检索结果-内蒙古大学图书馆

RemInD: Remembering Anatomical Variations for Interpretable Domain Adaptive Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Xin Guo, Yin Zhang, Kaiyu Balu, Niranjan Mossa-Basha, Mahmud Shapiro, Linda Yuan, Chun Department of Electrical and Computer Engineering University of Washington Seattle United States Department of Bioengineering University of Washington Seattle United States Vascular Imaging Lab Department of Radiology University of Washington Seattle United States Paul G. Allen School of Computer Science and Engineering University of Washington Seattle United States Department of Radiology and Imaging Sciences University of Utah Salt Lake City United States

This work presents a novel Bayesian framework for unsupervised domain adaptation (UDA) in medical image segmentation. While prior works have explored this clinically significant task using various strategies of domain alignment, they often lack an explicit and explainable mechanism to ensure that target image features capture meaningful structural information. Besides, these methods are prone to the curse of dimensionality, inevitably leading to challenges in interpretability and computational efficiency. To address these limitations, we propose RemInD, a framework inspired by human adaptation. RemInD learns a domain-agnostic latent manifold, characterized by several anchors, to memorize anatomical variations. By mapping images onto this manifold as weighted anchor averages, our approach ensures realistic and reliable predictions. This design mirrors how humans develop representative components to understand images and then retrieve component combinations from memory to guide segmentation. Notably, model prediction is determined by two explainable factors: a low-dimensional anchor weight vector, and a spatial deformation. This design facilitates computationally efficient and geometry-adherent adaptation by aligning weight vectors between domains on a probability simplex. Experiments on two public datasets, encompassing cardiac and abdominal imaging, demonstrate the superiority of RemInD, which achieves state-of-the-art performance using a single alignment approach, outperforming existing methods that often rely on multiple complex alignment strategies. Copyright © 2025, The Authors. All rights reserved.

关键词： Image segmentation

Learning Disentangled Representation for Multidimensional MR Image Reconstruction

学校读者我要写书评

暂无评论

Learning Disentangled Representation for Multidimensional MR...

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Ruiyang Zhao Zepeng Wang Fan Lam Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign Urbana IL USA Beckman Institute for Advanced Science and Technology University of Illinois Urbana-Champaign Urbana IL USA Department of Bioengineering University of Illinois Urbana-Champaign Urbana IL USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

We proposed a new way to represent and reconstruct multidimensional MR images. Specifically, a representation capable of disentangling different types of features in high-dimensional images was learned via training an autoencoder with separated sets of latent spaces for image style transfer, e.g., contrast or geometry transfer. A latent diffusion model was introduced to capture the distributions of the disentangled latents for constrained reconstruction. A new formulation was developed to integrate the pre-learned representation with other complementary constraints for reconstruction from sparse data. We demonstrated the ability of our model to disentangle contrast and geometry features in multicontrast MR images, and its effectiveness in accelerated T 1 and T 2 mapping.

关键词： Geometry Training Biological system modeling Autoencoders Diffusion models engineering in medicine and biology Image reconstruction

Virtual staining-based diagnosis of organ transplant rejection

学校读者我要写书评

暂无评论

Virtual staining-based diagnosis of organ transplant rejecti...

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Li, Yuzhu Pillar, Nir Liu, Tairan Ma, Guangdong de Haan, Kevin Zhang, Yijie Correa, Adrian J. Wu, Yulun Bai, Bijie Yang, Xilin Qi, Yuxuan Wallace, William Dean Ozcan, Aydogan Electrical and Computer Engineering Department University of California Los AngelesCA90095 United States Bioengineering Department University of California Los AngelesCA90095 United States University of California Los AngelesCA90095 United States School of Physics Xi'an Jiaotong University Shaanxi Xi'an710049 China Department of Pathology Keck School of Medicine University of Southern California Los AngelesCA90033 United States Department of Mathematics University of California Los AngelesCA90095 United States Computer Science Department University of California Los AngelesCA90095 United States Department of Surgery University of California Los AngelesCA90095 United States

We present deep learning-based virtual staining of unlabeled lung and heart tissue sections to diagnose organ transplant rejection, achieving comparable diagnostic accuracy to histochemical staining methods, while sig... 详细信息

ISBN: (纸本)9781957171395

关键词： Accuracy Costs Electro-optical waveguides Heart Lasers and electrooptics Lung Organ transplantation

GENIE-NF-AI: Identifying Neurofibromatosis Tumors using Liquid Neural Network (LTC) trained on AACR Genie Datasets

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bidollahkhani, Michael Atasoy, Ferhat Abedini, Elnaz Davar, Ali Hamza, Omid Sefaoğlu, Fırat Jafari, Amin Yalçın, Muhammed Nadir Abdellatef, Hamdan Department of Computer Engineering Institute of Graduate Studies Karabuk University Turkey Göttingen Germany Department of Biomedical Engineering Institute of Graduate Studies Karabuk University Turkey Department of Genetics and Bioengineering Faculty of Engineering and Architecture Kastamonu University Turkey Department of Medical Science Faculty of Medicine Karabuk University Turkey Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

