Javier Montalt‐Tordera

Endrit Pajaziti, Javier Montalt-Tordera, Claudio Capelli et al.

Computational fluid dynamics (CFD) can be used to simulate vascular haemodynamics and analyse potential treatment options. CFD has shown to be beneficial in improving patient outcomes. However, the implementation of CFD for routine clinical use is yet to be realised. Barriers for CFD include high computational resources, specialist experience needed for designing simulation set-ups, and long processing times. The aim of this study was to explore the use of machine learning (ML) to replicate conventional aortic CFD with automatic and fast regression models. Data used to train/test the model consisted of 3,000 CFD simulations performed on synthetically generated 3D aortic shapes. These subjects were generated from a statistical shape model (SSM) built on real patient-specific aortas (N=67). Inference performed on 200 test shapes resulted in average errors of 6.01% +/-3.12 SD and 3.99% +/-0.93 SD for pressure and velocity, respectively. Our ML-based models performed CFD in +/-0.075 seconds (4,000x faster than the solver). This proof-of-concept study shows that results from conventional vascular CFD can be reproduced using ML at a much faster rate, in an automatic process, and with high accuracy.

Olivier Jaubert, Javier Montalt-Tordera, James Brown et al.

Purpose: Real-time monitoring of cardiac output (CO) requires low latency reconstruction and segmentation of real-time phase contrast MR (PCMR), which has previously been difficult to perform. Here we propose a deep learning framework for 'Flow Reconstruction and Segmentation for low latency Cardiac Output monitoring' (FReSCO). Methods: Deep artifact suppression and segmentation U-Nets were independently trained. Breath hold spiral PCMR data (n=516) was synthetically undersampled using a variable density spiral sampling pattern and gridded to create aliased data for training of the artifact suppression U-net. A subset of the data (n=96) was segmented and used to train the segmentation U-net. Real-time spiral PCMR was prospectively acquired and then reconstructed and segmented using the trained models (FReSCO) at low latency at the scanner in 10 healthy subjects during rest, exercise and recovery periods. CO obtained via FReSCO was compared to a reference rest CO and rest and exercise Compressed Sensing (CS) CO. Results: FReSCO was demonstrated prospectively at the scanner. Beat-to-beat heartrate, stroke volume and CO could be visualized with a mean latency of 622ms. No significant differences were noted when compared to reference at rest (Bias = -0.21+-0.50 L/min, p=0.246) or CS at peak exercise (Bias=0.12+-0.48 L/min, p=0.458). Conclusion: FReSCO was successfully demonstrated for real-time monitoring of CO during exercise and could provide a convenient tool for assessment of the hemodynamic response to a range of stressors.

Olivier Jaubert, Javier Montalt-Tordera, Daniel Knight et al.

PURPOSE: Interactive cardiac magnetic resonance imaging is used for fast scan planning and MR guided interventions. However, the requirement for real-time acquisition and near real-time visualization constrains the achievable spatio-temporal resolution. This study aims to improve interactive imaging resolution through optimization of undersampled spiral sampling and leveraging of deep learning for low-latency reconstruction (deep artifact suppression). METHODS: A variable density spiral trajectory was parametrized and optimized via HyperBand to provide the best candidate trajectory for rapid deep artifact suppression. Training data consisted of 692 breath-held CINEs. The developed interactive sequence was tested in simulations and prospectively in 13 subjects (10 for image evaluation, 2 during catheterization, 1 during exercise). In the prospective study, the optimized framework -HyperSLICE- was compared to conventional Cartesian real-time, and breath-hold CINE imaging in terms quantitative and qualitative image metrics. Statistical differences were tested using Friedman chi-squared tests with post-hoc Nemenyi test (p<0.05). RESULTS: In simulations the NRMSE, pSNR, SSIM and LAPE were all statistically significantly higher using optimized spiral compared to radial and uniform spiral sampling, particularly after scan plan changes (SSIM: 0.71 vs 0.45 and 0.43). Prospectively, HyperSLICE enabled a higher spatial and temporal resolution than conventional Cartesian real-time imaging. The pipeline was demonstrated in patients during catheter pull back showing sufficiently fast reconstruction for interactive imaging. CONCLUSION: HyperSLICE enables high spatial and temporal resolution interactive imaging. Optimizing the spiral sampling enabled better overall image quality and superior handling of image transitions compared to radial and uniform spiral trajectories.

