Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Publications

Publications by Teresa Finisterra Araújo

2015

Optical Flow Based Approach for Automatic Cardiac Cycle Estimation in Ultrasound Images of the Carotid

Authors
Araujo, T; Aresta, G; Rouco, J; Ferreira, C; Azevedo, E; Campilho, A;

Publication
IMAGE ANALYSIS AND RECOGNITION (ICIAR 2015)

Abstract
This paper proposes a method to detect a reference frame in an ultrasound video of the carotid artery. This reference frame, usually located at the end of the diastole, is used as the location to measure several vascular biomarkers. Our approach is based on the analysis of the movement of the carotid walls in ultrasound images using an optical flow technique. A periodic movement resembling heart beat is observed in the resulting signals. The comparison of these signals with electrocardiograms validates the proposed method for detecting the reference frame.

2017

Classification of breast cancer histology images using Convolutional Neural Networks

Authors
Araujo, T; Aresta, G; Castro, E; Rouco, J; Aguiar, P; Eloy, C; Polonia, A; Campilho, A;

Publication
PLOS ONE

Abstract
Breast cancer is one of the main causes of cancer death worldwide. The diagnosis of biopsy tissue with hematoxylin and eosin stained images is non-trivial and specialists often disagree on the final diagnosis. Computer-aided Diagnosis systems contribute to reduce the cost and increase the efficiency of this process. Conventional classification approaches rely on feature extraction methods designed for a specific problem based on field-knowledge. To overcome the many difficulties of the feature-based approaches, deep learning methods are becoming important alternatives. A method for the classification of hematoxylin and eosin stained breast biopsy images using Convolutional Neural Networks (CNNs) is proposed. Images are classified in four classes, normal tissue, benign lesion, in situ carcinoma and invasive carcinoma, and in two classes, carcinoma and non-carcinoma. The architecture of the network is designed to retrieve information at different scales, including both nuclei and overall tissue organization. This design allows the extension of the proposed system to whole-slide histology images. The features extracted by the CNN are also used for training a Support Vector Machine classifier. Accuracies of 77.8% for four class and 83.3% for carcinoma/non-carcinoma are achieved. The sensitivity of our method for cancer cases is 95.6%.

2017

Improving Convolutional Neural Network Design via Variable Neighborhood Search

Authors
Araujo, T; Aresta, G; Almada Lobo, B; Mendonca, AM; Campilho, A;

Publication
IMAGE ANALYSIS AND RECOGNITION, ICIAR 2017

Abstract
An unsupervised method for convolutional neural network (CNN) architecture design is proposed. The method relies on a variable neighborhood search-based approach for finding CNN architectures and hyperparameter values that improve classification performance. For this purpose, t-Distributed Stochastic Neighbor Embedding (t-SNE) is applied to effectively represent the solution space in 2D. Then, k-Means clustering divides this representation space having in account the relative distance between neighbors. The algorithm is tested in the CIFAR-10 image dataset. The obtained solution improves the CNN validation loss by over 15% and the respective accuracy by 5%. Moreover, the network shows higher predictive power and robustness, validating our method for the optimization of CNN design.

2018

Retinal Image Quality Assessment by Mean-Subtracted Contrast-Normalized Coefficients

Authors
Galdran, A; Araujo, T; Mendonca, AM; Campilho, A;

Publication
VIPIMAGE 2017

Abstract
The automatic assessment of visual quality on images of the eye fundus is an important task in retinal image analysis. A novel quality assessment technique is proposed in this paper. We propose to compute Mean-Subtracted Contrast-Normalized (MSCN) coefficients on local spatial neighborhoods of a given image and analyze their distribution. It is known that for natural images, such distribution behaves normally, while distortions of different kinds perturb this regularity. The combination of MSCN coefficients with a simple measure of local contrast allows us to design a simple but effective retinal image quality assessment algorithm that successfully discriminates between good and low-quality images, while delivering a meaningful quality score. The proposed technique is validated on a recent database of quality-labeled retinal images, obtaining results aligned with state-of-the-art approaches at a low computational cost.

2017

Estimation of retinal vessel caliber using model fitting and random forests

Authors
Araujo, T; Mendonca, AM; Campilho, A;

Publication
MEDICAL IMAGING 2017: COMPUTER-AIDED DIAGNOSIS

Abstract
Retinal vessel caliber changes are associated with several major diseases, such as diabetes and hypertension. These caliber changes can be evaluated using eye fundus images. However, the clinical assessment is tiresome and prone to errors, motivating the development of automatic methods. An automatic method based on vessel crosssection intensity profile model fitting for the estimation of vessel caliber in retinal images is herein proposed. First, vessels are segmented from the image, vessel centerlines are detected and individual segments are extracted and smoothed. Intensity profiles are extracted perpendicularly to the vessel, and the profile lengths are determined. Then, model fitting is applied to the smoothed profiles. A novel parametric model (DoG-L7) is used, consisting on a Difference-of-Gaussians multiplied by a line which is able to describe profile asymmetry. Finally, the parameters of the best-fit model are used for determining the vessel width through regression using ensembles of bagged regression trees with random sampling of the predictors (random forests). The method is evaluated on the REVIEW public dataset. A precision close to the observers is achieved, outperforming other state-of-the-art methods. The method is robust and reliable for width estimation in images with pathologies and artifacts, with performance independent of the range of diameters.

2017

Segmentation and three-dimensional reconstruction of lesions using the automated breast volume scanner (ABVS)

Authors
Araujo, T; Abayazid, M; Rutten, MJCM; Misra, S;

Publication
INTERNATIONAL JOURNAL OF MEDICAL ROBOTICS AND COMPUTER ASSISTED SURGERY

Abstract
BackgroundUltrasound is an effective tool for breast cancer diagnosis. However, its relatively low image quality makes small lesion analysis challenging. This promotes the development of tools to help clinicians in the diagnosis. MethodsWe propose a method for segmentation and three-dimensional (3D) reconstruction of lesions from ultrasound images acquired using the automated breast volume scanner (ABVS). Segmentation and reconstruction algorithms are applied to obtain the lesion's 3D geometry. A total of 140 artificial lesions with different sizes and shapes are reconstructed in gelatin-based phantoms and biological tissue. Dice similarity coefficient (DSC) is used to evaluate the reconstructed shapes. The algorithm is tested using a human breast phantom and clinical data from six patients. ResultsDSC values are 0.860.06 and 0.86 +/- 0.05 for gelatin-based phantoms and biological tissue, respectively. The results are validated by a specialized clinician. ConclusionsEvaluation metrics show that the algorithm accurately segments and reconstructs various lesions. Copyright (c) 2016 John Wiley & Sons, Ltd.

  • 1
  • 4