Quantitative Methods
See recent articles
Showing new listings for Tuesday, 26 November 2024
- [1] arXiv:2411.15709 [pdf, other]
-
Title: Optimization of Bloch-Siegert B1 Mapping Sequence for Maximum Signal to NoiseSubjects: Quantitative Methods (q-bio.QM)
Adiabatic Bloch-Siegert B1+ mapping method addresses the long TE and high RF power deposition problems of conventional Bloch-Siegert B1+ mapping by introducing short frequency-swept ABS pulses with maximum sensitivity. Here, it is shown how maximum signal to noise ratio can be achieved in adiabatic Bloch-Siegert B1+ mapping. Signal to noise ratio of B1+ maps is maximized by optimizing the adiabatic pulse parameters such as width, amplitude and shape of the Bloch-Siegert pulse within a specified scan time and under approved SAR guidelines. Equations for optimized Bloch-Siegert pulse parameters are derived, which are dependent on the base pulse sequence used for B1+ mapping as well as tissue properties and transmit coil configuration. It is shown that by this optimization it is more efficient to increase TR rather than using the averaging method to increase signal to noise ratio.
New submissions (showing 1 of 1 entries)
- [2] arXiv:2411.15180 (cross-list from cs.LG) [pdf, html, other]
-
Title: Multi-layer matrix factorization for cancer subtyping using full and partial multi-omics datasetSubjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM)
Cancer, with its inherent heterogeneity, is commonly categorized into distinct subtypes based on unique traits, cellular origins, and molecular markers specific to each type. However, current studies primarily rely on complete multi-omics datasets for predicting cancer subtypes, often overlooking predictive performance in cases where some omics data may be missing and neglecting implicit relationships across multiple layers of omics data integration. This paper introduces Multi-Layer Matrix Factorization (MLMF), a novel approach for cancer subtyping that employs multi-omics data clustering. MLMF initially processes multi-omics feature matrices by performing multi-layer linear or nonlinear factorization, decomposing the original data into latent feature representations unique to each omics type. These latent representations are subsequently fused into a consensus form, on which spectral clustering is performed to determine subtypes. Additionally, MLMF incorporates a class indicator matrix to handle missing omics data, creating a unified framework that can manage both complete and incomplete multi-omics data. Extensive experiments conducted on 10 multi-omics cancer datasets, both complete and with missing values, demonstrate that MLMF achieves results that are comparable to or surpass the performance of several state-of-the-art approaches.
- [3] arXiv:2411.15240 (cross-list from cs.LG) [pdf, other]
-
Title: Is Attention All You Need For Actigraphy? Foundation Models of Wearable Accelerometer Data for Mental Health ResearchComments: Supplementary material can be found at the end of the documentSubjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Quantitative Methods (q-bio.QM)
Wearable accelerometry (actigraphy) has provided valuable data for clinical insights since the 1970s and is increasingly important as wearable devices continue to become widespread. The effectiveness of actigraphy in research and clinical contexts is heavily dependent on the modeling architecture utilized. To address this, we developed the Pretrained Actigraphy Transformer (PAT)--the first pretrained and fully attention-based model designed specifically to handle actigraphy. PAT was pretrained on actigraphy from 29,307 participants in NHANES, enabling it to deliver state-of-the-art performance when fine-tuned across various actigraphy prediction tasks in the mental health domain, even in data-limited scenarios. For example, when trained to predict benzodiazepine usage using actigraphy from only 500 labeled participants, PAT achieved an 8.8 percentage-point AUC improvement over the best baseline. With fewer than 2 million parameters and built-in model explainability, PAT is robust yet easy to deploy in health research settings.
GitHub: this https URL - [4] arXiv:2411.15331 (cross-list from cs.LG) [pdf, html, other]
-
Title: GeoScatt-GNN: A Geometric Scattering Transform-Based Graph Neural Network Model for Ames Mutagenicity PredictionSubjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV); Quantitative Methods (q-bio.QM)
This paper tackles the pressing challenge of mutagenicity prediction by introducing three ground-breaking approaches. First, it showcases the superior performance of 2D scattering coefficients extracted from molecular images, compared to traditional molecular descriptors. Second, it presents a hybrid approach that combines geometric graph scattering (GGS), Graph Isomorphism Networks (GIN), and machine learning models, achieving strong results in mutagenicity prediction. Third, it introduces a novel graph neural network architecture, MOLG3-SAGE, which integrates GGS node features into a fully connected graph structure, delivering outstanding predictive accuracy. Experimental results on the ZINC dataset demonstrate significant improvements, emphasizing the effectiveness of blending 2D and geometric scattering techniques with graph neural networks. This study illustrates the potential of GNNs and GGS for mutagenicity prediction, with broad implications for drug discovery and chemical safety assessment.
