View full text Add to dashboard Cite

show abstract

“…To accomplish this goal, deep learning researchers have proposed an encoder–decoder structure such as fully convolution network (FCN) [ 5 ], Deeplab [ 6 ], Unet [ 7 ], etc. These network models are applicable for medical image segmentation applications such as liver and liver tumor [ 8 , 9 , 10 ], brain and brain tumor [ 11 , 12 , 13 ], lung and lung nodule [ 14 , 15 ], nuclei [ 16 , 17 ], polyp [ 18 , 19 ], skin lesion [ 20 , 21 , 22 ], etc. Many studies have proposed these models for many different types of medical imaging [ 23 , 24 , 25 , 26 , 27 ].…”

Section: Introductionmentioning

confidence: 99%

TMD-Unet: Triple-Unet with Multi-Scale Input Features and Dense Skip Connection for Medical Image Segmentation

et al. 2021

View full text Add to dashboard Cite

Deep learning is one of the most effective approaches to medical image processing applications. Network models are being studied more and more for medical image segmentation challenges. The encoder–decoder structure is achieving great success, in particular the Unet architecture, which is used as a baseline architecture for the medical image segmentation networks. Traditional Unet and Unet-based networks still have a limitation that is not able to fully exploit the output features of the convolutional units in the node. In this study, we proposed a new network model named TMD-Unet, which had three main enhancements in comparison with Unet: (1) modifying the interconnection of the network node, (2) using dilated convolution instead of the standard convolution, and (3) integrating the multi-scale input features on the input side of the model and applying a dense skip connection instead of a regular skip connection. Our experiments were performed on seven datasets, including many different medical image modalities such as colonoscopy, electron microscopy (EM), dermoscopy, computed tomography (CT), and magnetic resonance imaging (MRI). The segmentation applications implemented in the paper include EM, nuclei, polyp, skin lesion, left atrium, spleen, and liver segmentation. The dice score of our proposed models achieved 96.43% for liver segmentation, 95.51% for spleen segmentation, 92.65% for polyp segmentation, 94.11% for EM segmentation, 92.49% for nuclei segmentation, 91.81% for left atrium segmentation, and 87.27% for skin lesion segmentation. The experimental results showed that the proposed model was superior to the popular models for all seven applications, which demonstrates the high generality of the proposed model.

show abstract

“…Early diagnosis and treatment greatly improve the probability of survival. However, clinical diagnosis is highly subjective and complex; thus, it relies heavily on dermatologists' expertise and is estimated to be between 75 -85% [6][7]. Dermoscopy is one of the most common imaging techniques for dermatologists.…”

Section: Introductionmentioning

confidence: 99%

Skin Lesions Classification Using Deep Learning Techniques: Review

Kareem

Abdulazeez

Zeebaree

2021

AJRCoS

View full text Add to dashboard Cite

Skin cancer is a significant health problem. More than 123,000 new cases per year are recorded. Melanoma is the most popular type of skin cancer, leading to more than 9000 deaths annually in the USA. Skin disease diagnosis is getting difficult due to visual similarities. While Melanoma is the most common form of skin cancer, other pathology types are also fatal. Automatic melanoma screening systems will be useful in identifying those skin cancers more appropriately. Advances in technology and growth in computational capabilities have allowed machine learning and deep learning algorithms to analyze skin lesion images. Deep Convolutional Neural Networks (DCNNs) have achieved more encouraging results, yet faster systems for diagnosing fatal diseases are the need of the hour. This paper presents a survey of techniques for skin cancer detection from images. The paper aims to present a review of existing state-of-the-art and effective models for automatically detecting Melanoma from skin images. The result of classifications and segmentation from the skin lesion images will be processed better using the ensemble deep learning algorithm.

show abstract

Skin Lesion Segmentation with Improved Convolutional Neural Network

Cited by 96 publications

References 42 publications

Skin Lesion Segmentation Using Local Binary Convolution-Deconvolution Architecture

Skin Lesion Segmentation Using Local Binary Convolution-Deconvolution Architecture

TMD-Unet: Triple-Unet with Multi-Scale Input Features and Dense Skip Connection for Medical Image Segmentation

Skin Lesions Classification Using Deep Learning Techniques: Review

Contact Info

Product

Resources

About