Alejandro F Frangi

Karim Lekadir, Aasa Feragen, Abdul Joseph Fofanah et al. · eth-zurich

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.

Nurbanu Aksoy, Nishant Ravikumar, Alejandro F Frangi

Medical image interpretation is central to most clinical applications such as disease diagnosis, treatment planning, and prognostication. In clinical practice, radiologists examine medical images and manually compile their findings into reports, which can be a time-consuming process. Automated approaches to radiology report generation, therefore, can reduce radiologist workload and improve efficiency in the clinical pathway. While recent deep-learning approaches for automated report generation from medical images have seen some success, most studies have relied on image-derived features alone, ignoring non-imaging patient data. Although a few studies have included the word-level contexts along with the image, the use of patient demographics is still unexplored. This paper proposes a novel multi-modal transformer network that integrates chest x-ray (CXR) images and associated patient demographic information, to synthesise patient-specific radiology reports. The proposed network uses a convolutional neural network to extract visual features from CXRs and a transformer-based encoder-decoder network that combines the visual features with semantic text embeddings of patient demographic information, to synthesise full-text radiology reports. Data from two public databases were used to train and evaluate the proposed approach. CXRs and reports were extracted from the MIMIC-CXR database and combined with corresponding patients' data MIMIC-IV. Based on the evaluation metrics used including patient demographic information was found to improve the quality of reports generated using the proposed approach, relative to a baseline network trained using CXRs alone. The proposed approach shows potential for enhancing radiology report generation by leveraging rich patient metadata and combining semantic text embeddings derived thereof, with medical image-derived visual features.

Rachael Harkness, Alejandro F Frangi, Kieran Zucker et al.

This study explores the use of the Dirichlet Variational Autoencoder (DirVAE) for learning disentangled latent representations of chest X-ray (CXR) images. Our working hypothesis is that distributional sparsity, as facilitated by the Dirichlet prior, will encourage disentangled feature learning for the complex task of multi-label classification of CXR images. The DirVAE is trained using CXR images from the CheXpert database, and the predictive capacity of multi-modal latent representations learned by DirVAE models is investigated through implementation of an auxiliary multi-label classification task, with a view to enforce separation of latent factors according to class-specific features. The predictive performance and explainability of the latent space learned using the DirVAE were quantitatively and qualitatively assessed, respectively, and compared with a standard Gaussian prior-VAE (GVAE). We introduce a new approach for explainable multi-label classification in which we conduct gradient-guided latent traversals for each class of interest. Study findings indicate that the DirVAE is able to disentangle latent factors into class-specific visual features, a property not afforded by the GVAE, and achieve a marginal increase in predictive performance relative to GVAE. We generate visual examples to show that our explainability method, when applied to the trained DirVAE, is able to highlight regions in CXR images that are clinically relevant to the class(es) of interest and additionally, can identify cases where classification relies on spurious feature correlations.

Xiang Chen, Yan Xia, Nishant Ravikumar et al.

Medical image registration is a challenging task involving the estimation of spatial transformations to establish anatomical correspondence between pairs or groups of images. Recently, deep learning-based image registration methods have been widely explored, and demonstrated to enable fast and accurate image registration in a variety of applications. However, most deep learning-based registration methods assume that the deformation fields are smooth and continuous everywhere in the image domain, which is not always true, especially when registering images whose fields of view contain discontinuities at tissue/organ boundaries. In such scenarios, enforcing smooth, globally continuous deformation fields leads to incorrect/implausible registration results. We propose a novel discontinuity-preserving image registration method to tackle this challenge, which ensures globally discontinuous and locally smooth deformation fields, leading to more accurate and realistic registration results. The proposed method leverages the complementary nature of image segmentation and registration and enables joint segmentation and pair-wise registration of images. A co-attention block is proposed in the segmentation component of the network to learn the structural correlations in the input images, while a discontinuity-preserving registration strategy is employed in the registration component of the network to ensure plausibility in the estimated deformation fields at tissue/organ interfaces. We evaluate our method on the task of intra-subject spatio-temporal image registration using large-scale cinematic cardiac magnetic resonance image sequences, and demonstrate that our method achieves significant improvements over the state-of-the-art for medical image registration, and produces high-quality segmentation masks for the regions of interest.

Fengming Lin, Yan Xia, Nishant Ravikumar et al.

