Proceedings of machine learning research最新文献

Voxel-based multiple testing is widely used in neuroimaging data analysis. Traditional false discovery rate (FDR) control methods often ignore the spatial dependence among the voxel-based tests and thus suffer from substantial loss of testing power. While recent spatial FDR control methods have emerged, their validity and optimality remain questionable when handling the complex spatial dependencies of the brain. Concurrently, deep learning methods have revolutionized image segmentation, a task closely related to voxel-based multiple testing. In this paper, we propose DeepFDR, a novel spatial FDR control method that leverages unsupervised deep learning-based image segmentation to address the voxel-based multiple testing problem. Numerical studies, including comprehensive simulations and Alzheimer's disease FDG-PET image analysis, demonstrate DeepFDR's superiority over existing methods. DeepFDR not only excels in FDR control and effectively diminishes the false nondiscovery rate, but also boasts exceptional computational efficiency highly suited for tackling large-scale neuroimaging data.

Contextual bandit algorithms are commonly used in digital health to recommend personalized treatments. However, to ensure the effectiveness of the treatments, patients are often requested to take actions that have no immediate benefit to them, which we refer to as pro-treatment actions. In practice, clinicians have a limited budget to encourage patients to take these actions and collect additional information. We introduce a novel optimization and learning algorithm to address this problem. This algorithm effectively combines the strengths of two algorithmic approaches in a seamless manner, including 1) an online primal-dual algorithm for deciding the optimal timing to reach out to patients, and 2) a contextual bandit learning algorithm to deliver personalized treatment to the patient. We prove that this algorithm admits a sub-linear regret bound. We illustrate the usefulness of this algorithm on both synthetic and real-world data.

We present Roto-Translation Equivariant Spherical Deconvolution (RT-ESD), an $E\left(3\right)\times SO\left(3\right)$ equivariant framework for sparse deconvolution of volumes where each voxel contains a spherical signal. Such 6D data naturally arises in diffusion MRI (dMRI), a medical imaging modality widely used to measure microstructure and structural connectivity. As each dMRI voxel is typically a mixture of various overlapping structures, there is a need for blind deconvolution to recover crossing anatomical structures such as white matter tracts. Existing dMRI work takes either an iterative or deep learning approach to sparse spherical deconvolution, yet it typically does not account for relationships between neighboring measurements. This work constructs equivariant deep learning layers which respect to symmetries of spatial rotations, reflections, and translations, alongside the symmetries of voxelwise spherical rotations. As a result, RT-ESD improves on previous work across several tasks including fiber recovery on the DiSCo dataset, deconvolution-derived partial volume estimation on real-world in vivo human brain dMRI, and improved downstream reconstruction of fiber tractograms on the Tractometer dataset. Our implementation is available at https://github.com/AxelElaldi/e3so3_conv.

Training Deep Neural Networks (DNNs) with adversarial examples often results in poor generalization to test-time adversarial data. This paper investigates this issue, known as adversarially robust generalization, through the lens of Rademacher complexity. Building upon the studies by Khim and Loh (2018); Yin et al. (2019), numerous works have been dedicated to this problem, yet achieving a satisfactory bound remains an elusive goal. Existing works on DNNs either apply to a surrogate loss instead of the robust loss or yield bounds that are notably looser compared to their standard counterparts. In the latter case, the bounds have a higher dependency on the width $m$ of the DNNs or the dimension $d$ of the data, with an extra factor of at least $𝒪\left(\sqrt{m}\right)$ or $𝒪\left(\sqrt{d}\right)$ . This paper presents upper bounds for adversarial Rademacher complexity of DNNs that match the best-known upper bounds in standard settings, as established in the work of Bartlett et al. (2017), with the dependency on width and dimension being $𝒪\left(\text{ln}\right(dm\left)\right)$ . The central challenge addressed is calculating the covering number of adversarial function classes. We aim to construct a new cover that possesses two properties: 1) compatibility with adversarial examples, and 2) precision comparable to covers used in standard settings. To this end, we introduce a new variant of covering number called the uniform covering number, specifically designed and proven to reconcile these two properties. Consequently, our method effectively bridges the gap between Rademacher complexity in robust and standard generalization.

Multiplex immunofluorescence (MxIF) is an advanced molecular imaging technique that can simultaneously provide biologists with multiple (i.e., more than 20) molecular markers on a single histological tissue section. Unfortunately, due to imaging restrictions, the more routinely used hematoxylin and eosin (H&E) stain is typically unavailable with MxIF on the same tissue section. As biological H&E staining is not feasible, previous efforts have been made to obtain H&E whole slide image (WSI) from MxIF via deep learning empowered virtual staining. However, the tiling effect is a long-lasting problem in high-resolution WSI-wise synthesis. The MxIF to H&E synthesis is no exception. Limited by computational resources, the cross-stain image synthesis is typically performed at the patch-level. Thus, discontinuous intensities might be visually identified along with the patch boundaries assembling all individual patches back to a WSI. In this work, we propose a deep learning based unpaired high-resolution image synthesis method to obtain virtual H&E WSIs from MxIF WSIs (each with 27 markers/stains) with reduced tiling effects. Briefly, we first extend the CycleGAN framework by adding simultaneous nuclei and mucin segmentation supervision as spatial constraints. Then, we introduce a random walk sliding window shifting strategy during the optimized inference stage, to alleviate the tiling effects. The validation results show that our spatially constrained synthesis method achieves a 56% performance gain for the downstream cell segmentation task. The proposed inference method reduces the tiling effects by using 50% fewer computation resources without compromising performance. The proposed random sliding window inference method is a plug-and-play module, which can be generalized for other high-resolution WSI image synthesis applications. The source code with our proposed model are available at https://github.com/MASILab/RandomWalkSlidingWindow.git.

