Cookies
Usamos cookies para melhorar nosso site e a sua experiência. Ao continuar a navegar no site, você aceita a nossa política de cookies. Ver mais
Aceitar Rejeitar
  • Menu
Publicações

Publicações por C-BER

2021

Explainability Metrics of Deep Convolutional Networks for Photoplethysmography Quality Assessment

Autores
Zhang, O; Ding, C; Pereira, T; Xiao, R; Gadhoumi, K; Meisel, K; Lee, RJ; Chen, YR; Hu, X;

Publicação
IEEE Access

Abstract

2021

Secure Triplet Loss: Achieving Cancelability and Non-Linkability in End-to-End Deep Biometrics

Autores
Pinto, JR; Correia, MV; Cardoso, JS;

Publicação
IEEE Transactions on Biometrics, Behavior, and Identity Science

Abstract

2021

LNDb Challenge on automatic lung cancer patient management

Autores
Pedrosa, J; Aresta, G; Ferreira, C; Atwal, G; Phoulady, HA; Chen, XY; Chen, RZ; Li, JL; Wang, LS; Galdran, A; Bouchachia, H; Kaluva, KC; Vaidhya, K; Chunduru, A; Tarai, S; Nadimpalli, SPP; Vaidya, S; Kim, I; Rassadin, A; Tian, ZH; Sun, ZW; Jia, YZ; Men, XJ; Ramos, I; Cunha, A; Campilho, A;

Publicação
Medical Image Analysis

Abstract

2021

Epistemic and Heteroscedastic Uncertainty Estimation in Retinal Blood Vessel Segmentation

Autores
Costa, P; Smailagic, A; Cardoso, JS; Campilho, A;

Publicação
U.Porto Journal of Engineering

Abstract
Current state-of-the-art medical image segmentation methods require high quality datasets to obtain good performance. However, medical specialists often disagree on diagnosis, hence, datasets contain contradictory annotations. This, in turn, leads to difficulties in the optimization process of Deep Learning models and hinder performance. We propose a method to estimate uncertainty in Convolutional Neural Network (CNN) segmentation models, that makes the training of CNNs more robust to contradictory annotations. In this work, we model two types of uncertainty, heteroscedastic and epistemic, without adding any additional supervisory signal other than the ground-truth segmentation mask. As expected, the uncertainty is higher closer to vessel boundaries, and on top of thinner and less visible vessels where it is more likely for medical specialists to disagree. Therefore, our method is more suitable to learn from datasets created with heterogeneous annotators. We show that there is a correlation between the uncertainty estimated by our method and the disagreement in the segmentation provided by two different medical specialists. Furthermore, by explicitly modeling the uncertainty, the Intersection over Union of the segmentation network improves 5.7 percentage points.

2021

The Role of Liquid Biopsy in Early Diagnosis of Lung Cancer

Autores
Freitas, C; Sousa, C; Machado, F; Serino, M; Santos, V; Cruz Martins, N; Teixeira, A; Cunha, A; Pereira, T; Oliveira, HP; Costa, JL; Hespanhol, V;

Publicação
Frontiers in Oncology

Abstract
Liquid biopsy is an emerging technology with a potential role in the screening and early detection of lung cancer. Several liquid biopsy-derived biomarkers have been identified and are currently under ongoing investigation. In this article, we review the available data on the use of circulating biomarkers for the early detection of lung cancer, focusing on the circulating tumor cells, circulating cell-free DNA, circulating micro-RNAs, tumor-derived exosomes, and tumor-educated platelets, providing an overview of future potential applicability in the clinical practice. While several biomarkers have shown exciting results, diagnostic performance and clinical applicability is still limited. The combination of different biomarkers, as well as their combination with other diagnostic tools show great promise, although further research is still required to define and validate the role of liquid biopsies in clinical practice.

2021

Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse

Autores
Magalhaes, SA; Castro, L; Moreira, G; dos Santos, FN; Cunha, M; Dias, J; Moreira, AP;

Publicação
Sensors

Abstract
The development of robotic solutions for agriculture requires advanced perception capabilities that can work reliably in any crop stage. For example, to automatise the tomato harvesting process in greenhouses, the visual perception system needs to detect the tomato in any life cycle stage (flower to the ripe tomato). The state-of-the-art for visual tomato detection focuses mainly on ripe tomato, which has a distinctive colour from the background. This paper contributes with an annotated visual dataset of green and reddish tomatoes. This kind of dataset is uncommon and not available for research purposes. This will enable further developments in edge artificial intelligence for in situ and in real-time visual tomato detection required for the development of harvesting robots. Considering this dataset, five deep learning models were selected, trained and benchmarked to detect green and reddish tomatoes grown in greenhouses. Considering our robotic platform specifications, only the Single-Shot MultiBox Detector (SSD) and YOLO architectures were considered. The results proved that the system can detect green and reddish tomatoes, even those occluded by leaves. SSD MobileNet v2 had the best performance when compared against SSD Inception v2, SSD ResNet 50, SSD ResNet 101 and YOLOv4 Tiny, reaching an F1-score of 66.15, an mAP of 51.46 and an inference time of 16.44ms with the NVIDIA Turing Architecture platform, an NVIDIA Tesla T4, with 12 GB. YOLOv4 Tiny also had impressive results, mainly concerning inferring times of about 5ms.

  • 1
  • 81