RECORD
Reconstructing Subject-Specific Effect Maps
Computer Vision and Pattern Recognition · Submitted 10 Jan 2017
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Results on synthetic data demonstrate that using RSM yields higher detection accuracy compared to using models directly or with bootstrap averaging.
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
Predictive models allow subject-specific inference when analyzing disease related alterations in neuroimaging data. Given a subject's data, inference can be made at two levels: global, i.e. identifiying condition presence for the subject, and local, i.e. detecting condition effect on each individual measurement extracted from the subject's data. While global inference is widely used, local inference, which can be used to form subject-specific effect maps, is rarely used because existing models often yield noisy detections composed of dispersed isolated islands. In this article, we propose a reconstruction method, named RSM, to improve subject-specific detections of predictive modeling approaches and in particular, binary classifiers. RSM specifically aims to reduce noise due to sampling error associated with using a finite sample of examples to train classifiers. The proposed method is a wrapper-type algorithm that can be used with different binary classifiers in a diagnostic manner, i.e. without information on condition presence. Reconstruction is posed as a Maximum-A-Posteriori problem with a prior model whose parameters are estimated from training data in a classifier-specific fashion. Experimental evaluation is performed on synthetically generated data and data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Results on synthetic data demonstrate that using RSM yields higher detection accuracy compared to using models directly or with bootstrap averaging. Analyses on the ADNI dataset show that RSM can also improve correlation between subject-specific detections in cortical thickness data and non-imaging markers of Alzheimer's Disease (AD), such as the Mini Mental State Examination Score and Cerebrospinal Fluid amyloid-$\beta$ levels. Further reliability studies on the longitudinal ADNI dataset show improvement on detection reliability when RSM is used.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Predictive models allow subject-specific inference when analyzing disease related alterations in neuroimaging data. | background 1.00 | 0.06 | 0.03 | asserted 0.89 |
| s1 | Given a subject's data, inference can be made at two levels: global, i.e. identifiying condition presence for the subject, and local, i.e. detecting condition effect on each individual measurement extracted from the subject's data. | background 1.00 | 0.06 | 0.03 | asserted 0.92 |
| s2 | While global inference is widely used, local inference, which can be used to form subject-specific effect maps, is rarely used because existing models often yield noisy detections composed of dispersed isolated islands. | gap 0.58 | 0.08 | 0.05 | asserted 1.00 |
| s3 | In this article, we propose a reconstruction method, named RSM, to improve subject-specific detections of predictive modeling approaches and in particular, binary classifiers. | contribution 1.00 | 0.84 | 0.09 | asserted 0.99 |
| s4 | RSM specifically aims to reduce noise due to sampling error associated with using a finite sample of examples to train classifiers. | method 0.56 | 0.36 | 0.04 | asserted 0.99 |
| s5 | The proposed method is a wrapper-type algorithm that can be used with different binary classifiers in a diagnostic manner, i.e. without information on condition presence. | method 0.96 | 0.64 | 0.04 | asserted 1.00 |
| s6 | Reconstruction is posed as a Maximum-A-Posteriori problem with a prior model whose parameters are estimated from training data in a classifier-specific fashion. | method 1.00 | 0.81 | 0.03 | asserted 1.00 |
| s7 | Experimental evaluation is performed on synthetically generated data and data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. | method 0.95 | 0.93 | 0.02 | asserted 0.94 |
| s8 | Results on synthetic data demonstrate that using RSM yields higher detection accuracy compared to using models directly or with bootstrap averaging. | result 1.00 | 0.96 | 0.21 | asserted 1.00 |
| s9 | Analyses on the ADNI dataset show that RSM can also improve correlation between subject-specific detections in cortical thickness data and non-imaging markers of Alzheimer's Disease (AD), such as the Mini Mental State Examination Score and Cerebrospinal Fluid amyloid-$\beta$ levels. | result 1.00 | 0.95 | 0.23 | asserted 0.96 |
| s10 | Further reliability studies on the longitudinal ADNI dataset show improvement on detection reliability when RSM is used. | result 1.00 | 0.94 | 0.15 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v3
- 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
Predictive models allow subject-specific inference when analyzing disease related alterations in neuroimaging data. Given a subject's data, inference can be made at two levels: global, i.e. identifiying condition presence for the subject, and local, i.e. detecting condition effect on each individual measurement extracted from the subject's data. While global inference is widely used, local inference, which can be used to form subject-specific effect maps, is rarely used because existing models often yield noisy detections composed of dispersed isolated islands. In this article, we propose a reconstruction method, named RSM, to improve subject-specific detections of predictive modeling approaches and in particular, binary classifiers. RSM specifically aims to reduce noise due to sampling error associated with using a finite sample of examples to train classifiers. The proposed method is a wrapper-type algorithm that can be used with different binary classifiers in a diagnostic manner, i.e. without information on condition presence. Reconstruction is posed as a Maximum-A-Posteriori problem with a prior model whose parameters are estimated from training data in a classifier-specific fashion. Experimental evaluation is performed on synthetically generated data and data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Results on synthetic data demonstrate that using RSM yields higher detection accuracy compared to using models directly or with bootstrap averaging. Analyses on the ADNI dataset show that RSM can also improve correlation between subject-specific detections in cortical thickness data and non-imaging markers of Alzheimer's Disease (AD), such as the Mini Mental State Examination Score and Cerebrospinal Fluid amyloid-$\beta$ levels. Further reliability studies on the longitudinal ADNI dataset show improvement on detection reliability when RSM is used.
Human review
How the literature uses it
1 arXiv paper cite this in 3 sentences
Papers citing it · 1 sentence without a confident label
Uses its method or tool 1 paper
-
We closely followed the synthetic data generation process described in [ref] where disease effects were studied in smaller cohorts of registered images.
Visual Feature Attribution using Wasserstein GANs · Synthetic experiments · 0.97
Cites it as background 1 paper
-
Maumet et al. took a one-versus-all group analysis approach [ref] , while Konukoglu and Glocker extracted subject-specific maps with predictive models and Markov Random Field restoration [ref] .
Visual Feature Attribution using Wasserstein GANs · Statistical disease models · 0.82
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.