FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308142133> ?p ?o ?g. }

• W4308142133 endingPage "A852" @default.
• W4308142133 startingPage "A852" @default.
• W4308142133 abstract "Abstract Purpose To evaluate deep learning analysis of thyroid nodule ultrasound images as a rule-out test for thyroid malignancy. Methods Supervised deep learning (DL) classifier of thyroid nodules was trained on 32,545 thyroid US images from 621 nodules representing all major benign and malignant types of thyroid lesions and tested on an independent set of 145 nodules collected at a different healthcare system in the United States. The Big Transfer BiT-M ResNet-50×1 convolutional neural net architecture was modified to contain 3, 4, 6 and 3 PreActBottleneck units per block 1 through 4. Weights pretrained on the ImageNet-21k dataset were loaded and weights for blocks 3 and 4 were fine-tuned for the binary classification task of distinguishing benign and malignant thyroid nodules. Results The deep learning thyroid nodule classifier achieved an area under receiver operating characteristic curve (AUROC) of 0.889 on five-fold cross-validation. The AUROC improved when images were scaled by nodule size and six randomly selected cine clip frames were added to the training set per epoch. GradCAM class activation heatmaps revealed that microcalcifications and spongiform appearance were reliably recognized by the classifier as malignant and benign features, respectively. Spongiform nodules were found to be benign even when microcystic spaces constituted less than 50% of nodule volume. To investigate the clinical relevance of the benign vs. malignant classifier, the binary classification threshold for the probability of malignancy generated by model was set at 7% to achieve sensitivity and negative predictive value (NPV) comparable to that of the fine needle aspiration biopsy (FNA). At this threshold, cross-validated deep-learning model achieved a sensitivity of 90%, specificity of 63%, positive predictive value (PPV) of 46% and negative predictive value of 94%. When tested on an independent image set that includes 18 classic papillary thyroid cancers (PTC), 5 follicular variant PTC, 4 medullary thyroid cancers, 3 follicular thyroid cancers (FTC), and 1 Hurthle cell thyroid cancer, the DL classifier achieved AUROC of 0.88, sensitivity of 97%, specificity of 61%, PPV of 40% and NPV of 99%. A single minimally-invasive FTC that had no suspicious features on thyroid ultrasound was incorrectly classified as benign. Conclusions This study demonstrates that the ultrasound-based deep-learning classifier of thyroid nodules achieves sensitivity and negative predictive value comparable to that of thyroid fine needle aspiration (FNA). Clinicians may use this tool to augment clinical judgment when determining whether to perform FNA procedures. Presentation: Saturday, June 11, 2022 1:00 p.m. - 3:00 p.m., Saturday, June 11, 2022 1:06 p.m. - 1:11 p.m." @default.
• W4308142133 created "2022-11-08" @default.
• W4308142133 creator A5001003453 @default.
• W4308142133 creator A5018764559 @default.
• W4308142133 creator A5020434909 @default.
• W4308142133 creator A5050257344 @default.
• W4308142133 creator A5051096329 @default.
• W4308142133 creator A5057636900 @default.
• W4308142133 creator A5071178113 @default.
• W4308142133 creator A5073085667 @default.
• W4308142133 date "2022-11-01" @default.
• W4308142133 modified "2023-10-06" @default.
• W4308142133 title "RF11 | PSAT234 Deep learning analysis of thyroid nodule ultrasound images has high sensitivity and negative predictive value to rule-out thyroid cancer" @default.
• W4308142133 doi "https://doi.org/10.1210/jendso/bvac150.1762" @default.
• W4308142133 hasPublicationYear "2022" @default.
• W4308142133 type Work @default.
• W4308142133 citedByCount "0" @default.
• W4308142133 crossrefType "journal-article" @default.
• W4308142133 hasAuthorship W4308142133A5001003453 @default.
• W4308142133 hasAuthorship W4308142133A5018764559 @default.
