FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209258301> ?p ?o ?g. }

• W3209258301 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 high-class 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.
• W3209258301 created "2021-11-08" @default.
• W3209258301 creator A5011328470 @default.
• W3209258301 creator A5023813361 @default.
• W3209258301 creator A5058447016 @default.
• W3209258301 creator A5060770511 @default.
• W3209258301 creator A5065112274 @default.
• W3209258301 creator A5083924160 @default.
• W3209258301 date "2021-10-01" @default.
• W3209258301 modified "2023-09-25" @default.
• W3209258301 title "Learning to Automatically Diagnose Multiple Diseases in Pediatric Chest Radiographs Using Deep Convolutional Neural Networks" @default.
• W3209258301 cites W1546561866 @default.
• W3209258301 cites W2108598243 @default.
• W3209258301 cites W2114315281 @default.
• W3209258301 cites W2146241755 @default.
• W3209258301 cites W2152575748 @default.
• W3209258301 cites W2157203477 @default.
• W3209258301 cites W2194775991 @default.
• W3209258301 cites W2746698216 @default.
• W3209258301 cites W2801837154 @default.
• W3209258301 cites W2901794879 @default.
• W3209258301 cites W2901954625 @default.
• W3209258301 cites W2913240367 @default.
• W3209258301 cites W2922477549 @default.
• W3209258301 cites W2932985000 @default.
• W3209258301 cites W2956123709 @default.
• W3209258301 cites W2962838801 @default.
• W3209258301 cites W2963351448 @default.
• W3209258301 cites W2963446712 @default.
• W3209258301 cites W2963466845 @default.
• W3209258301 cites W2964054038 @default.
• W3209258301 cites W2998957378 @default.
• W3209258301 cites W3000716014 @default.
• W3209258301 cites W3015658722 @default.
• W3209258301 cites W3017309755 @default.
• W3209258301 cites W3023022608 @default.
• W3209258301 cites W3025815763 @default.
• W3209258301 cites W3035253074 @default.
• W3209258301 cites W3093018928 @default.
• W3209258301 cites W3102564565 @default.
• W3209258301 cites W3122459568 @default.
• W3209258301 doi "https://doi.org/10.1109/iccvw54120.2021.00370" @default.
• W3209258301 hasPublicationYear "2021" @default.
• W3209258301 type Work @default.
• W3209258301 sameAs 3209258301 @default.
• W3209258301 citedByCount "5" @default.
• W3209258301 countsByYear W32092583012022 @default.
• W3209258301 countsByYear W32092583012023 @default.
• W3209258301 crossrefType "proceedings-article" @default.
• W3209258301 hasAuthorship W3209258301A5011328470 @default.
• W3209258301 hasAuthorship W3209258301A5023813361 @default.
• W3209258301 hasAuthorship W3209258301A5058447016 @default.
• W3209258301 hasAuthorship W3209258301A5060770511 @default.
• W3209258301 hasAuthorship W3209258301A5065112274 @default.
• W3209258301 hasAuthorship W3209258301A5083924160 @default.
• W3209258301 hasBestOaLocation W32092583012 @default.
• W3209258301 hasConcept C108583219 @default.
• W3209258301 hasConcept C119857082 @default.
• W3209258301 hasConcept C12267149 @default.
• W3209258301 hasConcept C126838900 @default.
• W3209258301 hasConcept C153180895 @default.
• W3209258301 hasConcept C154945302 @default.
• W3209258301 hasConcept C169903167 @default.
• W3209258301 hasConcept C183115368 @default.
• W3209258301 hasConcept C2781137159 @default.
• W3209258301 hasConcept C36454342 @default.
• W3209258301 hasConcept C41008148 @default.
• W3209258301 hasConcept C58471807 @default.
• W3209258301 hasConcept C66905080 @default.
• W3209258301 hasConcept C71924100 @default.
• W3209258301 hasConcept C81363708 @default.
• W3209258301 hasConceptScore W3209258301C108583219 @default.
• W3209258301 hasConceptScore W3209258301C119857082 @default.
• W3209258301 hasConceptScore W3209258301C12267149 @default.
• W3209258301 hasConceptScore W3209258301C126838900 @default.
• W3209258301 hasConceptScore W3209258301C153180895 @default.
• W3209258301 hasConceptScore W3209258301C154945302 @default.
• W3209258301 hasConceptScore W3209258301C169903167 @default.
• W3209258301 hasConceptScore W3209258301C183115368 @default.
• W3209258301 hasConceptScore W3209258301C2781137159 @default.
• W3209258301 hasConceptScore W3209258301C36454342 @default.
• W3209258301 hasConceptScore W3209258301C41008148 @default.
• W3209258301 hasConceptScore W3209258301C58471807 @default.
• W3209258301 hasConceptScore W3209258301C66905080 @default.
• W3209258301 hasConceptScore W3209258301C71924100 @default.
• W3209258301 hasConceptScore W3209258301C81363708 @default.
• W3209258301 hasLocation W32092583011 @default.
• W3209258301 hasLocation W32092583012 @default.
• W3209258301 hasLocation W32092583013 @default.
• W3209258301 hasOpenAccess W3209258301 @default.
• W3209258301 hasPrimaryLocation W32092583011 @default.
• W3209258301 hasRelatedWork W2530279937 @default.
• W3209258301 hasRelatedWork W2731899572 @default.
• W3209258301 hasRelatedWork W3019180786 @default.
• W3209258301 hasRelatedWork W3099765033 @default.
• W3209258301 hasRelatedWork W3133861977 @default.
• W3209258301 hasRelatedWork W4200173597 @default.
• W3209258301 hasRelatedWork W4221138918 @default.
• W3209258301 hasRelatedWork W4285703989 @default.
• W3209258301 hasRelatedWork W4312417841 @default.

• next