Accurate segmentation of brain vessels is crucial for cerebrovascular disease diagnosis and treatment. However, existing methods face challenges in capturing small vessels and handling datasets that are partially or ambiguously annotated. In this paper, we propose an adaptive semi-supervised approach to address these challenges. Our approach incorporates innovative techniques including progressive semi-supervised learning, adaptative training strategy, and boundary enhancement. Experimental results on 3DRA datasets demonstrate the superiority of our method in terms of mesh-based segmentation metrics. By leveraging the partially and ambiguously labeled data, which only annotates the main vessels, our method achieves impressive segmentation performance on mislabeled fine vessels, showcasing its potential for clinical applications.

Rodrigo Bonazzola, Enzo Ferrante, Nishant Ravikumar et al.

Recent genome-wide association studies (GWAS) have been successful in identifying associations between genetic variants and simple cardiac parameters derived from cardiac magnetic resonance (CMR) images. However, the emergence of big databases including genetic data linked to CMR, facilitates investigation of more nuanced patterns of shape variability. Here, we propose a new framework for gene discovery entitled Unsupervised Phenotype Ensembles (UPE). UPE builds a redundant yet highly expressive representation by pooling a set of phenotypes learned in an unsupervised manner, using deep learning models trained with different hyperparameters. These phenotypes are then analyzed via (GWAS), retaining only highly confident and stable associations across the ensemble. We apply our approach to the UK Biobank database to extract left-ventricular (LV) geometric features from image-derived three-dimensional meshes. We demonstrate that our approach greatly improves the discoverability of genes influencing LV shape, identifying 11 loci with study-wide significance and 8 with suggestive significance. We argue that our approach would enable more extensive discovery of gene associations with image-derived phenotypes for other organs or image modalities.

Nurbanu Aksoy, Serge Sharoff, Selcuk Baser et al.

Image-to-text radiology report generation aims to automatically produce radiology reports that describe the findings in medical images. Most existing methods focus solely on the image data, disregarding the other patient information accessible to radiologists. In this paper, we present a novel multi-modal deep neural network framework for generating chest X-rays reports by integrating structured patient data, such as vital signs and symptoms, alongside unstructured clinical notes.We introduce a conditioned cross-multi-head attention module to fuse these heterogeneous data modalities, bridging the semantic gap between visual and textual data. Experiments demonstrate substantial improvements from using additional modalities compared to relying on images alone. Notably, our model achieves the highest reported performance on the ROUGE-L metric compared to relevant state-of-the-art models in the literature. Furthermore, we employed both human evaluation and clinical semantic similarity measurement alongside word-overlap metrics to improve the depth of quantitative analysis. A human evaluation, conducted by a board-certified radiologist, confirms the model's accuracy in identifying high-level findings, however, it also highlights that more improvement is needed to capture nuanced details and clinical context.

Sebastien Andre-Sloan, Dibyakanti Kumar, Alejandro F Frangi et al.

This work establishes rigorous first-of-its-kind upper bounds on the generalization error for the method of approximating solutions to the (d+1)-dimensional incompressible Navier-Stokes equations by training depth-2 neural networks trained via the unsupervised Physics-Informed Neural Network (PINN) framework. This is achieved by bounding the Rademacher complexity of the PINN risk. For appropriately weight bounded net classes our derived generalization bounds do not explicitly depend on the network width and our framework characterizes the generalization gap in terms of the fluid's kinematic viscosity and loss regularization parameters. In particular, the resulting sample complexity bounds are dimension-independent. Our generalization bounds suggest using novel activation functions for solving fluid dynamics. We provide empirical validation of the suggested activation functions and the corresponding bounds on a PINN setup solving the Taylor-Green vortex benchmark.

Rachael Harkness, Geoff Hall, Alejandro F Frangi et al.

Since the emergence of COVID-19, deep learning models have been developed to identify COVID-19 from chest X-rays. With little to no direct access to hospital data, the AI community relies heavily on public data comprising numerous data sources. Model performance results have been exceptional when training and testing on open-source data, surpassing the reported capabilities of AI in pneumonia-detection prior to the COVID-19 outbreak. In this study impactful models are trained on a widely used open-source data and tested on an external test set and a hospital dataset, for the task of classifying chest X-rays into one of three classes: COVID-19, non-COVID pneumonia and no-pneumonia. Classification performance of the models investigated is evaluated through ROC curves, confusion matrices and standard classification metrics. Explainability modules are implemented to explore the image features most important to classification. Data analysis and model evaluations show that the popular open-source dataset COVIDx is not representative of the real clinical problem and that results from testing on this are inflated. Dependence on open-source data can leave models vulnerable to bias and confounding variables, requiring careful analysis to develop clinically useful/viable AI tools for COVID-19 detection in chest X-rays.

Zhengkai Sun, Dibyakanti Kumar, Alejandro F Frangi et al.

