Publications by authors named "Borja Rodriguez-Vila"
Article Synopsis
- Adaptive radiotherapy (ART) aims to improve cancer treatment by precisely targeting tissues while protecting nearby organs, but traditional imaging techniques like CBCT often lack the needed resolution for accurate treatment planning, especially in proton therapy.
- This study proposes a new method that synthesizes high-quality dual-energy computed tomography (DECT) images from CBCT scans using a novel 3D denoising diffusion probabilistic model (DDPM) to enhance dose calculations and tissue characterization.
- Results showed that the new DDPM model outperformed traditional GAN methods in producing DECT images, leading to better tissue analysis and improved potential for accurate dose calculations in ART planning.
Article Synopsis
- Proton therapy is effective for cancer treatment, but its success relies on accurate dose distribution, which can be affected by patient anatomy changes, highlighting the need for adaptive approaches.
- Conventional imaging techniques like CBCT are limited in accurately estimating stopping power ratios (SPR) for proton therapy, leading researchers to explore Deep Learning methods to create improved pseudo-CT images.
- The authors present a new 3D vision transformer model that effectively reduces SPR errors in pCT images when compared to traditional CT, marking a potential advancement for adaptive proton therapy, although further validation is required for broader clinical implementation.
We present the evolution of medical imaging software and its impact on the medical imaging community through the study of four open-source image analysis software platforms: 3D Slicer, FreeSurfer, FSL, and SPM. We have studied the impact of these software tools over time, measured by the number of scientific citations. Additionally, we have also studied the source code evolution by measuring the lines of code and the tarball size of the stable releases and the changes in programming languages.
View Article and Find Full Text PDFArticle Synopsis
- A new calibration method for dual energy CT (DECT) using material decomposition maps for iodine and water has been developed, aimed at enhancing the accuracy of imaging.
- Experiments conducted on a GE revolution CT scanner showed that the method successfully reproduces Hounsfield unit (HU) values with less than 1% error, validating its effectiveness.
- This novel calibration offers comparable accuracy to existing methods, while providing better precision, making it particularly beneficial for applications like proton therapy where accurate tissue differentiation is crucial.
In this study, we aimed to democratize access to convolutional neural networks (CNN) for segmenting cartilage volumes, generating state-of-the-art results for specialized, real-world applications in hospitals and research. Segmentation of cross-sectional and/or longitudinal magnetic resonance (MR) images of articular cartilage facilitates both clinical management of joint damage/disease and fundamental research. Manual delineation of such images is a time-consuming task susceptible to high intra- and interoperator variability and prone to errors.
View Article and Find Full Text PDFBackground: Motion analysis parameters (MAPs) have been extensively validated for assessment of minimally invasive surgical skills. However, there are discrepancies on how specific MAPs, tasks, and skills match with each other, reflecting that motion analysis cannot be generalized independently of the learning outcomes of a task. Additionally, there is a lack of knowledge on the meaning of motion analysis in terms of surgical skills, making difficult the provision of meaningful, didactic feedback.
View Article and Find Full Text PDFThe existence of residual stresses in human arteries has long been shown experimentally. Researchers have also demonstrated that residual stresses have a significant effect on the distribution of physiological stresses within arterial tissues, and hence on their development, e.g.
View Article and Find Full Text PDF