Helder Oliveira

Helder Oliveira
The University of Calgary | HBI · Department of Electrical and Computer Engineering

PhD in Electrical Engineering

About

37
Publications
7,968
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
122
Citations
Introduction
I have bachelor degree in Computer Science and masters and PhD in Electrical Engineering. Since 2019 I'm Postdoc at University of Calgary working with Bayesian Networks.
Additional affiliations
October 2019 - present
The University of Calgary
Position
  • PostDoc Position
December 2016 - June 2017
University of Rome Tor Vergata
Position
  • PhD Student
Description
  • Sandwich period
March 2016 - September 2019
University of São Paulo
Position
  • PhD Student

Publications

Publications (37)
Conference Paper
Full-text available
O Reconhecimento Óptico de Caracteres (Optical Charactere Recognition - OCR) é uma metodologia computacional capaz de extrair de forma completamente automática o texto (impresso ou manuscrito) contido em uma imagem digital. Embora avanços significativos tenham sido realizados nos últimos 40 anos com textos impressos baseados em alfabetos ocidentais...
Article
Full-text available
The novel coronavirus disease, COVID-19, has rapidly and abruptly changed the world as we knew it in 2020. It has become the most unprecedented challenge to analytic epidemiology (AE) in general and signal processing (SP) theories specifically. In this regard, medical imaging plays an important role for the management of COVID-19. SP and deep learn...
Preprint
Full-text available
The novel Coronavirus disease, COVID-19, has rapidly and abruptly changed the world as we knew in 2020. It becomes the most unprecedent challenge to analytic epidemiology in general and signal processing theories in specific. Given its high contingency nature and adverse effects across the world, it is important to develop efficient processing/lear...
Article
Architectural distortion (AD) is the earliest sign of breast cancer that can be detected on a mammogram, and it is usually associated with malignant tumors. Breast cancer is one of the major causes of death among women, and the chance of cure can increase significantly when detected early. Computer-aided detection (CAD) systems have been used in cl...
Conference Paper
This paper addresses the challenge of monitoring liveness of sleeping subjects, via breathing pattern monitoring at distance and under “night-light” conditions. We investigate videobased approach to estimate the breathing rate, based on chest or back movements. The ultimate application is to detect abnormalities in breathing, and, therefore, detect...
Article
Full-text available
Biometrics and biometric-enabled decision support systems (DSS) have become a mandatory part of complex dynamic systems such as security checkpoints, personal health monitoring systems, autonomous robots, and epidemiological surveillance. Risk, trust, and bias (R-T-B) are emerging measures of performance of such systems. The existing studies on the...
Preprint
Full-text available
Biometrics and biometric-enabled decision support systems (DSS) have become a mandatory part of complex dynamic systems such as security checkpoints, personal health monitoring systems, autonomous robots, and epidemiological surveillance. Risk, trust, and bias (R-T-B) are emerging measures of performance of such systems. The existing studies on the...
Preprint
Full-text available
Recognizing, assessing, countering, and mitigating the biases of different nature from heterogeneous sources is a critical problem in designing a cognitive Decision Support System (DSS). An example of such a system is a cognitive biometric-enabled security checkpoint. Biased algorithms affect the decision-making process in an unpredictable way, e.g...
Article
Background and objective: Full-field digital mammography (FFDM) is the predominant breast cancer screening exam used. However, with the emergence of digital breast tomosynthesis (DBT) the radiologists could improve early recognition of breast cancer signs. In this scenario, the detection of architectural distortion (AD) is still a challenging task....
Preprint
Full-text available
Early detection of breast cancer can increase treatment efficiency. Architectural Distortion (AD) is a very subtle contraction of the breast tissue and may represent the earliest sign of cancer. Since it is very likely to be unnoticed by radiologists, several approaches have been proposed over the years but none using deep learning techniques. To t...
Conference Paper
Full-text available
This paper proposes a computer-based system for automatic detection of architectural distortion of the breast (ADB) in digitized screen-film mammograms. ADB is a subtle contraction of the breast tissue that may represent the earliest sign of breast cancer. The proposed system has essentially two steps: feature extraction and classification. For the...
Conference Paper
Full-text available
This paper proposes the use of the bilateral filtering to denoise digital mammograms acquired with reduced radiation dose, improving their quality to mimic the signal-to-noise ratio of those acquired with the standard radiation dose. It is known that a small reduction in the radiation dose of a radiographic exam would increase the image degradation...
