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 Catarina Brito Carvalho

2018

Non-uniform deformation in Achilles tendon is not influenced by a change in knee angle or level of force production during isometric contractions

Authors
Bogaerts, S; De Brito Carvalho, C; Groef, D; Suetens, P; Peers, K;

Publication
Annals of Physical and Rehabilitation Medicine

Abstract

2018

Non-uniformity in pre-insertional Achilles tendon is not influenced by changing knee angle during isometric contractions

Authors
Bogaerts, S; Carvalho, CD; De Groef, A; Suetens, P; Peers, K;

Publication
SCANDINAVIAN JOURNAL OF MEDICINE & SCIENCE IN SPORTS

Abstract
Achilles tendinopathy remains a prevalent condition among recreational and high-level athletes. Mechanical loading has become the gold standard in managing these injuries, but exercises are often generic and prescribed in a "one-size-fits-all" principle. The aim of this study was to evaluate the impact of knee angle changes and different levels of force production on the non-uniform behavior in the Achilles tendon during isometric contractions. It was hypothesized that a flexed knee position would lead to a more distinct non-uniform behavior, due to greater differential loading of soleus vs gastrocnemius, and that this effect would be attenuated by higher levels of force production. Contrary to the hypotheses, it was found that the non-uniform deformation, that is, superficial-to-deep variation in displacement with highest displacement in the deep layer, is consistently present, irrespective of the level of force production and knee angle (n = 19; mean normalized displacement ratio 6.32%, 4.88%, and 4.09% with extended knee vs 5.47%, 2.56%, and 6.01% with flexed knee, at 25%, 50%, and 75% MVC, respectively; P > .05). From tendon perspective, aside from the influence on muscle behavior, this might question the mechanical rationale for a change in knee angle during eccentric heel drops. Additionally, despite reaching high levels of plantar flexion force, the relative contribution of the AT sometimes appears to be decreased, potentially due to compensatory actions by agonist muscle groups. These results are relevant for optimizing AT rehabilitation as the goal is to reach specific local tendon loading.

2018

End-to-End Ovarian Structures Segmentation

Authors
Wanderley, DS; Carvalho, CB; Domingues, A; Peixoto, C; Pignatelli, D; Beires, J; Silva, J; Campilho, A;

Publication
Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications - 23rd Iberoamerican Congress, CIARP 2018, Madrid, Spain, November 19-22, 2018, Proceedings

Abstract
The segmentation and characterization of the ovarian structures are important tasks in gynecological and reproductive medicine. Ultrasound imaging is typically used for the medical diagnosis within this field but the understanding of the images can be difficult due to their characteristics. Furthermore, the complexity of ultrasound data may lead to a heavy image processing, which makes the application of classical methods of computer vision difficult. This work presents the first supervised fully convolutional neural network (fCNN) for the automatic segmentation of ovarian structures in B-mode ultrasound images. Due to the small dataset available, only 57 images were used for training. In order to overcome this limitation, several regularization techniques were used and are discussed in this paper. The experiments show the ability of the fCNN to learn features to distinguish ovarian structures, achieving a Dice similarity coefficient (DSC) of 0.855 for the segmentation of the stroma and a DSC of 0.955 for the follicles. When compared with a semi-automatic commercial application for follicle segmentation, the proposed fCNN achieved an average improvement of 19%. © Springer Nature Switzerland AG 2019.

2019

Analysis of the performance of specialists and an automatic algorithm in retinal image quality assessment

Authors
Wanderley, DS; Araujo, T; Carvalho, CB; Maia, C; Penas, S; Carneiro, A; Mendonca, AM; Campilho, A;

Publication
2019 6TH IEEE PORTUGUESE MEETING IN BIOENGINEERING (ENBENG)

Abstract
This study describes a novel dataset with retinal image quality annotation, defined by three different retinal experts, and presents an inter-observer analysis for quality assessment that can be used as gold-standard for future studies. A state-of-the-art algorithm for retinal image quality assessment is also analysed and compared against the specialists performance. Results show that, for 71% of the images present in the dataset, the three experts agree on the given image quality label. The results obtained for accuracy, specificity and sensitivity when comparing one expert against another were in the ranges [83.0 - 85.2]%, [72.7 - 92.9]% and [80.0 - 94.7]%, respectively. The evaluated automatic quality assessment method, despite not being trained on the novel dataset, presents a performance which is within inter-observer variability.

2019

Deep Learning Approaches for Gynaecological Ultrasound Image Segmentation: A Radio-Frequency vs B-mode Comparison

Authors
Carvalho, C; Marques, S; Peixoto, C; Pignatelli, D; Beires, J; Silva, J; Campilho, A;

Publication
IMAGE ANALYSIS AND RECOGNITION (ICIAR 2019), PT II

Abstract
Ovarian cancer is one of the pathologies with the worst prognostic in adult women and it has a very difficult early diagnosis. Clinical evaluation of gynaecological ultrasound images is performed visually, and it is dependent on the experience of the medical doctor. Besides the dependency on the specialists, the malignancy of specific types of ovarian tumors cannot be asserted until their surgical removal. This work explores the use of ultrasound data for the segmentation of the ovary and the ovarian follicles, using two different convolutional neural networks, a fully connected residual network and a U-Net, with a binary and multi-class approach. Five different types of ultrasound data (from beam-formed radio-frequency to brightness mode) were used as input. The best performance was obtained using B-mode, for both ovary and follicles segmentation. No significant differences were found between the two convolutional neural networks. The use of the multi-class approach was beneficial as it provided the model information on the spatial relation between follicles and the ovary. This study demonstrates the suitability of combining convolutional neural networks with beam-formed radio-frequency data and with brightness mode data for segmentation of ovarian structures. Future steps involve the processing of pathological data and investigation of biomarkers of pathological ovaries.

2019

Segmentation of gynaecological ultrasound images using different U-Net based approaches

Authors
Marques, S; Carvalho, C; Peixoto, C; Pignatelli, D; Beires, J; Silva, J; Campilho, A;

Publication
2019 IEEE INTERNATIONAL ULTRASONICS SYMPOSIUM (IUS)

Abstract
Ovarian cancer is one of the most commonly occurring cancer in women. Transvaginal ultrasound is used as a screening test to detect the presence of tumors but, for specific types of ovarian tumors, malignancy can only be asserted through surgery. An automatic method to perform the detection and malignancy assessment of these tumours is thus necessary to prevent unnecessary oophorectomies. This work explores the U-Net's architecture and investigates the selection of different hyperparameters for the ovary and the ovarian follicles segmentation. The effect of applying different post-processing methods on beam-formed radio-frequency (BRF) data is also investigated. Results show that models trained only with BRF data have the worst performance. On the other hand, the combination of B-mode with BRF data performs better for ovary segmentation. As for the hyperparameter study, results show that the U-Net with 4 levels is the architecture with the worst performance. This shows that to achieve better performance in the segmentation of ovarian structures, it is important to select an architecture that takes into account the spatial context of the regions of interest. It is also possible to conclude that the method used to analyse BRF data should be designed to take advantage of the fine-resolution of BRF data.

  • 2
  • 3