Search

Despite major advances in artificial intelligence (AI) for medicine and healthcare, the deployment and adoption of AI technologies remain limited in real-world clinical practice. In recent years, concerns have been raised about the technical, clinical, ethical and legal risks associated with medical AI. To increase real world adoption, it is essential that medical AI tools are trusted and accepted by patients, clinicians, health organisations and authorities. This work describes the FUTURE-AI guideline as the first international consensus framework for guiding the development and deployment of trustworthy AI tools in healthcare. The FUTURE-AI consortium was founded in 2021 and currently comprises 118 inter-disciplinary experts from 51 countries representing all continents, including AI scientists, clinicians, ethicists, and social scientists. Over a two-year period, the consortium defined guiding principles and best practices for trustworthy AI through an iterative process comprising an in-depth literature review, a modified Delphi survey, and online consensus meetings. The FUTURE-AI framework was established based on 6 guiding principles for trustworthy AI in healthcare, i.e. Fairness, Universality, Traceability, Usability, Robustness and Explainability. Through consensus, a set of 28 best practices were defined, addressing technical, clinical, legal and socio-ethical dimensions. The recommendations cover the entire lifecycle of medical AI, from design, development and validation to regulation, deployment, and monitoring. FUTURE-AI is a risk-informed, assumption-free guideline which provides a structured approach for constructing medical AI tools that will be trusted, deployed and adopted in real-world practice. Researchers are encouraged to take the recommendations into account in proof-of-concept stages to facilitate future translation towards clinical practice of medical AI.

Prostate segmentation from magnetic resonance imaging (MRI) is a challenging task. In recent years, several network architectures have been proposed to automate this process and alleviate the burden of manual annotation. Although the performance of these models has achieved promising results, there is still room for improvement before these models can be used safely and effectively in clinical practice. One of the major challenges in prostate MR image segmentation is the presence of class imbalance in the image labels where the background pixels dominate over the prostate. In the present work we propose a DL-based pipeline for cropping the region around the prostate from MRI images to produce a more balanced distribution of the foreground pixels (prostate) and the background pixels and improve segmentation accuracy. The effect of DL-cropping for improving the segmentation performance compared to standard center-cropping is assessed using five popular DL networks for prostate segmentation, namely U-net, U-net+, Res Unet++, Bridge U-net and Dense U-net. The proposed smart-cropping outperformed the standard center cropping in terms of segmentation accuracy for all the evaluated prostate segmentation networks. In terms of Dice score, the highest improvement was achieved for the U-net+ and ResU-net++ architectures corresponding to 8.9% and 8%, respectively., Comment: 8 pages, 6 figures, 1 table

In this study we investigated the repeatability and reproducibility of radiomic features extracted from MRI images and provide a workflow to identify robust features. 2D and 3D T$_2$-weighted images of a pelvic phantom were acquired on three scanners of two manufacturers and two magnetic field strengths. The repeatability and reproducibility of the radiomic features were assessed respectively by intraclass correlation coefficient (ICC) and concordance correlation coefficient (CCC), considering repeated acquisitions with or without phantom repositioning, and with different scanner/acquisition type, and acquisition parameters. The features showing ICC/CCC > 0.9 were selected, and their dependence on shape information (Spearman's $\rho$> 0.8) was analyzed. They were classified for their ability to distinguish textures, after shuffling voxel intensities. From 944 2D features, 79.9% to 96.4% showed excellent repeatability in fixed position across all scanners. Much lower range (11.2% to 85.4%) was obtained after phantom repositioning. 3D extraction did not improve repeatability performance. Excellent reproducibility between scanners was observed in 4.6% to 15.6% of the features, at fixed imaging parameters. 82.4% to 94.9% of features showed excellent agreement when extracted from images acquired with TEs 5 ms apart (values decreased when increasing TE intervals) and 90.7% of the features exhibited excellent reproducibility for changes in TR. 2.0% of non-shape features were identified as providing only shape information. This study demonstrates that radiomic features are affected by specific MRI protocols. The use of our radiomic pelvic phantom allowed to identify unreliable features for radiomic analysis on T$_2$-weighted images. This paper proposes a general workflow to identify repeatable, reproducible, and informative radiomic features, fundamental to ensure robustness of clinical studies., Comment: 32 pages, 8 figures (7 + 1 supplemental), 8 tables (5 + 3 supplemental); Submitted to Magnetic Resonance in Medicine

A thorough theoretical study of the optical properties of periodic Si nanosphere arrays is undertaken, placing particular emphasis on the synergy between electric and magnetic Mie resonances, which occur in high-refractive-index nanoparticles and can lead to a rich variety of phenomena ranging from perfect reflection to controlled diffraction. By means of systematic calculations using the layer-multiple-scattering method that we properly extended so as to describe periodic arrays with many scatterers per unit cell, in conjunction with finite-element simulations, we optimized surfaces of Si nanospheres that efficiently channel the transmitted light into a single, first-order diffraction beam, following simple design rules based on physical insight. Our results provide compelling evidence that Huygens' metasurfaces consisting of simple Si nanosphere dimer lattices constitute a promising platform for large-angle unidirectional deflection of transmitted light in the visible, at wavelengths shorter than the diffraction edge of the lattice.

We introduce a model-checking tool intended specially for the analysis of quantum information protocols. The tool incorporates an efficient representation of a certain class of quantum circuits, namely those expressible in the so-called stabiliser formalism. Models of protocols are described using a simple, imperative style simulation language which includes commands for the unitary operators in the Clifford group as well as classical integer and boolean variables. Formulas for verification are expressed using a subset of quantum computational tree logic (QCTL). The model-checking procedure treats quantum measurements as the source of non-determinism, leading to multiple protocol runs, one for each outcome. Verification is performed for each run.

We establish fundamental and general techniques for formal verification of quantum protocols. Quantum protocols are novel communication schemes involving the use of quantum-mechanical phenomena for representation, storage and transmission of data. As opposed to quantum computers, quantum communication systems can and have been implemented using present-day technology; therefore, the ability to model and analyse such systems rigorously is of primary importance. While current analyses of quantum protocols use a traditional mathematical approach and require considerable understanding of the underlying physics, we argue that automated verification techniques provide an elegant alternative. We demonstrate these techniques through the use of PRISM, a probabilistic model-checking tool. Our approach is conceptually simpler than existing proofs, and allows us to disambiguate protocol definitions and assess their properties. It also facilitates detailed analyses of actual implemented systems. We illustrate our techniques by modelling a selection of quantum protocols (namely superdense coding, quantum teleportation, and quantum error correction) and verifying their basic correctness properties. Our results provide a foundation for further work on modelling and analysing larger systems such as those used for quantum cryptography, in which basic protocols are used as components., Comment: 15 pages + 2 page appendix

This paper discusses the use of computer-aided verification as a practical means for analysing quantum information systems; specifically, the BB84 protocol for quantum key distribution is examined using this method. This protocol has been shown to be unconditionally secure against all attacks in an information-theoretic setting, but the relevant security proof requires a thorough understanding of the formalism of quantum mechanics and is not easily adaptable to practical scenarios. Our approach is based on probabilistic model-checking; we have used the PRISM model-checker to show that, as the number of qubits transmitted in BB84 is increased, the equivocation of the eavesdropper with respect to the channel decreases exponentially. We have also shown that the probability of detecting the presence of an eavesdropper increases exponentially with the number of qubits. The results presented here are a testament to the effectiveness of the model-checking approach for systems where analytical solutions may not be possible or plausible.