Polyp Segmentation in Colonoscopy Images Using Fully Convolutional Network

Akbari, Mojtaba; Mohrekesh, Majid; Nasr-Esfahani, Ebrahim; Soroushmehr, S. M. Reza; Karimi, Nader; Samavi, Shadrokh; Najarian, Kayvan

doi:10.1109/embc.2018.8512197

Cited by 151 publications

(75 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Kang et al, 15 the IoU are 66.07% for ETIS-LaribPo-lypDB and 69.46% for CVC-ColonDB. The DICE is 81% for CVC-ColonDB dataset in Akbari et al, 12 and the DICE is 88.9% for ETIS-LaribPolypDB dataset in Nguyen et al 13 The IoU and the DICE in our methods show higher accuracy for image segmentation. It is helpful to establish the database for polyp segmentation and polyp recognition.…”

Section: Discussionmentioning

confidence: 66%

“…Some researchers used different machine learning methods to get good segmentation results . And some researchers improved several architectures of Full Convolution Networks (FCNs) and Convolutional Neural Network (CNN) . Nguyen et al proposed a method based on multiple encoder–decoder network.…”

Section: Introductionmentioning

confidence: 99%

“…[6][7][8][9] And some researchers improved several architectures of Full Convolution Networks (FCNs) and Convolutional Neural Network (CNN). [10][11][12] Nguyen et al 13 proposed a method based on multiple encoder-decoder network. Xiao et al 14 parallel combined Long Short-Term Memory networks and Dee-pLab_v3 to augment the signal of the polyps' location.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated polyp segmentation for colonoscopy images: A method based on convolutional neural networks and ensemble learning

et al. 2019

View full text Add to dashboard Cite

Purpose To automatically and efficiently segment the lesion area of the colonoscopy polyp image, a polyp segmentation method has been presented. Methods An ensemble model of pretrained convolutional neural networks was proposed, using Unet‐VGG, SegNet‐VGG, and PSPNet. Firstly, the Unet‐VGG is obtained by the first 10 layers of VGG16 as the contraction path of the left half of the Unet. Then, the SegNet‐VGG is acquired by fine‐tuned transfer learning VGG16, using the first 13 layers of VGG16 as the encoder of the SegNet and combined the original decoder of the SegNet. By adjusting the input size of the Unet‐VGG, SegNet‐VGG, and PSPNet, the preprocessed data can be correctly fed to the three network models. The three models are used as the basic trainer to train and segment the datasets. Based on the ensemble learning algorithm, the weight voting method is used to ensemble the segmentation results corresponding to single basic trainer. Results Both IoU and DICE similarity score were used to evaluate the segmentation quality for cvc300 with 300 images, CVC‐ClinicDB with 612 images, and ETIS‐LaribPolypDB with 196 images. From the experimental results, the IoU and DICE obtained by the proposed method for the cvc300 datasets can reach up to 96.16% and 98.04%, respectively, the IoU and DICE for the CVC‐ClinicDB datasets can reach up to 96.66% and 98.30%, respectively, whereas the IoU and DICE for the ETIS‐LaribPolypDB datasets can reach up to 96.95% and 98.45%, respectively. Evaluation of the IoU and DICE in our methods shows higher accuracy than previous methods. Conclusions The experimental results show that the proposed method improved correspondingly in IoU and DICE compared to a single basic trainer. The range of improvement is 1.98%–6.38%. The proposed ensemble learning succeeds in automatic polyp segmentation, which potentially helps to establish more polyp datasets.

show abstract

Section: Discussionmentioning

confidence: 66%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated polyp segmentation for colonoscopy images: A method based on convolutional neural networks and ensemble learning

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Iwahori . [2] Hessian filters used to enhance features of image and Primitive image processing techniques Mojtaba Akbari [1] Convolutional neural network and Otsu thresholding.…”

Section: Authors Methodsmentioning

confidence: 99%

Validation Techniques for Relating Ensemble Methods in Polyp Detection

2019

IJITEE

View full text Add to dashboard Cite

Endoscopy is one of the most efficient colon screening technique through which the polyps are identified and treated. This manual process of identifying the polyp has chance of missing some polyps while diagnosis. To overcome this an efficient computer aided detection technique need to designed, there are several computing techniques and algorithms available, this research article tries compare different techniques used in polyp detection and also proposes several performance evaluation metrics which can be used to find the proficiency of methods in identifying polyps in endoscopy videos. The article presents various identification methods, evaluation methods include various parameters like performance metrics. The proposed ensemble approaches are discussed in polyp detection mechanism.

show abstract

“…[33] Creating a CNN for polyp detection enabled precise detection at 88.6% and recall at 71.6%. A polyp segmentation method with full CNN for different sizes and shapes of colorectal polyps used as ground truth images for evaluation was developed in [34]. Segmentation accuracy of 97.77% was achieved.…”

Section: Introductionmentioning

confidence: 99%

Enhancement of Deep Learning in Image Classification Performance Using Xception with the Swish Activation Function for Colorectal Polyp Preliminary Screening

Jinsakul

Tsai

et al. 2019

Mathematics

View full text Add to dashboard Cite

One of the leading forms of cancer is colorectal cancer (CRC), which is responsible for increasing mortality in young people. The aim of this paper is to provide an experimental modification of deep learning of Xception with Swish and assess the possibility of developing a preliminary colorectal polyp screening system by training the proposed model with a colorectal topogram dataset in two and three classes. The results indicate that the proposed model can enhance the original convolutional neural network model with evaluation classification performance by achieving accuracy of up to 98.99% for classifying into two classes and 91.48% for three classes. For testing of the model with another external image, the proposed method can also improve the prediction compared to the traditional method, with 99.63% accuracy for true prediction of two classes and 80.95% accuracy for true prediction of three classes.

show abstract

Polyp Segmentation in Colonoscopy Images Using Fully Convolutional Network

Cited by 151 publications

References 15 publications

Automated polyp segmentation for colonoscopy images: A method based on convolutional neural networks and ensemble learning

Automated polyp segmentation for colonoscopy images: A method based on convolutional neural networks and ensemble learning

Validation Techniques for Relating Ensemble Methods in Polyp Detection

Enhancement of Deep Learning in Image Classification Performance Using Xception with the Swish Activation Function for Colorectal Polyp Preliminary Screening

Contact Info

Product

Resources

About