Matches in SemOpenAlex for { <https://semopenalex.org/work/W3169451353> ?p ?o ?g. }
- W3169451353 endingPage "5191" @default.
- W3169451353 startingPage "5179" @default.
- W3169451353 abstract "Abstract Purpose In the literature on automated phenotyping of chronic obstructive pulmonary disease (COPD), there is a multitude of isolated classical machine learning and deep learning techniques, mostly investigating individual phenotypes, with small study cohorts and heterogeneous meta‐parameters, e.g., different scan protocols or segmented regions. The objective is to compare the impact of different experimental setups, i.e., varying meta‐parameters related to image formation and data representation, with the impact of the learning technique for subtyping automation for a variety of phenotypes. The identified associations of these parameters with automation performance and their interactions might be a first step towards a determination of optimal meta‐parameters, i.e., a meta‐strategy. Methods A clinical cohort of 981 patients (53.8 ± 15.1 years, 554 male) was examined. The inspiratory CT images were analyzed to automate the diagnosis of 13 COPD phenotypes given by two radiologists. A benchmark feature set that integrates many quantitative criteria was extracted from the lung and trained a variety of learning algorithms on the first 654 patients (two thirds) and the respective algorithm retrospectively assessed the remaining 327 patients (one third). The automation performance was evaluated by the area under the receiver operating characteristic curve (AUC). 1717 experiments were conducted with varying meta‐parameters such as reconstruction kernel, segmented regions and input dimensionality, i.e., number of extracted features. The association of the meta‐parameters with the automation performance was analyzed by multivariable general linear model decomposition of the automation performance in the contributions of meta‐parameters and the learning technique. Results The automation performance varied strongly for varying meta‐parameters. For emphysema‐predominant phenotypes, an AUC of 93%–95% could be achieved for the best meta‐configuration. The airways‐predominant phenotypes led to a lower performance of 65%–85%, while smooth kernel configurations on average were unexpectedly superior to those with sharp kernels. The performance impact of meta‐parameters, even that of often neglected ones like the missing‐data imputation, was in general larger than that of the learning technique. Advanced learning techniques like 3D deep learning or automated machine learning yielded inferior automation performance for non‐optimal meta‐configurations in comparison to simple techniques with suitable meta‐configurations. The best automation performance was achieved by a combination of modern learning techniques and a suitable meta‐configuration. Conclusions Our results indicate that for COPD phenotype automation, study design parameters such as reconstruction kernel and the model input dimensionality should be adapted to the learning technique and may be more important than the technique itself. To achieve optimal automation and prediction results, the interaction between input those meta‐parameters and the learning technique should be considered. This might be particularly relevant for the development of specific scan protocols for novel learning algorithms, and towards an understanding of good study design for automated phenotyping." @default.
- W3169451353 created "2021-06-22" @default.
- W3169451353 creator A5004876604 @default.
- W3169451353 creator A5011400986 @default.
- W3169451353 creator A5012107855 @default.
- W3169451353 creator A5021951093 @default.
- W3169451353 creator A5026198361 @default.
- W3169451353 creator A5029055548 @default.
- W3169451353 creator A5053324036 @default.
- W3169451353 creator A5064451296 @default.
- W3169451353 creator A5090174631 @default.
- W3169451353 date "2021-07-20" @default.
- W3169451353 modified "2023-10-14" @default.
- W3169451353 title "Unraveling the interplay of image formation, data representation and learning in CT‐based COPD phenotyping automation: The need for a meta‐strategy" @default.
- W3169451353 cites W1540856690 @default.
- W3169451353 cites W1974194690 @default.
- W3169451353 cites W1992201997 @default.
- W3169451353 cites W2012100459 @default.
- W3169451353 cites W2013607764 @default.
- W3169451353 cites W2015853228 @default.
- W3169451353 cites W2020707691 @default.
- W3169451353 cites W2023963920 @default.
- W3169451353 cites W2049508426 @default.
- W3169451353 cites W2054404145 @default.
- W3169451353 cites W2071576650 @default.
- W3169451353 cites W2082907106 @default.
- W3169451353 cites W2084755508 @default.
- W3169451353 cites W2087387762 @default.
- W3169451353 cites W2096192437 @default.
- W3169451353 cites W2100080030 @default.
- W3169451353 cites W2121008097 @default.
- W3169451353 cites W2125269936 @default.
- W3169451353 cites W2129629665 @default.
- W3169451353 cites W2131987814 @default.
- W3169451353 cites W2132744910 @default.
- W3169451353 cites W2132826329 @default.
- W3169451353 cites W2138021835 @default.
- W3169451353 cites W2150264242 @default.
- W3169451353 cites W2155662634 @default.
- W3169451353 cites W2169927995 @default.
- W3169451353 cites W2171676943 @default.
- W3169451353 cites W2621042176 @default.
- W3169451353 cites W2754103191 @default.
- W3169451353 cites W2767128594 @default.
- W3169451353 cites W2798401174 @default.
- W3169451353 cites W2883529983 @default.
- W3169451353 cites W2890593601 @default.
- W3169451353 cites W2898197178 @default.
- W3169451353 cites W2900941277 @default.
- W3169451353 cites W2911964244 @default.
- W3169451353 cites W2920797638 @default.
- W3169451353 cites W2947123069 @default.
- W3169451353 cites W2972788736 @default.
- W3169451353 cites W2991791649 @default.
- W3169451353 cites W3006528928 @default.
- W3169451353 cites W3102476541 @default.
- W3169451353 cites W3106295246 @default.
- W3169451353 cites W4244777963 @default.
- W3169451353 doi "https://doi.org/10.1002/mp.15049" @default.
- W3169451353 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34129688" @default.
- W3169451353 hasPublicationYear "2021" @default.
- W3169451353 type Work @default.
- W3169451353 sameAs 3169451353 @default.
- W3169451353 citedByCount "4" @default.
- W3169451353 countsByYear W31694513532022 @default.
- W3169451353 countsByYear W31694513532023 @default.
- W3169451353 crossrefType "journal-article" @default.
- W3169451353 hasAuthorship W3169451353A5004876604 @default.
- W3169451353 hasAuthorship W3169451353A5011400986 @default.
- W3169451353 hasAuthorship W3169451353A5012107855 @default.
- W3169451353 hasAuthorship W3169451353A5021951093 @default.
- W3169451353 hasAuthorship W3169451353A5026198361 @default.
- W3169451353 hasAuthorship W3169451353A5029055548 @default.
- W3169451353 hasAuthorship W3169451353A5053324036 @default.
- W3169451353 hasAuthorship W3169451353A5064451296 @default.
- W3169451353 hasAuthorship W3169451353A5090174631 @default.
- W3169451353 hasConcept C108583219 @default.
- W3169451353 hasConcept C114614502 @default.
- W3169451353 hasConcept C115901376 @default.
- W3169451353 hasConcept C119857082 @default.
- W3169451353 hasConcept C124101348 @default.
- W3169451353 hasConcept C126322002 @default.
- W3169451353 hasConcept C127413603 @default.
- W3169451353 hasConcept C13280743 @default.
- W3169451353 hasConcept C142724271 @default.
- W3169451353 hasConcept C154945302 @default.
- W3169451353 hasConcept C185798385 @default.
- W3169451353 hasConcept C205649164 @default.
- W3169451353 hasConcept C2776780178 @default.
- W3169451353 hasConcept C2778827112 @default.
- W3169451353 hasConcept C33923547 @default.
- W3169451353 hasConcept C41008148 @default.
- W3169451353 hasConcept C58471807 @default.
- W3169451353 hasConcept C71924100 @default.
- W3169451353 hasConcept C74193536 @default.
- W3169451353 hasConcept C78519656 @default.
- W3169451353 hasConcept C95190672 @default.
- W3169451353 hasConceptScore W3169451353C108583219 @default.