Recently, deep-learning-based approaches have been proposed for the classification of neuroimaging data related to Alzheimer’s disease (AD), and significant progress has been made. However, end-to-end learning that is capable of maximizing the impact of deep learning has yet to receive much attention due to the endemic challenge of neuroimaging caused by the scarcity of data. Thus, this study presents an approach meant to encourage the end-to-end learning of a volumetric convolutional neural network (CNN) model for four binary classification tasks (AD vs. normal control (NC), progressive mild cognitive impairment (pMCI) vs. NC, stable mild cognitive impairment (sMCI) vs. NC and pMCI vs. sMCI) based on magnetic resonance imaging (MRI) and visualizes its outcomes in terms of the decision of the CNNs without any human intervention. In the proposed approach, we use convolutional autoencoder (CAE)-based unsupervised learning for the AD vs. NC classification task, and supervised transfer learning is applied to solve the pMCI vs. sMCI classification task. To detect the most important biomarkers related to AD and pMCI, a gradient-based visualization method that approximates the spatial influence of the CNN model’s decision was applied. To validate the contributions of this study, we conducted experiments on the ADNI database, and the results demonstrated that the proposed approach achieved the accuracies of 86.60% and 73.95% for the AD and pMCI classification tasks respectively, outperforming other network models. In the visualization results, the temporal and parietal lobes were identified as key regions for classification.

BackgroundThe GOLD 2011 document proposed a new classification system for COPD combining symptom assessment by COPD assessment test (CAT) or modified Medical Research Council (mMRC) dyspnea scores, and exacerbation risk. We postulated that classification of COPD would be different by the symptom scale; CAT vs mMRC.MethodsOutpatients with COPD were enrolled from January to June in 2012. The patients were categorized into A, B, C, and D according to the GOLD 2011; patients were categorized twice with mMRC and CAT score for symptom assessment, respectively. Additionally, correlations between mMRC scores and each item of CAT scores were analyzed.ResultsClassification of 257 patients using the CAT score vs mMRC scale was as follows. By using CAT score, 60 (23.3%) patients were assigned to group A, 55 (21.4%) to group B, 21 (8.2%) to group C, and 121 (47.1%) to group D. On the basis of the mMRC scale, 97 (37.7%) patients were assigned to group A, 18 (7.0%) to group B, 62 (24.1%) to group C, and 80 (31.1%) to group D. The kappa of agreement for the GOLD groups classified by CAT and mMRC was 0.510. The mMRC score displayed a wide range of correlation with each CAT item (r = 0.290 for sputum item to r = 0.731 for dyspnea item, p < 0.001).ConclusionsThe classification of COPD produced by the mMRC or CAT score was not identical. Care should be taken when stratifying COPD patients with one symptom scale versus another according to the GOLD 2011 document.

Abstract-This paper proposes a novel hybrid genetic algorithm for feature selection. Local search operations are devised and embedded in hybrid GAs to fine-tune the search. The operations are parameterized in terms of their fine-tuning power, and their effectiveness and timing requirements are analyzed and compared. The hybridization technique produces two desirable effects: a significant improvement in the final performance and the acquisition of subset-size control. The hybrid GAs showed better convergence properties compared to the classical GAs. A method of performing rigorous timing analysis was developed, in order to compare the timing requirement of the conventional and the proposed algorithms. Experiments performed with various standard data sets revealed that the proposed hybrid GA is superior to both a simple GA and sequential search algorithms.Index Terms-Feature selection, hybrid genetic algorithm, sequential search algorithm, local search operation, atomic operation, multistart algorithm.

No abstract

No abstract