FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312138082> ?p ?o ?g. }

• W4312138082 abstract "To implement two Artificial Intelligence (AI) methods, radiomics and deep learning, to build diagnostic models for patients presenting with architectural distortion on Digital Breast Tomosynthesis (DBT) images.A total of 298 patients were identified from a retrospective review, and all of them had confirmed pathological diagnoses, 175 malignant and 123 benign. The BI-RADS scores of DBT were obtained from the radiology reports, classified into 2, 3, 4A, 4B, 4C, and 5. The architectural distortion areas on craniocaudal (CC) and mediolateral oblique (MLO) views were manually outlined as the region of interest (ROI) for the radiomics analysis. Features were extracted using PyRadiomics, and then the support vector machine (SVM) was applied to select important features and build the classification model. Deep learning was performed using the ResNet50 algorithm, with the binary output of malignancy and benignity. The Gradient-weighted Class Activation Mapping (Grad-CAM) method was utilized to localize the suspicious areas. The predicted malignancy probability was used to construct the ROC curves, compared by the DeLong test. The binary diagnosis was made using the threshold of ≥ 0.5 as malignant.The majority of malignant lesions had BI-RADS scores of 4B, 4C, and 5 (148/175 = 84.6%). In the benign group, a substantial number of patients also had high BI-RADS ≥ 4B (56/123 = 45.5%), and the majority had BI-RADS ≥ 4A (102/123 = 82.9%). The radiomics model built using the combined CC+MLO features yielded an area under curve (AUC) of 0.82, the sensitivity of 0.78, specificity of 0.68, and accuracy of 0.74. If only features from CC were used, the AUC was 0.77, and if only features from MLO were used, the AUC was 0.72. The deep-learning model yielded an AUC of 0.61, significantly lower than all radiomics models (p<0.01), which was presumably due to the use of the entire image as input. The Grad-CAM could localize the architectural distortion areas.The radiomics model can achieve a satisfactory diagnostic accuracy, and the high specificity in the benign group can be used to avoid unnecessary biopsies. Deep learning can be used to localize the architectural distortion areas, which may provide an automatic method for ROI delineation to facilitate the development of a fully-automatic computer-aided diagnosis system using combined AI strategies." @default.
• W4312138082 created "2023-01-04" @default.
• W4312138082 creator A5000667041 @default.
• W4312138082 creator A5022802322 @default.
• W4312138082 creator A5034654778 @default.
• W4312138082 creator A5036009688 @default.
• W4312138082 creator A5051841864 @default.
• W4312138082 creator A5055004003 @default.
• W4312138082 creator A5058010200 @default.
• W4312138082 creator A5066852726 @default.
• W4312138082 creator A5074289470 @default.
• W4312138082 creator A5076521009 @default.
• W4312138082 creator A5080817461 @default.
• W4312138082 date "2022-12-13" @default.
• W4312138082 modified "2023-09-23" @default.
• W4312138082 title "Diagnosis of architectural distortion on digital breast tomosynthesis using radiomics and deep learning" @default.
• W4312138082 cites W1993745536 @default.
• W4312138082 cites W2016919269 @default.
• W4312138082 cites W2058399062 @default.
• W4312138082 cites W2104698944 @default.
• W4312138082 cites W2159205109 @default.
• W4312138082 cites W2172747264 @default.
• W4312138082 cites W2293509196 @default.
• W4312138082 cites W2399464218 @default.
• W4312138082 cites W2530666965 @default.
• W4312138082 cites W2581082771 @default.
• W4312138082 cites W2604629495 @default.
• W4312138082 cites W2616240394 @default.
• W4312138082 cites W2749362420 @default.
• W4312138082 cites W2795464441 @default.
• W4312138082 cites W2900898778 @default.
• W4312138082 cites W2900955936 @default.
• W4312138082 cites W2906868412 @default.
• W4312138082 cites W2911188335 @default.
• W4312138082 cites W2911492966 @default.
• W4312138082 cites W2912202601 @default.
• W4312138082 cites W2966665347 @default.
• W4312138082 cites W2982440353 @default.
• W4312138082 cites W2985003253 @default.
• W4312138082 cites W2994766824 @default.
• W4312138082 cites W3001021123 @default.
• W4312138082 cites W3029753047 @default.
• W4312138082 cites W3045607691 @default.
• W4312138082 cites W3088825280 @default.
• W4312138082 cites W3095915252 @default.
• W4312138082 cites W3109181793 @default.
• W4312138082 cites W3128672542 @default.
• W4312138082 cites W3134521793 @default.
• W4312138082 cites W3136313460 @default.
• W4312138082 cites W3141480089 @default.
• W4312138082 cites W3164953453 @default.
• W4312138082 cites W3174574517 @default.
• W4312138082 cites W3207689590 @default.
• W4312138082 cites W4200215549 @default.
• W4312138082 cites W4200525895 @default.
• W4312138082 cites W4225378664 @default.
• W4312138082 cites W4252607836 @default.
• W4312138082 cites W4285087845 @default.
• W4312138082 doi "https://doi.org/10.3389/fonc.2022.991892" @default.
• W4312138082 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36582788" @default.
• W4312138082 hasPublicationYear "2022" @default.
• W4312138082 type Work @default.
• W4312138082 citedByCount "3" @default.
• W4312138082 countsByYear W43121380822023 @default.
• W4312138082 crossrefType "journal-article" @default.
• W4312138082 hasAuthorship W4312138082A5000667041 @default.
• W4312138082 hasAuthorship W4312138082A5022802322 @default.
• W4312138082 hasAuthorship W4312138082A5034654778 @default.
• W4312138082 hasAuthorship W4312138082A5036009688 @default.
• W4312138082 hasAuthorship W4312138082A5051841864 @default.
• W4312138082 hasAuthorship W4312138082A5055004003 @default.
• W4312138082 hasAuthorship W4312138082A5058010200 @default.
• W4312138082 hasAuthorship W4312138082A5066852726 @default.
• W4312138082 hasAuthorship W4312138082A5074289470 @default.
• W4312138082 hasAuthorship W4312138082A5076521009 @default.
• W4312138082 hasAuthorship W4312138082A5080817461 @default.
• W4312138082 hasBestOaLocation W43121380821 @default.
• W4312138082 hasConcept C108583219 @default.
• W4312138082 hasConcept C119857082 @default.
• W4312138082 hasConcept C121608353 @default.
• W4312138082 hasConcept C12267149 @default.
• W4312138082 hasConcept C126322002 @default.
• W4312138082 hasConcept C126838900 @default.
• W4312138082 hasConcept C142724271 @default.
• W4312138082 hasConcept C147454874 @default.
• W4312138082 hasConcept C153180895 @default.
• W4312138082 hasConcept C154945302 @default.
• W4312138082 hasConcept C2776316164 @default.
• W4312138082 hasConcept C2777432617 @default.
• W4312138082 hasConcept C2778559731 @default.
• W4312138082 hasConcept C2779399171 @default.
• W4312138082 hasConcept C2780472235 @default.
• W4312138082 hasConcept C41008148 @default.
• W4312138082 hasConcept C530470458 @default.
• W4312138082 hasConcept C534262118 @default.
• W4312138082 hasConcept C58471807 @default.
• W4312138082 hasConcept C71924100 @default.
• W4312138082 hasConceptScore W4312138082C108583219 @default.
• W4312138082 hasConceptScore W4312138082C119857082 @default.
• W4312138082 hasConceptScore W4312138082C121608353 @default.

• next