Proceedings of machine learning research最新文献

{"title":"A foundation-model approach to pediatric headache classification from resting-state fMRI.","authors":"Guilherme S Imai Aldeia, Clara Moon, Julie Shulman, Navil Sethna, Allison Smith, Alyssa Lebel, William G La Cava, Scott Holmes","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Headache is the most common neurological disorder in children and substantially affects quality of life. We investigated whether resting-state functional MRI (rs-fMRI) can support pediatric headache classification using machine learning. We encoded rs-fMRI data using NeuroSTORM, a recent foundation model, and fine-tuned it to distinguish healthy controls from children with headache and subsequently classify headache subtypes. We then compared NeuroSTORM with a standard neuroscience approach that uses functional connectivity (FC) matrices derived from brain activity as predictors. Using 189 rs-fMRI scans from 110 individuals collected across two visits (prevalence of any headache: 74%), NeuroSTORM achieved an area under the receiver operating characteristic curve (AUROC) of 0.82 (95% CI, 0.82-0.82) and an area under the precision-recall curve (AUPRC) of 0.93 (95% CI, 0.93-0.94) in discriminating headache from non-headache. In contrast, models trained on FC matrices showed limited performance (AUROC, 0.67 [95% CI, 0.67-0.67]; AUPRC, 0.85 [95% CI, 0.85-0.85]). In a multiclass setting, when tasked with classifying individuals as healthy controls, individuals with chronic migraine, or individuals with non-chronic headaches (e.g., post-viral headache, new daily persistent headache, post-traumatic headache), NeuroSTORM achieved a macro-AUROC of 0.69 (95% CI, 0.68-0.69). The results suggest this approach can distinguish chronic migraine, the most common headache syndrome, but has difficulty differentiating other headache subtypes from chronic migraine. Overall, under limited-data conditions, NeuroSTORM appears to capture latent rs-fMRI representations that transfer to headache-related tasks. The findings provide proof-of-concept for fMRI-based prediction of pediatric headache using a foundation model without relying on functional connectivity features and highlight the potential of this approach for subtype identification. Further development of such tools may help clinicians improve diagnosis based on brain activity and tailor treatment strategies to individual patients.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"340 ","pages":"55-76"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13668307/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149198341","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":"Colormaps Matter: Evaluating Their Impact on CNN-Based Clinical Thermal Imaging.","authors":"Allison Ng, Miriam Asare-Baiden, Sharon Eve Sonenblum, Kathleen Jordan, Judy Wawira Gichoya, Vicki Stover Hertzberg, Joyce C Ho","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Thermal imaging is an increasingly used modality for clinical deep learning, yet a key preprocessing step in convolutional neural network (CNN)-based pipelines has gone largely unexamined. Each thermal image encodes scalar temperature values rendered into RGB via a colormap, determining how temperature information is visually represented. While existing work shows colormap selection influences human interpretation of thermal images, its impact on CNN-based classification remains unstudied. We address this gap through an evaluation of five colormaps across three pretrained CNN architectures and two clinical prediction tasks. Our results show that colormap choice produces consistent differences in predictive performance and substantially shifts the spatial regions CNNs attend to when making predictions. These findings suggest that colormap selection must be treated and reported as a factor shaping model behavior, with direct implications for how CNN-based pipelines are developed, validated, and deployed in clinical thermal imaging.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"340 ","pages":"1403-1431"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13619305/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149076969","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":"An Unsupervised Approach for Artifact Severity Scoring in Multi-Contrast MR Images.","authors":"Savannah P Hays, Lianrui Zuo, Blake E Dewey, Samuel W Remedios, Jinwei Zhang, Ellen M Mowry, Scott D Newsome, Aaron Carass, Jerry L Prince","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Quality assurance (QA) in magnetic resonance (MR) imaging is critical but remains a challenging and time-intensive process, particularly when working with large-scale, multi-site imaging datasets. Manual QA methods are subjective, prone to inter-rater variability, and impractical for high-throughput workflows. Existing automated QA methods often lack generalizability to diverse datasets or fail to provide interpretable insights into the causes of poor image quality. To address these limitations, we introduce an unsupervised and interpretable QA framework for multi-contrast MR images that quantifies artifact severity. By assigning a numerical score to each image, our method enables objective, consistent evaluation of image quality and highlights specific levels of artifact presence that can impair downstream analysis. Our framework employs an unsupervised contrastive learning approach, leveraging simulated artifact transformations, including random bias, noise, anisotropy, and ghosting, to train the model without requiring manual labels or preprocessing. A margin-based contrastive loss further enables differentiation between varying levels of artifact severity. We validate our framework using simulated artifacts on a public dataset and real artifacts on a private clinical dataset, demonstrating its robustness and generalizability for automatic MR image QA. By efficiently evaluating image quality and identifying artifacts prior to data processing, our approach streamlines QA workflows and enhances the reliability of subsequent analyses in both research and clinical settings.