Transformers have revolutionized machine learning and deploying attention layers in the model is increasingly standard across a myriad of applications. Further, for large models, it is common to implement Low Rank Adaptation (LoRA), whereby a factorized parameterization of them is trained, to achieve a surprisingly beneficial accuracy-size trade-off. In this work, via a unified framework we rigorously establish trainability of such models under stochastic methods. We prove that for any mild regularization, the empirical regression loss on a attention layer and LoRA on a shallow neural net, both induce Poincaré inequality for the corresponding Gibbs' measure. Then it follows via invoking recent results that a certain SDE, which mimics the SGD, minimizes the corresponding losses. In both the cases, our first-of-its-kind results of trainability on attention and nets, do not rely on any assumptions on the data or the size of the architecture.

Cynthia Maldonado-Garcia, Rodrigo Bonazzola, Enzo Ferrante et al.

Cardiovascular diseases (CVD) are the leading cause of death globally. Non-invasive, cost-effective imaging techniques play a crucial role in early detection and prevention of CVD. Optical coherence tomography (OCT) has gained recognition as a potential tool for early CVD risk prediction, though its use remains underexplored. In this study, we investigated the potential of OCT as an additional imaging technique to predict future CVD events. We analysed retinal OCT data from the UK Biobank. The dataset included 612 patients who suffered a myocardial infarction (MI) or stroke within five years of imaging and 2,234 controls without CVD (total: 2,846 participants). A self-supervised deep learning approach based on Variational Autoencoders (VAE) was used to extract low-dimensional latent representations from high-dimensional 3D OCT images, capturing distinct features of retinal layers. These latent features, along with clinical data, were used to train a Random Forest (RF) classifier to differentiate between patients at risk of future CVD events (MI or stroke) and healthy controls. Our model achieved an AUC of 0.75, sensitivity of 0.70, specificity of 0.70, and accuracy of 0.70, outperforming the QRISK3 score (the third version of the QRISK cardiovascular disease risk prediction algorithm; AUC = 0.60, sensitivity = 0.60, specificity = 0.55, accuracy = 0.55). The choroidal layer in OCT images was identified as a key predictor of future CVD events, revealed through a novel model explainability approach. This study demonstrates that retinal OCT imaging is a cost-effective, non-invasive alternative for predicting CVD risk, offering potential for widespread application in optometry practices and hospitals.

Yuhao Huang, Ao Chang, Haoran Dou et al.

Accurate segmentation of nodules in both 2D breast ultrasound (BUS) and 3D automated breast ultrasound (ABUS) is crucial for clinical diagnosis and treatment planning. Therefore, developing an automated system for nodule segmentation can enhance user independence and expedite clinical analysis. Unlike fully-supervised learning, weakly-supervised segmentation (WSS) can streamline the laborious and intricate annotation process. However, current WSS methods face challenges in achieving precise nodule segmentation, as many of them depend on inaccurate activation maps or inefficient pseudo-mask generation algorithms. In this study, we introduce a novel multi-agent reinforcement learning-based WSS framework called Flip Learning, which relies solely on 2D/3D boxes for accurate segmentation. Specifically, multiple agents are employed to erase the target from the box to facilitate classification tag flipping, with the erased region serving as the predicted segmentation mask. The key contributions of this research are as follows: (1) Adoption of a superpixel/supervoxel-based approach to encode the standardized environment, capturing boundary priors and expediting the learning process. (2) Introduction of three meticulously designed rewards, comprising a classification score reward and two intensity distribution rewards, to steer the agents' erasing process precisely, thereby avoiding both under- and over-segmentation. (3) Implementation of a progressive curriculum learning strategy to enable agents to interact with the environment in a progressively challenging manner, thereby enhancing learning efficiency. Extensively validated on the large in-house BUS and ABUS datasets, our Flip Learning method outperforms state-of-the-art WSS methods and foundation models, and achieves comparable performance as fully-supervised learning algorithms.

Cynthia Maldonado-Garcia, Arezoo Zakeri, Alejandro F Frangi et al.

Early identification of patients at risk of cardiovascular diseases (CVD) is crucial for effective preventive care, reducing healthcare burden, and improving patients' quality of life. This study demonstrates the potential of retinal optical coherence tomography (OCT) imaging combined with fundus photographs for identifying future adverse cardiac events. We used data from 977 patients who experienced CVD within a 5-year interval post-image acquisition, alongside 1,877 control participants without CVD, totaling 2,854 subjects. We propose a novel binary classification network based on a Multi-channel Variational Autoencoder (MCVAE), which learns a latent embedding of patients' fundus and OCT images to classify individuals into two groups: those likely to develop CVD in the future and those who are not. Our model, trained on both imaging modalities, achieved promising results (AUROC 0.78 +/- 0.02, accuracy 0.68 +/- 0.002, precision 0.74 +/- 0.02, sensitivity 0.73 +/- 0.02, and specificity 0.68 +/- 0.01), demonstrating its efficacy in identifying patients at risk of future CVD events based on their retinal images. This study highlights the potential of retinal OCT imaging and fundus photographs as cost-effective, non-invasive alternatives for predicting cardiovascular disease risk. The widespread availability of these imaging techniques in optometry practices and hospitals further enhances their potential for large-scale CVD risk screening. Our findings contribute to the development of standardized, accessible methods for early CVD risk identification, potentially improving preventive care strategies and patient outcomes.

