Leonardo A. Ferreira’s research while affiliated with Centro Universitário Fundação Santo André and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (8)


Reconstructing Electrical Impedance Tomography 3D Brain Images with Anatomical Atlas and Total Variation Priors
  • Conference Paper

January 2024

·

14 Reads

IFMBE proceedings

Roberto G. Beraldo

·

Leonardo A. Ferreira

·

·

[...]

·

Electrical Impedance Tomography (EIT) is an imaging modality that allows the visualization of internal resistivities of a region of interest from electrical measurements external to the same region. In this work, we reconstruct 3D static images using two regularization terms, an anatomical atlas with 1\ell _1-norm and a total variation (TV) term. We chose the iteratively reweighted least squares (IRLS) algorithm to approximate the 1\ell _1-norms by quadratic terms and the Gauss-Newton algorithm to perform the optimization of the resulting functional. Together with the anatomical atlas, using a traditional 2\ell _2-norm and a high-pass filter as the regularizer tends to reconstruct the target on the mesh elements near the region boundary. In comparison, the reconstructed targets with the proposed method are better located, especially when reconstructing multiple targets, in addition to detecting a higher resistivity variation with the same number of iterations.


2D Time-Difference Electrical Impedance Tomography Image Reconstruction in a Head Model with Regularization by Denoising

January 2024

·

9 Reads

IFMBE proceedings

Time-Difference Electrical Impedance Tomography (TDEIT) is an imaging technique to visualize resistivity changes over time in a region of interest. Regularization is necessary because TDEIT is an ill-posed problem. In this work, we use Regularization by Denoising (RED) with four different denoisers to reconstruct brain images in a simplified 2D head model. We compared the RED results to two traditional reconstruction methods, generalized Tikhonov regularization and total variation regularization. In both the noiseless and the noisy scenarios, we achieved the best results using RED with non-local means as the denoiser in relation to figures of merit such as ringing, resolution and shape deformation.


2D Electrical Impedance Tomography Brain Image Reconstruction Using Deep Image Prior

January 2024

·

13 Reads

·

2 Citations

IFMBE proceedings

Electrical impedance tomography (EIT) is a medical imaging modality that has the potential to benefit diagnosing, monitoring, and understanding several pathological conditions. However, some regions of the body, such as the brain, are more challenging to reconstruct, demanding improvements before the technique can be used in clinical practice. In this study, we implemented and evaluated an algorithm for 2D static EIT image reconstruction based on the Deep Image Prior (DIP) method. The method was tested in measurements calculated from a computational human head model, where we included a region representing the occurrence of a stroke. The results showed that the DIP-based algorithm had some advantages compared to a more classical method, such as robustness to noise and independence of an initial solution. Therefore, this method could be better suited for real-life EIT image reconstructions.





Anatomical atlas of the upper part of the human head for electroencephalography and bioimpedance applications
  • Article
  • Full-text available

October 2021

·

35 Reads

·

11 Citations

Physiological Measurement

Objective. The objective of this work is to develop a 4D (3D+T) statistical anatomical atlas of the electrical properties of the upper part of the human head for cerebral electrophysiology and bioimpedance applications. Approach. The atlas was constructed based on 3D magnetic resonance images (MRI) of 107 human individuals and comprises the electrical properties of the main internal structures and can be adjusted for specific electrical frequencies. T1w+T2w MRI images were used to segment the main structures of the head while angiography MRI was used to segment the main arteries. The proposed atlas also comprises a time-varying model of arterial brain circulation, based on the solution of the Navier–Stokes equation in the main arteries and their vascular territories. Main results. High-resolution, multi-frequency and time-varying anatomical atlases of resistivity, conductivity and relative permittivity were created and evaluated using a forward problem solver for EIT. The atlas was successfully used to simulate electrical impedance tomography measurements indicating the necessity of signal-to-noise between 100 and 125 dB to identify vascular changes due to the cardiac cycle, corroborating previous studies. The source code of the atlas and solver are freely available to download. Significance. Volume conductor problems in cerebral electrophysiology and bioimpedance do not have analytical solutions for nontrivial geometries and require a 3D model of the head and its electrical properties for solving the associated PDEs numerically. Ideally, the model should be made with patient-specific information. In clinical practice, this is not always the case and an average head model is often used. Also, the electrical properties of the tissues might not be completely known due to natural variability. Anatomical atlases are important tools for in silico studies on cerebral circulation and electrophysiology that require statistically consistent data, e.g. machine learning, sensitivity analyses, and as a benchmark to test inverse problem solvers.

