Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286561308> ?p ?o ?g. }
- W4286561308 abstract "Abstract Background We describe and evaluate a deep network algorithm which automatically contours organs at risk in the thorax and pelvis on computed tomography (CT) images for radiation treatment planning. Methods The algorithm identifies the region of interest (ROI) automatically by detecting anatomical landmarks around the specific organs using a deep reinforcement learning technique. The segmentation is restricted to this ROI and performed by a deep image-to-image network (DI2IN) based on a convolutional encoder-decoder architecture combined with multi-level feature concatenation. The algorithm is commercially available in the medical products “syngo.via RT Image Suite VB50” and “AI-Rad Companion Organs RT VA20” (Siemens Healthineers). For evaluation, thoracic CT images of 237 patients and pelvic CT images of 102 patients were manually contoured following the Radiation Therapy Oncology Group (RTOG) guidelines and compared to the DI2IN results using metrics for volume, overlap and distance, e.g., Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD 95 ). The contours were also compared visually slice by slice. Results We observed high correlations between automatic and manual contours. The best results were obtained for the lungs (DSC 0.97, HD 95 2.7 mm/2.9 mm for left/right lung), followed by heart (DSC 0.92, HD 95 4.4 mm), bladder (DSC 0.88, HD 95 6.7 mm) and rectum (DSC 0.79, HD 95 10.8 mm). Visual inspection showed excellent agreements with some exceptions for heart and rectum. Conclusions The DI2IN algorithm automatically generated contours for organs at risk close to those by a human expert, making the contouring step in radiation treatment planning simpler and faster. Few cases still required manual corrections, mainly for heart and rectum." @default.
- W4286561308 created "2022-07-22" @default.
- W4286561308 creator A5004320806 @default.
- W4286561308 creator A5006734660 @default.
- W4286561308 creator A5012682914 @default.
- W4286561308 creator A5015910933 @default.
- W4286561308 creator A5016715976 @default.
- W4286561308 creator A5019884467 @default.
- W4286561308 creator A5028391029 @default.
- W4286561308 creator A5038323479 @default.
- W4286561308 creator A5040858678 @default.
- W4286561308 creator A5060575327 @default.
- W4286561308 creator A5061499646 @default.
- W4286561308 creator A5065547065 @default.
- W4286561308 creator A5070820517 @default.
- W4286561308 creator A5086762445 @default.
- W4286561308 creator A5087446167 @default.
- W4286561308 date "2022-07-22" @default.
- W4286561308 modified "2023-10-16" @default.
- W4286561308 title "A deep image-to-image network organ segmentation algorithm for radiation treatment planning: principles and evaluation" @default.
- W4286561308 cites W1901129140 @default.
- W4286561308 cites W1977860701 @default.
- W4286561308 cites W1982441646 @default.
- W4286561308 cites W1982668309 @default.
- W4286561308 cites W1984483689 @default.
- W4286561308 cites W2007733896 @default.
- W4286561308 cites W2028344184 @default.
- W4286561308 cites W2065493387 @default.
- W4286561308 cites W2082030252 @default.
- W4286561308 cites W2115051059 @default.
- W4286561308 cites W2153409462 @default.
- W4286561308 cites W2153431772 @default.
- W4286561308 cites W2416980609 @default.
- W4286561308 cites W2477265066 @default.
- W4286561308 cites W2502594064 @default.
- W4286561308 cites W2560725027 @default.
- W4286561308 cites W2738232076 @default.
- W4286561308 cites W2771590529 @default.
- W4286561308 cites W2773960327 @default.
- W4286561308 cites W2801722003 @default.
- W4286561308 cites W2889615630 @default.
- W4286561308 cites W2899427548 @default.
- W4286561308 cites W2900237898 @default.
- W4286561308 cites W2920206089 @default.
- W4286561308 cites W2921146673 @default.
- W4286561308 cites W2922812404 @default.
- W4286561308 cites W2941434555 @default.
- W4286561308 cites W2986021933 @default.
- W4286561308 cites W3027961002 @default.
- W4286561308 doi "https://doi.org/10.1186/s13014-022-02102-6" @default.
- W4286561308 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35869525" @default.
- W4286561308 hasPublicationYear "2022" @default.
- W4286561308 type Work @default.
- W4286561308 citedByCount "4" @default.
- W4286561308 countsByYear W42865613082022 @default.
- W4286561308 countsByYear W42865613082023 @default.
- W4286561308 crossrefType "journal-article" @default.
- W4286561308 hasAuthorship W4286561308A5004320806 @default.
- W4286561308 hasAuthorship W4286561308A5006734660 @default.
- W4286561308 hasAuthorship W4286561308A5012682914 @default.
- W4286561308 hasAuthorship W4286561308A5015910933 @default.
- W4286561308 hasAuthorship W4286561308A5016715976 @default.
- W4286561308 hasAuthorship W4286561308A5019884467 @default.
- W4286561308 hasAuthorship W4286561308A5028391029 @default.
- W4286561308 hasAuthorship W4286561308A5038323479 @default.
- W4286561308 hasAuthorship W4286561308A5040858678 @default.
- W4286561308 hasAuthorship W4286561308A5060575327 @default.
- W4286561308 hasAuthorship W4286561308A5061499646 @default.
- W4286561308 hasAuthorship W4286561308A5065547065 @default.
- W4286561308 hasAuthorship W4286561308A5070820517 @default.
- W4286561308 hasAuthorship W4286561308A5086762445 @default.
- W4286561308 hasAuthorship W4286561308A5087446167 @default.
- W4286561308 hasBestOaLocation W42865613081 @default.
- W4286561308 hasConcept C108583219 @default.
- W4286561308 hasConcept C11413529 @default.
- W4286561308 hasConcept C126838900 @default.
- W4286561308 hasConcept C141071460 @default.
- W4286561308 hasConcept C141898687 @default.
- W4286561308 hasConcept C154945302 @default.
- W4286561308 hasConcept C19609008 @default.
- W4286561308 hasConcept C201645570 @default.
- W4286561308 hasConcept C2781074409 @default.
- W4286561308 hasConcept C2989005 @default.
- W4286561308 hasConcept C41008148 @default.
- W4286561308 hasConcept C509974204 @default.
- W4286561308 hasConcept C71924100 @default.
- W4286561308 hasConcept C89600930 @default.
- W4286561308 hasConceptScore W4286561308C108583219 @default.
- W4286561308 hasConceptScore W4286561308C11413529 @default.
- W4286561308 hasConceptScore W4286561308C126838900 @default.
- W4286561308 hasConceptScore W4286561308C141071460 @default.
- W4286561308 hasConceptScore W4286561308C141898687 @default.
- W4286561308 hasConceptScore W4286561308C154945302 @default.
- W4286561308 hasConceptScore W4286561308C19609008 @default.
- W4286561308 hasConceptScore W4286561308C201645570 @default.
- W4286561308 hasConceptScore W4286561308C2781074409 @default.
- W4286561308 hasConceptScore W4286561308C2989005 @default.
- W4286561308 hasConceptScore W4286561308C41008148 @default.
- W4286561308 hasConceptScore W4286561308C509974204 @default.
- W4286561308 hasConceptScore W4286561308C71924100 @default.