João F. Teixeira

Dr. João F. Teixeira

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
26 July 2024 in Entropy
Verified
Journal Article
Open access
PDF file
BABernardo Araújo
Bernardo Araújo
JTJoão F. Teixeira
João F. Teixeira
JFJoaquim Fonseca
Joaquim Fonseca
RCRicardo Cerqueira
Ricardo Cerqueira
SBSofia C. Beco
Sofia C. Beco
Deep learning approaches have been gaining importance in several applications. However, the widespread use of these methods in safety-critical domains, such as Autonomous Driving, is still dependent on their reliability and trustworthiness. The goal of this paper is to provide a review of deep learning-based uncertainty methods and their applications to support perception tasks for Autonomous Driving. We detail significant Uncertainty Quantification and calibration methods, and their contributions and limitations, as well as important metrics and concepts. We present an overview of the state of the art of out-of-distribution detection and active learning, where uncertainty estimates are commonly applied. We show how these methods have been applied in the automotive context, providing a comprehensive analysis of reliable AI for Autonomous Driving. Finally, challenges and opportunities for future work are discussed for each topic.

9 January 2018 in Sensors
Verified
Journal Article
Open access
PDF file
HZHooshiar Zolfagharnasab
Hooshiar Zolfagharnasab
SBSílvia Bessa
Sílvia Bessa
SOSara Oliveira
Sara Oliveira
Pedro FariaPedro Faria
Pedro Faria
JTJoão F. Teixeira
João F. Teixeira
HOHelder Oliveira
Helder Oliveira
Breast cancer treatments can have a negative impact on breast aesthetics, in case when surgery is intended to intersect tumor. For many years mastectomy was the only surgical option, but more recently breast conserving surgery (BCS) has been promoted as a liable alternative to treat cancer while preserving most part of the breast. However, there is still a significant number of BCS intervened patients who are unpleasant with the result of the treatment, which leads to self-image issues and emotional overloads. Surgeons recognize the value of a tool to predict the breast shape after BCS to facilitate surgeon/patient communication and allow more educated decisions; however, no such tool is available that is suited for clinical usage. These tools could serve as a way of visually sensing the aesthetic consequences of the treatment. In this research, it is intended to propose a methodology for predict the deformation after BCS by using machine learning techniques. Nonetheless, there is no appropriate dataset containing breast data before and after surgery in order to train a learning model. Therefore, an in-house semi-synthetic dataset is proposed to fulfill the requirement of this research. Using the proposed dataset, several learning methodologies were investigated, and promising outcomes are obtained.


17 May 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JTJoão F. Teixeira
João F. Teixeira
MDMariana Dias
Mariana Dias
EBEva Batista
Eva Batista
JCJoana Costa
Joana Costa
LTLuis Teixeira
Luis Teixeira
HOHelder Oliveira
Helder Oliveira
The scarcity of balanced and annotated datasets has been a recurring problem in medical image analysis. Several researchers have tried to fill this gap employing dataset synthesis with adversarial networks (GANs). Breast magnetic resonance imaging (MRI) provides complex, texture-rich medical images, with the same annotation shortage issues, for which, to the best of our knowledge, no previous work tried synthesizing data. Within this context, our work addresses the problem of synthesizing breast MRI images from corresponding annotations and evaluate the impact of this data augmentation strategy on a semantic segmentation task. We explored variations of image-to-image translation using conditional GANs, namely fitting the generator’s architecture with residual blocks and experimenting with cycle consistency approaches. We studied the impact of these changes on visual verisimilarity and how an U-Net segmentation model is affected by the usage of synthetic data. We achieved sufficiently realistic-looking breast MRI images and maintained a stable segmentation score even when completely replacing the dataset with the synthetic set. Our results were promising, especially when concerning to Pix2PixHD and Residual CycleGAN architectures.


1 July 2019
Verified
Conference Paper
Closed access
MDMariana Dias
Mariana Dias
BRBeatriz Rocha
Beatriz Rocha
JTJoão F. Teixeira
João F. Teixeira
HOHelder Oliveira
Helder Oliveira
The Sternum is a human bone located in the anterior area of the thoracic cage. It is present in most of the axial cuts provided from the Magnetic Resonance Imaging (MRI) acquisitions, used in the medical field. Detecting the Sternum is relevant as it contains rigid key-points for 3D model reconstructions, assisting in the planning and evaluation of several surgical procedures, and for atlas development by segmenting structures in anatomical proximity. In the absence of applicable approaches for this specific problem, this paper focuses on two distinct automated methods for Sternum segmentation in MRI. The first, relies on K-Means (Clustering) to perform the segmentation, while the second encompasses the closed Minimum Path over the elliptical transformation of Gradient images. A dataset of 14 annotated acquisitions was used for evaluation. The results favored the Gradient approach over Clustering.