检索结果-内蒙古大学图书馆

Development of Deep learning Model for Detection of Abdominal Diseases using Radiological Images

学校读者我要写书评

暂无评论

Development of Deep Learning Model for Detection of Abdomina...

Artificial Intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Vidhi Wankhade Soyal Nimbalkar Kajal Dakhare Rohan Jangamwar Meher Langote Prateek Verma Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra India Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra India

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

As the abdominal and chest injuries are high morbidity and mortality around the globe, these pose an acute challenge in emergency care. Current data from recently released sources indicate that more than half of the patients visiting ER and also being admitted into hospital account for trauma; and the burden of both abdominal and chest injuries is quite high. Imaging plays an important role in diagnosis and treatment planning in the management of abdominal and chest injuries. The most widely practiced modality is radiograph imaging simply because it produces quality and easy results. Improving Automated pathology object detection of things in radiographs with deep learning algorithms promises much for the precision of diagnosis and optimization in health care. This paper discusses and provides a very detailed review of optimized CNNs, primarily ResNet18, ResNet34, along with a custom-built neural network for the identification of disease from X-ray pictures. Such models are trained and validated to reach excellent sensitivity and specificity on a wide variety of diseases by using the annotated RSNA 2023 dataset by professionals in radiology. It extended the scope of earlier research in this field by looking at other imaging conditions and diseases as well. This puts its contribution into the larger, ongoing discussion of AI in radiology. The results of this study help to contribute to the thesis that the promise of deep learning in radiological diagnosis is substantial, and it could be used to better enhance patient outcomes in the practice of emergency radiology.

关键词： Deep learning Pathology Ethics Neural networks Imaging Radiology Artificial intelligence Injuries X-ray imaging Diseases

Reliability and predictability of phenotype information from functional connectivity in large imaging datasets

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dafflon, Jessica Moraczewski, Dustin Earl, Eric Nielson, Dylan M. Loewinger, Gabriel McClure, Patrick Thomas, Adam G. Pereira, Francisco Data Science & Sharing Team National Institute of Mental Health BethesdaMD United States Machine Learning Team National Institute of Mental Health BethesdaMD United States Naval Postgraduate School MontereyCA United States

One of the central objectives of contemporary neuroimaging research is to create predictive models that can disentangle the connection between patterns of functional connectivity across the entire brain and various behavioral traits. Previous studies have shown that models trained to predict behavioral features from the individual’s functional connectivity have modest to poor performance. In this study, we trained models that predict observable individual traits (phenotypes) and their corresponding singular value decomposition (SVD) representations – herein referred to as latent phenotypes from resting state functional connectivity. For this task, we predicted phenotypes in two large neuroimaging datasets: the Human Connectome Project (HCP) and the Philadelphia Neurodevelopmental Cohort (PNC). We illustrate the importance of regressing out confounds, which could significantly influence phenotype prediction. Our findings reveal that both phenotypes and their corresponding latent phenotypes yield similar predictive performance. Interestingly, only the first five latent phenotypes were reliably identified, and using just these reliable phenotypes for predicting phenotypes yielded a similar performance to using all latent phenotypes. This suggests that the predictable information is present in the first latent phenotypes, allowing the remainder to be filtered out without any harm in performance. This study sheds light on the intricate relationship between functional connectivity and the predictability and reliability of phenotypic information, with potential implications for enhancing predictive modeling in the realm of neuroimaging research. © 2024, CC0.

关键词： Neuroimaging

Approximating Positive Homogeneous Functions with Scale Invariant Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bamberger, Stefan Heckel, Reinhard Krahmer, Felix Department of Mathematics Technical University of Munich Holsten Systems GmbH Germany Department of Computer Engineering Technical University of Munich Munich Center for Machine Learning Germany Department of Mathematics Munich Data Science Institute Technical University of Munich Munich Center for Machine Learning Germany

We investigate to what extent it is possible to solve linear inverse problems with ReLu networks. Due to the scaling invariance arising from the linearity, an optimal reconstruction function f for such a problem is positive homogeneous, i.e., satisfies f(λx) = λf(x) for all non-negative λ. In a ReLu network, this condition translates to considering networks without bias terms. We first consider recovery of sparse vectors from few linear measurements. We prove that ReLu- networks with only one hidden layer cannot even recover 1-sparse vectors, not even approximately, and regardless of the width of the network. However, with two hidden layers, approximate recovery with arbitrary precision and arbitrary sparsity level s is possible in a stable way. We then extend our results to a wider class of recovery problems including low-rank matrix recovery and phase retrieval. Furthermore, we also consider the approximation of general positive homogeneous functions with neural networks. Extending previous work, we establish new results explaining under which conditions such functions can be approximated with neural networks. Our results also shed some light on the seeming contradiction between previous works showing that neural networks for inverse problems typically have very large Lipschitz constants, but still perform very well also for adversarial noise. Namely, the error bounds in our expressivity results include a combination of a small constant term and a term that is linear in the noise level, indicating that robustness issues may occur only for very small noise *** Codes 41A30, 68T07 Copyright © 2023, The Authors. All rights reserved.

