Matches in SemOpenAlex for { <https://semopenalex.org/work/W4282938761> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4282938761 endingPage "455" @default.
- W4282938761 startingPage "455" @default.
- W4282938761 abstract "We investigated the feasibility of measuring the hydronephrosis area to renal parenchyma (HARP) ratio from ultrasound images using a deep-learning network.The coronal renal ultrasound images of 195 pediatric and adolescent patients who underwent pyeloplasty to repair ureteropelvic junction obstruction were retrospectively reviewed. After excluding cases without a representative longitudinal renal image, we used a dataset of 168 images for deep-learning segmentation. Ten novel networks, such as combinations of DeepLabV3+ and UNet++, were assessed for their ability to calculate hydronephrosis and kidney areas, and the ensemble method was applied for further improvement. By dividing the image set into four, cross-validation was conducted, and the segmentation performance of the deep-learning network was evaluated using sensitivity, specificity, and dice similarity coefficients by comparison with the manually traced area.All 10 networks and ensemble methods showed good visual correlation with the manually traced kidney and hydronephrosis areas. The dice similarity coefficient of the 10-model ensemble was 0.9108 on average, and the best 5-model ensemble had a dice similarity coefficient of 0.9113 on average. We included patients with severe hydronephrosis who underwent renal ultrasonography at a single institution; thus, external validation of our algorithm in a heterogeneous ultrasonography examination setup with a diverse set of instruments is recommended.Deep-learning-based calculation of the HARP ratio is feasible and showed high accuracy for imaging of the severity of hydronephrosis using ultrasonography. This algorithm can help physicians make more accurate and reproducible diagnoses of hydronephrosis using ultrasonography." @default.
- W4282938761 created "2022-06-16" @default.
- W4282938761 creator A5000980947 @default.
- W4282938761 creator A5028898025 @default.
- W4282938761 creator A5042149207 @default.
- W4282938761 creator A5066043989 @default.
- W4282938761 creator A5080229165 @default.
- W4282938761 creator A5081219590 @default.
- W4282938761 creator A5087652733 @default.
- W4282938761 date "2022-01-01" @default.
- W4282938761 modified "2023-10-02" @default.
- W4282938761 title "Deep-learning segmentation of ultrasound images for automated calculation of the hydronephrosis area to renal parenchyma ratio" @default.
- W4282938761 cites W1917483584 @default.
- W4282938761 cites W1960255425 @default.
- W4282938761 cites W2027509324 @default.
- W4282938761 cites W2114849661 @default.
- W4282938761 cites W2425644800 @default.
- W4282938761 cites W2528706105 @default.
- W4282938761 cites W2884436604 @default.
- W4282938761 cites W2928165649 @default.
- W4282938761 cites W2941964694 @default.
- W4282938761 cites W2959828872 @default.
- W4282938761 cites W2999205267 @default.
- W4282938761 cites W3002592716 @default.
- W4282938761 cites W3038276577 @default.
- W4282938761 cites W3081020615 @default.
- W4282938761 cites W3082577495 @default.
- W4282938761 cites W3178233354 @default.
- W4282938761 doi "https://doi.org/10.4111/icu.20220085" @default.
- W4282938761 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35670007" @default.
- W4282938761 hasPublicationYear "2022" @default.
- W4282938761 type Work @default.
- W4282938761 citedByCount "4" @default.
- W4282938761 countsByYear W42829387612023 @default.
- W4282938761 crossrefType "journal-article" @default.
- W4282938761 hasAuthorship W4282938761A5000980947 @default.
- W4282938761 hasAuthorship W4282938761A5028898025 @default.
- W4282938761 hasAuthorship W4282938761A5042149207 @default.
- W4282938761 hasAuthorship W4282938761A5066043989 @default.
- W4282938761 hasAuthorship W4282938761A5080229165 @default.
- W4282938761 hasAuthorship W4282938761A5081219590 @default.
- W4282938761 hasAuthorship W4282938761A5087652733 @default.
- W4282938761 hasBestOaLocation W42829387611 @default.
- W4282938761 hasConcept C105702510 @default.
- W4282938761 hasConcept C124504099 @default.
- W4282938761 hasConcept C126838900 @default.
- W4282938761 hasConcept C143753070 @default.
- W4282938761 hasConcept C154945302 @default.
- W4282938761 hasConcept C163892561 @default.
- W4282938761 hasConcept C2781040948 @default.
- W4282938761 hasConcept C41008148 @default.
- W4282938761 hasConcept C71924100 @default.
- W4282938761 hasConcept C77411442 @default.
- W4282938761 hasConcept C89600930 @default.
- W4282938761 hasConceptScore W4282938761C105702510 @default.
- W4282938761 hasConceptScore W4282938761C124504099 @default.
- W4282938761 hasConceptScore W4282938761C126838900 @default.
- W4282938761 hasConceptScore W4282938761C143753070 @default.
- W4282938761 hasConceptScore W4282938761C154945302 @default.
- W4282938761 hasConceptScore W4282938761C163892561 @default.
- W4282938761 hasConceptScore W4282938761C2781040948 @default.
- W4282938761 hasConceptScore W4282938761C41008148 @default.
- W4282938761 hasConceptScore W4282938761C71924100 @default.
- W4282938761 hasConceptScore W4282938761C77411442 @default.
- W4282938761 hasConceptScore W4282938761C89600930 @default.
- W4282938761 hasFunder F4320322107 @default.
- W4282938761 hasFunder F4320323011 @default.
- W4282938761 hasIssue "4" @default.
- W4282938761 hasLocation W42829387611 @default.
- W4282938761 hasLocation W42829387612 @default.
- W4282938761 hasLocation W42829387613 @default.
- W4282938761 hasOpenAccess W4282938761 @default.
- W4282938761 hasPrimaryLocation W42829387611 @default.
- W4282938761 hasRelatedWork W134976887 @default.
- W4282938761 hasRelatedWork W1582206143 @default.
- W4282938761 hasRelatedWork W2138214894 @default.
- W4282938761 hasRelatedWork W2402817811 @default.
- W4282938761 hasRelatedWork W2464972745 @default.
- W4282938761 hasRelatedWork W2734888972 @default.
- W4282938761 hasRelatedWork W2999580839 @default.
- W4282938761 hasRelatedWork W3027394838 @default.
- W4282938761 hasRelatedWork W3161321444 @default.
- W4282938761 hasRelatedWork W4376624981 @default.
- W4282938761 hasVolume "63" @default.
- W4282938761 isParatext "false" @default.
- W4282938761 isRetracted "false" @default.
- W4282938761 workType "article" @default.