Loading...
Research Project
Strategic Project - LA 8 - 2013-2014
Funder
Authors
Publications
Classification of reticular pattern and streaks in dermoscopic images based on texture analysis
Publication . Machado, Marlene; Pereira, Jorge; Fonseca-Pinto, Rui
The early detection of melanoma is one of the greatest challenges in clinical practice of dermatology,
and the reticular pattern is one of the most important dermoscopic structures to improve melanocytic lesion
diagnosis. A texture-based approach is developed for the automatic detection of reticular patterns, whose output
will assist clinical decision-making. Feature selection was based on the use of two algorithms by means of the
classical graylevel co-occurrence matrix and Laws energy masks optimized on a set of 104 dermoscopy images.
The AdaBoost (adaptive boosting) approach to machine learning was used within this strategy. Results suggest
superiority of LEM for reticular pattern detection in dermoscopic images, achieving a sensitivity of 90.16% and a
specificity of 86.67%. The use of automatic classification in dermoscopy to support clinicians is a strong tool to
assist diagnosis; however, the use of automatic classification as a complementary tool in clinical routine requires
algorithms with high levels of sensitivity and specificity. The results presented in this work will contribute to
achieving this goal.
A method to improve HEVC lossless coding of volumetric medical images
Publication . F.R. Guarda, André F. R.; Santos, João M.; Cruz, Luís A. da Silva; Assunção, Pedro A. A.; Rodrigues, Nuno M. M.; Faria, Sérgio M. M. de
Medical imaging technology and applications are continuously evolving, dealing with images of increasing spatial and temporal resolutions, which enable more accurate processing, feature analysis and medical diagnosis. However, the increase in resolution also requires a growing amount of data to be stored, processed and exchanged or transmitted through networks. Despite the high coding efficiency achieved by the most recent image and video coding standards in lossy compression, they are not well suited for quality-critical medical image compression
where either near-lossless or lossless coding is required. In this paper we propose a method to improve lossless coding of volumetric medical images, such as Magnetic Resonance and Computed Tomography, and medical sequences such as X-ray Angiography images, using the latest standard High Efficiency Video Encoder (HEVC). New pixel-wise prediction techniques are proposed to extend the current HEVC lossless tools, based on Least-Squares Prediction (LSP). Experimental results show a bitrate reduction of over 44%, when compared to DICOM recommended encoders, and 13.8% when compared to standard lossless HEVC, for 8 bpp volumetric images, and over 8% and 4.6%, respectively, for volumetric images using more than 8 bpp.
Hybrid RSS-AoA technique for 3-D node localization in wireless sensor networks
Publication . Tomic, Slavisa; Marikj, Milica; Beko, Marko; Dinis, Rui; Orfao, Nuno
We consider 3-D target positioning in noncooperative wireless sensor network (WSN) by employing received signal strength (RSS) and angle-of-arrival (AoA) measurements. Based on the least squares (LS) criterion, we derive a novel objective function for solving the hybrid localization problem. Despite the fact that the resulting optimization problem is non-convex, we show that it can be approximated into a convex problem by applying second-order cone programming (SOCP) relaxation. Moreover, we show that the objective function can be written in the form that belongs to the generalized trust region subproblems (GTRS), which can be solved exactly. Our numerical results exhibit remarkable performance of the new approaches, reducing the estimation error for more than 5 m and 3 m, in comparison to the state-of-the-art approach.
Substrate noise isolation improvement in a single-well standard CMOS process
Publication . Santos, P. Mendonça dos; Moreira Mendes, Luís Miguel; João Caldinhas Vaz
This work describes a fully CMOS compatible methodology, which makes available a pseudo deep n-well in single-well standard CMOS process. The proposed method is based on mask manipulation to accommodate the field implant p-type region into the n-well, and does not require any additional masks or modification in the CMOS process flow. According to the experimental results, the floating NMOS made available by the methodology shows a reduction in the threshold voltage, which implies a slight improvement in its performance, when compared with its standard NMOS counterpart. It was also experimentally demonstrated up to 3 GHz, that the guard-ring field implant/pseudo deep n-well proposed structure improves substrate noise isolation when compared to the classical p+ guard-ring, with a maximum improvement above 20 dB for low frequencies and a minimum of 4 dB at 3 GHz.
Organizational Units
Description
Keywords
Telecommunications,Wireless communications,Optical Communications,Networks and multimedia,
Contributors
Funders
Funding agency
Fundação para a Ciência e a Tecnologia, I.P.
Fundação para a Ciência e a Tecnologia, I.P.
Fundação para a Ciência e a Tecnologia, I.P.
Funding programme
6817 - DCRRNI ID
Financiamento de Projectos de IC&DT Estratégicos e de Interesse Público promovidos por Laboratórios Associados e Unidades de I&D - 2013 - OE
Financiamento de Projectos de IC&DT Estratégicos e de Interesse Público promovidos por Laboratórios Associados e Unidades de I&D - 2013 - OE
Funding Award Number
PEst-OE/EEI/LA0008/2013