Ziwei Zou, Bei Zou, Xiaoyan Kui et al.

Atlas construction is fundamental to medical image analysis, offering a standardized spatial reference for tasks such as population-level anatomical modeling. While data-driven registration methods have recently shown promise in pairwise settings, their reliance on large training datasets, limited generalizability, and lack of true inference phases in groupwise contexts hinder their practical use. In contrast, model-driven methods offer training-free, theoretically grounded, and data-efficient alternatives, though they often face scalability and optimization challenges when applied to large 3D datasets. In this work, we introduce DARC (Diffeomorphic Atlas Registration via Coordinate descent), a novel model-driven groupwise registration framework for atlas construction. DARC supports a broad range of image dissimilarity metrics and efficiently handles arbitrary numbers of 3D images without incurring GPU memory issues. Through a coordinate descent strategy and a centrality-enforcing activation function, DARC produces unbiased, diffeomorphic atlases with high anatomical fidelity. Beyond atlas construction, we demonstrate two key applications: (1) One-shot segmentation, where labels annotated only on the atlas are propagated to subjects via inverse deformations, outperforming state-of-the-art few-shot methods; and (2) shape synthesis, where new anatomical variants are generated by warping the atlas mesh using synthesized diffeomorphic deformation fields. Overall, DARC offers a flexible, generalizable, and resource-efficient framework for atlas construction and applications.

Yuhao Huang, Xin Yang, Yuxin Zou et al.

Nodule segmentation from breast ultrasound images is challenging yet essential for the diagnosis. Weakly-supervised segmentation (WSS) can help reduce time-consuming and cumbersome manual annotation. Unlike existing weakly-supervised approaches, in this study, we propose a novel and general WSS framework called Flip Learning, which only needs the box annotation. Specifically, the target in the label box will be erased gradually to flip the classification tag, and the erased region will be considered as the segmentation result finally. Our contribution is three-fold. First, our proposed approach erases on superpixel level using a Multi-agent Reinforcement Learning framework to exploit the prior boundary knowledge and accelerate the learning process. Second, we design two rewards: classification score and intensity distribution reward, to avoid under- and over-segmentation, respectively. Third, we adopt a coarse-to-fine learning strategy to reduce the residual errors and improve the segmentation performance. Extensively validated on a large dataset, our proposed approach achieves competitive performance and shows great potential to narrow the gap between fully-supervised and weakly-supervised learning.

Zhendong Liu, Van Manh, Xin Yang et al.

The performance of deep segmentation models often degrades due to distribution shifts in image intensities between the training and test data sets. This is particularly pronounced in multi-centre studies involving data acquired using multi-vendor scanners, with variations in acquisition protocols. It is challenging to address this degradation because the shift is often not known \textit{a priori} and hence difficult to model. We propose a novel framework to ensure robust segmentation in the presence of such distribution shifts. Our contribution is three-fold. First, inspired by the spirit of curriculum learning, we design a novel style curriculum to train the segmentation models using an easy-to-hard mode. A style transfer model with style fusion is employed to generate the curriculum samples. Gradually focusing on complex and adversarial style samples can significantly boost the robustness of the models. Second, instead of subjectively defining the curriculum complexity, we adopt an automated gradient manipulation method to control the hard and adversarial sample generation process. Third, we propose the Local Gradient Sign strategy to aggregate the gradient locally and stabilise training during gradient manipulation. The proposed framework can generalise to unknown distribution without using any target data. Extensive experiments on the public M\&Ms Challenge dataset demonstrate that our proposed framework can generalise deep models well to unknown distributions and achieve significant improvements in segmentation accuracy.

Mingyuan Luo, Xin Yang, Xiaoqiong Huang et al.

