posted on 2020-09-25, 17:28authored byObioma Pelka, Christoph M. Friedrich, Felix Nensa, Christoph Mönninghoff, Louise Bloch, Karl-Heinz Jöckel, Sara Schramm, Sarah Sanchez Hoffmann, Angela Winkler, Christian Weimar, Martha Jokisch
Prediction performance of the LSTM classification model using various image input types. The highlighted values are the best per evaluation metric. Evaluation was calculated on the k = 5-fold cross validation sets from the training set with n = 561 participants of the ADNI Phase 1 dataset. The values are the average and standard deviation rates across all k = 5-fold cross validation sets. Visual representation were extracted using the ChestX-Ray8 database [16].