Matches in SemOpenAlex for { <https://semopenalex.org/work/W2899332989> ?p ?o ?g. }
- W2899332989 endingPage "228" @default.
- W2899332989 startingPage "215" @default.
- W2899332989 abstract "Purpose Due to the low contrast, blurry boundaries, and large amount of shadows in breast ultrasound (BUS) images, automatic tumor segmentation remains a challenging task. Deep learning provides a solution to this problem, since it can effectively extract representative features from lesions and the background in BUS images. Methods A novel automatic tumor segmentation method is proposed by combining a dilated fully convolutional network (DFCN) with a phase-based active contour (PBAC) model. The DFCN is an improved fully convolutional neural network with dilated convolution in deeper layers, fewer parameters, and batch normalization techniques; and has a large receptive field that can separate tumors from background. The predictions made by the DFCN are relatively rough due to blurry boundaries and variations in tumor sizes; thus, the PBAC model, which adds both region-based and phase-based energy functions, is applied to further improve segmentation results. The DFCN model is trained and tested in dataset 1 which contains 570 BUS images from 89 patients. In dataset 2, a 10-fold support vector machine (SVM) classifier is employed to verify the diagnostic ability using 460 features extracted from the segmentation results of the proposed method. Results Advantages of the present method were compared with three state-of-the-art networks; the FCN-8s, U-net, and dilated residual network (DRN). Experimental results from 170 BUS images show that the proposed method had a Dice Similarity coefficient of 88.97 ± 10.01%, a Hausdorff distance (HD) of 35.54 ± 29.70 pixels, and a mean absolute deviation (MAD) of 7.67 ± 6.67 pixels, which showed the best segmentation performance. In dataset 2, the area under curve (AUC) of the 10-fold SVM classifier was 0.795 which is similar to the classification using the manual segmentation results. Conclusions The proposed automatic method may be sufficiently accurate, robust, and efficient for medical ultrasound applications." @default.
- W2899332989 created "2018-11-09" @default.
- W2899332989 creator A5002579815 @default.
- W2899332989 creator A5008416988 @default.
- W2899332989 creator A5026449840 @default.
- W2899332989 creator A5036381691 @default.
- W2899332989 creator A5049706279 @default.
- W2899332989 creator A5065831190 @default.
- W2899332989 creator A5069948190 @default.
- W2899332989 date "2018-11-28" @default.
- W2899332989 modified "2023-10-11" @default.
- W2899332989 title "Automatic tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour model" @default.
- W2899332989 cites W142368000 @default.
- W2899332989 cites W1901129140 @default.
- W2899332989 cites W1982652137 @default.
- W2899332989 cites W1983023265 @default.
- W2899332989 cites W1984211790 @default.
- W2899332989 cites W1984516823 @default.
- W2899332989 cites W1987060390 @default.
- W2899332989 cites W1988819287 @default.
- W2899332989 cites W1989924788 @default.
- W2899332989 cites W1994967594 @default.
- W2899332989 cites W2003188860 @default.
- W2899332989 cites W2011585383 @default.
- W2899332989 cites W2021731869 @default.
- W2899332989 cites W2028672930 @default.
- W2899332989 cites W2050997943 @default.
- W2899332989 cites W2060005420 @default.
- W2899332989 cites W2101521775 @default.
- W2899332989 cites W2113282793 @default.
- W2899332989 cites W2119249988 @default.
- W2899332989 cites W2122264932 @default.
- W2899332989 cites W2123139184 @default.
- W2899332989 cites W2124653673 @default.
- W2899332989 cites W2159511100 @default.
- W2899332989 cites W2167536222 @default.
- W2899332989 cites W2253429366 @default.
- W2899332989 cites W2290687990 @default.
- W2899332989 cites W2337428771 @default.
- W2899332989 cites W2395611524 @default.
- W2899332989 cites W2556177465 @default.
- W2899332989 cites W2592929672 @default.
- W2899332989 cites W2606179580 @default.
- W2899332989 cites W2919115771 @default.
- W2899332989 cites W2962850830 @default.
- W2899332989 cites W2964309882 @default.
- W2899332989 doi "https://doi.org/10.1002/mp.13268" @default.
- W2899332989 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30374980" @default.
- W2899332989 hasPublicationYear "2018" @default.
- W2899332989 type Work @default.
- W2899332989 sameAs 2899332989 @default.
- W2899332989 citedByCount "105" @default.
- W2899332989 countsByYear W28993329892019 @default.
- W2899332989 countsByYear W28993329892020 @default.
- W2899332989 countsByYear W28993329892021 @default.
- W2899332989 countsByYear W28993329892022 @default.
- W2899332989 countsByYear W28993329892023 @default.
- W2899332989 crossrefType "journal-article" @default.
- W2899332989 hasAuthorship W2899332989A5002579815 @default.
- W2899332989 hasAuthorship W2899332989A5008416988 @default.
- W2899332989 hasAuthorship W2899332989A5026449840 @default.
- W2899332989 hasAuthorship W2899332989A5036381691 @default.
- W2899332989 hasAuthorship W2899332989A5049706279 @default.
- W2899332989 hasAuthorship W2899332989A5065831190 @default.
- W2899332989 hasAuthorship W2899332989A5069948190 @default.
- W2899332989 hasConcept C108583219 @default.
- W2899332989 hasConcept C112353826 @default.
- W2899332989 hasConcept C11413529 @default.
- W2899332989 hasConcept C121608353 @default.
- W2899332989 hasConcept C12267149 @default.
- W2899332989 hasConcept C124504099 @default.
- W2899332989 hasConcept C126322002 @default.
- W2899332989 hasConcept C136886441 @default.
- W2899332989 hasConcept C141898687 @default.
- W2899332989 hasConcept C144024400 @default.
- W2899332989 hasConcept C153180895 @default.
- W2899332989 hasConcept C154945302 @default.
- W2899332989 hasConcept C155512373 @default.
- W2899332989 hasConcept C160633673 @default.
- W2899332989 hasConcept C19165224 @default.
- W2899332989 hasConcept C20749125 @default.
- W2899332989 hasConcept C2777423100 @default.
- W2899332989 hasConcept C2780472235 @default.
- W2899332989 hasConcept C31972630 @default.
- W2899332989 hasConcept C41008148 @default.
- W2899332989 hasConcept C530470458 @default.
- W2899332989 hasConcept C71924100 @default.
- W2899332989 hasConcept C81363708 @default.
- W2899332989 hasConcept C89600930 @default.
- W2899332989 hasConceptScore W2899332989C108583219 @default.
- W2899332989 hasConceptScore W2899332989C112353826 @default.
- W2899332989 hasConceptScore W2899332989C11413529 @default.
- W2899332989 hasConceptScore W2899332989C121608353 @default.
- W2899332989 hasConceptScore W2899332989C12267149 @default.
- W2899332989 hasConceptScore W2899332989C124504099 @default.
- W2899332989 hasConceptScore W2899332989C126322002 @default.
- W2899332989 hasConceptScore W2899332989C136886441 @default.
- W2899332989 hasConceptScore W2899332989C141898687 @default.