Olivier Jaubert, Michele Pascale, Javier Montalt-Tordera et al.

Purpose: To develop and assess a deep learning (DL) pipeline to learn dynamic MR image reconstruction from publicly available natural videos (Inter4K). Materials and Methods: Learning was performed for a range of DL architectures (VarNet, 3D UNet, FastDVDNet) and corresponding sampling patterns (Cartesian, radial, spiral) either from true multi-coil cardiac MR data (N=692) or from pseudo-MR data simulated from Inter4K natural videos (N=692). Real-time undersampled dynamic MR images were reconstructed using DL networks trained with cardiac data and natural videos, and compressed sensing (CS). Differences were assessed in simulations (N=104 datasets) in terms of MSE, PSNR, and SSIM and prospectively for cardiac (short axis, four chambers, N=20) and speech (N=10) data in terms of subjective image quality ranking, SNR and Edge sharpness. Friedman Chi Square tests with post-hoc Nemenyi analysis were performed to assess statistical significance. Results: For all simulation metrics, DL networks trained with cardiac data outperformed DL networks trained with natural videos, which outperformed CS (p<0.05). However, in prospective experiments DL reconstructions using both training datasets were ranked similarly (and higher than CS) and presented no statistical differences in SNR and Edge Sharpness for most conditions. Additionally, high SSIM was measured between the DL methods with cardiac data and natural videos (SSIM>0.85). Conclusion: The developed pipeline enabled learning dynamic MR reconstruction from natural videos preserving DL reconstruction advantages such as high quality fast and ultra-fast reconstructions while overcoming some limitations (data scarcity or sharing). The natural video dataset, code and pre-trained networks are made readily available on github. Key Words: real-time; dynamic MRI; deep learning; image reconstruction; machine learning;

Michele Pascale, Vivek Muthurangu, Javier Montalt Tordera et al.

Three-dimensional (3D) imaging is popular in medical applications, however, anisotropic 3D volumes with thick, low-spatial-resolution slices are often acquired to reduce scan times. Deep learning (DL) offers a solution to recover high-resolution features through super-resolution reconstruction (SRR). Unfortunately, paired training data is unavailable in many 3D medical applications and therefore we propose a novel unpaired approach; CLADE (Cycle Loss Augmented Degradation Enhancement). CLADE uses a modified CycleGAN architecture with a cycle-consistent gradient mapping loss, to learn SRR of the low-resolution dimension, from disjoint patches of the high-resolution plane within the anisotropic 3D volume data itself. We show the feasibility of CLADE in abdominal MRI and abdominal CT and demonstrate significant improvements in CLADE image quality over low-resolution volumes and state-of-the-art self-supervised SRR; SMORE (Synthetic Multi-Orientation Resolution Enhancement). Quantitative PIQUE (qualitative perception-based image quality evaluator) scores and quantitative edge sharpness (ES - calculated as the maximum gradient of pixel intensities over a border of interest), showed superior performance for CLADE in both MRI and CT. Qualitatively CLADE had the best overall image quality and highest perceptual ES over the low-resolution volumes and SMORE. This paper demonstrates the potential of using CLADE for super-resolution reconstruction of anisotropic 3D medical imaging data without the need for paired 3D training data.

Guillermo Jimenez-Perez, Pedro Osorio, Josef Cersovsky et al.

