Alert button
Picture for Dornoosh Zonoobi

Dornoosh Zonoobi

Alert button

End-to-end detection-segmentation network with ROI convolution

Jan 08, 2018
Zichen Zhang, Min Tang, Dana Cobzas, Dornoosh Zonoobi, Martin Jagersand, Jacob L. Jaremko

Figure 1 for End-to-end detection-segmentation network with ROI convolution
Figure 2 for End-to-end detection-segmentation network with ROI convolution
Figure 3 for End-to-end detection-segmentation network with ROI convolution

We propose an end-to-end neural network that improves the segmentation accuracy of fully convolutional networks by incorporating a localization unit. This network performs object localization first, which is then used as a cue to guide the training of the segmentation network. We test the proposed method on a segmentation task of small objects on a clinical dataset of ultrasound images. We show that by jointly learning for detection and segmentation, the proposed network is able to improve the segmentation accuracy compared to only learning for segmentation.

* accepted at ISBI 2018 
Viaarxiv icon

Dependent Nonparametric Bayesian Group Dictionary Learning for online reconstruction of Dynamic MR images

Feb 12, 2015
Dornoosh Zonoobi, Shahrooz Faghih Roohi, Ashraf A. Kassim

Figure 1 for Dependent Nonparametric Bayesian Group Dictionary Learning for online reconstruction of Dynamic MR images
Figure 2 for Dependent Nonparametric Bayesian Group Dictionary Learning for online reconstruction of Dynamic MR images
Figure 3 for Dependent Nonparametric Bayesian Group Dictionary Learning for online reconstruction of Dynamic MR images
Figure 4 for Dependent Nonparametric Bayesian Group Dictionary Learning for online reconstruction of Dynamic MR images

In this paper, we introduce a dictionary learning based approach applied to the problem of real-time reconstruction of MR image sequences that are highly undersampled in k-space. Unlike traditional dictionary learning, our method integrates both global and patch-wise (local) sparsity information and incorporates some priori information into the reconstruction process. Moreover, we use a Dependent Hierarchical Beta-process as the prior for the group-based dictionary learning, which adaptively infers the dictionary size and the sparsity of each patch; and also ensures that similar patches are manifested in terms of similar dictionary atoms. An efficient numerical algorithm based on the alternating direction method of multipliers (ADMM) is also presented. Through extensive experimental results we show that our proposed method achieves superior reconstruction quality, compared to the other state-of-the- art DL-based methods.

Viaarxiv icon

Low-Rank and Sparse Matrix Decomposition with a-priori knowledge for Dynamic 3D MRI reconstruction

Nov 23, 2014
Dornoosh Zonoobi, Shahrooz Faghih Roohi, Ashraf A. Kassim

Figure 1 for Low-Rank and Sparse Matrix Decomposition with a-priori knowledge for Dynamic 3D MRI reconstruction
Figure 2 for Low-Rank and Sparse Matrix Decomposition with a-priori knowledge for Dynamic 3D MRI reconstruction
Figure 3 for Low-Rank and Sparse Matrix Decomposition with a-priori knowledge for Dynamic 3D MRI reconstruction
Figure 4 for Low-Rank and Sparse Matrix Decomposition with a-priori knowledge for Dynamic 3D MRI reconstruction

It has been recently shown that incorporating priori knowledge significantly improves the performance of basic compressive sensing based approaches. We have managed to successfully exploit this idea for recovering a matrix as a summation of a Low-rank and a Sparse component from compressive measurements. When applied to the problem of construction of 4D Cardiac MR image sequences in real-time from highly under-sampled $k-$space data, our proposed method achieves superior reconstruction quality compared to the other state-of-the-art methods.

* conference 
Viaarxiv icon