FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200270809> ?p ?o ?g. }

• W3200270809 endingPage "5988" @default.
• W3200270809 startingPage "5978" @default.
• W3200270809 abstract "Background The nature of input data is an essential factor when training neural networks. Research concerning magnetic resonance imaging (MRI)-based diagnosis of liver tumors using deep learning has been rapidly advancing. Still, evidence to support the utilization of multi-dimensional and multi-parametric image data is lacking. Due to higher information content, three-dimensional input should presumably result in higher classification precision. Also, the differentiation between focal liver lesions (FLLs) can only be plausible with simultaneous analysis of multi-sequence MRI images. Aim To compare diagnostic efficiency of two-dimensional (2D) and three-dimensional (3D)-densely connected convolutional neural networks (DenseNet) for FLLs on multi-sequence MRI. Methods We retrospectively collected T2-weighted, gadoxetate disodium-enhanced arterial phase, portal venous phase, and hepatobiliary phase MRI scans from patients with focal nodular hyperplasia (FNH), hepatocellular carcinomas (HCC) or liver metastases (MET). Our search identified 71 FNH, 69 HCC and 76 MET. After volume registration, the same three most representative axial slices from all sequences were combined into four-channel images to train the 2D-DenseNet264 network. Identical bounding boxes were selected on all scans and stacked into 4D volumes to train the 3D-DenseNet264 model. The test set consisted of 10-10-10 tumors. The performance of the models was compared using area under the receiver operating characteristic curve (AUROC), specificity, sensitivity, positive predictive values (PPV), negative predictive values (NPV), and f1 scores. Results The average AUC value of the 2D model (0.98) was slightly higher than that of the 3D model (0.94). Mean PPV, sensitivity, NPV, specificity and f1 scores (0.94, 0.93, 0.97, 0.97, and 0.93) of the 2D model were also superior to metrics of the 3D model (0.84, 0.83, 0.92, 0.92, and 0.83). The classification metrics of FNH were 0.91, 1.00, 1.00, 0.95, and 0.95 using the 2D and 0.90, 0.90, 0.95, 0.95, and 0.90 using the 3D models. The 2D and 3D networks' performance in the diagnosis of HCC were 1.00, 0.80, 0.91, 1.00, and 0.89 and 0.88, 0.70, 0.86, 0.95, and 0.78, respectively; while the evaluation of MET lesions resulted in 0.91, 1.00, 1.00, 0.95, and 0.95 and 0.75, 0.90, 0.94, 0.85, and 0.82 using the 2D and 3D networks, respectively. Conclusion Both 2D and 3D-DenseNets can differentiate FNH, HCC and MET with good accuracy when trained on hepatocyte-specific contrast-enhanced multi-sequence MRI volumes." @default.
• W3200270809 created "2021-09-27" @default.
• W3200270809 creator A5012153745 @default.
• W3200270809 creator A5012244506 @default.
• W3200270809 creator A5018991520 @default.
• W3200270809 creator A5028441703 @default.
• W3200270809 creator A5068880985 @default.
• W3200270809 creator A5074481982 @default.
• W3200270809 creator A5082898800 @default.
• W3200270809 creator A5091313305 @default.
• W3200270809 creator A5091905327 @default.
• W3200270809 date "2021-09-21" @default.
• W3200270809 modified "2023-10-15" @default.
• W3200270809 title "Diagnosis of focal liver lesions with deep learning-based multi-channel analysis of hepatocyte-specific contrast-enhanced magnetic resonance imaging" @default.
• W3200270809 cites W1443939293 @default.
• W3200270809 cites W1972276317 @default.
• W3200270809 cites W2026616100 @default.
• W3200270809 cites W2080256222 @default.
• W3200270809 cites W2107897014 @default.
• W3200270809 cites W2149082288 @default.
• W3200270809 cites W2167090712 @default.
• W3200270809 cites W2328176404 @default.
• W3200270809 cites W2911605224 @default.
• W3200270809 cites W2912035464 @default.
• W3200270809 cites W2921808862 @default.
• W3200270809 cites W2934291851 @default.
• W3200270809 cites W2941555836 @default.
• W3200270809 cites W2945472816 @default.
• W3200270809 cites W2946713019 @default.