关键词： Recovery

Uni-Mol2: Exploring Molecular Pretraining Model at Scale

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ji, Xiaohong Wang, Zhen Gao, Zhifeng Zheng, Hang Zhang, Linfeng Ke, Guolin Weinan, E. DP Technology Beijing100080 China AI for Science Institute Beijing100080 China School of Mathematical Sciences Peking University Beijing100871 China Center for Machine Learning Research Peking University Beijing100084 China

In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences. The significant advancements in NLP and CV are predominantly driven by the expansion of model parameters and data size, a phenomenon now recognized as the scaling laws. However, research exploring scaling law in molecular pretraining models remains unexplored. In this work, we present Uni-Mol2, an innovative molecular pretraining model that leverages a two-track transformer to effectively integrate features at the atomic level, graph level, and geometry structure level. Along with this, we systematically investigate the scaling law within molecular pretraining models, characterizing the power-law correlations between validation loss and model size, dataset size, and computational resources. Consequently, we successfully scale Uni-Mol2 to 1.1 billion parameters through pretraining on 800 million conformations, making it the largest molecular pretraining model to date. Extensive experiments show consistent improvement in the downstream tasks as the model size grows. The Uni-Mol2 with 1.1B parameters also outperforms existing methods, achieving an average 27% improvement on the QM9 and 14% on COMPAS-1D dataset. © 2024, CC BY-NC-ND.

关键词： Natural language processing systems

Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zeng, Qingjie Xie, Yutong Lu, Zilin Lu, Mengkang Wu, Yicheng Xia, Yong School of Computer Science and Engineering Northwestern Polytechnical University China Australian Institute for Machine Learning University of Adelaide Australia Department of Data Science & AI Faculty of Information Technology Monash University Australia

Annotation scarcity has become a major obstacle for training powerful deep-learning models for medical image segmentation, restricting their deployment in clinical scenarios. To address it, semi-supervised learning by exploiting abundant unlabeled data is highly desirable to boost the model training. However, most existing works still focus on limited medical tasks and underestimate the potential of learning across diverse tasks and multiple datasets. Therefore, in this paper, we introduce a Versatile Semi-supervised framework (VerSemi) to point out a new perspective that integrates various tasks into a unified model with a broad label space, to exploit more unlabeled data for semi-supervised medical image segmentation. Specifically, we introduce a dynamic task-prompted design to segment various targets from different datasets. Next, this unified model is used to identify the foreground regions from all labeled data, to capture cross-dataset semantics. Particularly, we create a synthetic task with a cutmix strategy to augment foreground targets within the expanded label space. To effectively utilize unlabeled data, we introduce a consistency constraint. This involves aligning aggregated predictions from various tasks with those from the synthetic task, further guiding the model in accurately segmenting foreground regions during training. We evaluated our VerSemi model on four public benchmarking datasets. Extensive experiments demonstrated that VerSemi can consistently outperform the second-best method by a large margin (e.g., an average 2.69% Dice gain on four datasets), setting new SOTA performance for semi-supervised medical image segmentation. The code will be released. © 2023, CC BY.

关键词： Semantics

Audio-based Kinship Verification Using Age Domain Conversion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Qiyang Akman, Alican Jing, Xin Milling, Manuel Schuller, Björn W. GLAM Department of Computing Imperial College London United Kingdom MRI Technical University of Munich Germany MDSI – Munich Data Science Institute Munich Germany MCML – Munich Center for Machine Learning Munich Germany

Audio-based kinship verification (AKV) is important in many domains, such as home security monitoring, forensic identification, and social network analysis. A key challenge in the task arises from differences in age across samples from different individuals, which can be interpreted as a domain bias in a cross-domain verification task. To address this issue, we design the notion of an "age-standardised domain" wherein we utilise the optimised CycleGAN-VC3 network to perform age-audio conversion to generate the in-domain audio. The generated audio dataset is employed to extract a range of features, which are then fed into a metric learning architecture to verify kinship. Experiments are conducted on the KAN_AV audio dataset, which contains age and kinship labels. The results demonstrate that the method markedly enhances the accuracy of kinship verification, while also offering novel insights for future kinship verification *** Codes 68T10 © 2024, CC BY-NC-SA.

