A Speech-to-Video Synthesis Approach Using Spatio-Temporal Diffusion for Vocal Tract MRI

Understanding the relationship between vocal tract motion during speech and the resulting acoustic signal is crucial for aided clinical assessment and developing personalized treatment and rehabilitation strategies. Toward this goal, we introduce an audio-to-video generation framework for creating Real Time/cine-Magnetic Resonance Imaging (RT-/cine-MRI) visuals of the vocal tract from speech signals. Our framework first preprocesses RT-/cine-MRI sequences and speech samples to achieve temporal alignment, ensuring synchronization between visual and audio data. We then employ a modified stable diffusion model, integrating structural and temporal blocks, to effectively capture movement characteristics and temporal dynamics in the synchronized data. This process enables the generation of MRI sequences from new speech inputs, improving the conversion of audio into visual data. We evaluated our framework on healthy controls and tongue cancer patients by analyzing and comparing the vocal tract movements in synthesized videos. Our framework demonstrated adaptability to new speech inputs and effective generalization. In addition, positive human evaluations confirmed its effectiveness, with realistic and accurate visualizations, suggesting its potential for outpatient therapy and personalized simulation of vocal tract visualizations.

ECLARE: Efficient cross-planar learning for anisotropic resolution enhancement

In clinical imaging, magnetic resonance (MR) image volumes are often acquired as stacks of 2D slices, permitting decreased scan times, improved signal-to-noise ratio, and image contrasts unique to 2D MR pulse sequences. While this is sufficient for clinical evaluation, automated algorithms designed for 3D analysis perform sub-optimally on 2D-acquired scans, especially those with thick slices and gaps between slices. Super-resolution (SR) methods aim to address this problem, but previous methods do not address all of the following: slice profile shape estimation, slice gap, domain shift, and non-integer / arbitrary upsampling factors. In this paper, we propose ECLARE (Efficient Cross-planar Learning for Anisotropic Resolution Enhancement), a self-SR method that addresses each of these factors. ECLARE estimates the slice profile from the 2D-acquired multi-slice MR volume, trains a network to learn the mapping from low-resolution to high-resolution in-plane patches from the same volume, and performs SR with anti-aliasing. We compared ECLARE to cubic B-spline interpolation, SMORE, and other contemporary SR methods. We used realistic and representative simulations so that quantitative performance against a ground truth could be computed, and ECLARE outperformed all other methods in both signal recovery and downstream tasks. On real data for which there is no ground truth, ECLARE demonstrated qualitative superiority over other methods as well. Importantly, as ECLARE does not use external training data it cannot suffer from domain shift between training and testing. Our code is open-source and available at https://www.github.com/sremedios/eclare.

Pitfalls of defacing whole-head MRI: re-identification risk with diffusion models and compromised research potential

Defacing is often applied to head magnetic resonance image (MRI) datasets prior to public release to address privacy concerns. The alteration of facial and nearby voxels has provoked discussions about the true capability of these techniques to ensure privacy as well as their impact on downstream tasks. With advancements in deep generative models, the extent to which defacing can protect privacy is uncertain. Additionally, while the altered voxels are known to contain valuable anatomical information, their potential to support research beyond the anatomical regions directly affected by defacing remains uncertain. To evaluate these considerations, we develop a refacing pipeline that recovers faces in defaced head MRIs using cascaded diffusion probabilistic models (DPMs). The DPMs are trained on images from 180 subjects and tested on images from 484 unseen subjects, 469 of whom are from a different dataset. To assess whether the altered voxels in defacing contain universally useful information, we also predict computed tomography (CT)-derived skeletal muscle radiodensity from facial voxels in both defaced and original MRIs. The results show that DPMs can generate high-fidelity faces that resemble the original faces from defaced images, with surface distances to the original faces significantly smaller than those of a population average face (p < 0.05). This performance also generalizes well to previously unseen datasets. For skeletal muscle radiodensity predictions, using defaced images results in significantly weaker Spearman's rank correlation coefficients compared to using original images (p < 10-4). For shin muscle, the correlation is statistically significant (p < 0.05) when using original images but not statistically significant (p > 0.05) when any defacing method is applied, suggesting that defacing might not only fail to protect privacy but also eliminate valuable information.

