Efficient skin lesion segmentation using separable-Unet with stochastic weight averaging

Tang, Peng; Liang, Qiaokang; Yan, Xintong; Shao, Xiang; Sun, Wei; Zhang, Dan; Coppola, Gianmarc

doi:10.1016/j.cmpb.2019.07.005

Cited by 133 publications

(54 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to get high efficiency, a pretrained deep learning model was obtained by training a ResNet 41 model from a database called ImageNet, which contains more than 1 million images of over 1,000 categories. On that basis, colposcopy images were input to fine-tune multi-modal ResNet classification model, U-Net 42 segmentation model and Mask R-CNN 43 detection model, which use the pre-trained ResNet model as backbone.…”

Section: Methodsmentioning

confidence: 99%

The application of deep learning based diagnostic system to cervical squamous intraepithelial lesions recognition in colposcopy images

Yuan

Yao

Cheng

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Background Deep learning has presented considerable potential and is gaining more importance in computer assisted diagnosis. As the gold standard for pathologically diagnosing cervical intraepithelial lesions and invasive cervical cancer, colposcopy-guided biopsy faces challenges in improving accuracy and efficiency worldwide, especially in developing countries. To ease the heavy burden of cervical cancer screening, it is urgent to establish a scientific, accurate and efficient method for assisting diagnosis and biopsy. Methods The data were collected to establish three deeplearning-based models. For every case, one saline image, one acetic image, one iodine image and the corresponding clinical information, including age, the results of human papillomavirus testing and cytology, type of transformation zone, and pathologic diagnosis, were collected. The dataset was proportionally divided into three subsets including the training set, the test set and the validation set, at a ratio of 8:1:1. The validation set was used to evaluate model performance. After model establishment, an independent dataset of high-definition images was collected to further evaluate the model performance. In addition, the comparison of diagnostic accuracy between colposcopists and models weas performed. Results The sensitivity, specificity and accuracy of the classification model to differentiate negative cases from positive cases were 85.38%, 82.62% and 84.10% respectively, with an AUC of 0.93. The recall and DICE of the segmentation model to segment suspicious lesions in acetic images were 84.73% and 61.64%, with an average accuracy of 95.59%. Furthermore, 84.67% of highgrade lesions were detected by the acetic detection model. Compared to colposcopists, the diagnostic system performed better in ordinary colposcopy images but slightly unsatisfactory in high-definition images. Implications The deep learning-based diagnostic system could help assist colposcopy diagnosis and biopsy for HSILs.

show abstract

Section: Methodsmentioning

confidence: 99%

The application of deep learning based diagnostic system to cervical squamous intraepithelial lesions recognition in colposcopy images

Yuan

Yao

Cheng

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…LIN (Li and Shen, 2018) 95.0 75.3 83.9 biDFL (Wang et al, 2019) 94.65 81.47 88.54 SLS 94.31 79.26 86.93 FCNs (Zhang et al, 2019) 92.73 72.94 81.81 DCEDN (Adegun and Viriri, 2019a) (Bi et al, 2017) 94.24 83.99 90.66 FrCN (Al-Masni et al, 2018) 95.08 84.79 91.77 Ensemble (Goyal et al, 2020) 93.80 83.96 90.70 SRMP (Salih and Viriri, 2020) 91 The Local binary convolutional-deconvolutional approach overcomes the limitation of deep convolutional networks in producing coarsely segmented outputs when processing challenging skin lesion images. In this approach, the whole network is divided into stages, with each stage handling a section of the segmentation process.…”

Section: Methods Acc Ji Dicementioning

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

“…The three models are applied (U-Net, VGG16-Segnet, and DeepLabv3+) in the proposed system, since their decoders produce outputs that are of the same dimensions as the input image, which suits the task of segmentation. In addition, they have repeatedly used in similar medical image segmentation tasks, such as skin lesion segmentation [19], Liver lesion segmentation [20], [21], lung segmentation [22], [23], and pathological lymph node segmentation [24].…”

Section: Feature Extractionmentioning

confidence: 99%

MRI Brain Tumor Segmentation Using Deep Learning. (Dept. E)

Nassar

Mohamed

Elnakib

2021

MEJ. Mansoura Engineering Journal

View full text Add to dashboard Cite

 I. INTRODUCTIONRAIN tumor is an epidemic causes of cancer death. In USA, 700.000 people are diagnosed with brain tumors (80% benign and 20% malignant) [1]. In 2020, the American Cancer Society (ACS) for brain tumor estimated about 23,890 malignant tumors of the brain and around 18,020 deaths from malignant brain tumors [2]. Accurate segmentation and quantitative analysis of brain tumor is critical for tumor diagnosis and treatment planning.Magnetic resonance imaging (MRI) is usually used for brain tumor segmentation and classification. Since manual segmentation is a difficult and a time consuming task, the

show abstract

Efficient skin lesion segmentation using separable-Unet with stochastic weight averaging

Cited by 133 publications

References 25 publications

The application of deep learning based diagnostic system to cervical squamous intraepithelial lesions recognition in colposcopy images

The application of deep learning based diagnostic system to cervical squamous intraepithelial lesions recognition in colposcopy images

Skin Lesion Segmentation Using Local Binary Convolution-Deconvolution Architecture

MRI Brain Tumor Segmentation Using Deep Learning. (Dept. E)

Contact Info

Product

Resources

About