Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289551005> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4289551005 abstract "Segmentation of lymphoma lesions is challenging due to their varied sizes and locations in whole-body PET scans. This work presents a fully-automated segmentation technique using a multi-center dataset of diffuse large B-cell lymphoma (DLBCL) with heterogeneous characteristics. We utilized a dataset of [18F]FDG-PET scans (n=194) from two different imaging centers, including cases with primary mediastinal large B-cell lymphoma (PMBCL) (n=104). Automated brain and bladder removal approaches were utilized as preprocessing steps to tackle false positives caused by normal hypermetabolic uptake in these organs. Our segmentation model is a convolutional neural network (CNN) based on a 3D U-Net architecture that includes squeeze and excitation (SE) modules. Hybrid distribution, region, and boundary-based losses (Unified Focal and Mumford-Shah (MS)) were utilized that showed the best performance compared to other combinations (p<0.05). Cross-validation between different centers, DLBCL and PMBCL cases, and three random splits were applied on train/validation data. The ensemble of these six models achieved a Dice similarity coefficient (DSC) of 0.77 +- 0.08 and Hausdorff distance (HD) of 16.5 +-12.5. Our 3D U-net model with SE modules for segmentation with hybrid loss performed significantly better (p<0.05) as compared to the 3D U-Net (without SE modules) using the same loss function (Unified Focal and MS loss) (DSC= 0.64 +-0.21 and HD= 26.3 +- 18.7). Our model can facilitate a fully automated quantification pipeline in a multi-center context that opens the possibility for routine reporting of total metabolic tumor volume (TMTV) and other metrics shown useful for the management of lymphoma." @default.
- W4289551005 created "2022-08-03" @default.
- W4289551005 creator A5009567562 @default.
- W4289551005 creator A5013315582 @default.
- W4289551005 creator A5032700631 @default.
- W4289551005 creator A5035649203 @default.
- W4289551005 creator A5040257052 @default.
- W4289551005 creator A5056135337 @default.
- W4289551005 creator A5058744346 @default.
- W4289551005 creator A5077969822 @default.
- W4289551005 creator A5078819407 @default.
- W4289551005 creator A5084855878 @default.
- W4289551005 creator A5085739405 @default.
- W4289551005 creator A5086508714 @default.
- W4289551005 date "2022-07-30" @default.
- W4289551005 modified "2023-09-27" @default.
- W4289551005 title "Convolutional neural network with a hybrid loss function for fully automated segmentation of lymphoma lesions in FDG PET images" @default.
- W4289551005 doi "https://doi.org/10.48550/arxiv.2208.00274" @default.
- W4289551005 hasPublicationYear "2022" @default.
- W4289551005 type Work @default.
- W4289551005 citedByCount "0" @default.
- W4289551005 crossrefType "posted-content" @default.
- W4289551005 hasAuthorship W4289551005A5009567562 @default.
- W4289551005 hasAuthorship W4289551005A5013315582 @default.
- W4289551005 hasAuthorship W4289551005A5032700631 @default.
- W4289551005 hasAuthorship W4289551005A5035649203 @default.
- W4289551005 hasAuthorship W4289551005A5040257052 @default.
- W4289551005 hasAuthorship W4289551005A5056135337 @default.
- W4289551005 hasAuthorship W4289551005A5058744346 @default.
- W4289551005 hasAuthorship W4289551005A5077969822 @default.
- W4289551005 hasAuthorship W4289551005A5078819407 @default.
- W4289551005 hasAuthorship W4289551005A5084855878 @default.
- W4289551005 hasAuthorship W4289551005A5085739405 @default.
- W4289551005 hasAuthorship W4289551005A5086508714 @default.
- W4289551005 hasBestOaLocation W42895510051 @default.
- W4289551005 hasConcept C124504099 @default.
- W4289551005 hasConcept C141898687 @default.
- W4289551005 hasConcept C142724271 @default.
- W4289551005 hasConcept C151730666 @default.
- W4289551005 hasConcept C153180895 @default.
- W4289551005 hasConcept C154945302 @default.
- W4289551005 hasConcept C163892561 @default.
- W4289551005 hasConcept C2778559949 @default.
- W4289551005 hasConcept C2779338263 @default.
- W4289551005 hasConcept C2779343474 @default.
- W4289551005 hasConcept C41008148 @default.
- W4289551005 hasConcept C64869954 @default.
- W4289551005 hasConcept C71924100 @default.
- W4289551005 hasConcept C81363708 @default.
- W4289551005 hasConcept C86803240 @default.
- W4289551005 hasConcept C89600930 @default.
- W4289551005 hasConceptScore W4289551005C124504099 @default.
- W4289551005 hasConceptScore W4289551005C141898687 @default.
- W4289551005 hasConceptScore W4289551005C142724271 @default.
- W4289551005 hasConceptScore W4289551005C151730666 @default.
- W4289551005 hasConceptScore W4289551005C153180895 @default.
- W4289551005 hasConceptScore W4289551005C154945302 @default.
- W4289551005 hasConceptScore W4289551005C163892561 @default.
- W4289551005 hasConceptScore W4289551005C2778559949 @default.
- W4289551005 hasConceptScore W4289551005C2779338263 @default.
- W4289551005 hasConceptScore W4289551005C2779343474 @default.
- W4289551005 hasConceptScore W4289551005C41008148 @default.
- W4289551005 hasConceptScore W4289551005C64869954 @default.
- W4289551005 hasConceptScore W4289551005C71924100 @default.
- W4289551005 hasConceptScore W4289551005C81363708 @default.
- W4289551005 hasConceptScore W4289551005C86803240 @default.
- W4289551005 hasConceptScore W4289551005C89600930 @default.
- W4289551005 hasLocation W42895510051 @default.
- W4289551005 hasOpenAccess W4289551005 @default.
- W4289551005 hasPrimaryLocation W42895510051 @default.
- W4289551005 hasRelatedWork W2415731916 @default.
- W4289551005 hasRelatedWork W2769435486 @default.
- W4289551005 hasRelatedWork W2979932740 @default.
- W4289551005 hasRelatedWork W2995422253 @default.
- W4289551005 hasRelatedWork W3012978760 @default.
- W4289551005 hasRelatedWork W3086857729 @default.
- W4289551005 hasRelatedWork W3201793090 @default.
- W4289551005 hasRelatedWork W4220959946 @default.
- W4289551005 hasRelatedWork W4221141253 @default.
- W4289551005 hasRelatedWork W4289551005 @default.
- W4289551005 isParatext "false" @default.
- W4289551005 isRetracted "false" @default.
- W4289551005 workType "article" @default.