Pedro Sanchez

Pedro Sanchez

Auto-generated profile, based on publicly available information

Pedro Sanchez

School of Engineering, University of Edinburgh, Edinburgh, U.K.

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 August 2022 in Royal Society Open Science
Verified
Journal Article
Open access
PSPedro Sanchez
Pedro Sanchez
JVJeremy P. Voisey
Jeremy P. Voisey
TXTian Xia
Tian Xia
HWHannah I. Watson
Hannah I. Watson
AOAlison Q. O’nEil
Alison Q. O’nEil
STSotirios A. Tsaftaris
Sotirios A. Tsaftaris
Causal machine learning (CML) has experienced increasing popularity in healthcare. Beyond the inherent capabilities of adding domain knowledge into learning systems, CML provides a complete toolset for investigating how a system would react to an intervention (e.g. outcome given a treatment). Quantifying effects of interventions allows actionable decisions to be made while maintaining robustness in the presence of confounders. Here, we explore how causal inference can be incorporated into different aspects of clinical decision support systems by using recent advances in machine learning. Throughout this paper, we use Alzheimer’s disease to create examples for illustrating how CML can be advantageous in clinical scenarios. Furthermore, we discuss important challenges present in healthcare applications such as processing high-dimensional and unstructured data, generalization to out-of-distribution samples and temporal relationships, that despite the great effort from the research community remain to be solved. Finally, we review lines of research within causal representation learning, causal discovery and causal reasoning which offer the potential towards addressing the aforementioned challenges.

11 September 2023 in Medical Image Analysis
Verified
Journal Article
Closed access
AKAntanas Kascenas
Antanas Kascenas
PSPedro Sanchez
Pedro Sanchez
PSPatrick Schrempf
Patrick Schrempf
CWChaoyang Wang
Chaoyang Wang
WCWilliam Clackett
William Clackett
AOAlison O'Neil
Alison O'Neil

8 October 2022
Verified
Book Chapter
Closed access
PDF file
PSPedro Sanchez
Pedro Sanchez
AKAntanas Kascenas
Antanas Kascenas
XLXiao Liu
Xiao Liu
AOAlison Q. O’nEil
Alison Q. O’nEil
STSotirios A. Tsaftaris
Sotirios A. Tsaftaris

20 February 2024
Verified
Book Chapter
Closed access
PDF file
VFVirginia Fernandez
Virginia Fernandez
PSPedro Sanchez
Pedro Sanchez
WPWalter Hugo Lopez Pinaya
Walter Hugo Lopez Pinaya
GJGrzegorz Jacenków
Grzegorz Jacenków
STSotirios A. Tsaftaris
Sotirios A. Tsaftaris
MCM. Jorge Cardoso
M. Jorge Cardoso

8 November 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
KVKonstantinos Vilouras
Konstantinos Vilouras
PSPedro Sanchez
Pedro Sanchez
AOAlison O'Neil
Alison O'Neil
STSotirios A. Tsaftaris
Sotirios A. Tsaftaris
Localizing the exact pathological regions in a given medical scan is an important imaging problem that traditionally requires a large amount of bounding box ground truth annotations to be accurately solved. However, there exist alternative, potentially weaker, forms of supervision, such as accompanying free-text reports, which are readily available. The task of performing localization with textual guidance is commonly referred to as phrase grounding. In this work, we use a publicly available Foundation Model, namely the Latent Diffusion Model, to perform this challenging task. This choice is supported by the fact that the Latent Diffusion Model, despite being generative in nature, contains cross-attention mechanisms that implicitly align visual and textual features, thus leading to intermediate representations that are suitable for the task at hand. In addition, we aim to perform this task in a zero-shot manner, i.e., without any training on the target task, meaning that the model's weights remain frozen. To this end, we devise strategies to select features and also refine them via post-processing without extra learnable parameters. We compare our proposed method with state-of-the-art approaches which explicitly enforce image-text alignment in a joint embedding space via contrastive learning. Results on a popular chest X-ray benchmark indicate that our method is competitive with SOTA on different types of pathology, and even outperforms them on average in terms of two metrics (mean IoU and AUC-ROC). Source code will be released upon acceptance at https://github.com/vios-s .

26 January 2024 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
XLXiao Liu
Xiao Liu
PSPedro Sanchez
Pedro Sanchez
STSpyridon Thermos
Spyridon Thermos
AOAlison O'Neil
Alison O'Neil
STSotirios A. Tsaftaris
Sotirios A. Tsaftaris
Deep learning models often need sufficient supervision (i.e. labelled data) in order to be trained effectively. By contrast, humans can swiftly learn to identify important anatomy in medical images like MRI and CT scans, with minimal guidance. This recognition capability easily generalises to new images from different medical facilities and to new tasks in different settings. This rapid and generalisable learning ability is largely due to the compositional structure of image patterns in the human brain, which are not well represented in current medical models. In this paper, we study the utilisation of compositionality in learning more interpretable and generalisable representations for medical image segmentation. Overall, we propose that the underlying generative factors that are used to generate the medical images satisfy compositional equivariance property, where each factor is compositional (e.g. corresponds to human anatomy) and also equivariant to the task. Hence, a good representation that approximates well the ground truth factor has to be compositionally equivariant. By modelling the compositional representations with learnable von-Mises-Fisher (vMF) kernels, we explore how different design and learning biases can be used to enforce the representations to be more compositionally equivariant under un-, weakly-, and semi-supervised settings. Extensive results show that our methods achieve the best performance over several strong baselines on the task of semi-supervised domain-generalised medical image segmentation. Code will be made publicly available upon acceptance at https://github.com/vios-s.