- [5] arXiv:2411.15398 (cross-list from stat.ME) [pdf, html, other]
-
Title: The ultimate issue error: mistaking parameters for hypothesesSubjects: Methodology (stat.ME); Quantitative Methods (q-bio.QM); Applications (stat.AP)
In a criminal investigation, an inferential error occurs when the probability that a suspect is the source of some evidence -- such as a fingerprint -- is taken as the probability of guilt. This is known as the ultimate issue error, and the same error occurs in statistical inference when the probability that a parameter equals some value is incorrectly taken to be the probability of a hypothesis. Almost all statistical inference in the social and biological sciences is subject to this error, and replacing every instance of "hypothesis testing" with "parameter testing" in these fields would more accurately describe the target of inference. The relationship between parameter values and quantities derived from them, such as p-values or Bayes factors, have no direct quantitative relationship with scientific hypotheses. Here, we describe the problem, its consequences, and suggest options for improving scientific inference.
- [6] arXiv:2411.16349 (cross-list from cs.LG) [pdf, html, other]
-
Title: Machine learning for cerebral blood vessels' malformationsIrem Topal, Alexander Cherevko, Yuri Bugay, Maxim Shishlenin, Jean Barbier, Deniz Eroglu, Édgar Roldán, Roman BelousovComments: 14 pages, 6 main figures, 5 supplementary figures, 2 supplementary tablesSubjects: Machine Learning (cs.LG); Statistical Mechanics (cond-mat.stat-mech); Quantitative Methods (q-bio.QM)
Cerebral aneurysms and arteriovenous malformations are life-threatening hemodynamic pathologies of the brain. While surgical intervention is often essential to prevent fatal outcomes, it carries significant risks both during the procedure and in the postoperative period, making the management of these conditions highly challenging. Parameters of cerebral blood flow, routinely monitored during medical interventions, could potentially be utilized in machine learning-assisted protocols for risk assessment and therapeutic prognosis. To this end, we developed a linear oscillatory model of blood velocity and pressure for clinical data acquired from neurosurgical operations. Using the method of Sparse Identification of Nonlinear Dynamics (SINDy), the parameters of our model can be reconstructed online within milliseconds from a short time series of the hemodynamic variables. The identified parameter values enable automated classification of the blood-flow pathologies by means of logistic regression, achieving an accuracy of 73 %. Our results demonstrate the potential of this model for both diagnostic and prognostic applications, providing a robust and interpretable framework for assessing cerebral blood vessel conditions.
Cross submissions (showing 5 of 5 entries)
- [7] arXiv:1904.05675 (replaced) [pdf, html, other]
-
Title: Beyond the Nucleus: Cytoplasmic Dominance in Follicular Thyroid Carcinoma Detection Using Single-Cell Raman Imaging Across Multiple DevicesAurelien Pelissier, Kosuke Hashimoto, Kentaro Mochizuki, J. Nicholas Taylor, Jean-Emmanuel Clement, Yasuaki Kumamoto, Katsumasa Fujita, Yoshinori Harada, Tamiki KomatsuzakiSubjects: Quantitative Methods (q-bio.QM); Cell Behavior (q-bio.CB)
Cytological diagnosis of follicular thyroid carcinoma (FTC) is one of major challenges in the field of endocrine oncology due to absence of evident morphological indicators. Morphological abnormalities in the nucleus are typically key indicators in cancer cytopathology and are attributed to a range of biochemical alterations in nuclear components. Consequently, Raman spectroscopy has been widely used to detect cancer in various cytological samples, often identifying biochemical changes prior to observable morphological alterations. However, in the case of FTC, cytoplasmic features such as carotenoids, cytochromes, and lipid droplets have shown greater diagnostic relevance compared to nuclear features. This study leverages single-cell Raman imaging to explore the spatial origin of diagnostic signals in FTC and normal thyroid (NT) cells, assessing the contributions of the nucleus and cytoplasm independently. Our results demonstrate that Raman spectra from the cytoplasmic region can distinguish between FTC and NT cells with an accuracy of 84% under co-culture conditions, maintaining robustness across multiple devices. In contrast, classification based on nuclear spectra achieved only 53% accuracy, suggesting that biochemical alterations in the cytoplasm play a more significant role in FTC detection than those in the nucleus. Our work elevates the promise of Raman-based cytopathology by providing complementary organelle-dependent information to traditional diagnostic methods and demonstrating transferability across different devices.
