FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186382323> ?p ?o ?g. }

• W3186382323 endingPage "109878" @default.
• W3186382323 startingPage "109878" @default.
• W3186382323 abstract "Purpose To utilize a neural architecture search (NAS) approach to develop a convolutional neural network (CNN) method for distinguishing benign and malignant lesions on breast cone-beam CT (BCBCT). Method 165 patients with 114 malignant and 86 benign lesions were collected by two institutions from May 2012 to August 2014. The NAS method autonomously generated a CNN model using one institution’s dataset for training (patients/lesions: 71/91) and validation (patients/lesions: 20/23). The model was externally tested on another institution’s dataset (patients/lesions: 74/87), and its performance was compared with fine-tuned ResNet-50 models and two breast radiologists who independently read the lesions in the testing dataset without knowing lesion diagnosis. Results The lesion diameters (mean ± SD) were 18.8 ± 12.9 mm, 22.7 ± 10.5 mm, and 20.0 ± 11.8 mm in the training, validation, and external testing set, respectively. Compared to the best ResNet-50 model, the NAS-generated CNN model performed three times faster and, in the external testing set, achieved a higher (though not statistically different) AUC, with sensitivity (95% CI) and specificity (95% CI) of 0.727, 80% (66–90%), and 60% (42–75%), respectively. Meanwhile, the performances of the NAS-generated CNN and the two radiologists’ visual ratings were not statistically different. Conclusions Our preliminary results demonstrated that a CNN autonomously generated by NAS performed comparably to pre-trained ResNet models and radiologists in predicting malignant breast lesions on contrast-enhanced BCBCT. In comparison to ResNet, which must be designed by an expert, the NAS approach may be used to automatically generate a deep learning architecture for medical image analysis." @default.
• W3186382323 created "2021-08-02" @default.
• W3186382323 creator A5004107409 @default.
• W3186382323 creator A5006052576 @default.
• W3186382323 creator A5043281384 @default.
• W3186382323 creator A5045641777 @default.
• W3186382323 creator A5054444050 @default.
• W3186382323 creator A5058825770 @default.
• W3186382323 creator A5059742610 @default.
• W3186382323 creator A5060117211 @default.
• W3186382323 creator A5063922467 @default.
• W3186382323 creator A5067518637 @default.
• W3186382323 creator A5073322132 @default.
• W3186382323 creator A5077844760 @default.
• W3186382323 creator A5085609481 @default.
• W3186382323 creator A5090286598 @default.
• W3186382323 date "2021-09-01" @default.
• W3186382323 modified "2023-10-17" @default.
• W3186382323 title "Distinguishing benign and malignant lesions on contrast-enhanced breast cone-beam CT with deep learning neural architecture search" @default.
• W3186382323 cites W1966483343 @default.
• W3186382323 cites W1980527762 @default.
• W3186382323 cites W1993056688 @default.
• W3186382323 cites W2008521294 @default.
• W3186382323 cites W2026616100 @default.
• W3186382323 cites W2036132386 @default.
• W3186382323 cites W2055385925 @default.
• W3186382323 cites W2083296039 @default.
• W3186382323 cites W2123618524 @default.
• W3186382323 cites W2152575748 @default.
• W3186382323 cites W2158732932 @default.
• W3186382323 cites W2173540191 @default.
• W3186382323 cites W2328176404 @default.
• W3186382323 cites W2558580397 @default.
• W3186382323 cites W2757343416 @default.
• W3186382323 cites W2772228139 @default.
• W3186382323 cites W2783710041 @default.
• W3186382323 cites W2794666526 @default.
• W3186382323 cites W2803899823 @default.
• W3186382323 cites W2807685710 @default.
• W3186382323 cites W2915829734 @default.
• W3186382323 cites W2996253120 @default.
• W3186382323 doi "https://doi.org/10.1016/j.ejrad.2021.109878" @default.
• W3186382323 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34388626" @default.
• W3186382323 hasPublicationYear "2021" @default.
• W3186382323 type Work @default.
• W3186382323 sameAs 3186382323 @default.
• W3186382323 citedByCount "7" @default.
• W3186382323 countsByYear W31863823232021 @default.
• W3186382323 countsByYear W31863823232022 @default.
• W3186382323 countsByYear W31863823232023 @default.
• W3186382323 crossrefType "journal-article" @default.
• W3186382323 hasAuthorship W3186382323A5004107409 @default.
• W3186382323 hasAuthorship W3186382323A5006052576 @default.
• W3186382323 hasAuthorship W3186382323A5043281384 @default.
• W3186382323 hasAuthorship W3186382323A5045641777 @default.
• W3186382323 hasAuthorship W3186382323A5054444050 @default.
• W3186382323 hasAuthorship W3186382323A5058825770 @default.
• W3186382323 hasAuthorship W3186382323A5059742610 @default.
• W3186382323 hasAuthorship W3186382323A5060117211 @default.
• W3186382323 hasAuthorship W3186382323A5063922467 @default.
• W3186382323 hasAuthorship W3186382323A5067518637 @default.
• W3186382323 hasAuthorship W3186382323A5073322132 @default.
• W3186382323 hasAuthorship W3186382323A5077844760 @default.
• W3186382323 hasAuthorship W3186382323A5085609481 @default.
• W3186382323 hasAuthorship W3186382323A5090286598 @default.
• W3186382323 hasConcept C108583219 @default.
• W3186382323 hasConcept C126838900 @default.
• W3186382323 hasConcept C142724271 @default.
• W3186382323 hasConcept C154945302 @default.
• W3186382323 hasConcept C2776502983 @default.
• W3186382323 hasConcept C2781156865 @default.
• W3186382323 hasConcept C2944601119 @default.
• W3186382323 hasConcept C2989005 @default.
• W3186382323 hasConcept C41008148 @default.
• W3186382323 hasConcept C71924100 @default.
• W3186382323 hasConcept C81363708 @default.
• W3186382323 hasConceptScore W3186382323C108583219 @default.
• W3186382323 hasConceptScore W3186382323C126838900 @default.
• W3186382323 hasConceptScore W3186382323C142724271 @default.
• W3186382323 hasConceptScore W3186382323C154945302 @default.
• W3186382323 hasConceptScore W3186382323C2776502983 @default.
• W3186382323 hasConceptScore W3186382323C2781156865 @default.
• W3186382323 hasConceptScore W3186382323C2944601119 @default.
• W3186382323 hasConceptScore W3186382323C2989005 @default.
• W3186382323 hasConceptScore W3186382323C41008148 @default.
• W3186382323 hasConceptScore W3186382323C71924100 @default.
• W3186382323 hasConceptScore W3186382323C81363708 @default.
• W3186382323 hasFunder F4320322161 @default.
• W3186382323 hasFunder F4320335777 @default.
• W3186382323 hasLocation W31863823231 @default.
• W3186382323 hasOpenAccess W3186382323 @default.
• W3186382323 hasPrimaryLocation W31863823231 @default.
• W3186382323 hasRelatedWork W2604192360 @default.
• W3186382323 hasRelatedWork W3029198973 @default.
• W3186382323 hasRelatedWork W3133861977 @default.
• W3186382323 hasRelatedWork W3167935049 @default.
• W3186382323 hasRelatedWork W3193565141 @default.
• W3186382323 hasRelatedWork W3213976941 @default.

• next