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"301 ","pages":"604-614"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13345458/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148414251","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":"Explainable Pathomics Feature Visualization via Correlation-aware Conditional Feature Editing.","authors":"Yuechen Yang, Junlin Guo, Ruining Deng, Junchao Zhu, Zhengyi Lu, Chongyu Qu, Yanfan Zhu, Xingyi Guo, Yu Wang, Shilin Zhao, Haichun Yang, Yuankai Huo","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Pathomics is a recent approach that offers rich quantitative features beyond what black-box deep learning can provide, supporting more reproducible and explainable biomarkers in digital pathology. However, many derived features (e.g., \"second-order moment\") remain difficult to interpret, especially across different clinical contexts, which limits their practical adoption. Conditional diffusion models show promise for explainability through feature editing, but they typically assume feature independence, an assumption violated by intrinsically correlated pathomics features. Consequently, editing one feature while fixing others can push the model off the biological manifold and produce unrealistic artifacts. To address this, we propose a Manifold-Aware Diffusion (MAD) framework for controllable and biologically plausible cell nuclei editing. Unlike existing approaches, our method regularizes feature trajectories within a disentangled latent space learned by a variational auto-encoder (VAE). This ensures that manipulating a target feature automatically adjusts correlated attributes to remain within the learned distribution of real cells. These optimized features then guide a conditional diffusion model to synthesize high-fidelity images. Experiments demonstrate that our approach is able to navigate the manifold of pathomics features when editing those features. The proposed method outperforms baseline methods in conditional feature editing while preserving structural coherence.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"315 ","pages":"2563-2581"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13590203/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149013276","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":"Co-distilled attention guided masked image modeling with noisy teacher for self-supervised learning on medical images.","authors":"Jue Jiang, Aneesh Rangnekar, Harini Veeraraghavan","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Masked image modeling (MIM) is a highly effective self-supervised learning (SSL) approach to extract useful feature representations from unannotated data. Predominantly used random masking methods make SSL less effective for medical images due to the contextual similarity of neighboring patches, leading to information leakage and SSL simplification. Hierarchical shifted window (Swin) transformer, a highly effective approach for medical images cannot use advanced masking methods as it lacks a global [CLS] token. Hence, we introduced an attention guided masking mechanism for Swin within a co-distillation learning framework to selectively mask semantically co-occurring and discriminative patches, to reduce information leakage and increase the difficulty of SSL pretraining. However, attention guided masking inevitably reduces the diversity of attention heads, which negatively impacts downstream task performance. To address this, we for the first time, integrate a noisy teacher into the co-distillation framework (termed DAGMaN) that performs attentive masking while preserving high attention head diversity. We demonstrate the capability of DAGMaN on multiple tasks including full- and few-shot lung nodule classification, immunotherapy outcome prediction, tumor segmentation, and unsupervised organs clustering.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"301 ","pages":"679-694"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193228/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148019190","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":"Active Measuring in Reinforcement Learning With Delayed Negative Effects.","authors":"Daiqi Gao, Ziping Xu, Aseel Rawashdeh, Predrag Klasnja, Susan A Murphy","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Measuring states in reinforcement learning (RL) can be costly in real-world settings and may negatively influence future outcomes. We introduce the Actively Observable Markov Decision Process (AOMDP), where an agent not only selects control actions but also decides whether to measure the latent state. The measurement action reveals the true latent state but may have a negative delayed effect on the environment. We show that this reduced uncertainty enables sample-efficient learning and may increase the value of the optimal policy despite these costs. We formulate an AOMDP as a periodic partially observable MDP and propose an online RL algorithm based on belief states. To approximate the belief states, we further propose a sequential Monte Carlo method to jointly approximate the posterior of unknown static environment parameters and unobserved latent states. We evaluate the proposed algorithm in a digital health application, where the agent decides when to deliver digital interventions and when to assess users' psychological status through surveys.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"300 ","pages":"3907-3915"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13597144/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149026985","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":"Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models.","authors":"Mathis Pink, Vy Ai Vo, Qinyuan Wu, Jianing Mu, Javier Turek, Uri Hasson, Kenneth A Norman, Sebastian Michelmann, Alexander Huth, Mariya Toneva","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Human episodic memory supports the retrieval of experiences that unfold over extended timescales, yet the computational mechanisms underlying this ability remain debated due to the limited mechanistic accessibility in long-term memory experiments in humans. Long-context LLMs may offer promising ways to reveal plausible computational mechanisms that drive this type of retrieval. Here, we investigate whether and how LLMs capture the core behavioral signatures of episodic memory via a temporal order memory task. Using a new dataset of human behavior based on memory of a full-length novel, we show that models exhibit the same characteristic distance effect observed in humans on this task. We next apply long-context mechanistic interpretability analyses to uncover how models solve this task, and find that model performance relies on a one-dimensional temporal code that is reinstated during retrieval by a single time-reinstatement attention head. These findings support temporal context reinstatement as an important mechanism for episodic-like temporal-order memory in LLMs, offering new insights into how temporal aspects of long-term episodic memory may be instantiated in both artificial and biological systems.