Unique MS Lesion Identification from MRI

Unique identification of multiple sclerosis (MS) white matter lesions (WMLs) is important to help characterize MS progression. WMLs are routinely identified from magnetic resonance images (MRIs) but the resultant total lesion load does not correlate well with EDSS; whereas mean unique lesion volume has been shown to correlate with EDSS. Our approach builds on prior work by incorporating Hessian matrix computation from lesion probability maps before using the random walker algorithm to estimate the volume of each unique lesion. Synthetic images demonstrate our ability to accurately count the number of lesions present. The takeaways, are: 1) that our method correctly identifies all lesions including many that are missed by previous methods; 2) we can better separate confluent lesions; and 3) we can accurately capture the total volume of WMLs in a given probability map. This work will allow new more meaningful statistics to be computed from WMLs in brain MRIs

Bi-Directional MS Lesion Filling and Synthesis Using Denoising Diffusion Implicit Model-based Lesion Repainting

Automatic magnetic resonance (MR) image processing pipelines are widely used to study people with multiple sclerosis (PwMS), encompassing tasks such as lesion segmentation and brain parcellation. However, the presence of lesion often complicates these analysis, particularly in brain parcellation. Lesion filling is commonly used to mitigate this issue, but existing lesion filling algorithms often fall short in accurately reconstructing realistic lesion-free images, which are vital for consistent downstream analysis. Additionally, the performance of lesion segmentation algorithms is often limited by insufficient data with lesion delineation as training labels. In this paper, we propose a novel approach leveraging Denoising Diffusion Implicit Models (DDIMs) for both MS lesion filling and synthesis based on image inpainting. Our modified DDIM architecture, once trained, enables both MS lesion filing and synthesis. Specifically, it can generate lesion-free T1-weighted or FLAIR images from those containing lesions; Or it can add lesions to T1-weighted or FLAIR images of healthy subjects. The former is essential for downstream analyses that require lesion-free images, while the latter is valuable for augmenting training datasets for lesion segmentation tasks. We validate our approach through initial experiments in this paper and demonstrate promising results in both lesion filling and synthesis, paving the way for future work.

RATNUS: Rapid, Automatic Thalamic Nuclei Segmentation using Multimodal MRI inputs

Accurate segmentation of thalamic nuclei is important for better understanding brain function and improving disease treatment. Traditional segmentation methods often rely on a single T1-weighted image, which has limited contrast in the thalamus. In this work, we introduce RATNUS, which uses synthetic T1-weighted images with many inversion times along with diffusion-derived features to enhance the visibility of nuclei within the thalamus. Using these features, a convolutional neural network is used to segment 13 thalamic nuclei. For comparison with other methods, we introduce a unified nuclei labeling scheme. Our results demonstrate an 87.19% average true positive rate (TPR) against manual labeling. In comparison, FreeSurfer and THOMAS achieve TPRs of 64.25% and 57.64%, respectively, demonstrating the superiority of RATNUS in thalamic nuclei segmentation.

Beyond MR Image Harmonization: Resolution Matters Too

Magnetic resonance (MR) imaging is commonly used in the clinical setting to non-invasively monitor the body. There exists a large variability in MR imaging due to differences in scanner hardware, software, and protocol design. Ideally, a processing algorithm should perform robustly to this variability, but that is not always the case in reality. This introduces a need for image harmonization to overcome issues of domain shift when performing downstream analysis such as segmentation. Most image harmonization models focus on acquisition parameters such as inversion time or repetition time, but they ignore an important aspect in MR imaging -- resolution. In this paper, we evaluate the impact of image resolution on harmonization using a pretrained harmonization algorithm. We simulate 2D acquisitions of various slice thicknesses and gaps from 3D acquired, 1mm3 isotropic MR images and demonstrate how the performance of a state-of-the-art image harmonization algorithm varies as resolution changes. We discuss the most ideal scenarios for image resolution including acquisition orientation when 3D imaging is not available, which is common for many clinical scanners. Our results show that harmonization on low-resolution images does not account for acquisition resolution and orientation variations. Super-resolution can be used to alleviate resolution variations but it is not always used. Our methodology can generalize to help evaluate the impact of image acquisition resolution for multiple tasks. Determining the limits of a pretrained algorithm is important when considering preprocessing steps and trust in the results.

