Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285185718> ?p ?o ?g. }
- W4285185718 endingPage "179" @default.
- W4285185718 startingPage "165" @default.
- W4285185718 abstract "Computer Aided Diagnosis (CAD) is an ever-growing field as it facilitates the effective diagnosis of diseases at an early stage. This type of diagnosis system includes segmentation of abnormal tissues, polyps, disease staging and classification etc. All the aforementioned CAD system tasks rely directly upon the quality of the medical images that are taken as input. Image quality depends on various parameters, out of which contrast is an important attribute. The task of segmenting gallbladder and soft tissues from Magnetic Resonance Cholangiopancreatography (MRCP) images has significance in the investigation of many pancreatico-biliary disorders. Efficacy of the segmentation of the structures from MRCP images requires the parameter of contrast to be maintained to a confined level. Though the performance of artificial intelligence in medical image analysis seems compromising, the concepts of reliability and explainability for the developed algorithms are needed as it deals with health aided systems. Thus, through this research we developed an explainable approach that articulates the various soft tissues present in the MRCP images by clustering them into groups. The use of Tree Seed Algorithm (TSA), a nature inspired optimization algorithm with a deep neural network, provides a perfect learning machine that creates exact clusters even in low contrast MRCP images. Unlike the conventional black box method, this machine provides nearest neighbors and clusters that are responsible for the lowest distance between them. The model’s interpretability can be explained by Local Interpretable Model-agnostic Explanations (LIME). The efficacy of the trained network is imposed on a 120 MRCP image dataset obtained from a diagnostic center in Tamilnadu. The proposed network provides improved accuracy when compared with other Deep learning models such as ResNet50, DenseNet201." @default.
- W4285185718 created "2022-07-14" @default.
- W4285185718 creator A5031850271 @default.
- W4285185718 creator A5054180101 @default.
- W4285185718 creator A5084415408 @default.
- W4285185718 date "2022-01-01" @default.
- W4285185718 modified "2023-10-06" @default.
- W4285185718 title "An Articulated Learning Method Based on Optimization Approach for Gallbladder Segmentation from MRCP Images and an Effective IoT Based Recommendation Framework" @default.
- W4285185718 cites W1487258128 @default.
- W4285185718 cites W1933887497 @default.
- W4285185718 cites W1964960560 @default.
- W4285185718 cites W2045757115 @default.
- W4285185718 cites W2045902838 @default.
- W4285185718 cites W2078094470 @default.
- W4285185718 cites W2119249988 @default.
- W4285185718 cites W2166418144 @default.
- W4285185718 cites W2283531730 @default.
- W4285185718 cites W237869302 @default.
- W4285185718 cites W2504861291 @default.
- W4285185718 cites W2569492231 @default.
- W4285185718 cites W2604319603 @default.
- W4285185718 cites W2743603598 @default.
- W4285185718 cites W2749468071 @default.
- W4285185718 cites W2784176562 @default.
- W4285185718 cites W2797287986 @default.
- W4285185718 cites W2809925683 @default.
- W4285185718 cites W2891503716 @default.
- W4285185718 cites W2894841830 @default.
- W4285185718 cites W2899084328 @default.
- W4285185718 cites W2902739702 @default.
- W4285185718 cites W2927576543 @default.
- W4285185718 cites W2958089299 @default.
- W4285185718 cites W2963847595 @default.
- W4285185718 cites W2972441196 @default.
- W4285185718 cites W2981731882 @default.
- W4285185718 cites W3019109475 @default.
- W4285185718 cites W3036694883 @default.
- W4285185718 cites W3044569690 @default.
- W4285185718 cites W3081090156 @default.
- W4285185718 cites W3092389932 @default.
- W4285185718 cites W3134691236 @default.
- W4285185718 cites W3155744436 @default.
- W4285185718 doi "https://doi.org/10.1007/978-3-030-97929-4_8" @default.
- W4285185718 hasPublicationYear "2022" @default.
- W4285185718 type Work @default.
- W4285185718 citedByCount "15" @default.
- W4285185718 countsByYear W42851857182022 @default.
- W4285185718 countsByYear W42851857182023 @default.
- W4285185718 crossrefType "book-chapter" @default.
- W4285185718 hasAuthorship W4285185718A5031850271 @default.
- W4285185718 hasAuthorship W4285185718A5054180101 @default.
- W4285185718 hasAuthorship W4285185718A5084415408 @default.
- W4285185718 hasConcept C119857082 @default.
- W4285185718 hasConcept C127413603 @default.
- W4285185718 hasConcept C153180895 @default.
- W4285185718 hasConcept C154945302 @default.
- W4285185718 hasConcept C194789388 @default.
- W4285185718 hasConcept C199639397 @default.
- W4285185718 hasConcept C2775967933 @default.
- W4285185718 hasConcept C2776474662 @default.
- W4285185718 hasConcept C2778444009 @default.
- W4285185718 hasConcept C2779549770 @default.
- W4285185718 hasConcept C2781067378 @default.
- W4285185718 hasConcept C41008148 @default.
- W4285185718 hasConcept C50644808 @default.
- W4285185718 hasConcept C71924100 @default.
- W4285185718 hasConcept C73555534 @default.
- W4285185718 hasConcept C89600930 @default.
- W4285185718 hasConcept C90924648 @default.
- W4285185718 hasConceptScore W4285185718C119857082 @default.
- W4285185718 hasConceptScore W4285185718C127413603 @default.
- W4285185718 hasConceptScore W4285185718C153180895 @default.
- W4285185718 hasConceptScore W4285185718C154945302 @default.
- W4285185718 hasConceptScore W4285185718C194789388 @default.
- W4285185718 hasConceptScore W4285185718C199639397 @default.
- W4285185718 hasConceptScore W4285185718C2775967933 @default.
- W4285185718 hasConceptScore W4285185718C2776474662 @default.
- W4285185718 hasConceptScore W4285185718C2778444009 @default.
- W4285185718 hasConceptScore W4285185718C2779549770 @default.
- W4285185718 hasConceptScore W4285185718C2781067378 @default.
- W4285185718 hasConceptScore W4285185718C41008148 @default.
- W4285185718 hasConceptScore W4285185718C50644808 @default.
- W4285185718 hasConceptScore W4285185718C71924100 @default.
- W4285185718 hasConceptScore W4285185718C73555534 @default.
- W4285185718 hasConceptScore W4285185718C89600930 @default.
- W4285185718 hasConceptScore W4285185718C90924648 @default.
- W4285185718 hasLocation W42851857181 @default.
- W4285185718 hasOpenAccess W4285185718 @default.
- W4285185718 hasPrimaryLocation W42851857181 @default.
- W4285185718 hasRelatedWork W2605281151 @default.
- W4285185718 hasRelatedWork W3006943036 @default.
- W4285185718 hasRelatedWork W3012234327 @default.
- W4285185718 hasRelatedWork W3119715496 @default.
- W4285185718 hasRelatedWork W3191046242 @default.
- W4285185718 hasRelatedWork W4200511449 @default.
- W4285185718 hasRelatedWork W4205364923 @default.
- W4285185718 hasRelatedWork W4206534706 @default.
- W4285185718 hasRelatedWork W4229079080 @default.