FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136618371> ?p ?o ?g. }

• W3136618371 abstract "With the rapid growth and increasing use of brain MRI, there is an interest in automated image classification to aid human interpretation and improve workflow. We aimed to train a deep convolutional neural network and assess its performance in identifying abnormal brain MRIs and critical intracranial findings including acute infarction, acute hemorrhage and mass effect. A total of 13,215 clinical brain MRI studies were categorized to training (74%), validation (9%), internal testing (8%) and external testing (8%) datasets. Up to eight contrasts were included from each brain MRI and each image volume was reformatted to common resolution to accommodate for differences between scanners. Following reviewing the radiology reports, three neuroradiologists assigned each study to abnormal vs normal, and identified three critical findings including acute infarction, acute hemorrhage, and mass effect. A deep convolutional neural network was constructed by a combination of localization feature extraction (LFE) modules and global classifiers to identify the presence of 4 variables in brain MRIs including abnormal, acute infarction, acute hemorrhage and mass effect. Training, validation and testing sets were randomly defined on a patient basis. Training was performed on 9845 studies using balanced sampling to address class imbalance. Receiver operating characteristic (ROC) analysis was performed. The ROC analysis of our models for 1050 studies within our internal test data showed AUC/sensitivity/specificity of 0.91/83%/86% for normal versus abnormal brain MRI, 0.95/92%/88% for acute infarction, 0.90/89%/81% for acute hemorrhage, and 0.93/93%/85% for mass effect. For 1072 studies within our external test data, it showed AUC/sensitivity/specificity of 0.88/80%/80% for normal versus abnormal brain MRI, 0.97/90%/97% for acute infarction, 0.83/72%/88% for acute hemorrhage, and 0.87/79%/81% for mass effect. Our proposed deep convolutional network can accurately identify abnormal and critical intracranial findings on individual brain MRIs, while addressing the fact that some MR contrasts might not be available in individual studies." @default.
• W3136618371 created "2021-03-29" @default.
• W3136618371 creator A5001522611 @default.
• W3136618371 creator A5011888340 @default.
• W3136618371 creator A5012751147 @default.
• W3136618371 creator A5013218779 @default.
• W3136618371 creator A5017606290 @default.
• W3136618371 creator A5020165775 @default.
• W3136618371 creator A5025274219 @default.
• W3136618371 creator A5029200200 @default.
• W3136618371 creator A5031310336 @default.
• W3136618371 creator A5040302301 @default.
• W3136618371 creator A5040894533 @default.
• W3136618371 creator A5054596824 @default.
• W3136618371 creator A5055448355 @default.
• W3136618371 creator A5070157093 @default.
• W3136618371 creator A5074300820 @default.
• W3136618371 creator A5075801763 @default.
• W3136618371 creator A5076638731 @default.
• W3136618371 creator A5082339536 @default.
• W3136618371 creator A5084958871 @default.
• W3136618371 creator A5086739048 @default.
• W3136618371 creator A5089434484 @default.
• W3136618371 date "2021-03-25" @default.
• W3136618371 modified "2023-10-06" @default.
• W3136618371 title "Automated detection of critical findings in multi-parametric brain MRI using a system of 3D neural networks" @default.
• W3136618371 cites W131526450 @default.
• W3136618371 cites W1790909941 @default.
• W3136618371 cites W1991295948 @default.
• W3136618371 cites W2011506481 @default.
• W3136618371 cites W2017896827 @default.
• W3136618371 cites W2038344945 @default.
• W3136618371 cites W2070896918 @default.
• W3136618371 cites W2075710390 @default.
• W3136618371 cites W2087030179 @default.
• W3136618371 cites W2090680978 @default.
• W3136618371 cites W2094585602 @default.
• W3136618371 cites W2136587148 @default.
• W3136618371 cites W2153567216 @default.
• W3136618371 cites W2475249440 @default.
• W3136618371 cites W2520127694 @default.
• W3136618371 cites W2561981131 @default.
• W3136618371 cites W2592929672 @default.
• W3136618371 cites W2607941059 @default.
• W3136618371 cites W2626711511 @default.
• W3136618371 cites W2725984455 @default.
• W3136618371 cites W2738232076 @default.
• W3136618371 cites W2770835535 @default.
• W3136618371 cites W2780099243 @default.
• W3136618371 cites W2795774310 @default.
• W3136618371 cites W2883545264 @default.
• W3136618371 cites W2896817483 @default.
• W3136618371 cites W2906302663 @default.
• W3136618371 cites W2906374901 @default.
• W3136618371 cites W2963222567 @default.
• W3136618371 cites W2979487364 @default.
• W3136618371 doi "https://doi.org/10.1038/s41598-021-86022-7" @default.
• W3136618371 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7994311" @default.
• W3136618371 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33767226" @default.
• W3136618371 hasPublicationYear "2021" @default.
• W3136618371 type Work @default.
• W3136618371 sameAs 3136618371 @default.
• W3136618371 citedByCount "11" @default.
• W3136618371 countsByYear W31366183712021 @default.
• W3136618371 countsByYear W31366183712022 @default.
• W3136618371 countsByYear W31366183712023 @default.
• W3136618371 crossrefType "journal-article" @default.
• W3136618371 hasAuthorship W3136618371A5001522611 @default.
• W3136618371 hasAuthorship W3136618371A5011888340 @default.
• W3136618371 hasAuthorship W3136618371A5012751147 @default.
• W3136618371 hasAuthorship W3136618371A5013218779 @default.
• W3136618371 hasAuthorship W3136618371A5017606290 @default.
• W3136618371 hasAuthorship W3136618371A5020165775 @default.
• W3136618371 hasAuthorship W3136618371A5025274219 @default.
• W3136618371 hasAuthorship W3136618371A5029200200 @default.
• W3136618371 hasAuthorship W3136618371A5031310336 @default.
• W3136618371 hasAuthorship W3136618371A5040302301 @default.
• W3136618371 hasAuthorship W3136618371A5040894533 @default.
• W3136618371 hasAuthorship W3136618371A5054596824 @default.
• W3136618371 hasAuthorship W3136618371A5055448355 @default.
• W3136618371 hasAuthorship W3136618371A5070157093 @default.
• W3136618371 hasAuthorship W3136618371A5074300820 @default.
• W3136618371 hasAuthorship W3136618371A5075801763 @default.
• W3136618371 hasAuthorship W3136618371A5076638731 @default.
• W3136618371 hasAuthorship W3136618371A5082339536 @default.
• W3136618371 hasAuthorship W3136618371A5084958871 @default.
• W3136618371 hasAuthorship W3136618371A5086739048 @default.
• W3136618371 hasAuthorship W3136618371A5089434484 @default.
• W3136618371 hasBestOaLocation W31366183711 @default.
• W3136618371 hasConcept C126322002 @default.
• W3136618371 hasConcept C126838900 @default.
• W3136618371 hasConcept C143409427 @default.
• W3136618371 hasConcept C154945302 @default.
• W3136618371 hasConcept C2777798775 @default.
• W3136618371 hasConcept C41008148 @default.
• W3136618371 hasConcept C500558357 @default.
• W3136618371 hasConcept C58471807 @default.
• W3136618371 hasConcept C71924100 @default.
• W3136618371 hasConcept C81363708 @default.
• W3136618371 hasConceptScore W3136618371C126322002 @default.

• next