top of page
Contact us:

Your message was successfully sent!

About us

Welcome to the Biomedical Image Processing group

Bringing Intelligence to Pixels

 

Founded in 2011 by professor Ricardo J. Ferrari, Ph.D. with the goal of developing practical solutions to significant problems in the biomedical field, the BIPGroup has its focus on Image and Video Processing, Computer Vision, and Machine Learning (including applications of Artificial Intelligence (AI) technology, such as CNNs and Autoencoders) techniques for automatically assessing and interpreting biomedical images.

​

Current research projects aim to segmenting, classifying and analyzing 3D magnetic resonance (MR) brain images for neurodegenerative diseases' studies, such as Alzheimer's, Vascular Cognitive Impairment and Multiple Sclerosis, among others biomedical imaging issues.

​

Our group is composed of innovative, talented and committed under and graduate students and, despite being relatively small, it is vibrant and very focused. 

​

If you would like to know more about our research projects or to be a part of our group, please contact us or look at our recent publication works. We are always looking for very interested and committed students to join our team.
​
Companies interested in consulting services or collaboration in research projects may also contact Prof. Dr. Ricardo J. Ferrari.

BIP News
Recent published works

​

1) J.B. Aily, M.Noronha, L.F.A. Selistre, R.J. Ferrari, D.K.White, S.M. Mattiello, Face-to-face and  telerehabilitation delivery of circuit training have similar benefits and acceptability in patients with knee osteoarthritis: a randomised trial, Journal of Physiotherapy, in press, 2023.

​

2) Lucas J.C. de Mendonça, Ricardo J. Ferrari, "Alzheimer’s disease classification based on graph kernel support vector
machines constructed with 3D texture features extracted from magnetic resonance images", Expert Systems With Applications, 211 (118633), 2023.

​

3) Katia M. Poloni, Ricardo J. Ferrari, "A deep ensemble hippocampal CNN model for brain age estimation applied to Alzheimer's diagnosis", Expert Systems With Applications, 195 (116622), p.1-12, 2022.

​

4) Katia M. Poloni, Ricardo J. Ferrari, "Automated detection, selection and classification of hippocampal landmark points for the diagnosis of Alzheimer's disease", Computer Methods and Programs in Biomedicine, 214(106581), p. 1-14, 2022.

​

5) Katia M. Poloni, Italo A.D. de Oliveira, Roger Tam, Ricardo J. Ferrari, "Brain MR image classification for Alzheimer's disease diagnosis using structural hippocampal asymmetrical attributes from directional 3-D log-Gabor filter responses", Neurocomputing, 419, p.126-135, 2021.

 

  • Image Processing / Computer Vision

    • Deformable 3-D mesh models​.

    • 3-D keypoint detectors​.

    • Object detection and tracking in 2- and 3-D images.

    • Spatiotemporal image analysis.

    • 3-D image segmentation.

    • Directional 3-D filtering.

  • Machine Learning / Deep Learning

    • Support Vector Machines (SVMs).

    • Deep Autoencoders, Convolutional Neural Networks (CNNs),  Generative Adversarial Networks (GANs).

    • Smart data augmentation.

  • Statistical Pattern Recognition

    • Bayes and Naïve Bayes classifiers​.

    • Finite Mixture Models (FMM).

    • Principal Component Analysis.

    • EigenAnalysis.

  • Neurodegenerative diseases

    • Structural MR brain image analysis using Deep Autoencoders for predicting brain ageing. 

    • Development of CNN models for classifying MR image in Alzheimer´s diseases.

    • Quantification of hippocampal volume in MR images using deformable mesh models.

    • Segmentation and classification (active and non-active) of Multiple Sclerosis lesions in FLAIR MR images.

    • Mapping structural brain changes via 3-D keypoint analysis.

  • Intravital Microscopy (in vivo studies)

    • Detection and tracking of blood cells in in-vivo studies.

  • Other topics

    • Automatic quantification of abdominal and thighs adipose tissues in CT images.

Research Areas
Research Applications
Interesting Reading
AI in medicine
 
Going Deep in Medical Image Analysis: Concepts, Methods, Challenges and Future Directions.

​

 

Financial Support:
bottom of page