- [8] arXiv:2403.08685 (replaced) [pdf, html, other]
-
Title: Elastic shape analysis for unsupervised clustering of left atrial appendage morphologySubjects: Quantitative Methods (q-bio.QM)
Morphological variations in the left atrial appendage (LAA) are associated with different levels of ischemic stroke risk for patients with atrial fibrillation (AF). Studying LAA morphology can elucidate mechanisms behind this association and lead to the development of advanced stroke risk stratification tools. However, current categorical descriptions of LAA morphologies are qualitative and inconsistent across studies, which impedes advancements in our understanding of stroke pathogenesis in AF. To mitigate these issues, we introduce a quantitative pipeline that combines elastic shape analysis with unsupervised learning for the categorization of LAA morphology in AF patients. As part of our pipeline, we compute pairwise elastic distances between LAA meshes from a cohort of 20 AF patients, and leverage these distances to cluster our shape data. We demonstrate that our method clusters LAA morphologies based on distinctive shape features, overcoming the innate inconsistencies of current LAA categorization systems, and paving the way for improved stroke risk metrics using objective LAA shape groups.
- [9] arXiv:2410.12830 (replaced) [pdf, html, other]
-
Title: Incorporating Metabolic Information into LLMs for Anomaly Detection in Clinical Time-SeriesJournal-ref: NeurIPS 2024 Workshop on Time Series in the Age of Large ModelsSubjects: Quantitative Methods (q-bio.QM); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Anomaly detection in clinical time-series holds significant potential in identifying suspicious patterns in different biological parameters. In this paper, we propose a targeted method that incorporates the clinical domain knowledge into LLMs to improve their ability to detect anomalies. We introduce the Metabolism Pathway-driven Prompting (MPP) method, which integrates the information about metabolic pathways to better capture the structural and temporal changes in biological samples. We applied our method for doping detection in sports, focusing on steroid metabolism, and evaluated using real-world data from athletes. The results show that our method improves anomaly detection performance by leveraging metabolic context, providing a more nuanced and accurate prediction of suspicious samples in athletes' profiles.
- [10] arXiv:2411.13263 (replaced) [pdf, html, other]
-
Title: Estimating the tails of the spectrum of the Hessian of the log-likelihood for \textit{ab-initio} single-particle reconstruction in electron cryomicroscopySubjects: Quantitative Methods (q-bio.QM)
Electron cryomicroscopy (cryo-EM) is a technique in structural biology used to reconstruct accurate volumetric maps of molecules. One step of the cryo-EM pipeline involves solving an inverse-problem. This inverse-problem, referred to as \textit{ab-initio} single-particle reconstruction, takes as input a collection of 2d-images -- each a projection of a molecule from an unknown viewing-angle -- and attempts to reconstruct the 3d-volume representing the underlying molecular density.
Most methods for solving this inverse-problem search for a solution which optimizes a posterior likelihood of generating the observed image-data, given the reconstructed volume. Within this framework, it is natural to study the Hessian of the log-likelihood: the eigenvectors and eigenvalues of the Hessian determine how the likelihood changes with respect to perturbations in the solution, and can give insight into the sensitivity of the solution to aspects of the input.
In this paper we describe a simple strategy for estimating the smallest eigenvalues and eigenvectors (i.e., the `softest modes') of the Hessian of the log-likelihood for the \textit{ab-initio} single-particle reconstruction problem. This strategy involves rewriting the log-likelihood as a 3d-integral. This interpretation holds in the low-noise limit, as well as in many practical scenarios which allow for noise-marginalization.
