Robust Unmixing of Dynamic Sequences Using Regions of Interest

Filippi, Marc; Desvignes, Michel; Moisan, Éric

doi:10.1109/tmi.2017.2759661

Cited by 6 publications

(16 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dataset I was created to show unmixing of signals/spectra taking into account different situations that could occur in real applications such as fMRI or astronomical data unmixing. Dataset II is an example of realistic synthetic data in scintigraphy used in [18], for which the authors have proposed an unmixing method based on prior knowledge of the location of the regions of interest. This method, called Robust Unmixing of Dynamic Sequences Using Regions of Interest (RUDUR), has been compared in [18] to 2) Algorithm details: The ground truth is given by the localisation map in Fig.…”

Section: Evaluation On Synthetic Datasetsmentioning

confidence: 99%

“…In an effort to objectively evaluate the performances of our approach, we propose to test and compare our method on a more realistic synthetic data set of scintigraphy images created for the evaluation of the performances of the state-of-the-art RUDUR method [18]. We have reused the RUDUR code, as it is distributed by the authors [18].…”

Section: B Dataset IImentioning

confidence: 99%

“…1) Data description: This second dataset provides a first test case in which the method is confronted with a real application, on physical model-based simulations of scintigraphic images, with ground truth. It enables a comparison with a recent reference method in the field [18]. Region of interest-based unmixing methods are common in scintigraphy [5], [19], [23].…”

Section: B Dataset IImentioning

confidence: 99%

“…We rather aim at exploiting a segmentation information from a high spatial resolution image in order to improve the unmixing of spectral or temporal sources at a lower resolution image level. In some applications, such a segmentation map is not available, but approximate spatial location information can be provided by an expert who can define regions of interest (ROIs) (see for example the unmixing method for highly realistic simulated renography dataset in [18], [19]). This paper is organised as follow: section II presents the observation model and the dictionary learning approach for unmixing spatially structured data based on the spatial sparsity constraint.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Spatially Constrained Online Dictionary Learning for Source Separation

Bhanot

Meillier

Heitz

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Whether in medical imaging, astronomy or remote sensing, the data are increasingly complex. In addition to the spatial dimension, the data may contain temporal or spectral information that characterises the different sources present in the image. The compromise between spatial resolution and temporal/spectral resolution is often at the expense of spatial resolution, resulting in a potentially large mixing of sources in the same pixel/voxel. Source separation methods must incorporate spatial information to estimate the contribution and signature of each source in the image. We consider the particular case where the position of the sources is approximately known thanks to external information that may come from another imaging modality or from a priori knowledge. We propose a spatially constrained dictionary learning source separation algorithm that uses e.g. high resolution segmentation map or regions of interest defined by an expert to regularise the source contribution estimation. The originality of the proposed model is the replacement of the sparsity constraint classically expressed in the form of an 1 penalty on the localisation of sources by an indicator function exploiting the external source localisation information.The model is easily adaptable to different applications by adding or modifying the constraints on the sources properties in the optimisation problem. The performance of this algorithm has been validated on synthetic and quasi-real data, before being applied on real data previously analysed by other methods of the literature in order to compare the results. To illustrate the potential of the approach, different applications have been considered, from scintigraphic data to astronomy or fMRI data.

show abstract

Section: Evaluation On Synthetic Datasetsmentioning

confidence: 99%

Section: B Dataset IImentioning

confidence: 99%

Section: B Dataset IImentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spatially Constrained Online Dictionary Learning for Source Separation

Bhanot

Meillier

Heitz

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Blind-source separation (BSS) involves separating the best estimation of the hidden source signals from certain observed signals (at the receiving end) when the theoretical model of the signal and the source signal are unknown [12][13][14]. Specifically, underdetermined blind-source separation is a low-element model of sensors at the receiving end for signal processing, which remains an ill-posed and abstruse problem for information transmission [15][16][17][18]. At present, there are two types of solutions to address this issue.…”

Section: Introductionmentioning

confidence: 99%

Low-Element Image Restoration Based on an Out-of-Order Elimination Algorithm

Xie

Chen

et al. 2019

Entropy

View full text Add to dashboard Cite

To reduce the consumption of receiving devices, a number of devices at the receiving end undergo low-element treatment (the number of devices at the receiving end is less than that at the transmitting ends). The underdetermined blind-source separation system is a classic low-element model at the receiving end. Blind signal extraction in an underdetermined system remains an ill-posed problem, as it is difficult to extract all the source signals. To realize fewer devices at the receiving end without information loss, this paper proposes an image restoration method for underdetermined blind-source separation based on an out-of-order elimination algorithm. Firstly, a chaotic system is used to perform hidden transmission of source signals, where the source signals can hardly be observed and confidentiality is guaranteed. Secondly, empirical mode decomposition is used to decompose and complement the missing observed signals, and the fast independent component analysis (FastICA) algorithm is used to obtain part of the source signals. Finally, all the source signals are successfully separated using the out-of-order elimination algorithm and the FastICA algorithm. The results show that the performance of the underdetermined blind separation algorithm is related to the configuration of the transceiver antenna. When the signal is 3 × 4 antenna configuration, the algorithm in this paper is superior to the comparison algorithm in signal recovery, and its separation performance is better for a lower degree of missing array elements. The end result is that the algorithms discussed in this paper can effectively and completely extract all the source signals.

show abstract

A weakly supervised NMF method to decipher molecular subtype-related dynamic patterns in breast DCE-MR images

Guan,

Fan,

2023

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is an important imaging modality for breast cancer diagnosis. Intratumoral heterogeneity causes a major challenge in the interpretation of breast DCE-MRI. Previous studies have introduced decomposition methods on DCE-MRI to reveal intratumoral heterogeneity by analyzing distinct dynamic patterns within each tumor. However, these methods estimated the dynamic patterns and their corresponding component coefficients in an unsupervised manner, without considering any clinically relevant information. Approach. To decipher molecular subtype-related dynamic patterns, we propose a weakly supervised nonnegative matrix factorization method (WSNMF), which is able to decompose the pixel kinetics of DCE-MRI with image-level subtype labels. The WSNMF is developed based on a discriminant NMF to utilize coarse-grained subtype information, in which between- and within-class scatters are defined on the mean vector of component coefficients over all pixels in each tumor, rather than directly on the vector of component coefficients of each pixel. Main results. Experiments demonstrated that the dynamic patterns identified by WSNMF had superior performance in distinguishing between luminal A and the other subtype tumors. The classification performance was evaluated using the area under the receiver operating characteristic curve (AUC). WSNMF yielded better classification performance (AUC = 0.822) than other heterogeneity analysis methods, including two partitioning based methods (KPC with AUC = 0.697 and TTP with AUC =0.760) and two unsupervised decomposition-based methods (PCA with AUC = 0.774 and NMF with AUC = 0.797). Significance. Our method adds a valuable new perspective into DCEMRI decomposition-based heterogeneity analysis by taking advantage of intrinsic tumor characteristics to improve the diagnosis of breast cancer.

show abstract

Robust Unmixing of Dynamic Sequences Using Regions of Interest

Cited by 6 publications

References 25 publications

Spatially Constrained Online Dictionary Learning for Source Separation

Spatially Constrained Online Dictionary Learning for Source Separation

Low-Element Image Restoration Based on an Out-of-Order Elimination Algorithm

A weakly supervised NMF method to decipher molecular subtype-related dynamic patterns in breast DCE-MR images

Contact Info

Product

Resources

About