• W3200270809 cites W2963331285 @default.
• W3200270809 cites W3020996329 @default.
• W3200270809 cites W3035715385 @default.
• W3200270809 cites W3083622693 @default.
• W3200270809 cites W4210501746 @default.
• W3200270809 cites W4292229870 @default.
• W3200270809 doi "https://doi.org/10.3748/wjg.v27.i35.5978" @default.
• W3200270809 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8475009" @default.
• W3200270809 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34629814" @default.
• W3200270809 hasPublicationYear "2021" @default.
• W3200270809 type Work @default.
• W3200270809 sameAs 3200270809 @default.
• W3200270809 citedByCount "7" @default.
• W3200270809 countsByYear W32002708092022 @default.
• W3200270809 countsByYear W32002708092023 @default.
• W3200270809 crossrefType "journal-article" @default.
• W3200270809 hasAuthorship W3200270809A5012153745 @default.
• W3200270809 hasAuthorship W3200270809A5012244506 @default.
• W3200270809 hasAuthorship W3200270809A5018991520 @default.
• W3200270809 hasAuthorship W3200270809A5028441703 @default.
• W3200270809 hasAuthorship W3200270809A5068880985 @default.
• W3200270809 hasAuthorship W3200270809A5074481982 @default.
• W3200270809 hasAuthorship W3200270809A5082898800 @default.
• W3200270809 hasAuthorship W3200270809A5091313305 @default.
• W3200270809 hasAuthorship W3200270809A5091905327 @default.
• W3200270809 hasBestOaLocation W32002708091 @default.
• W3200270809 hasConcept C121332964 @default.
• W3200270809 hasConcept C126838900 @default.
• W3200270809 hasConcept C142724271 @default.
• W3200270809 hasConcept C143409427 @default.
• W3200270809 hasConcept C154945302 @default.
• W3200270809 hasConcept C185592680 @default.
• W3200270809 hasConcept C202751555 @default.
• W3200270809 hasConcept C2776200302 @default.
• W3200270809 hasConcept C2776502983 @default.
• W3200270809 hasConcept C41008148 @default.
• W3200270809 hasConcept C46141821 @default.
• W3200270809 hasConcept C55493867 @default.
• W3200270809 hasConcept C71924100 @default.
• W3200270809 hasConceptScore W3200270809C121332964 @default.
• W3200270809 hasConceptScore W3200270809C126838900 @default.
• W3200270809 hasConceptScore W3200270809C142724271 @default.
• W3200270809 hasConceptScore W3200270809C143409427 @default.
• W3200270809 hasConceptScore W3200270809C154945302 @default.
• W3200270809 hasConceptScore W3200270809C185592680 @default.
• W3200270809 hasConceptScore W3200270809C202751555 @default.
• W3200270809 hasConceptScore W3200270809C2776200302 @default.
• W3200270809 hasConceptScore W3200270809C2776502983 @default.
• W3200270809 hasConceptScore W3200270809C41008148 @default.
• W3200270809 hasConceptScore W3200270809C46141821 @default.
• W3200270809 hasConceptScore W3200270809C55493867 @default.
• W3200270809 hasConceptScore W3200270809C71924100 @default.
• W3200270809 hasIssue "35" @default.
• W3200270809 hasLocation W32002708091 @default.
• W3200270809 hasLocation W32002708092 @default.
• W3200270809 hasLocation W32002708093 @default.
• W3200270809 hasOpenAccess W3200270809 @default.
• W3200270809 hasPrimaryLocation W32002708091 @default.
• W3200270809 hasRelatedWork W2021501977 @default.
• W3200270809 hasRelatedWork W2028945745 @default.
• W3200270809 hasRelatedWork W2136102538 @default.
• W3200270809 hasRelatedWork W2324195327 @default.
• W3200270809 hasRelatedWork W2337546649 @default.
• W3200270809 hasRelatedWork W2410974768 @default.
• W3200270809 hasRelatedWork W2889503726 @default.
• W3200270809 hasRelatedWork W2965799289 @default.
• W3200270809 hasRelatedWork W3027341238 @default.
• W3200270809 hasRelatedWork W3084527062 @default.
• W3200270809 hasVolume "27" @default.

• next