3D ultrasound (US) is widely used for its rich diagnostic information. However, it is criticized for its limited field of view. 3D freehand US reconstruction is promising in addressing the problem by providing broad range and freeform scan. The existing deep learning based methods only focus on the basic cases of skill sequences, and the model relies on the training data heavily. The sequences in real clinical practice are a mix of diverse skills and have complex scanning paths. Besides, deep models should adapt themselves to the testing cases with prior knowledge for better robustness, rather than only fit to the training cases. In this paper, we propose a novel approach to sensorless freehand 3D US reconstruction considering the complex skill sequences. Our contribution is three-fold. First, we advance a novel online learning framework by designing a differentiable reconstruction algorithm. It realizes an end-to-end optimization from section sequences to the reconstructed volume. Second, a self-supervised learning method is developed to explore the context information that reconstructed by the testing data itself, promoting the perception of the model. Third, inspired by the effectiveness of shape prior, we also introduce adversarial training to strengthen the learning of anatomical shape prior in the reconstructed volume. By mining the context and structural cues of the testing data, our online learning methods can drive the model to handle complex skill sequences. Experimental results on developmental dysplasia of the hip US and fetal US datasets show that, our proposed method can outperform the start-of-the-art methods regarding the shift errors and path similarities.

Xiang Chen, Nishant Ravikumar, Yan Xia et al.

Image registration aims to establish spatial correspondence across pairs, or groups of images, and is a cornerstone of medical image computing and computer-assisted-interventions. Currently, most deep learning-based registration methods assume that the desired deformation fields are globally smooth and continuous, which is not always valid for real-world scenarios, especially in medical image registration (e.g. cardiac imaging and abdominal imaging). Such a global constraint can lead to artefacts and increased errors at discontinuous tissue interfaces. To tackle this issue, we propose a weakly-supervised Deep Discontinuity-preserving Image Registration network (DDIR), to obtain better registration performance and realistic deformation fields. We demonstrate that our method achieves significant improvements in registration accuracy and predicts more realistic deformations, in registration experiments on cardiac magnetic resonance (MR) images from UK Biobank Imaging Study (UKBB), than state-of-the-art approaches.

Xiang Chen, Yan Xia, Nishant Ravikumar et al.

Image registration is a fundamental building block for various applications in medical image analysis. To better explore the correlation between the fixed and moving images and improve registration performance, we propose a novel deep learning network, Co-Attention guided Registration Network (CAR-Net). CAR-Net employs a co-attention block to learn a new representation of the inputs, which drives the registration of the fixed and moving images. Experiments on UK Biobank cardiac cine-magnetic resonance image data demonstrate that CAR-Net obtains higher registration accuracy and smoother deformation fields than state-of-the-art unsupervised registration methods, while achieving comparable or better registration performance than corresponding weakly-supervised variants. In addition, our approach can provide critical structural information of the input fixed and moving images simultaneously in a completely unsupervised manner.

Zhendong Liu, Xiaoqiong Huang, Xin Yang et al.

Deep segmentation models that generalize to images with unknown appearance are important for real-world medical image analysis. Retraining models leads to high latency and complex pipelines, which are impractical in clinical settings. The situation becomes more severe for ultrasound image analysis because of their large appearance shifts. In this paper, we propose a novel method for robust segmentation under unknown appearance shifts. Our contribution is three-fold. First, we advance a one-stage plug-and-play solution by embedding hierarchical style transfer units into a segmentation architecture. Our solution can remove appearance shifts and perform segmentation simultaneously. Second, we adopt Dynamic Instance Normalization to conduct precise and dynamic style transfer in a learnable manner, rather than previously fixed style normalization. Third, our solution is fast and lightweight for routine clinical adoption. Given 400*400 image input, our solution only needs an additional 0.2ms and 1.92M FLOPs to handle appearance shifts compared to the baseline pipeline. Extensive experiments are conducted on a large dataset from three vendors demonstrate our proposed method enhances the robustness of deep segmentation models.

Daiqing Li, Amlan Kar, Nishant Ravikumar et al.

Labelling data is expensive and time consuming especially for domains such as medical imaging that contain volumetric imaging data and require expert knowledge. Exploiting a larger pool of labeled data available across multiple centers, such as in federated learning, has also seen limited success since current deep learning approaches do not generalize well to images acquired with scanners from different manufacturers. We aim to address these problems in a common, learning-based image simulation framework which we refer to as Federated Simulation. We introduce a physics-driven generative approach that consists of two learnable neural modules: 1) a module that synthesizes 3D cardiac shapes along with their materials, and 2) a CT simulator that renders these into realistic 3D CT Volumes, with annotations. Since the model of geometry and material is disentangled from the imaging sensor, it can effectively be trained across multiple medical centers. We show that our data synthesis framework improves the downstream segmentation performance on several datasets. Project Page: https://nv-tlabs.github.io/fed-sim/ .