RECORD
Bilinear pooling and metric learning network for early Alzheimer's disease identification with FDG-PET images
Image and Video Processing · Submitted 9 Nov 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experiments show that most metrics are improved after adding the bilinear pooling module and metric losses to the Baseline model respectively.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
FDG-PET reveals altered brain metabolism in individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD). Some biomarkers derived from FDG-PET by computer-aided-diagnosis (CAD) technologies have been proved that they can accurately diagnosis normal control (NC), MCI, and AD. However, the studies of identification of early MCI (EMCI) and late MCI (LMCI) with FDG-PET images are still insufficient. Compared with studies based on fMRI and DTI images, the researches of the inter-region representation features in FDG-PET images are insufficient. Moreover, considering the variability in different individuals, some hard samples which are very similar with both two classes limit the classification performance. To tackle these problems, in this paper, we propose a novel bilinear pooling and metric learning network (BMNet), which can extract the inter-region representation features and distinguish hard samples by constructing embedding space. To validate the proposed method, we collect 998 FDG-PET images from ADNI. Following the common preprocessing steps, 90 features are extracted from each FDG-PET image according to the automatic anatomical landmark (AAL) template and then sent into the proposed network. Extensive 5-fold cross-validation experiments are performed for multiple two-class classifications. Experiments show that most metrics are improved after adding the bilinear pooling module and metric losses to the Baseline model respectively. Specifically, in the classification task between EMCI and LMCI, the specificity improves 6.38% after adding the triple metric loss, and the negative predictive value (NPV) improves 3.45% after using the bilinear pooling module.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | FDG-PET reveals altered brain metabolism in individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD). | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s1 | Some biomarkers derived from FDG-PET by computer-aided-diagnosis (CAD) technologies have been proved that they can accurately diagnosis normal control (NC), MCI, and AD. | background 1.00 | 0.04 | 0.03 | asserted 1.00 |
| s2 | However, the studies of identification of early MCI (EMCI) and late MCI (LMCI) with FDG-PET images are still insufficient. | gap 1.00 | 0.07 | 0.02 | asserted 0.99 |
| s3 | Compared with studies based on fMRI and DTI images, the researches of the inter-region representation features in FDG-PET images are insufficient. | gap 0.97 | 0.06 | 0.02 | asserted 1.00 |
| s4 | Moreover, considering the variability in different individuals, some hard samples which are very similar with both two classes limit the classification performance. | gap 0.66 | 0.08 | 0.02 | asserted 0.96 |
| s5 | To tackle these problems, in this paper, we propose a novel bilinear pooling and metric learning network (BMNet), which can extract the inter-region representation features and distinguish hard samples by constructing embedding space. | contribution 0.89 | 0.85 | 0.23 | asserted 0.98 |
| s6 | To validate the proposed method, we collect 998 FDG-PET images from ADNI. | method 0.98 | 0.97 | 0.02 | asserted 1.00 |
| s7 | Following the common preprocessing steps, 90 features are extracted from each FDG-PET image according to the automatic anatomical landmark (AAL) template and then sent into the proposed network. | method 1.00 | 0.93 | 0.02 | asserted 0.99 |
| s8 | Extensive 5-fold cross-validation experiments are performed for multiple two-class classifications. | method 1.00 | 0.95 | 0.03 | asserted 0.79 |
| s9 | Experiments show that most metrics are improved after adding the bilinear pooling module and metric losses to the Baseline model respectively. | result 1.00 | 0.96 | 0.36 | asserted 1.00 |
| s10 | Specifically, in the classification task between EMCI and LMCI, the specificity improves 6.38% after adding the triple metric loss, and the negative predictive value (NPV) improves 3.45% after using the bilinear pooling module. | result 1.00 | 0.97 | 0.30 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
FDG-PET reveals altered brain metabolism in individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD). Some biomarkers derived from FDG-PET by computer-aided-diagnosis (CAD) technologies have been proved that they can accurately diagnosis normal control (NC), MCI, and AD. However, the studies of identification of early MCI (EMCI) and late MCI (LMCI) with FDG-PET images are still insufficient. Compared with studies based on fMRI and DTI images, the researches of the inter-region representation features in FDG-PET images are insufficient. Moreover, considering the variability in different individuals, some hard samples which are very similar with both two classes limit the classification performance. To tackle these problems, in this paper, we propose a novel bilinear pooling and metric learning network (BMNet), which can extract the inter-region representation features and distinguish hard samples by constructing embedding space. To validate the proposed method, we collect 998 FDG-PET images from ADNI. Following the common preprocessing steps, 90 features are extracted from each FDG-PET image according to the automatic anatomical landmark (AAL) template and then sent into the proposed network. Extensive 5-fold cross-validation experiments are performed for multiple two-class classifications. Experiments show that most metrics are improved after adding the bilinear pooling module and metric losses to the Baseline model respectively. Specifically, in the classification task between EMCI and LMCI, the specificity improves 6.38% after adding the triple metric loss, and the negative predictive value (NPV) improves 3.45% after using the bilinear pooling module.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.