FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2986167844> ?p ?o ?g. }

• W2986167844 abstract "Background Chronic Pulmonary Aspergillosis (CPA) is a severe fungal infection caused by the ubiquitous genus Aspergillus. Individuals with mild immunocompromise and/or pre-existing lung conditions are susceptible to CPA. Signs on high-resolution computed tomography (HRCT) imaging include uni- or bilateral fungal balls in lung cavities and associated pleural thickening and fibrosis. Despite antifungal therapy, mortality is high. Early diagnosis and radiological identification of disease progression are key to improve prognosis. We have designed a weakly-supervised deep learning network to recognize CPA, localize affected lung regions and predict 2 year survival post baseline on HRCT imaging. Methods Our dataset consists of 75 normal HRCT studies and 277 studies from 99 patients showing signs of CPA, which were gathered over a period of 12 years. Following segmentation of the lung regions, an original approach was used via axial-view projection of the average intensity values (in HU) within the segmented lung masks, which provide contextual visualization of the whole lung volume in just two dimensions (figure 1b). We then fine-tuned the deep Convolutional Neural Network (CNN) VGG19 to classify axial-projections into two classes: CPA or not CPA. Data augmentation was performed via rotation of HRCT scans in 3D prior to projection, as well as scaling and rotating projections in 2D. The CNN was designed to output maps of visual features, which serve as a localizer of pathological signs on the studies (figure 1c). Finally, the CNN was trained to predict 2 year survival from baseline imaging. Results For the classification of CPA, we achieved an accuracy on the training set (n=2790 projections) of 99.2% and on the test set (n=962 projections) of 96.2%. For 2 year survival prediction, we achieved an accuracy of 86.1% on the training set (n=510 projections) and 85.8% on the test set (n=255 projections). Conclusion We present an original framework to simplify HRCT imaging via axial projections and exploit these in a deep-learning framework to enable accurate CPA identification and prediction of 2 year survival. Further work will aim to facilitate early CPA diagnosis and stratification and pave the way towards an automated scoring system with accurate mortality prediction." @default.
• W2986167844 created "2019-11-22" @default.
• W2986167844 creator A5006584973 @default.
• W2986167844 creator A5026173669 @default.
• W2986167844 creator A5052464094 @default.
• W2986167844 creator A5062429575 @default.
• W2986167844 creator A5063132610 @default.
• W2986167844 creator A5063148422 @default.
• W2986167844 creator A5075594841 @default.
• W2986167844 creator A5078997486 @default.
• W2986167844 creator A5087286592 @default.
• W2986167844 creator A5089458771 @default.
• W2986167844 creator A5089531062 @default.
• W2986167844 date "2018-12-01" @default.
• W2986167844 modified "2023-10-14" @default.
• W2986167844 title "P28 Weakly supervised deep learning on CT scans predicts survival from chronic pulmonary aspergillosis" @default.
• W2986167844 doi "https://doi.org/10.1136/thorax-2018-212555.186" @default.
• W2986167844 hasPublicationYear "2018" @default.
• W2986167844 type Work @default.
• W2986167844 sameAs 2986167844 @default.
• W2986167844 citedByCount "0" @default.
• W2986167844 crossrefType "proceedings-article" @default.
• W2986167844 hasAuthorship W2986167844A5006584973 @default.
• W2986167844 hasAuthorship W2986167844A5026173669 @default.
• W2986167844 hasAuthorship W2986167844A5052464094 @default.
• W2986167844 hasAuthorship W2986167844A5062429575 @default.
• W2986167844 hasAuthorship W2986167844A5063132610 @default.
• W2986167844 hasAuthorship W2986167844A5063148422 @default.
• W2986167844 hasAuthorship W2986167844A5075594841 @default.
• W2986167844 hasAuthorship W2986167844A5078997486 @default.
• W2986167844 hasAuthorship W2986167844A5087286592 @default.
• W2986167844 hasAuthorship W2986167844A5089458771 @default.
• W2986167844 hasAuthorship W2986167844A5089531062 @default.
• W2986167844 hasConcept C108583219 @default.
• W2986167844 hasConcept C11413529 @default.
• W2986167844 hasConcept C126322002 @default.
• W2986167844 hasConcept C126838900 @default.
• W2986167844 hasConcept C154945302 @default.
• W2986167844 hasConcept C203014093 @default.
• W2986167844 hasConcept C2776391196 @default.
• W2986167844 hasConcept C2777524225 @default.
• W2986167844 hasConcept C2777714996 @default.
• W2986167844 hasConcept C2989005 @default.
• W2986167844 hasConcept C41008148 @default.
• W2986167844 hasConcept C544519230 @default.
• W2986167844 hasConcept C57493831 @default.
• W2986167844 hasConcept C71924100 @default.
• W2986167844 hasConcept C81363708 @default.
• W2986167844 hasConceptScore W2986167844C108583219 @default.
• W2986167844 hasConceptScore W2986167844C11413529 @default.
• W2986167844 hasConceptScore W2986167844C126322002 @default.
• W2986167844 hasConceptScore W2986167844C126838900 @default.
• W2986167844 hasConceptScore W2986167844C154945302 @default.
• W2986167844 hasConceptScore W2986167844C203014093 @default.
• W2986167844 hasConceptScore W2986167844C2776391196 @default.
• W2986167844 hasConceptScore W2986167844C2777524225 @default.
• W2986167844 hasConceptScore W2986167844C2777714996 @default.
• W2986167844 hasConceptScore W2986167844C2989005 @default.
• W2986167844 hasConceptScore W2986167844C41008148 @default.
• W2986167844 hasConceptScore W2986167844C544519230 @default.
• W2986167844 hasConceptScore W2986167844C57493831 @default.
• W2986167844 hasConceptScore W2986167844C71924100 @default.
• W2986167844 hasConceptScore W2986167844C81363708 @default.
• W2986167844 hasLocation W29861678441 @default.
• W2986167844 hasOpenAccess W2986167844 @default.
• W2986167844 hasPrimaryLocation W29861678441 @default.
• W2986167844 hasRelatedWork W2084220915 @default.
• W2986167844 hasRelatedWork W2731899572 @default.
• W2986167844 hasRelatedWork W2803198604 @default.
• W2986167844 hasRelatedWork W2999805992 @default.
• W2986167844 hasRelatedWork W3103566983 @default.
• W2986167844 hasRelatedWork W3116150086 @default.
• W2986167844 hasRelatedWork W3133861977 @default.
• W2986167844 hasRelatedWork W3215138031 @default.
• W2986167844 hasRelatedWork W4200173597 @default.
• W2986167844 hasRelatedWork W4226493464 @default.
• W2986167844 isParatext "false" @default.
• W2986167844 isRetracted "false" @default.
• W2986167844 magId "2986167844" @default.
• W2986167844 workType "article" @default.