Once we have estimated the softest modes, we can use them to perform many kinds of sensitivity analysis. For example, we can determine which parts of the reconstructed volume are trustworthy, and which are unreliable, and how this unreliability might depend on the data-set and the imaging parameters. We believe that this kind of analysis can be used alongside more traditional strategies for sensitivity analysis, as well as in other applications, such as free-energy estimation. - [11] arXiv:2405.10488 (replaced) [pdf, other]
-
Title: Comparative prospects of imaging methods for whole-brain mammalian connectomicsComments: See page 16 after references for Supplemental InformationSubjects: Neurons and Cognition (q-bio.NC); Quantitative Methods (q-bio.QM)
Mammalian whole-brain connectomes at nanoscale synaptic resolution are a crucial ingredient for holistic understanding of brain function. Imaging these connectomes at sufficient resolution to densely reconstruct cellular morphology and synapses represents a longstanding goal in neuroscience. Although the technologies needed to reconstruct whole-brain connectomes have not yet reached full maturity, they are advancing rapidly enough that the mouse brain might be within reach in the near future. Detailed exploration of these technologies is warranted to help plan projects with varying goals and requirements. Whole-brain human connectomes remain a more distant goal yet are worthy of consideration to orient large-scale neuroscience program plans. Here, we quantitatively compare existing and emerging imaging technologies that have potential to enable whole-brain mammalian connectomics. We perform calculations on electron microscopy (EM) techniques and expansion microscopy coupled with light-sheet fluorescence microscopy (ExLSFM) methods. We consider techniques from the literature that have sufficiently high resolution to identify all synapses and sufficiently high speed to be relevant for whole mammalian brains. Each imaging modality comes with benefits and drawbacks, so we suggest that attacking the problem through multiple approaches could yield the best outcomes. We offer this analysis as a resource for those considering how to organize efforts towards imaging whole-brain mammalian connectomes.
- [12] arXiv:2409.16531 (replaced) [pdf, html, other]
-
Title: Estimation of end-of-outbreak probabilities in the presence of delayed and incomplete case reportingSubjects: Populations and Evolution (q-bio.PE); Quantitative Methods (q-bio.QM)
Towards the end of an infectious disease outbreak, when a period has elapsed without new case notifications, a key question for public health policy makers is whether the outbreak can be declared over. This requires the benefits of a declaration (e.g., relaxation of outbreak control measures) to be balanced against the risk of a resurgence in cases. To support this decision making, mathematical methods have been developed to quantify the end-of-outbreak probability. Here, we propose a new approach to this problem that accounts for a range of features of real-world outbreaks, specifically: (i) incomplete case ascertainment; (ii) reporting delays; (iii) individual heterogeneity in transmissibility; and (iv) whether cases were imported or infected locally. We showcase our approach using two case studies: Covid-19 in New Zealand in 2020, and Ebola virus disease in the Democratic Republic of the Congo in 2018. In these examples, we found that the date when the estimated probability of no future infections reached 95% was relatively consistent across a range of modelling assumptions. This suggests that our modelling framework can generate robust quantitative estimates that can be used by policy advisors, alongside other sources of evidence, to inform end-of-outbreak declarations.
- [13] arXiv:2410.00509 (replaced) [pdf, html, other]
-
Title: Learning Personalized Treatment Decisions in Precision Medicine: Disentangling Treatment Assignment Bias in Counterfactual Outcome Prediction and Biomarker IdentificationMichael Vollenweider, Manuel Schürch, Chiara Rohrer, Gabriele Gut, Michael Krauthammer, Andreas WickiComments: 9 pages, 5 figures, ML4H conference 2024Subjects: Machine Learning (cs.LG); Information Theory (cs.IT); Quantitative Methods (q-bio.QM)
Precision medicine has the potential to tailor treatment decisions to individual patients using machine learning (ML) and artificial intelligence (AI), but it faces significant challenges due to complex biases in clinical observational data and the high-dimensional nature of biological data. This study models various types of treatment assignment biases using mutual information and investigates their impact on ML models for counterfactual prediction and biomarker identification. Unlike traditional counterfactual benchmarks that rely on fixed treatment policies, our work focuses on modeling different characteristics of the underlying observational treatment policy in distinct clinical settings. We validate our approach through experiments on toy datasets, semi-synthetic tumor cancer genome atlas (TCGA) data, and real-world biological outcomes from drug and CRISPR screens. By incorporating empirical biological mechanisms, we create a more realistic benchmark that reflects the complexities of real-world data. Our analysis reveals that different biases lead to varying model performances, with some biases, especially those unrelated to outcome mechanisms, having minimal effect on prediction accuracy. This highlights the crucial need to account for specific biases in clinical observational data in counterfactual ML model development, ultimately enhancing the personalization of treatment decisions in precision medicine.