关键词： Economic and social effects

Pitfalls of epistemic uncertainty quantification through loss minimisation 22

学校读者我要写书评

暂无评论

Pitfalls of epistemic uncertainty quantification through los...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Viktor Bengs Eyke Hüllermeier Willem Waegeman Institute of Informatics University of Munich (LMU) Institute of Informatics University of Munich (LMU) and Munich Center for Machine Learning Department of Data Analysis and Mathematical Modeling Ghent University

ISBN: (纸本)9781713871088

Uncertainty quantification has received increasing attention in machine learning in the recent past. In particular, a distinction between aleatoric and epistemic uncertainty has been found useful in this regard. The latter refers to the learner's (lack of) knowledge and appears to be especially difficult to measure and quantify. In this paper, we analyse a recent proposal based on the idea of a second-order learner, which yields predictions in the form of distributions over probability distributions. While standard (first-order) learners can be trained to predict accurate probabilities, namely by minimising suitable loss functions on sample data, we show that loss minimisation does not work for second-order predictors: The loss functions proposed for inducing such predictors do not incentivise the learner to represent its epistemic uncertainty in a faithful way.

关键词：

Enrolment-based personalisation for improving individual-level fairness in speech emotion recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Triantafyllopoulos, Andreas Schuller, Björn MRI Technical University of Munich Germany MCML - Munich Center for Machine Learning Germany MDSI - Munich Data Science Institute Germany GLAM - Group on Language Audio & Music Imperial College London United Kingdom

The expression of emotion is highly individualistic. However, contemporary speech emotion recognition (SER) systems typically rely on population-level models that adopt a 'one-size-fits-all' approach for predicting emotion. Moreover, standard evaluation practices measure performance also on the population level, thus failing to characterise how models work across different speakers. In the present contribution, we present a new method for capitalising on individual differences to adapt an SER model to each new speaker using a minimal set of enrolment utterances. In addition, we present novel evaluation schemes for measuring fairness across different speakers. Our findings show that aggregated evaluation metrics may obfuscate fairness issues on the individual-level, which are uncovered by our evaluation, and that our proposed method can improve performance both in aggregated and disaggregated terms. © 2024, CC BY-NC-ND.

关键词： Emotion Recognition

MATHGLANCE: Multimodal Large Language Models Do Not Know Where to Look in mathematical Diagrams

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Sun, Yanpeng Zhang, Shan Tang, Wei Chen, Aotian Koniusz, Piotr Zou, Kai Xue, Yuan van den Hengel, Anton National University of Singapore Singapore Australian Institute for Machine Learning Australia Nanjing University of Science and Technology China Ohio State University United States Data61 CSIRO Australia NetMind.ai United Kingdom

Diagrams serve as a fundamental form of visual language, representing complex concepts and their interrelationships through structured symbols, shapes, and spatial arrangements. Unlike natural images, their inherently symbolic and abstract nature poses significant challenges for Multimodal Large Language Models (MLLMs). However, current benchmarks conflate perceptual and reasoning tasks, making it difficult to assess whether MLLMs genuinely understand mathematical diagrams beyond superficial pattern recognition. To address this gap, we introduce MATHGLANCE, a benchmark specifically designed to isolate and evaluate mathematical perception in MLLMs. MATHGLANCE comprises 1.2K images and 1.6K carefully curated questions spanning four perception tasks: shape classification, object counting, relationship identification, and object grounding, covering diverse domains including plane geometry, solid geometry, and graphical representations. Our evaluation of MLLMs reveals that their ability to understand diagrams is notably limited, particularly in fine-grained grounding tasks. In response, we construct GeoPeP, a perception-oriented dataset of 200K structured geometry image-text pairs explicitly annotated with geometric primitives and precise spatial relationships. Training MLLM on GeoPeP leads to significant gains in perceptual accuracy, which in turn substantially improves mathematical reasoning. Our benchmark and dataset establish critical standards for evaluating and advancing multimodal mathematical understanding, providing valuable resources and insights to foster future MLLM research. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages