FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951733170> ?p ?o ?g. }

• W2951733170 abstract "Abstract A large number of papers have introduced novel machine learning and feature extraction methods for automatic classification of Alzheimer’s disease (AD). However, while the vast majority of these works use the public dataset ADNI for evaluation, they are difficult to reproduce because different key components of the validation are often not readily available. These components include selected participants and input data, image preprocessing and cross-validation procedures. The performance of the different approaches is also difficult to compare objectively. In particular, it is often difficult to assess which part of the method (e.g. preprocessing, feature extraction or classification algorithms) provides a real improvement, if any. In the present paper, we propose a framework for reproducible and objective classification experiments in AD using three publicly available datasets (ADNI, AIBL and OASIS). The framework comprises: i) automatic conversion of the three datasets into a standard format (BIDS); ii) a modular set of preprocessing pipelines, feature extraction and classification methods, together with an evaluation framework, that provide a baseline for benchmarking the different components. We demonstrate the use of the framework for a large-scale evaluation on 1960 participants using T1 MRI and FDG PET data. In this evaluation, we assess the influence of different modalities, preprocessing, feature types (regional or voxel-based features), classifiers, training set sizes and datasets. Performances were in line with the state-of-the-art. FDG PET outperformed T1 MRI for all classification tasks. No difference in performance was found for the use of different atlases, image smoothing, partial volume correction of FDG PET images, or feature type. Linear SVM and L2-logistic regression resulted in similar performance and both outperformed random forests. The classification performance increased along with the number of subjects used for training. Classifiers trained on ADNI generalized well to AIBL and OASIS, performing better than the classifiers trained and tested on each of these datasets independently. All the code of the framework and the experiments is publicly available." @default.
• W2951733170 created "2019-06-27" @default.
• W2951733170 creator A5000067675 @default.
• W2951733170 creator A5005778444 @default.
• W2951733170 creator A5022937525 @default.
• W2951733170 creator A5023757770 @default.
• W2951733170 creator A5032959358 @default.
• W2951733170 creator A5035338217 @default.
• W2951733170 creator A5043406904 @default.
• W2951733170 creator A5044646422 @default.
• W2951733170 creator A5053042574 @default.
• W2951733170 creator A5073134184 @default.
• W2951733170 creator A5078737983 @default.
• W2951733170 creator A5079882077 @default.
• W2951733170 creator A5080254367 @default.
• W2951733170 creator A5083973401 @default.
• W2951733170 creator A5084369967 @default.
• W2951733170 creator A5091095411 @default.
• W2951733170 date "2018-04-06" @default.
• W2951733170 modified "2023-10-18" @default.
• W2951733170 title "Reproducible evaluation of classification methods in Alzheimer’s disease: framework and application to MRI and PET data" @default.
• W2951733170 cites W1026628557 @default.
• W2951733170 cites W1434354835 @default.
• W2951733170 cites W1906409993 @default.
• W2951733170 cites W1938122124 @default.
• W2951733170 cites W1957380691 @default.
• W2951733170 cites W1977714477 @default.
• W2951733170 cites W1978763244 @default.
• W2951733170 cites W1984544413 @default.
• W2951733170 cites W2001648635 @default.
• W2951733170 cites W2011481459 @default.
• W2951733170 cites W2014418634 @default.
• W2951733170 cites W2017237939 @default.
• W2951733170 cites W2019583087 @default.
• W2951733170 cites W2042865986 @default.
• W2951733170 cites W2044614452 @default.
• W2951733170 cites W2049546272 @default.
• W2951733170 cites W2050861431 @default.
• W2951733170 cites W2054540100 @default.
• W2951733170 cites W2055649795 @default.
• W2951733170 cites W2058046532 @default.
• W2951733170 cites W2063237661 @default.
• W2951733170 cites W2064173428 @default.
• W2951733170 cites W2065338300 @default.
• W2951733170 cites W2069528898 @default.
• W2951733170 cites W2074267385 @default.
• W2951733170 cites W2078524519 @default.
• W2951733170 cites W2079073956 @default.
• W2951733170 cites W2079484785 @default.
• W2951733170 cites W2083099567 @default.
• W2951733170 cites W2086967335 @default.
• W2951733170 cites W2092496538 @default.
• W2951733170 cites W2093602450 @default.
• W2951733170 cites W2094637188 @default.
• W2951733170 cites W2101282194 @default.
• W2951733170 cites W2106931873 @default.
• W2951733170 cites W2113127248 @default.
• W2951733170 cites W2115017507 @default.
• W2951733170 cites W2115799070 @default.
• W2951733170 cites W2116709840 @default.
• W2951733170 cites W2122328291 @default.
• W2951733170 cites W2129497119 @default.
• W2951733170 cites W2129965408 @default.
• W2951733170 cites W2135011268 @default.
• W2951733170 cites W2146089088 @default.
• W2951733170 cites W2150534249 @default.
• W2951733170 cites W2153171432 @default.
• W2951733170 cites W2155298532 @default.
• W2951733170 cites W2156220037 @default.
• W2951733170 cites W2167840686 @default.
• W2951733170 cites W2171380313 @default.
• W2951733170 cites W2171723438 @default.
• W2951733170 cites W2171831801 @default.
• W2951733170 cites W2310177520 @default.
• W2951733170 cites W2335094569 @default.
• W2951733170 cites W2421101021 @default.
• W2951733170 cites W2542549468 @default.
• W2951733170 cites W2571093196 @default.
• W2951733170 cites W2582524520 @default.
• W2951733170 cites W2590116164 @default.
• W2951733170 cites W2606546398 @default.
• W2951733170 cites W2789348411 @default.
• W2951733170 cites W282373936 @default.
• W2951733170 cites W3047446556 @default.
• W2951733170 cites W4230920194 @default.
• W2951733170 cites W569000258 @default.
• W2951733170 doi "https://doi.org/10.1101/274324" @default.
• W2951733170 hasPublicationYear "2018" @default.
• W2951733170 type Work @default.
• W2951733170 sameAs 2951733170 @default.
• W2951733170 citedByCount "3" @default.
• W2951733170 countsByYear W29517331702020 @default.
• W2951733170 countsByYear W29517331702022 @default.
• W2951733170 crossrefType "posted-content" @default.
• W2951733170 hasAuthorship W2951733170A5000067675 @default.
• W2951733170 hasAuthorship W2951733170A5005778444 @default.
• W2951733170 hasAuthorship W2951733170A5022937525 @default.
• W2951733170 hasAuthorship W2951733170A5023757770 @default.
• W2951733170 hasAuthorship W2951733170A5032959358 @default.
• W2951733170 hasAuthorship W2951733170A5035338217 @default.

• next