Diffusion models (DMs) have emerged as powerful foundation models for a variety of tasks, with a large focus in synthetic image generation. However, their requirement of large annotated datasets for training limits their applicability in medical imaging, where datasets are typically smaller and sparsely annotated. We introduce DiNO-Diffusion, a self-supervised method for training latent diffusion models (LDMs) that conditions the generation process on image embeddings extracted from DiNO. By eliminating the reliance on annotations, our training leverages over 868k unlabelled images from public chest X-Ray (CXR) datasets. Despite being self-supervised, DiNO-Diffusion shows comprehensive manifold coverage, with FID scores as low as 4.7, and emerging properties when evaluated in downstream tasks. It can be used to generate semantically-diverse synthetic datasets even from small data pools, demonstrating up to 20% AUC increase in classification performance when used for data augmentation. Images were generated with different sampling strategies over the DiNO embedding manifold and using real images as a starting point. Results suggest, DiNO-Diffusion could facilitate the creation of large datasets for flexible training of downstream AI models from limited amount of real data, while also holding potential for privacy preservation. Additionally, DiNO-Diffusion demonstrates zero-shot segmentation performance of up to 84.4% Dice score when evaluating lung lobe segmentation. This evidences good CXR image-anatomy alignment, akin to segmenting using textual descriptors on vanilla DMs. Finally, DiNO-Diffusion can be easily adapted to other medical imaging modalities or state-of-the-art diffusion models, opening the door for large-scale, multi-domain image generation pipelines for medical imaging.

Kun Zhao, Jakub Prokop, Javier Montalt Tordera et al.

Mammography is crucial for breast cancer surveillance and early diagnosis. However, analyzing mammography images is a demanding task for radiologists, who often review hundreds of mammograms daily, leading to overdiagnosis and overtreatment. Computer-Aided Diagnosis (CAD) systems have been developed to assist in this process, but their capabilities, particularly in lesion segmentation, remained limited. With the contemporary advances in deep learning their performance may be improved. Recently, vision-language diffusion models emerged, demonstrating outstanding performance in image generation and transferability to various downstream tasks. We aim to harness their capabilities for breast lesion segmentation in a panoptic setting, which encompasses both semantic and instance-level predictions. Specifically, we propose leveraging pretrained features from a Stable Diffusion model as inputs to a state-of-the-art panoptic segmentation architecture, resulting in accurate delineation of individual breast lesions. To bridge the gap between natural and medical imaging domains, we incorporated a mammography-specific MAM-E diffusion model and BiomedCLIP image and text encoders into this framework. We evaluated our approach on two recently published mammography datasets, CDD-CESM and VinDr-Mammo. For the instance segmentation task, we noted 40.25 AP0.1 and 46.82 AP0.05, as well as 25.44 PQ0.1 and 26.92 PQ0.05. For the semantic segmentation task, we achieved Dice scores of 38.86 and 40.92, respectively.

Pedro Osorio, Guillermo Jimenez-Perez, Javier Montalt-Tordera et al.

Artificial Intelligence (AI) based image analysis has an immense potential to support diagnostic histopathology, including cancer diagnostics. However, developing supervised AI methods requires large-scale annotated datasets. A potentially powerful solution is to augment training data with synthetic data. Latent diffusion models, which can generate high-quality, diverse synthetic images, are promising. However, the most common implementations rely on detailed textual descriptions, which are not generally available in this domain. This work proposes a method that constructs structured textual prompts from automatically extracted image features. We experiment with the PCam dataset, composed of tissue patches only loosely annotated as healthy or cancerous. We show that including image-derived features in the prompt, as opposed to only healthy and cancerous labels, improves the Fréchet Inception Distance (FID) from 178.8 to 90.2. We also show that pathologists find it challenging to detect synthetic images, with a median sensitivity/specificity of 0.55/0.55. Finally, we show that synthetic data effectively trains AI models.

Javier Montalt-Tordera, Vivek Muthurangu, Andreas Hauptmann et al.

Magnetic Resonance Imaging (MRI) plays a vital role in diagnosis, management and monitoring of many diseases. However, it is an inherently slow imaging technique. Over the last 20 years, parallel imaging, temporal encoding and compressed sensing have enabled substantial speed-ups in the acquisition of MRI data, by accurately recovering missing lines of k-space data. However, clinical uptake of vastly accelerated acquisitions has been limited, in particular in compressed sensing, due to the time-consuming nature of the reconstructions and unnatural looking images. Following the success of machine learning in a wide range of imaging tasks, there has been a recent explosion in the use of machine learning in the field of MRI image reconstruction. A wide range of approaches have been proposed, which can be applied in k-space and/or image-space. Promising results have been demonstrated from a range of methods, enabling natural looking images and rapid computation. In this review article we summarize the current machine learning approaches used in MRI reconstruction, discuss their drawbacks, clinical applications, and current trends.