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"306 ","pages":"98845-98862"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13626393/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119397","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":"Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox.","authors":"Jiacheng Pang, Ashutosh Chaubey, Mohammad Soleymani","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Audio large language models (Audio LLMs) demonstrate strong performance on speech understanding tasks, yet their ability to understand paralinguistic information remains limited. To systematically quantify this issue, we introduce <b>VoxParadox</b>, an adversarial benchmark with 2,000 verified examples, spanning 10 paralinguistic tasks, created with controlled speech synthesis to intentionally mismatch transcript claims and speaking style, enabling direct measurement of speech paralinguistic understanding. Evaluation of a diverse set of Audio LLMs reveals consistently low accuracy on acoustic ground truth and a strong tendency to follow language-implied (incorrect) answers. To understand the cause of this gap, we perform layer-wise probing and find that (i) paralinguistic cues can degrade in deeper encoder layers and at the encoder-LLM interface, and (ii) even when such cues are available in audio tokens, the language model frequently ignores them. To address these problems, we propose <b>Prompt-Conditioned Layer Mixer (PCLM)</b>, which adaptively combines information from multiple audio layers based on the input prompt, and pair it with <b>Direct Preference Optimization (DPO)</b> to explicitly prefer acoustically supported options over language-implied alternatives. These methods substantially improve Audio LLM paralinguistic understanding, improving Audio Flamingo 3 from <b>17.40%</b> to <b>65.20%</b> on VoxParadox, and from <b>37.74%</b> to <b>54.78%</b> on MMSU paralinguistic subset. Our project page is available at https://voxparadox.github.io/.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"306 ","pages":"96307-96334"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13626453/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119984","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":"STNAGNN: Data-driven Spatio-temporal Brain Connectivity beyond FC.","authors":"Jiyao Wang, Nicha C Dvornek, Peiyu Duan, Lawrence H Staib, Pamela Ventola, James S Duncan","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>In recent years, graph neural networks (GNNs) have been widely applied in the analysis of brain fMRI, yet defining the connectivity between ROIs remains a challenge in noisy fMRI data. Among all approaches, Functional Connectome (FC) is the most popular method. Computed by the correlation coefficients between ROI time series, FC is a powerful and computationally efficient way to estimate ROI connectivity. However, it is well known for neglecting structural connections and causality in ROI interactions. Also, FC becomes much more noisy in the short spatio-temporal sliding-window subsequences of fMRI. Effective Connectome (EC) is proposed as a directional alternative, but is difficult to accurately estimate. Furthermore, for optimal GNN performance, usually only a small percentage of the strongest connections are selected as sparse edges, resulting in oversimplification of complex brain connections. To tackle these challenges, we propose the Spatio-Temporal Node Attention Graph Neural Network (STNAGNN) as a data-driven alternative that combines sparse predefined FC with dense data-driven spatio-temporal connections, allowing for flexible and spatio-temporal learning of ROI interaction patterns. Our implementation is publicly available at https://github.com/Jiyao96/STNAGNN-fMRI/.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"301 ","pages":"1688-1705"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13218448/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148140033","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":"Perspective: Machine Learning for Health Should Consider Social Drivers of Health.","authors":"Neha Srivathsa, Sherri Rose","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Clinical machine learning (ML) algorithms can exacerbate a wide range of injustices across multiple domains and levels of society. These harms are often underemphasized and differentially distributed, with minoritized communities disproportionately experiencing the harms and not the benefits of health ML algorithms. By proposing a correspondence between prominent algorithmic harm and social drivers of health (SDOH) frameworks, we show that a range of algorithmic harms ultimately impact human health through SDOH factors, especially structural factors. This presents an inherent tension in the development of ML for health, where the harms of algorithms may lead to the worsening of health inequities. We recommend the consideration of SDOH throughout the pipeline of ML system development for examining algorithmic harms to health. Effectively considering SDOH necessitates developing competencies in structural analysis and community-engaged approaches. Accounting for SDOH could illuminate pathways toward equity-promoting algorithms, although we highlight that, in many cases, an equity-promoting algorithm may not exist. Thus, we also emphasize the need for interventions on the root causes of health inequities.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"297 ","pages":"1637-1644"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13268202/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148267412","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}