Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384157150> ?p ?o ?g. }
- W4384157150 endingPage "102882" @default.
- W4384157150 startingPage "102882" @default.
- W4384157150 abstract "We present a novel computer algorithm to automatically detect and segment pulmonary embolisms (PEs) on computed tomography pulmonary angiography (CTPA). This algorithm is based on deep learning but does not require manual outlines of the PE regions. Given a CTPA scan, both intra- and extra-pulmonary arteries were firstly segmented. The arteries were then partitioned into several parts based on size (radius). Adaptive thresholding and constrained morphological operations were used to identify suspicious PE regions within each part. The confidence of a suspicious region to be PE was scored based on its contrast in the arteries. This approach was applied to the publicly available RSNA Pulmonary Embolism CT Dataset (RSNA-PE) to identify three-dimensional (3-D) PE negative and positive image patches, which were used to train a 3-D Recurrent Residual U-Net (R2-Unet) to automatically segment PE. The feasibility of this computer algorithm was validated on an independent test set consisting of 91 CTPA scans acquired from a different medical institute, where the PE regions were manually located and outlined by a thoracic radiologist (>18 years' experience). An R2-Unet model was also trained and validated on the manual outlines using a 5-fold cross-validation method. The CNN model trained on the high-confident PE regions showed a Dice coefficient of 0.676±0.168 and a false positive rate of 1.86 per CT scan, while the CNN model trained on the manual outlines demonstrated a Dice coefficient of 0.647±0.192 and a false positive rate of 4.20 per CT scan. The former model performed significantly better than the latter model (p<0.01). The promising performance of the developed PE detection and segmentation algorithm suggests the feasibility of training a deep learning network without dedicating significant efforts to manual annotations of the PE regions on CTPA scans." @default.
- W4384157150 created "2023-07-14" @default.
- W4384157150 creator A5002457632 @default.
- W4384157150 creator A5006752343 @default.
- W4384157150 creator A5023527328 @default.
- W4384157150 creator A5031125243 @default.
- W4384157150 creator A5031499770 @default.
- W4384157150 creator A5041650010 @default.
- W4384157150 creator A5065866225 @default.
- W4384157150 creator A5068216869 @default.
- W4384157150 creator A5083749577 @default.
- W4384157150 date "2023-10-01" @default.
- W4384157150 modified "2023-10-17" @default.
- W4384157150 title "Automated detection and segmentation of pulmonary embolisms on computed tomography pulmonary angiography (CTPA) using deep learning but without manual outlining" @default.
- W4384157150 cites W1637661457 @default.
- W4384157150 cites W1901129140 @default.
- W4384157150 cites W1964181473 @default.
- W4384157150 cites W1965039247 @default.
- W4384157150 cites W1993785915 @default.
- W4384157150 cites W1999244633 @default.
- W4384157150 cites W2002754201 @default.
- W4384157150 cites W2011612504 @default.
- W4384157150 cites W2027003306 @default.
- W4384157150 cites W2032770855 @default.
- W4384157150 cites W2035584525 @default.
- W4384157150 cites W2040934840 @default.
- W4384157150 cites W2049279157 @default.
- W4384157150 cites W2065716674 @default.
- W4384157150 cites W2070461514 @default.
- W4384157150 cites W2088026962 @default.
- W4384157150 cites W2093114008 @default.
- W4384157150 cites W2112295276 @default.
- W4384157150 cites W2120268328 @default.
- W4384157150 cites W2120989355 @default.
- W4384157150 cites W2168732003 @default.
- W4384157150 cites W2213701027 @default.
- W4384157150 cites W2345716184 @default.
- W4384157150 cites W2778232801 @default.
- W4384157150 cites W2800884849 @default.
- W4384157150 cites W2888185784 @default.
- W4384157150 cites W2902537990 @default.
- W4384157150 cites W2923997689 @default.
- W4384157150 cites W2954494473 @default.
- W4384157150 cites W2964135926 @default.
- W4384157150 cites W2966744887 @default.
- W4384157150 cites W2968152933 @default.
- W4384157150 cites W3018185338 @default.
- W4384157150 cites W3039113409 @default.
- W4384157150 cites W3103194435 @default.
- W4384157150 cites W3112701542 @default.
- W4384157150 cites W3119904398 @default.
- W4384157150 cites W3123661268 @default.
- W4384157150 cites W3159010703 @default.
- W4384157150 cites W3167877233 @default.
- W4384157150 cites W3181748866 @default.
- W4384157150 cites W4206643511 @default.
- W4384157150 cites W4220661517 @default.
- W4384157150 cites W4220815429 @default.
- W4384157150 cites W4280573806 @default.
- W4384157150 cites W4281384031 @default.
- W4384157150 cites W4288712241 @default.
- W4384157150 cites W4293103839 @default.
- W4384157150 cites W4318464713 @default.
- W4384157150 doi "https://doi.org/10.1016/j.media.2023.102882" @default.
- W4384157150 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37482032" @default.
- W4384157150 hasPublicationYear "2023" @default.
- W4384157150 type Work @default.
- W4384157150 citedByCount "0" @default.
- W4384157150 crossrefType "journal-article" @default.
- W4384157150 hasAuthorship W4384157150A5002457632 @default.
- W4384157150 hasAuthorship W4384157150A5006752343 @default.
- W4384157150 hasAuthorship W4384157150A5023527328 @default.
- W4384157150 hasAuthorship W4384157150A5031125243 @default.
- W4384157150 hasAuthorship W4384157150A5031499770 @default.
- W4384157150 hasAuthorship W4384157150A5041650010 @default.
- W4384157150 hasAuthorship W4384157150A5065866225 @default.
- W4384157150 hasAuthorship W4384157150A5068216869 @default.
- W4384157150 hasAuthorship W4384157150A5083749577 @default.
- W4384157150 hasConcept C115961682 @default.
- W4384157150 hasConcept C119857082 @default.
- W4384157150 hasConcept C124504099 @default.
- W4384157150 hasConcept C126838900 @default.
- W4384157150 hasConcept C141071460 @default.
- W4384157150 hasConcept C153180895 @default.
- W4384157150 hasConcept C154945302 @default.
- W4384157150 hasConcept C163864269 @default.
- W4384157150 hasConcept C163892561 @default.
- W4384157150 hasConcept C191178318 @default.
- W4384157150 hasConcept C2776265017 @default.
- W4384157150 hasConcept C2780149156 @default.
- W4384157150 hasConcept C2781347138 @default.
- W4384157150 hasConcept C41008148 @default.
- W4384157150 hasConcept C544519230 @default.
- W4384157150 hasConcept C71924100 @default.
- W4384157150 hasConcept C89600930 @default.
- W4384157150 hasConceptScore W4384157150C115961682 @default.
- W4384157150 hasConceptScore W4384157150C119857082 @default.
- W4384157150 hasConceptScore W4384157150C124504099 @default.