Matches in SemOpenAlex for { <https://semopenalex.org/work/W4290730664> ?p ?o ?g. }
- W4290730664 endingPage "102374" @default.
- W4290730664 startingPage "102374" @default.
- W4290730664 abstract "The accurate classification of mass lesions in the adrenal glands (‘adrenal masses’), detected with computed tomography (CT), is important for diagnosis and patient management. Adrenal masses can be benign or malignant and benign masses have varying prevalence. Classification methods based on convolutional neural networks (CNNs) are the state-of-the-art in maximizing inter-class differences in large medical imaging training datasets. The application of CNNs, to adrenal masses is challenging due to large intra-class variations, large inter-class similarities and imbalanced training data due to the size of the mass lesions. We developed a deep multi-scale resemblance network (DMRN) to overcome these limitations and leveraged paired CNNs to evaluate the intra-class similarities. We used multi-scale feature embedding to improve the inter-class separability by iteratively combining complementary information produced at different scales of the input to create structured feature descriptors. We augmented the training data with randomly sampled paired adrenal masses to reduce the influence of imbalanced training data. We used 229 CT scans of patients with adrenal masses for evaluation. In a five-fold cross-validation, our method had the best results (89.52 % in accuracy) when compared to the state-of-the-art methods (p < 0.05). We conducted a generalizability analysis of our method on the ImageCLEF 2016 competition dataset for medical subfigure classification, which consists of a training set of 6776 images and a test set of 4166 images across 30 classes. Our method achieved better classification performance (85.90 % in accuracy) when compared to the existing methods and was competitive when compared with methods that require additional training data (1.47 % lower in accuracy). Our DMRN sub-classified adrenal masses on CT and was superior to state-of-the-art approaches." @default.
- W4290730664 created "2022-08-09" @default.
- W4290730664 creator A5007640483 @default.
- W4290730664 creator A5015039086 @default.
- W4290730664 creator A5068891693 @default.
- W4290730664 creator A5069611208 @default.
- W4290730664 creator A5082979981 @default.
- W4290730664 creator A5091321504 @default.
- W4290730664 date "2022-10-01" @default.
- W4290730664 modified "2023-10-16" @default.
- W4290730664 title "Deep multi-scale resemblance network for the sub-class differentiation of adrenal masses on computed tomography images" @default.
- W4290730664 cites W1975020933 @default.
- W4290730664 cites W1978070069 @default.
- W4290730664 cites W2014418634 @default.
- W4290730664 cites W2044769820 @default.
- W4290730664 cites W2066720700 @default.
- W4290730664 cites W2073541423 @default.
- W4290730664 cites W2078014989 @default.
- W4290730664 cites W2079707637 @default.
- W4290730664 cites W2091967951 @default.
- W4290730664 cites W2110261828 @default.
- W4290730664 cites W2110290656 @default.
- W4290730664 cites W2112063803 @default.
- W4290730664 cites W2132744910 @default.
- W4290730664 cites W2141619730 @default.
- W4290730664 cites W2148626383 @default.
- W4290730664 cites W2152542893 @default.
- W4290730664 cites W2153364064 @default.
- W4290730664 cites W2153635508 @default.
- W4290730664 cites W2155662634 @default.
- W4290730664 cites W2163922914 @default.
- W4290730664 cites W2237167366 @default.
- W4290730664 cites W2253429366 @default.
- W4290730664 cites W2323929895 @default.
- W4290730664 cites W2343172899 @default.
- W4290730664 cites W2553191729 @default.
- W4290730664 cites W2558580397 @default.
- W4290730664 cites W2559785631 @default.
- W4290730664 cites W2598853550 @default.
- W4290730664 cites W2613049942 @default.
- W4290730664 cites W2739836671 @default.
- W4290730664 cites W2769497098 @default.
- W4290730664 cites W2794022343 @default.
- W4290730664 cites W2883190781 @default.
- W4290730664 cites W2888442043 @default.
- W4290730664 cites W2914959431 @default.
- W4290730664 cites W2916845318 @default.
- W4290730664 doi "https://doi.org/10.1016/j.artmed.2022.102374" @default.
- W4290730664 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36207084" @default.
- W4290730664 hasPublicationYear "2022" @default.
- W4290730664 type Work @default.
- W4290730664 citedByCount "1" @default.
- W4290730664 countsByYear W42907306642023 @default.
- W4290730664 crossrefType "journal-article" @default.
- W4290730664 hasAuthorship W4290730664A5007640483 @default.
- W4290730664 hasAuthorship W4290730664A5015039086 @default.
- W4290730664 hasAuthorship W4290730664A5068891693 @default.
- W4290730664 hasAuthorship W4290730664A5069611208 @default.
- W4290730664 hasAuthorship W4290730664A5082979981 @default.
- W4290730664 hasAuthorship W4290730664A5091321504 @default.
- W4290730664 hasBestOaLocation W42907306642 @default.
- W4290730664 hasConcept C105795698 @default.
- W4290730664 hasConcept C108583219 @default.
- W4290730664 hasConcept C119857082 @default.
- W4290730664 hasConcept C138885662 @default.
- W4290730664 hasConcept C153180895 @default.
- W4290730664 hasConcept C154945302 @default.
- W4290730664 hasConcept C177264268 @default.
- W4290730664 hasConcept C199360897 @default.
- W4290730664 hasConcept C205649164 @default.
- W4290730664 hasConcept C27158222 @default.
- W4290730664 hasConcept C2776401178 @default.
- W4290730664 hasConcept C2777212361 @default.
- W4290730664 hasConcept C2778755073 @default.
- W4290730664 hasConcept C33923547 @default.
- W4290730664 hasConcept C41008148 @default.
- W4290730664 hasConcept C41895202 @default.
- W4290730664 hasConcept C50644808 @default.
- W4290730664 hasConcept C58489278 @default.
- W4290730664 hasConcept C58640448 @default.
- W4290730664 hasConcept C81363708 @default.
- W4290730664 hasConceptScore W4290730664C105795698 @default.
- W4290730664 hasConceptScore W4290730664C108583219 @default.
- W4290730664 hasConceptScore W4290730664C119857082 @default.
- W4290730664 hasConceptScore W4290730664C138885662 @default.
- W4290730664 hasConceptScore W4290730664C153180895 @default.
- W4290730664 hasConceptScore W4290730664C154945302 @default.
- W4290730664 hasConceptScore W4290730664C177264268 @default.
- W4290730664 hasConceptScore W4290730664C199360897 @default.
- W4290730664 hasConceptScore W4290730664C205649164 @default.
- W4290730664 hasConceptScore W4290730664C27158222 @default.
- W4290730664 hasConceptScore W4290730664C2776401178 @default.
- W4290730664 hasConceptScore W4290730664C2777212361 @default.
- W4290730664 hasConceptScore W4290730664C2778755073 @default.
- W4290730664 hasConceptScore W4290730664C33923547 @default.
- W4290730664 hasConceptScore W4290730664C41008148 @default.
- W4290730664 hasConceptScore W4290730664C41895202 @default.
- W4290730664 hasConceptScore W4290730664C50644808 @default.