Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897874631> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2897874631 endingPage "e548" @default.
- W2897874631 startingPage "e548" @default.
- W2897874631 abstract "Manually contouring gross tumor volume (GTV) is a crucial and time-consuming process in rectum cancer radiotherapy. This study aims to develop a simple deep learning based rectum tumor auto segmentation algorithm on MRI T2 images. MRI scans (3T, T2-weighted) of 93 patients with locally advanced (cT3-4 and/or cN1-2) rectal cancer treated with neoadjuvant chemoradiotherapy followed by surgery were enrolled in this study. A very deep convolutional networks (VGG16) based full convolution network (FCN) was established as training model. The model was trained in two phases to increase efficiency, including tumor recognition and tumor segmentation. An opening (erosion and dilation) process was implemented to make contours smoother. Data were randomly separated into training (90%) and validation (10%) dataset for 10 folder cross-validation. Additionally, 20 patients were double contoured for performance evaluation. Four indices were calculated to evaluate the similarity of automated and manual segmentation, including Hausdorff distance (HD), average surface distance (ASD), Dice index (DSC) and Jaccard index (JSC). The DSC, JSC, HD, ASD (mean±SD) were 0.74±0.14, 0.60±0.16, 20.44±13.35mm and 3.25±1.69mm for validation dataset; And these indices were 0.71±0.13, 0.57±0.15, 14.91±7.62mm and 2.67±1.46mm between two human radiation oncologists. T-test suggested there is no statistically significant difference between automated segmentation and manual segmentation considering DSC (p=0.42), JSC (p=0.35), HD (p=0.079) and ASD (p=0.16). However, significant difference was found for HD (p=0.0027) without opening process. This study showed that a simple deep learning neural network can perform a human comparable segmentation for rectum cancer based on MRI T2 images." @default.
- W2897874631 created "2018-10-26" @default.
- W2897874631 creator A5005180151 @default.
- W2897874631 creator A5026318768 @default.
- W2897874631 creator A5026994163 @default.
- W2897874631 creator A5041227791 @default.
- W2897874631 creator A5067222419 @default.
- W2897874631 creator A5069226662 @default.
- W2897874631 creator A5086337383 @default.
- W2897874631 creator A5088314148 @default.
- W2897874631 date "2018-11-01" @default.
- W2897874631 modified "2023-10-17" @default.
- W2897874631 title "A Novel Deep Learning Based Auto Segmentation For Rectum Tumor On MRI Image" @default.
- W2897874631 doi "https://doi.org/10.1016/j.ijrobp.2018.07.1529" @default.
- W2897874631 hasPublicationYear "2018" @default.
- W2897874631 type Work @default.
- W2897874631 sameAs 2897874631 @default.
- W2897874631 citedByCount "0" @default.
- W2897874631 crossrefType "journal-article" @default.
- W2897874631 hasAuthorship W2897874631A5005180151 @default.
- W2897874631 hasAuthorship W2897874631A5026318768 @default.
- W2897874631 hasAuthorship W2897874631A5026994163 @default.
- W2897874631 hasAuthorship W2897874631A5041227791 @default.
- W2897874631 hasAuthorship W2897874631A5067222419 @default.
- W2897874631 hasAuthorship W2897874631A5069226662 @default.
- W2897874631 hasAuthorship W2897874631A5086337383 @default.
- W2897874631 hasAuthorship W2897874631A5088314148 @default.
- W2897874631 hasConcept C108583219 @default.
- W2897874631 hasConcept C121684516 @default.
- W2897874631 hasConcept C126838900 @default.
- W2897874631 hasConcept C141071460 @default.
- W2897874631 hasConcept C141898687 @default.
- W2897874631 hasConcept C153180895 @default.
- W2897874631 hasConcept C154945302 @default.
- W2897874631 hasConcept C203519979 @default.
- W2897874631 hasConcept C2779104521 @default.
- W2897874631 hasConcept C2781074409 @default.
- W2897874631 hasConcept C2989005 @default.
- W2897874631 hasConcept C41008148 @default.
- W2897874631 hasConcept C509974204 @default.
- W2897874631 hasConcept C71924100 @default.
- W2897874631 hasConcept C89600930 @default.
- W2897874631 hasConceptScore W2897874631C108583219 @default.
- W2897874631 hasConceptScore W2897874631C121684516 @default.
- W2897874631 hasConceptScore W2897874631C126838900 @default.
- W2897874631 hasConceptScore W2897874631C141071460 @default.
- W2897874631 hasConceptScore W2897874631C141898687 @default.
- W2897874631 hasConceptScore W2897874631C153180895 @default.
- W2897874631 hasConceptScore W2897874631C154945302 @default.
- W2897874631 hasConceptScore W2897874631C203519979 @default.
- W2897874631 hasConceptScore W2897874631C2779104521 @default.
- W2897874631 hasConceptScore W2897874631C2781074409 @default.
- W2897874631 hasConceptScore W2897874631C2989005 @default.
- W2897874631 hasConceptScore W2897874631C41008148 @default.
- W2897874631 hasConceptScore W2897874631C509974204 @default.
- W2897874631 hasConceptScore W2897874631C71924100 @default.
- W2897874631 hasConceptScore W2897874631C89600930 @default.
- W2897874631 hasIssue "3" @default.
- W2897874631 hasLocation W28978746311 @default.
- W2897874631 hasOpenAccess W2897874631 @default.
- W2897874631 hasPrimaryLocation W28978746311 @default.
- W2897874631 hasRelatedWork W2167230651 @default.
- W2897874631 hasRelatedWork W2790662084 @default.
- W2897874631 hasRelatedWork W2948658236 @default.
- W2897874631 hasRelatedWork W3017840285 @default.
- W2897874631 hasRelatedWork W3039022597 @default.
- W2897874631 hasRelatedWork W3206966550 @default.
- W2897874631 hasRelatedWork W4220708658 @default.
- W2897874631 hasRelatedWork W4243168368 @default.
- W2897874631 hasRelatedWork W4293211451 @default.
- W2897874631 hasRelatedWork W4318992034 @default.
- W2897874631 hasVolume "102" @default.
- W2897874631 isParatext "false" @default.
- W2897874631 isRetracted "false" @default.
- W2897874631 magId "2897874631" @default.
- W2897874631 workType "article" @default.