Vector Field Attention for Deformable Image Registration

Deformable image registration establishes non-linear spatial correspondences between fixed and moving images. Deep learning-based deformable registration methods have been widely studied in recent years due to their speed advantage over traditional algorithms as well as their better accuracy. Most existing deep learning-based methods require neural networks to encode location information in their feature maps and predict displacement or deformation fields though convolutional or fully connected layers from these high-dimensional feature maps. In this work, we present Vector Field Attention (VFA), a novel framework that enhances the efficiency of the existing network design by enabling direct retrieval of location correspondences. VFA uses neural networks to extract multi-resolution feature maps from the fixed and moving images and then retrieves pixel-level correspondences based on feature similarity. The retrieval is achieved with a novel attention module without the need of learnable parameters. VFA is trained end-to-end in either a supervised or unsupervised manner. We evaluated VFA for intra- and inter-modality registration and for unsupervised and semi-supervised registration using public datasets, and we also evaluated it on the Learn2Reg challenge. Experimental results demonstrate the superior performance of VFA compared to existing methods. The source code of VFA is publicly available at https://github.com/yihao6/vfa/.

Revisiting registration-based synthesis: A focus on unsupervised MR image synthesis

Deep learning (DL) has led to significant improvements in medical image synthesis, enabling advanced image-to-image translation to generate synthetic images. However, DL methods face challenges such as domain shift and high demands for training data, limiting their generalizability and applicability. Historically, image synthesis was also carried out using deformable image registration (DIR), a method that warps moving images of a desired modality to match the anatomy of a fixed image. However, concerns about its speed and accuracy led to its decline in popularity. With the recent advances of DL-based DIR, we now revisit and reinvigorate this line of research. In this paper, we propose a fast and accurate synthesis method based on DIR. We use the task of synthesizing a rare magnetic resonance (MR) sequence, white matter nulled (WMn) T1-weighted (T1-w) images, to demonstrate the potential of our approach. During training, our method learns a DIR model based on the widely available MPRAGE sequence, which is a cerebrospinal fluid nulled (CSFn) T1-w inversion recovery gradient echo pulse sequence. During testing, the trained DIR model is first applied to estimate the deformation between moving and fixed CSFn images. Subsequently, this estimated deformation is applied to align the paired WMn counterpart of the moving CSFn image, yielding a synthetic WMn image for the fixed CSFn image. Our experiments demonstrate promising results for unsupervised image synthesis using DIR. These findings highlight the potential of our technique in contexts where supervised synthesis methods are constrained by limited training data.

Speech motion anomaly detection via cross-modal translation of 4D motion fields from tagged MRI

Understanding the relationship between tongue motion patterns during speech and their resulting speech acoustic outcomes -- i.e., articulatory-acoustic relation -- is of great importance in assessing speech quality and developing innovative treatment and rehabilitative strategies. This is especially important when evaluating and detecting abnormal articulatory features in patients with speech-related disorders. In this work, we aim to develop a framework for detecting speech motion anomalies in conjunction with their corresponding speech acoustics. This is achieved through the use of a deep cross-modal translator trained on data from healthy individuals only, which bridges the gap between 4D motion fields obtained from tagged MRI and 2D spectrograms derived from speech acoustic data. The trained translator is used as an anomaly detector, by measuring the spectrogram reconstruction quality on healthy individuals or patients. In particular, the cross-modal translator is likely to yield limited generalization capabilities on patient data, which includes unseen out-of-distribution patterns and demonstrates subpar performance, when compared with healthy individuals.~A one-class SVM is then used to distinguish the spectrograms of healthy individuals from those of patients. To validate our framework, we collected a total of 39 paired tagged MRI and speech waveforms, consisting of data from 36 healthy individuals and 3 tongue cancer patients. We used both 3D convolutional and transformer-based deep translation models, training them on the healthy training set and then applying them to both the healthy and patient testing sets. Our framework demonstrates a capability to detect abnormal patient data, thereby illustrating its potential in enhancing the understanding of the articulatory-acoustic relation for both healthy individuals and patients.