arXiv subjects

Hélder P. Oliveira

Publications and source records attributed to Hélder P. Oliveira.

4 recordsLinked to original sources

arXiv2026

HUydra: Full-Range Lung CT Synthesis via Multiple HU Interval Generative Modelling

Currently, a central challenge and bottleneck in the deployment and validation of computer-aided diagnosis (CAD) models within the field of medical imaging is data scarcity. For lung cancer, one of the most prevalent types worldwide, limited datasets can delay diagnosis and have an impact on patient outcome. Generative AI offers a promising solution for this issue, but dealing with the complex distribution of full Hounsfield Unit (HU) range lung CT scans is challenging and remains as a highly computationally demanding task. This paper introduces a novel decomposition strategy that synthesizes CT images one HU interval at a time, rather than modelling the entire HU domain at once. This framework focuses on training generative architectures on individual tissue-focused HU windows, then merges their output into a full-range scan via a learned reconstruction network that effectively reverses the HU-windowing process. We further propose multi-head and multi-decoder models to better capture textures while preserving anatomical consistency, with a multi-head VQVAE achieving the best performance for the generative task. Quantitative evaluation shows this approach significantly outperforms conventional 2D full-range baselines, achieving a 6.2% improvement in FID and superior MMD, Precision, and Recall across all HU intervals. The best performance is achieved by a multi-head VQVAE variant, demonstrating that it is possible to enhance visual fidelity and variability while also reducing model complexity and computational cost. This work establishes a new paradigm for structure-aware medical image synthesis, aligning generative modelling with clinical interpretation.

cs.CV↗

arXiv2025

Markerless Multi-view 3D Human Pose Estimation: a survey

3D human pose estimation involves reconstructing the human skeleton by detecting the body joints. Accurate and efficient solutions are required for several real-world applications including animation, human-robot interaction, surveillance, and sports. However, challenges such as occlusions, 2D pose mismatches, random camera perspectives, and limited 3D labelled data have been hampering the models' performance and limiting their deployment in real-world scenarios. The higher availability of cameras has led researchers to explore multi-view solutions to take advantage of the different perspectives to reconstruct the pose. Most existing reviews have mainly focused on monocular 3D human pose estimation, so a comprehensive survey on multi-view approaches has been missing since 2012. According to the reviewed articles, the majority of the existing methods are fully-supervised approaches based on geometric constraints, which are often limited by 2D pose mismatches. To mitigate this, researchers have proposed incorporating temporal consistency or depth information. Alternatively, working directly with 3D features has been shown to completely overcome this issue, albeit at the cost of increased computational complexity. Additionally, models with lower levels of supervision have been identified to help address challenges such as annotated data scarcity and generalisation to new setups. Therefore, no method currently addresses all challenges associated with 3D pose reconstruction, and a trade-off between complexity and performance exists. Further research is needed to develop approaches capable of quickly inferring a highly accurate 3D pose with bearable computation cost. Techniques such as active learning, low-supervision methods, temporal consistency, view selection, depth information estimation, and multi-modal approaches are strategies to consider when developing a new method for this task.

cs.CV↗

arXiv2024

Vision-Radio Experimental Infrastructure Architecture Towards 6G

Telecommunications and computer vision have evolved separately so far. Yet, with the shift to sub-terahertz (sub-THz) and terahertz (THz) radio communications, there is an opportunity to explore computer vision technologies together with radio communications, considering the dependency of both technologies on Line of Sight. The combination of radio sensing and computer vision can address challenges such as obstructions and poor lighting. Also, machine learning algorithms, capable of processing multimodal data, play a crucial role in deriving insights from raw and low-level sensing data, offering a new level of abstraction that can enhance various applications and use cases such as beamforming and terminal handovers. This paper introduces CONVERGE, a pioneering vision-radio paradigm that bridges this gap by leveraging Integrated Sensing and Communication (ISAC) to facilitate a dual "View-to-Communicate, Communicate-to-View" approach. CONVERGE offers tools that merge wireless communications and computer vision, establishing a novel Research Infrastructure (RI) that will be open to the scientific community and capable of providing open datasets. This new infrastructure will support future research in 6G and beyond concerning multiple verticals, such as telecommunications, automotive, manufacturing, media, and health.

cs.NI↗

arXiv2019

Computer Aided Detection of Deep Inferior Epigastric Perforators in Computed Tomography Angiography scans

The deep inferior epigastric artery perforator (DIEAP) flap is the most common free flap used for breast reconstruction after a mastectomy. It makes use of the skin and fat of the lower abdomen to build a new breast mound either at the same time of the mastectomy or in a second surgery. This operation requires preoperative imaging studies to evaluate the branches - the perforators - that irrigate the tissue that will be used to reconstruct the breast mound. These branches will support tissue viability after the microsurgical ligation of the inferior epigastric vessels to the receptor vessels in the thorax. Usually through a Computed Tomography Angiography (CTA), each perforator, diameter and direction is manually identified by the imaging team, who will subsequently draw a map for the identification of the best vascular support for the reconstruction. In the current work we propose a semi-automatic methodology that aims at reducing the time and subjectivity inherent to the manual annotation. In 21 CTAs from patients proposed for breast reconstruction with DIEAP flaps, the subcutaneous region of each perforator was extracted, by means of a tracking procedure, whereas the intramuscular portion was detected through a minimum cost approach. Both were subsequently compared with the radiologist manual annotation. Results showed that the semi-automatic procedure was able to correctly detect the course of the DIEAPs with a minimum error (average error of 0.64 mm and 0.50 mm regarding the extraction of subcutaneous and intramuscular paths, respectively). The objective methodology is a promising tool in the automatic detection of perforators in CTA and can contribute to spare human resources and reduce subjectivity in the aforementioned task.

eess.IV↗