Helder C. R. Oliveira
I am a Postdoctoral Fellow at the University of Calgary where I work with Bayesian networks.
My background is in medical imaging (mammography and digital breast tomosynthesis), machine learning and computer vision. My work with mammography aimed to detect "architectural distortion of the breast", a very sublet sign of what could become breast cancer. I also worked with denoising filters (BM3D, NLM, Wavelet based) to remove spared noise when the mammography is acquired with a low radiation dose.
My background is in medical imaging (mammography and digital breast tomosynthesis), machine learning and computer vision. My work with mammography aimed to detect "architectural distortion of the breast", a very sublet sign of what could become breast cancer. I also worked with denoising filters (BM3D, NLM, Wavelet based) to remove spared noise when the mammography is acquired with a low radiation dose.
news
Jan 22, 2022
Nov 13, 2021
New web page layout!
projects
some of the projects I have worked on
Decision Support for Infection Outbreak Analysis: the case of the Diamond Princess cruise ship
Conference: 2021 IEEE Symp. Series on Computational Intelligence (SSCI).
Code or Jupyter Notebook.
A cross-cutting approach for tracking architectural distortion locii on digital breast tomosynthesis slices
Journal: Biomedical Signal Processing and Control.
Exploratory learning with convolutional autoencoder for discrimination of architectural distortion in digital mammography
Conference: SPIE Medical Imaging 2019: Computer-Aided Diagnosis.
Reduction of false-positives in a CAD scheme for automated detection of architectural distortion in digital mammography
Conference: SPIE Medical Imaging 2018: Computer-Aided Diagnosis.
Validation of no-reference image quality index for the assessment of digital mammographic images
Conference: SPIE Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment.
Use of Wavelet Multiresolution Analysis to Reduce Radiation Dose in Digital Mammography
Conference: 2015 IEEE 28th Intl Symp. on Computer-Based Medical Systems.
Code.
Feasibility study of dose reduction in digital breast tomosynthesis using non-local denoising algorithms
Conference: SPIE Medical Imaging 2015: Physics of Medical Imaging.