• W4308142133 hasAuthorship W4308142133A5020434909 @default.
• W4308142133 hasAuthorship W4308142133A5050257344 @default.
• W4308142133 hasAuthorship W4308142133A5051096329 @default.
• W4308142133 hasAuthorship W4308142133A5057636900 @default.
• W4308142133 hasAuthorship W4308142133A5071178113 @default.
• W4308142133 hasAuthorship W4308142133A5073085667 @default.
• W4308142133 hasBestOaLocation W43081421331 @default.
• W4308142133 hasConcept C12267149 @default.
• W4308142133 hasConcept C126322002 @default.
• W4308142133 hasConcept C126838900 @default.
• W4308142133 hasConcept C142724271 @default.
• W4308142133 hasConcept C151730666 @default.
• W4308142133 hasConcept C153180895 @default.
• W4308142133 hasConcept C154945302 @default.
• W4308142133 hasConcept C2776731575 @default.
• W4308142133 hasConcept C2779022025 @default.
• W4308142133 hasConcept C2779399171 @default.
• W4308142133 hasConcept C2779761222 @default.
• W4308142133 hasConcept C41008148 @default.
• W4308142133 hasConcept C526584372 @default.
• W4308142133 hasConcept C58471807 @default.
• W4308142133 hasConcept C66905080 @default.
• W4308142133 hasConcept C71924100 @default.
• W4308142133 hasConcept C86803240 @default.
• W4308142133 hasConcept C95623464 @default.
• W4308142133 hasConceptScore W4308142133C12267149 @default.
• W4308142133 hasConceptScore W4308142133C126322002 @default.
• W4308142133 hasConceptScore W4308142133C126838900 @default.
• W4308142133 hasConceptScore W4308142133C142724271 @default.
• W4308142133 hasConceptScore W4308142133C151730666 @default.
• W4308142133 hasConceptScore W4308142133C153180895 @default.
• W4308142133 hasConceptScore W4308142133C154945302 @default.
• W4308142133 hasConceptScore W4308142133C2776731575 @default.
• W4308142133 hasConceptScore W4308142133C2779022025 @default.
• W4308142133 hasConceptScore W4308142133C2779399171 @default.
• W4308142133 hasConceptScore W4308142133C2779761222 @default.
• W4308142133 hasConceptScore W4308142133C41008148 @default.
• W4308142133 hasConceptScore W4308142133C526584372 @default.
• W4308142133 hasConceptScore W4308142133C58471807 @default.
• W4308142133 hasConceptScore W4308142133C66905080 @default.
• W4308142133 hasConceptScore W4308142133C71924100 @default.
• W4308142133 hasConceptScore W4308142133C86803240 @default.
• W4308142133 hasConceptScore W4308142133C95623464 @default.
• W4308142133 hasIssue "Supplement_1" @default.
• W4308142133 hasLocation W43081421331 @default.
• W4308142133 hasLocation W43081421332 @default.
• W4308142133 hasOpenAccess W4308142133 @default.
• W4308142133 hasPrimaryLocation W43081421331 @default.
• W4308142133 hasRelatedWork W1601676555 @default.
• W4308142133 hasRelatedWork W1974989040 @default.
• W4308142133 hasRelatedWork W2028726180 @default.
• W4308142133 hasRelatedWork W2052691691 @default.
• W4308142133 hasRelatedWork W2062093940 @default.
• W4308142133 hasRelatedWork W2157743352 @default.
• W4308142133 hasRelatedWork W2381331392 @default.
• W4308142133 hasRelatedWork W2886256612 @default.
• W4308142133 hasRelatedWork W2970248038 @default.
• W4308142133 hasRelatedWork W3031809124 @default.
• W4308142133 hasVolume "6" @default.
• W4308142133 isParatext "false" @default.
• W4308142133 isRetracted "false" @default.
• W4308142133 workType "article" @default.