FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285221389> ?p ?o ?g. }

• W4285221389 endingPage "385" @default.
• W4285221389 startingPage "373" @default.
• W4285221389 abstract "Lung cancer growth is one of the significant reasons for disease-related deaths because of its firm nature and late identifications at critical phases. Early identification of lung disease is substantial for the treatment of a person. Testing and diagnosis remain a critical issue for them. Most chest radiographs (X-beam) and recorded tomography (CT) scans are used at first to assess the hazardous knobs; in either event, the possible existence of polite keys prompts inappropriate decisions. At the initial phases, the nice and fragile knobs are next to each other. Here, a new, profound learning-based paradigm with different approaches is suggested to examine the dangerous knobs exactly. Owing to ongoing achievements in in-depth convolution neural systems (CNN) in picture analysis, we used two extreme three-dimensional (3D) altered blended relation arrangement (CMixNet) constructs independently for lung knob exploration and characterization. Knob recognition was performed via faster R-CNN on effectively taking highlights from CmixNet and UNet like encoder/decoder engineering. Characterization of the knobs was accomplished by an orientation boosting machine (GBM) on the outlines of the intended 3D CmixNet layout. To reject false positive outcomes and misdiagnosis due to various mistake types, an acceptable urge was acted on clinical side effects and clinical pathogenesis. Through the network of things (IoT) approach and electro-clinical engineering, remote body popular frameworks (WBANs) provide reliable patient management, helping to decide endless diseases—particularly metastatic sicknesses. The deep neural network for identification and classification of knobs, related to clinical components, begins to reduce disorder, and false optimism (FP) contributes to discovering the initial step of lung disease. The suggested system was tested as affectability (94%) and explicitness (91%) on LIDC-IDRI datasets, and better findings were obtained in comparison with current techniques. In this article, we analyze the consistency of a deep learning technique to diagnose lung disease on clinical image analysis problems. Convolution neural systems (CNNs) have become popular within example recognition and PC vision testing territories as a function of their encouraging impact on substantial level representations." @default.
• W4285221389 created "2022-07-14" @default.
• W4285221389 creator A5004996005 @default.
• W4285221389 creator A5029688969 @default.
• W4285221389 creator A5065360503 @default.
• W4285221389 creator A5077120405 @default.
• W4285221389 creator A5089627115 @default.
• W4285221389 creator A5091294659 @default.
• W4285221389 date "2022-01-01" @default.
• W4285221389 modified "2023-09-27" @default.
• W4285221389 title "Lung Cancer Detection Using Deep Convolutional Neural Networks" @default.
• W4285221389 cites W1482506445 @default.
• W4285221389 cites W1898227994 @default.
• W4285221389 cites W2043103662 @default.
• W4285221389 cites W2191992728 @default.
• W4285221389 cites W2524399695 @default.
• W4285221389 cites W2734776202 @default.
• W4285221389 cites W2743008510 @default.
• W4285221389 cites W2807838269 @default.
• W4285221389 cites W2998336244 @default.
• W4285221389 cites W3113939469 @default.
• W4285221389 cites W3169330763 @default.
• W4285221389 cites W3169534941 @default.
• W4285221389 cites W3172778638 @default.
• W4285221389 cites W3196639764 @default.
• W4285221389 cites W3216295476 @default.
• W4285221389 cites W4200147778 @default.
• W4285221389 cites W4210583217 @default.
• W4285221389 cites W4213419842 @default.
• W4285221389 cites W4214528532 @default.
• W4285221389 doi "https://doi.org/10.1007/978-981-19-1559-8_37" @default.
• W4285221389 hasPublicationYear "2022" @default.
• W4285221389 type Work @default.
• W4285221389 citedByCount "1" @default.
• W4285221389 countsByYear W42852213892023 @default.
• W4285221389 crossrefType "book-chapter" @default.
• W4285221389 hasAuthorship W4285221389A5004996005 @default.
• W4285221389 hasAuthorship W4285221389A5029688969 @default.
• W4285221389 hasAuthorship W4285221389A5065360503 @default.
• W4285221389 hasAuthorship W4285221389A5077120405 @default.
• W4285221389 hasAuthorship W4285221389A5089627115 @default.
• W4285221389 hasAuthorship W4285221389A5091294659 @default.
• W4285221389 hasConcept C108583219 @default.
• W4285221389 hasConcept C116834253 @default.
• W4285221389 hasConcept C154945302 @default.
• W4285221389 hasConcept C41008148 @default.
• W4285221389 hasConcept C59822182 @default.
• W4285221389 hasConcept C71924100 @default.
• W4285221389 hasConcept C81363708 @default.
• W4285221389 hasConcept C86803240 @default.
• W4285221389 hasConceptScore W4285221389C108583219 @default.
• W4285221389 hasConceptScore W4285221389C116834253 @default.
• W4285221389 hasConceptScore W4285221389C154945302 @default.
• W4285221389 hasConceptScore W4285221389C41008148 @default.
• W4285221389 hasConceptScore W4285221389C59822182 @default.
• W4285221389 hasConceptScore W4285221389C71924100 @default.
• W4285221389 hasConceptScore W4285221389C81363708 @default.
• W4285221389 hasConceptScore W4285221389C86803240 @default.
• W4285221389 hasLocation W42852213891 @default.
• W4285221389 hasOpenAccess W4285221389 @default.
• W4285221389 hasPrimaryLocation W42852213891 @default.
• W4285221389 hasRelatedWork W2731899572 @default.
• W4285221389 hasRelatedWork W2999805992 @default.
• W4285221389 hasRelatedWork W3011074480 @default.
• W4285221389 hasRelatedWork W3116150086 @default.
• W4285221389 hasRelatedWork W3133861977 @default.
• W4285221389 hasRelatedWork W3192840557 @default.
• W4285221389 hasRelatedWork W4200173597 @default.
• W4285221389 hasRelatedWork W4291897433 @default.
• W4285221389 hasRelatedWork W4312417841 @default.
• W4285221389 hasRelatedWork W4321369474 @default.
• W4285221389 isParatext "false" @default.
• W4285221389 isRetracted "false" @default.
• W4285221389 workType "book-chapter" @default.