Conference Paper
Full-text available
Resumo: Esse trabalho apresenta uma nova proposta do algoritmo de médias não-locais para a filtragem do ruído quântico de imagens mamográficas digitais adquiridas com dose de radiação reduzida. Nessa nova abordagem, chamada de Variance Map Non-local Means (VM-NLM), a filtragem do ruído quântico é realizada no próprio domínio da imagem. Com isso, el...
Article
Full-text available
Purpose: This work proposes an accurate method for simulating dose reduction in digital mammography starting from a clinical image acquired with a standard dose.
Conference Paper
Full-text available
To ensure optimal clinical performance of digital mammography, it is necessary to obtain images with high spatial resolution and low noise, keeping radiation exposure as low as possible. These requirements directly affect the interpretation of radiologists. The quality of a digital image should be assessed using objective measurements. In general,...
Conference Paper
Full-text available
This paper presents a comparative study on the use of Non-Local Means algorithms (NLM) for filtering the quantum noise found in digital mammography with reduced radiation dose. It is known that a small decrease in radiation dose of a radiographic examination would cause an increase in the quantum noise that is embedded in the image, impairing medic...
Conference Paper
Full-text available
This paper investigates the use of two denoising filters, the Block-Matching and 3D Filtering (BM3D) and Wavelet transform with Shrink-Thresholding (WTST), to attenuate Poisson noise in digital mammography images. The main objective is to evaluate the possibility of reducing the radiation dose normally used for clinical acquisition, by using those...
Conference Paper
This paper investigates the use of a wavelet multiresolution analysis to reduce noise in mammographic images acquired with low levels of radiation dose. We studied the use of a wavelet denoising technique to filter the quantum noise that is incorporated in mammographic images when the radiation dose is reduced. Results were obtained by denoising a...
Conference Paper
Full-text available
The quality of clinical x-ray images is closely related to the radiation dose used in the imaging study. The general principle for selecting the radiation is ALARA (“as low as reasonably achievable”). The practical optimization, however, remains challenging. It is well known that reducing the radiation dose increases the quantum noise, which could...
Conference Paper
Full-text available
The main purpose of this work is to study the ability of denoising algorithms to reduce the radiation dose in Digital Breast Tomosynthesis (DBT) examinations. Clinical use of DBT is normally performed in “combo-mode”, in which, in addition to DBT projections, a 2D mammogram is taken with the standard radiation dose. As a result, patients have been...
Conference Paper
Full-text available
This paper investigates the use of the Block-Matching 3D algorithm (BM3D) to remove noise in mammographic images. The main objective is to study the possibility of using the BM3D technique to allow a radiation dose reduction in digital mammography, by removing the extra noise incorporated in the image when the photon-counting rate is reduced. Resul...
Conference Paper
Full-text available
It is well known that a reduction on the radiation dose in digital mammography increases image noise. The urge to optimize image quality vs. radiation dose caused the necessity of obtaining clinical images at different doses. However, acquiring several images from the same patient into different doses results in undesirable additional exposures and...
Conference Paper
Full-text available
This paper presents a study on the use of non-local means algorithm (NLM) as a tool for reducing radiation dose in digital mammography. It is known that a small decrease in radiation dose of an X-ray examination causes an increase in the quantum noise that is embedded in the image, affecting medical diagnosis. In this study, the proposal is to gene...
Conference Paper
Full-text available
Uma das operações básicas passível de ser feita sobre uma imagem é, indiscutivelmente, a detecção de arestas. Isto se deve em função do fato de que as bordas de um objeto são capazes de capturar sua forma e, muitas vezes, isso é suficiente para a resolução de inúmeros problemas associado às áreas de processamento de imagem e de visão computacional,...
Conference Paper
Full-text available
This paper presents a study on the use of non-local means algorithm (NLM) as a tool for noise filtering in digital mammography images acquired in low-dose rates. It is known that a small decrease in radiation dose of an X-ray examination causes an increase in the quantum noise that is embedded in the image, affecting medical diagnosis. In this stud...

Network

Cited By

Projects

Projects (2)
Project
Development of methods to improve the detection rate of "Architectural Distortion of Breast" in digital mammograms
Project
To develop new denoising algorithms to filter Poisson noise in breast images.