Deolinda M. L. Dias Rasteiro

Prof. Deolinda M. L. Dias Rasteiro

Polytechnic Institute of Coimbra, Coimbra, Portugal

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2018 in Pattern Recognition
Verified
Journal Article
Closed access
APAdriano Pinto
Adriano Pinto
SPSérgio Pereira
Sérgio Pereira
DRDeolinda M. L. Dias Rasteiro
Deolinda M. L. Dias Rasteiro
CSCarlos A. Silva
Carlos A. Silva

1 August 2015
Verified
Conference Paper
Closed access
APAdriano Pinto
Adriano Pinto
SPSergio Pereira
Sergio Pereira
HCHigino Correia
Higino Correia
JOJ. Oliveira
J. Oliveira
DRDeolinda M. L. Dias Rasteiro
Deolinda M. L. Dias Rasteiro
CSCarlos A. Silva
Carlos A. Silva
Gliomas are among the most common and aggressive brain tumours. Segmentation of these tumours is important for surgery and treatment planning, but also for follow-up evaluations. However, it is a difficult task, given that its size and locations are variable, and the delineation of all tumour tissue is not trivial, even with all the different modalities of the Magnetic Resonance Imaging (MRI). We propose a discriminative and fully automatic method for the segmentation of gliomas, using appearance- and context-based features to feed an Extremely Randomized Forest (Extra-Trees). Some of these features are computed over a non-linear transformation of the image. The proposed method was evaluated using the publicly available Challenge database from BraTS 2013, having obtained a Dice score of 0.83, 0.78 and 0.73 for the complete tumour, and the core and the enhanced regions, respectively. Our results are competitive, when compared against other results reported using the same database.

30 May 2022 in Future Internet
Verified
Journal Article
Open access
PDF file
Joana Carolina TomásJoana Carolina Tomás
Joana Carolina Tomás
DRDeolinda M. L. Dias Rasteiro
Deolinda M. L. Dias Rasteiro
Jorge BernardinoJorge Bernardino
Jorge Bernardino
In recent years, the use of personal data in marketing, scientific and medical investigation, and forecasting future trends has really increased. This information is used by the government, companies, and individuals, and should not contain any sensitive information that allows the identification of an individual. Therefore, data anonymization is essential nowadays. Data anonymization changes the original data to make it difficult to identify an individual. ARX Data Anonymization and Amnesia are two popular open-source tools that simplify this process. In this paper, we evaluate these tools in two ways: with the OSSpal methodology, and using a public dataset with the most recent tweets about the Pfizer and BioNTech vaccine. The assessment with the OSSpal methodology determines that ARX Data Anonymization has better results than Amnesia. In the experimental evaluation using the public dataset, it is possible to verify that Amnesia has some errors and limitations, but the anonymization process is simpler. Using ARX Data Anonymization, it is possible to upload big datasets and the tool does not show any error in the anonymization process. We concluded that ARX Data Anonymization is the one recommended to use in data anonymization.

1 February 2015
Verified
Conference Paper
Closed access
APAdriano Pinto
Adriano Pinto
SPSergio Pereira
Sergio Pereira
HDHugo Dinis
Hugo Dinis
CSCarlos A. Silva
Carlos A. Silva
DRDeolinda M. L. Dias Rasteiro
Deolinda M. L. Dias Rasteiro
Brain tumour segmentation from Magnetic Resonance Imaging (MRI) scans have an important role in the early tumour diagnosis and radiotherapy planning. However, MRI images of the brain contain complex characteristics, such as high diversity in tumour appearance and ambiguous tumour boundaries, even when using multi-sequence MRI images. We propose a fully automatic segmentation algorithm based on a Random Decision Forest, using a k-fold cross-validation approach. The extracted features are the intensity complemented with other appearance and context based features. The post-processing phase has a morphological filter to deal with misclassification errors. Our method is capable of detecting the tumour and segmenting the different tumorous tissues of the glioma achieving competitive results.

1 January 2012 in Lecture Notes in Computer Science
Verified
Book Chapter
Closed access
PDF file
RSRicardo Jorge Santos
Ricardo Jorge Santos
Jorge BernardinoJorge Bernardino
Jorge Bernardino
MVMarco Vieira
Marco Vieira
DRDeolinda M. L. Dias Rasteiro
Deolinda M. L. Dias Rasteiro

3 January 2023
Verified
Book Chapter
Closed access
PDF file
Lurdes Vasconcelos BaboLurdes Vasconcelos Babo
Lurdes Vasconcelos Babo
Carla Manuela PintoCarla Manuela Pinto
Carla Manuela Pinto
JMJorge Manuel Pires MENDONÇA
Jorge Manuel Pires MENDONÇA
DRDeolinda M. L. Dias Rasteiro
Deolinda M. L. Dias Rasteiro
Cristina M.R. CaridadeCristina M.R. Caridade
Cristina M.R. Caridade
IVIoannis Vardiambasis
Ioannis Vardiambasis