Proceedings of machine learning research最新文献

{"title":"Simple and Scalable Algorithms for Cluster-Aware Precision Medicine.","authors":"Amanda M Buch, Conor Liston, Logan Grosenick","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>AI-enabled precision medicine promises a transformational improvement in healthcare outcomes. However, training on biomedical data presents significant challenges as they are often high dimensional, clustered, and of limited sample size. To overcome these challenges, we propose a simple and scalable approach for cluster-aware embedding that combines latent factor methods with a convex clustering penalty in a modular way. Our novel approach overcomes the complexity and limitations of current joint embedding and clustering methods and enables hierarchically clustered principal component analysis (PCA), locally linear embedding (LLE), and canonical correlation analysis (CCA). Through numerical experiments and real-world examples, we demonstrate that our approach outperforms fourteen clustering methods on highly underdetermined problems (e.g., with limited sample size) as well as on large sample datasets. Importantly, our approach does not require the user to choose the desired number of clusters, yields improved model selection if they do, and yields interpretable hierarchically clustered embedding dendrograms. Thus, our approach improves significantly on existing methods for identifying patient subgroups in multiomics and neuroimaging data and enables scalable and interpretable biomarkers for precision medicine.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"238 ","pages":"136-144"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11251711/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141629518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data.","authors":"Taehyo Kim, Hai Shu, Qiran Jia, Mony J de Leon","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"238 ","pages":"946-954"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11090200/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140917629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contextual Bandits with Budgeted Information Reveal.","authors":"Kyra Gan, Esmaeil Keyvanshokooh, Xueqing Liu, Susan Murphy","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>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 <i>pro-treatment</i> 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.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"238 ","pages":"3970-3978"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11503011/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"E(3) × SO(3)-Equivariant Networks for Spherical Deconvolution in Diffusion MRI.","authors":"Axel Elaldi, Guido Gerig, Neel Dey","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>We present Roto-Translation Equivariant Spherical Deconvolution (RT-ESD), an <math><mi>E</mi><mo>(</mo><mn>3</mn><mo>)</mo><mo>×</mo><mi>S</mi><mi>O</mi><mo>(</mo><mn>3</mn><mo>)</mo></math> 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 <i>in vivo</i> 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.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"227 ","pages":"301-319"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10901527/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139991995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization.","authors":"Jiancong Xiao, Ruoyu Sun, Qi Long, Weijie J Su","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>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 <math><mi>m</mi></math> of the DNNs or the dimension <math><mi>d</mi></math> of the data, with an extra factor of at least <math><mi>𝒪</mi> <mo>(</mo> <msqrt><mi>m</mi></msqrt> <mo>)</mo></math> or <math><mi>𝒪</mi> <mo>(</mo> <msqrt><mi>d</mi></msqrt> <mo>)</mo></math> . 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 <math><mi>𝒪</mi> <mo>(</mo> <mtext>ln</mtext> <mspace></mspace> <mo>(</mo> <mi>d</mi> <mi>m</mi> <mo>)</mo> <mo>)</mo></math> . 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 <i>uniform covering number</i>, specifically designed and proven to reconcile these two properties. Consequently, our method effectively bridges the gap between Rademacher complexity in robust and standard generalization.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"247 ","pages":"5074-5075"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11350389/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142115745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Alleviating tiling effect by random walk sliding window in high-resolution histological whole slide image synthesis.","authors":"Shunxing Bao, Ho Hin Lee, Qi Yang, Lucas W Remedios, Ruining Deng, Can Cui, Leon Y Cai, Kaiwen Xu, Xin Yu, Sophie Chiron, Yike Li, Nathan Heath Patterson, Yaohong Wang, Jia Li, Qi Liu, Ken S Lau, Joseph T Roland, Lori A Coburn, Keith T Wilson, Bennett A Landman, Yuankai Huo","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"227 ","pages":"1406-1422"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11238901/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141592304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data Consistent Deep Rigid MRI Motion Correction.","authors":"Nalini M Singh, Neel Dey, Malte Hoffmann, Bruce Fischl, Elfar Adalsteinsson, Robert Frost, Adrian V Dalca, Polina Golland","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"227 ","pages":"368-381"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11482239/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142482672","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MULTIPAR: Supervised Irregular Tensor Factorization with Multi-task Learning for Computational Phenotyping.","authors":"Yifei Ren, Jian Lou, Li Xiong, Joyce C Ho, Xiaoqian Jiang, Sivasubramanium Venkatraman Bhavani","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Tensor factorization has received increasing interest due to its intrinsic ability to capture latent factors in multi-dimensional data with many applications including Electronic Health Records (EHR) mining. PARAFAC2 and its variants have been proposed to address irregular tensors where one of the tensor modes is not aligned, e.g., different patients in EHRs may have different length of records. PARAFAC2 has been successfully applied to EHRs for extracting meaningful medical concepts (phenotypes). Despite recent advancements, current models' predictability and interpretability are not satisfactory, which limits its utility for downstream analysis. In this paper, we propose MULTIPAR: a supervised irregular tensor factorization with multi-task learning for computational phenotyping. MULTIPAR is flexible to incorporate both static (e.g. in-hospital mortality prediction) and continuous or dynamic (e.g. the need for ventilation) tasks. By supervising the tensor factorization with downstream prediction tasks and leveraging information from multiple related predictive tasks, MULTIPAR can yield not only more meaningful phenotypes but also better predictive performance for downstream tasks. We conduct extensive experiments on two real-world temporal EHR datasets to demonstrate that MULTIPAR is scalable and achieves better tensor fit with more meaningful subgroups and stronger predictive performance compared to existing state-of-the-art methods. The implementation of MULTIPAR is available.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"225 ","pages":"498-511"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11611252/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142775499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Probabilistic Method to Predict Classifier Accuracy on Larger Datasets given Small Pilot Data.","authors":"Ethan Harvey, Wansu Chen, David M Kent, Michael C Hughes","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Practitioners building classifiers often start with a smaller pilot dataset and plan to grow to larger data in the near future. Such projects need a toolkit for extrapolating how much classifier accuracy may improve from a 2x, 10x, or 50x increase in data size. While existing work has focused on finding a single \"best-fit\" curve using various functional forms like power laws, we argue that modeling and assessing the <i>uncertainty</i> of predictions is critical yet has seen less attention. In this paper, we propose a Gaussian process model to obtain probabilistic extrapolations of accuracy or similar performance metrics as dataset size increases. We evaluate our approach in terms of error, likelihood, and coverage across six datasets. Though we focus on medical tasks and image modalities, our open source approach generalizes to any kind of classifier.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"225 ","pages":"129-144"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11826957/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143434464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GANcMRI: Cardiac magnetic resonance video generation and physiologic guidance using latent space prompting.","authors":"Milos Vukadinovic, Alan C Kwan, Debiao Li, David Ouyang","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"225 ","pages":"594-606"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10783442/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139426220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}