Motion artifacts are a pervasive problem in MRI, leading to misdiagnosis or mischaracterization in population-level imaging studies. Current retrospective rigid intra-slice motion correction techniques jointly optimize estimates of the image and the motion parameters. In this paper, we use a deep network to reduce the joint image-motion parameter search to a search over rigid motion parameters alone. Our network produces a reconstruction as a function of two inputs: corrupted k-space data and motion parameters. We train the network using simulated, motion-corrupted k-space data generated with known motion parameters. At test-time, we estimate unknown motion parameters by minimizing a data consistency loss between the motion parameters, the network-based image reconstruction given those parameters, and the acquired measurements. Intra-slice motion correction experiments on simulated and realistic 2D fast spin echo brain MRI achieve high reconstruction fidelity while providing the benefits of explicit data consistency optimization. Our code is publicly available at https://www.github.com/nalinimsingh/neuroMoCo.

Generative artificial intelligence can be applied to medical imaging on tasks such as privacy-preserving image generation and superresolution and denoising of existing images. Few prior approaches have used cardiac magnetic resonance imaging (cMRI) as a modality given the complexity of videos (the addition of the temporal dimension) as well as the limited scale of publicly available datasets. We introduce GANcMRI, a generative adversarial network that can synthesize cMRI videos with physiological guidance based on latent space prompting. GANcMRI uses a StyleGAN framework to learn the latent space from individual video frames and leverages the timedependent trajectory between end-systolic and end-diastolic frames in the latent space to predict progression and generate motion over time. We proposed various methods for modeling latent time-dependent trajectories and found that our Frame-to-frame approach generates the best motion and video quality. GANcMRI generated high-quality cMRI image frames that are indistinguishable by cardiologists, however, artifacts in video generation allow cardiologists to still recognize the difference between real and generated videos. The generated cMRI videos can be prompted to apply physiologybased adjustments which produces clinically relevant phenotypes recognizable by cardiologists. GANcMRI has many potential applications such as data augmentation, education, anomaly detection, and preoperative planning.

Identifying regions of late mechanical activation (LMA) of the left ventricular (LV) myocardium is critical in determining the optimal pacing site for cardiac resynchronization therapy in patients with heart failure. Several deep learning-based approaches have been developed to predict 3D LMA maps of LV myocardium from a stack of sparse 2D cardiac magnetic resonance imaging (MRIs). However, these models often loosely consider the geometric shape structure of the myocardium. This makes the reconstructed activation maps suboptimal; hence leading to a reduced accuracy of predicting the late activating regions of hearts. In this paper, we propose to use shape-constrained diffusion models to better reconstruct a 3D LMA map, given a limited number of 2D cardiac MRI slices. In contrast to previous methods that primarily rely on spatial correlations of image intensities for 3D reconstruction, our model leverages object shape as priors learned from the training data to guide the reconstruction process. To achieve this, we develop a joint learning network that simultaneously learns a mean shape under deformation models. Each reconstructed image is then considered as a deformed variant of the mean shape. To validate the performance of our model, we train and test the proposed framework on a publicly available mesh dataset of 3D myocardium and compare it with state-of-the-art deep learning-based reconstruction models. Experimental results show that our model achieves superior performance in reconstructing the 3D LMA maps as compared to the state-of-the-art models.

Long-form clinical summarization of hospital admissions has real-world significance because of its potential to help both clinicians and patients. The factual consistency of summaries-their faithfulness-is critical to their safe usage in clinical settings. To better understand the limitations of state-of-the-art natural language processing (NLP) systems, as well as the suitability of existing evaluation metrics, we benchmark faithfulness metrics against fine-grained human annotations for model-generated summaries of a patient's Brief Hospital Course. We create a corpus of patient hospital admissions and summaries for a cohort of HIV patients, each with complex medical histories. Annotators are presented with summaries and source notes, and asked to categorize manually highlighted summary elements (clinical entities like conditions and medications as well as actions like "following up") into one of three categories: "Incorrect," "Missing," and "Not in Notes." We meta-evaluate a broad set of faithfulness metrics-proposed for the general NLP domain-by measuring the correlation of metric scores to clinician ratings. Across metrics, we explore the importance of domain adaptation (e.g. the impact of in-domain pre-training and metric fine-tuning), the use of source-summary alignments, and the effects of distilling a single metric from an ensemble. We find that off-the-shelf metrics with no exposure to clinical text correlate well to clinician ratings yet overly rely on copy-and-pasted text. As a practical guide, we observe that most metrics correlate best to clinicians when provided with one summary sentence at a time and a minimal set of supporting sentences from the notes before discharge.

Aortic stenosis (AS) is a degenerative valve condition that causes substantial morbidity and mortality. This condition is under-diagnosed and under-treated. In clinical practice, AS is diagnosed with expert review of transthoracic echocardiography, which produces dozens of ultrasound images of the heart. Only some of these views show the aortic valve. To automate screening for AS, deep networks must learn to mimic a human expert's ability to identify views of the aortic valve then aggregate across these relevant images to produce a study-level diagnosis. We find previous approaches to AS detection yield insufficient accuracy due to relying on inflexible averages across images. We further find that off-the-shelf attention-based multiple instance learning (MIL) performs poorly. We contribute a new end-to-end MIL approach with two key methodological innovations. First, a supervised attention technique guides the learned attention mechanism to favor relevant views. Second, a novel self-supervised pretraining strategy applies contrastive learning on the representation of the whole study instead of individual images as commonly done in prior literature. Experiments on an open-access dataset and a temporally-external heldout set show that our approach yields higher accuracy while reducing model size.