FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3187782056> ?p ?o ?g. }

• W3187782056 abstract "Abstract Chest radiograph (CXR) interpretation is critical for the diagnosis of various thoracic diseases in pediatric patients. This task, however, is error-prone and requires a high level of understanding of radiologic expertise. Recently, deep convolutional neural networks (D-CNNs) have shown remarkable performance in interpreting CXR in adults. However, there is a lack of evidence indicating that D-CNNs can recognize accurately multiple lung pathologies from pediatric CXR scans. In particular, the development of diagnostic models for the detection of pediatric chest diseases faces significant challenges such as ( i ) lack of physician-annotated datasets and ( ii ) class imbalance problems. In this paper, we retrospectively collect a large dataset of 5,017 pediatric CXR scans, for which each is manually labeled by an experienced radiologist for the presence of 10 common pathologies. A D-CNN model is then trained on 3,550 annotated scans to classify multiple pediatric lung pathologies automatically. To address the highclass imbalance issue, we propose to modify and apply “Distribution-Balanced loss” for training D-CNNs which reshapes the standard Binary-Cross Entropy loss (BCE) to efficiently learn harder samples by down-weighting the loss assigned to the majority classes. On an independent test set of 777 studies, the proposed approach yields an area under the receiver operating characteristic (AUC) of 0.709 (95% CI, 0.690–0.729). The sensitivity, specificity, and F1-score at the cutoff value are 0.722 (0.694–0.750), 0.579 (0.563–0.595), and 0.389 (0.373–0.405), respectively. These results significantly outperform previous state-of-the-art methods on most of the target diseases. Moreover, our ablation studies validate the effectiveness of the proposed loss function compared to other standard losses, e.g., BCE and Focal Loss, for this learning task. Overall, we demonstrate the potential of D-CNNs in interpreting pediatric CXRs." @default.
• W3187782056 created "2021-08-16" @default.
• W3187782056 creator A5011328470 @default.
• W3187782056 creator A5023813361 @default.
• W3187782056 creator A5058447016 @default.
• W3187782056 creator A5060770511 @default.
• W3187782056 creator A5065112274 @default.
• W3187782056 creator A5083924160 @default.
• W3187782056 date "2021-08-13" @default.
• W3187782056 modified "2023-09-24" @default.
• W3187782056 title "Learning to Automatically Diagnose Multiple Diseases in Pediatric Chest Radiographs Using Deep Convolutional Neural Networks" @default.
• W3187782056 cites W1546561866 @default.
• W3187782056 cites W2108598243 @default.
• W3187782056 cites W2146241755 @default.
• W3187782056 cites W2152575748 @default.
• W3187782056 cites W2157203477 @default.
• W3187782056 cites W2746698216 @default.
• W3187782056 cites W2901794879 @default.
• W3187782056 cites W2901954625 @default.
• W3187782056 cites W2932985000 @default.
• W3187782056 cites W2956123709 @default.
• W3187782056 cites W2963446712 @default.
• W3187782056 cites W2963466845 @default.
• W3187782056 cites W2964054038 @default.
• W3187782056 cites W2998957378 @default.
• W3187782056 cites W3000716014 @default.
• W3187782056 cites W3015658722 @default.
• W3187782056 cites W3017309755 @default.
• W3187782056 cites W3023022608 @default.
• W3187782056 cites W3025815763 @default.
• W3187782056 cites W3035253074 @default.
• W3187782056 cites W3095576386 @default.
• W3187782056 cites W3095707208 @default.
• W3187782056 cites W3122459568 @default.
• W3187782056 doi "https://doi.org/10.1101/2021.08.12.21261954" @default.
• W3187782056 hasPublicationYear "2021" @default.
• W3187782056 type Work @default.
• W3187782056 sameAs 3187782056 @default.
• W3187782056 citedByCount "1" @default.
• W3187782056 countsByYear W31877820562022 @default.
• W3187782056 crossrefType "posted-content" @default.
• W3187782056 hasAuthorship W3187782056A5011328470 @default.
• W3187782056 hasAuthorship W3187782056A5023813361 @default.
• W3187782056 hasAuthorship W3187782056A5058447016 @default.
• W3187782056 hasAuthorship W3187782056A5060770511 @default.
• W3187782056 hasAuthorship W3187782056A5065112274 @default.
• W3187782056 hasAuthorship W3187782056A5083924160 @default.
• W3187782056 hasBestOaLocation W31877820561 @default.
• W3187782056 hasConcept C108583219 @default.
• W3187782056 hasConcept C119857082 @default.
• W3187782056 hasConcept C12267149 @default.
• W3187782056 hasConcept C126838900 @default.
• W3187782056 hasConcept C153180895 @default.
• W3187782056 hasConcept C154945302 @default.
• W3187782056 hasConcept C169903167 @default.
• W3187782056 hasConcept C183115368 @default.
• W3187782056 hasConcept C2781137159 @default.
• W3187782056 hasConcept C36454342 @default.
• W3187782056 hasConcept C41008148 @default.
• W3187782056 hasConcept C58471807 @default.
• W3187782056 hasConcept C66905080 @default.
• W3187782056 hasConcept C71924100 @default.
• W3187782056 hasConcept C81363708 @default.
• W3187782056 hasConceptScore W3187782056C108583219 @default.
• W3187782056 hasConceptScore W3187782056C119857082 @default.
• W3187782056 hasConceptScore W3187782056C12267149 @default.
• W3187782056 hasConceptScore W3187782056C126838900 @default.
• W3187782056 hasConceptScore W3187782056C153180895 @default.
• W3187782056 hasConceptScore W3187782056C154945302 @default.
• W3187782056 hasConceptScore W3187782056C169903167 @default.
• W3187782056 hasConceptScore W3187782056C183115368 @default.
• W3187782056 hasConceptScore W3187782056C2781137159 @default.
• W3187782056 hasConceptScore W3187782056C36454342 @default.
• W3187782056 hasConceptScore W3187782056C41008148 @default.
• W3187782056 hasConceptScore W3187782056C58471807 @default.
• W3187782056 hasConceptScore W3187782056C66905080 @default.
• W3187782056 hasConceptScore W3187782056C71924100 @default.
• W3187782056 hasConceptScore W3187782056C81363708 @default.
• W3187782056 hasLocation W31877820561 @default.
• W3187782056 hasLocation W31877820562 @default.
• W3187782056 hasOpenAccess W3187782056 @default.
• W3187782056 hasPrimaryLocation W31877820561 @default.
• W3187782056 hasRelatedWork W2530279937 @default.
• W3187782056 hasRelatedWork W2731899572 @default.
• W3187782056 hasRelatedWork W3019180786 @default.
• W3187782056 hasRelatedWork W3099765033 @default.
• W3187782056 hasRelatedWork W3133861977 @default.
• W3187782056 hasRelatedWork W4200173597 @default.
• W3187782056 hasRelatedWork W4221138918 @default.
• W3187782056 hasRelatedWork W4285703989 @default.
• W3187782056 hasRelatedWork W4312417841 @default.
• W3187782056 hasRelatedWork W4321369474 @default.
• W3187782056 isParatext "false" @default.
• W3187782056 isRetracted "false" @default.
• W3187782056 magId "3187782056" @default.
• W3187782056 workType "article" @default.