Download

Figure 2: Slices of the reference image MNI ICBM 152.
Figure 3: Superior aortic system considered in the simulations. The names of the vessels are presented in Table 1.
Figure 4: Main cerebral vascular territories. Acronyms: Anterior cerebral artery (ACA), Middle cerebral artery (MCA), Posterior cerebral artery (PCA), Superior cerebellar artery (SCA).
Geometrical and mechanical properties of the arteries.
Anatomical atlas of the upper part of the human head for electroencephalography and bioimpedance applications

August 2021

·

266 Reads

Volume conductor problems in cerebral electrophysiology and bioimpedance do not have analytical solutions for nontrivial geometries and require a 3D model of the head and its electrical properties for solving the associated PDEs numerically. Ideally, the model should be made with patient-specific information. In clinical practice, this is not always the case and an average head model is often used. Also, the electrical properties of the tissues might not be completely known due to natural variability. The objective of this work is to develop a 4D (3D+T) statistical anatomical atlas of the electrical properties of the upper part of the human head for cerebral electrophysiology and bioimpedance applications. The atlas is an important tool for in silico studies on cerebral circulation and electrophysiology that require statistically consistent data, e.g., machine learning, sensitivity analyses, and as a benchmark to test inverse problem solvers. The atlas was constructed based on MRI images of human individuals and comprises the electrical properties of the main internal structures and can be adjusted for specific electrical frequencies. The proposed atlas also comprises a time-varying model of arterial brain circulation, based on the solution of the Navier-Stokes equation in the main arteries and their vascular territories. The atlas was successfully used to simulate electrical impedance tomography measurements indicating the necessity of signal-to-noise between 100 and 125dB to identify vascular changes due to the cardiac cycle, corroborating previous studies.

Citations (3)


... 00X: KTC example code with the smoothness prior from (14) and λ = 1 1 ; 01B: This was the second submission of our group to the KTC 2 . It was based on the deep image prior [38] with total variation regularization [14]; 02G: (3 rd place) A level set method with gradient descent for EIT 3 ; 06B: (1 st place) A conditional diffusion model for EIT segmentation 4 . The results were generated according to the original codes submitted to the KTC2023, without modifications. ...

Reference:

Post-processing electrical impedance tomography reconstructions with incomplete data using convolutional neural networks
2D Electrical Impedance Tomography Brain Image Reconstruction Using Deep Image Prior
  • Citing Conference Paper
  • January 2024

IFMBE proceedings

... Since the limitedangle problem is ill-posed, regularization strategies such as total variation (TV) [7] and sparsity constraints [5] are often used to incorporate prior information, such as piecewise constant solutions or specific shapes. Increasingly, Deep Image Priors (DIP) [22] have been used to regularize the reconstructions to favor solutions with more "natural" image statistics [8,3]. These methods are computationally intensive but offer flexibility in integrating priors and physical models of the imaging system. ...

Deep image prior with sparsity constraint for limited-angle computed tomography reconstruction
  • Citing Article
  • January 2023

Applied Mathematics for Modern Challenges

... Apesar disso, o mínimo obtido pela otimização não se altera, pois a raiz quadrada é uma função monótona crescente. Calculando-se os parâmetros a partir da Equação Entre os priors possíveis nesse framework, estão aqueles que não são facilmente expressadas em termos quantitativos [58], como os atlas anatômicos [217]. ...

Anatomical atlas of the upper part of the human head for electroencephalography and bioimpedance applications

Physiological Measurement