kwic
low
low
right
off
ON
185
1
100
500
strict
ELIZA cgi-bash version rev. 1.90
- Medical English LInking keywords finder for the PubMed Zipped Archive (ELIZA) -
return
kwic search for low out of >500 occurrences
318584 occurrences (No.68 in the rank) during 5 years in the PubMed. [no cache] 500 found
--- ABSTRACT ---
--- ABSTRACT END ---
[frequency of next (right) word to low]
318584 occurrences (No.68 in the rank) during 5 years in the PubMed. [no cache] 500 found
| 185) We believe that there exist latent non-linear complicated patterns inherent in the low-level features such as relations among features. |
| PMID:24363140 DOI:10.1007/s00429-013-0687-3 |
| 2015 Brain structure & function |
| * Latent feature representation with stacked auto-encoder for AD/MCI diagnosis. |
| - Recently, there have been great interests for computer-aided diagnosis of Alzheimer's disease (AD) and its prodromal stage, mild cognitive impairment (MCI). Unlike the previous methods that considered simple low-level features such as gray matter tissue volumes from MRI, and mean signal intensities from PET, in this paper, we propose a deep learning-based latent feature representation with a stacked auto-encoder (SAE). We believe that there exist latent non-linear complicated patterns inherent in the low-level features such as relations among features. Combining the latent information with the original features helps build a robust model in AD/MCI classification, with high diagnostic accuracy. Furthermore, thanks to the unsupervised characteristic of the pre-training in deep learning, we can benefit from the target-unrelated samples to initialize parameters of SAE, thus finding optimal parameters in fine-tuning with the target-related samples, and further enhancing the classification performances across four binary classification problems: AD vs. healthy normal control (HC), MCI vs. HC, AD vs. MCI, and MCI converter (MCI-C) vs. MCI non-converter (MCI-NC). In our experiments on ADNI dataset, we validated the effectiveness of the proposed method, showing the accuracies of 98.8, 90.7, 83.7, and 83.3 % for AD/HC, MCI/HC, AD/MCI, and MCI-C/MCI-NC classification, respectively. We believe that deep learning can shed new light on the neuroimaging data analysis, and our work presented the applicability of this method to brain disease diagnosis. |
[
right
kwic]
(1)21  and |
(18)4 or |
(35)2 Chilean |
(52)2 energy |
| (2)19 laser |
(19)4 socioeconomic |
(36)2 HLB |
(53)2 families |
| (3)11 doses |
(20)3 Er:YAG |
(37)2 OAs |
(54)2 genetic |
| (4)11 levels |
(21)3 O2 |
(38)2 acculturation |
(55)2 group |
| (5)10 *null* | (22)3 PFR |
(39)2 activities |
(56)2 maternal |
| (6)10 cost |
(23)3 PbB |
(40)2 activity |
(57)2 method |
| (7)10 lipoprotein |
(24)3 STT |
(41)2 after |
(58)2 molecular |
| (8)8 back |
(25)3 concentrations |
(42)2 areas |
(59)2 oral |
| (9)8 birth |
(26)3 educational |
(43)2 at |
(60)2 pH |
| (10)8 dose |
(27)3 features |
(44)2 bioavailability |
(61)2 peer |
| (11)7 in |
(28)3 risk |
(45)2 body |
(62)2 population |
| (12)7 level |
(29)3 serum |
(46)2 cancer |
(63)2 radiation |
| (13)6 birthweight |
(30)3 shear |
(47)2 children |
(64)2 resilience |
| (14)5 but |
(31)3 tumours |
(48)2 coverage |
(65)2 running |
| (15)4 as |
(32)3 vagal |
(49)2 degree |
(66)2 sensitivity |
| (16)4 carbon |
(33)3 water |
(50)2 density |
(67)2 settings |
| (17)4 income |
(34)3 whole-body |
(51)2 education |
(68)2 temperature |
add keyword
--- WordNet output for low ---