In recent years, the field of medicine has been increasingly adopting artificial intelligence (AI) technologies to provide faster and more accurate disease detection, prediction, and assessment. In this study, we propose an interpretable AI approach to diagnose patients with neurofibromatosis using blood tests and pathogenic variables. We evaluated the proposed method using a dataset from the AACR GENIE project and compared its performance with modern approaches. Our proposed approach outperformed existing models with 99.86% accuracy. We also conducted NF1 and interpretable AI tests to validate our approach. Our work provides an explainable approach model using logistic regression and explanatory stimulus as well as a black-box model. The explainable models help to explain the predictions of black-box models while the glass-box models provide information about the best-fit features. Overall, our study presents an interpretable AI approach for diagnosing patients with neurofibromatosis and demonstrates the potential of AI in the medical field. © 2023, CC BY-NC-ND.

关键词： Machine learning

Multiplane Quantitative Phase Imaging Using a Wavelength-Multiplexed Diffractive Optical Processor

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shen, Che-Yung Li, Jingxi Gan, Tianyi Li, Yuhang Bai, Langxing Jarrahi, Mona Ozcan, Aydogan Electrical and Computer Engineering Department University of California Los AngelesCA90095 United States Bioengineering Department University of California Los AngelesCA90095 United States University of California Los AngelesCA90095 United States Department of Computer Science University of California Los AngelesCA90095 United States

Quantitative phase imaging (QPI) is a label-free technique that provides optical path length information for transparent specimens, finding utility in biology, materials science, and engineering. Here, we present quantitative phase imaging of a 3D stack of phase-only objects using a wavelength-multiplexed diffractive optical processor. Utilizing multiple spatially engineered diffractive layers trained through deep learning, this diffractive processor can transform the phase distributions of multiple 2D objects at various axial positions into intensity patterns, each encoded at a unique wavelength channel. These wavelength-multiplexed patterns are projected onto a single field-of-view (FOV) at the output plane of the diffractive processor, enabling the capture of quantitative phase distributions of input objects located at different axial planes using an intensity-only image sensor. Based on numerical simulations, we show that our diffractive processor could simultaneously achieve all-optical quantitative phase imaging across several distinct axial planes at the input by scanning the illumination wavelength. A proof-of-concept experiment with a 3D-fabricated diffractive processor further validated our approach, showcasing successful imaging of two distinct phase objects at different axial positions by scanning the illumination wavelength in the terahertz spectrum. Diffractive network-based multiplane QPI designs can open up new avenues for compact on-chip phase imaging and sensing devices. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational Imaging

Inference-Enabled Mental Stress Tracking Via Multi-Modal Wearable Physiological Sensing: A Proof-of-Concept Study

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Zhou, Yuanyuan Mousavi, Azin S. Chalumuri, Yekanth R. Parreira, Jesse D. Modak, Mihir Sanchez-Perez, Jesus Antonio Gazi, Asim H. Inan, Omer T. Hahn, Jin-Oh Department of Mechanical Engineering University of Maryland College ParkMD United States Department of Bioengineering University of Maryland College ParkMD United States School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA United States

Objective: To develop a novel mental stress tracking algorithm that can infer mental stress state from multi-modal digital signatures of physiological parameters compatible with wearable-enabled sensing. Methods: We derived prominent digital signatures of physiological responses to mental stress using cross-integration of multi-modal physiological signals including the electrocardiogram (ECG), photoplethysmogram (PPG), seismocardiogram (SCG), ballistocardiogram (BCG), electrodermal activity (EDA), and respiratory effort. Then, we developed a mental stress tracking algorithm that can continuously classify stress vs no stress conditions based on an aggregated likelihood computed with respect to a priori probability density distributions associated with the digital signatures of mental stress under stress and no stress conditions. Results: Our mental stress tracking algorithm could adequately infer mental stress state (average classification accuracy: 0.85, sensitivity: 0.85, specificity: 0.86) using a small number of prominent digital signatures derived from cross-integration of multi-modal physiological signals. It significantly outperformed mental stress trackers based on the digital signatures employed in the state-of-the-art. Its exploitation of collective inference allowed for improved inference of mental stress state relative to naïve data mining techniques. Conclusion: Our mental stress tracking algorithm has the potential to make a leap in continuous, high-accuracy, and high-confidence inference of mental stress via convenient wearable-enabled physiological sensing. Significance: The ability to continuously monitor and track mental stress can collectively improve human wellbeing. © 2023, The Authors. All rights reserved.

关键词： Data mining

Virtual staining-based diagnosis of organ transplant rejection

学校读者我要写书评

暂无评论

Virtual staining-based diagnosis of organ transplant rejecti...

CLEO: Applications and Technology in CLEO 2024, CLEO: A and T 2024 - Part of Conference on Lasers and Electro-Optics

关键词： Lung cancer

Prior-guided Diffusion Model for Cell Segmentation in Quantitative Phase Imaging

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shao, Zhuchen Anastasio, Mark A. Li, Hua University of Illinois Urbana-Champaign Department of Electrical and Computer Engineering UrbanaIL United States University of Illinois Urbana-Champaign Department of Bioengineering UrbanaIL United States Washington University School of Medicine Department of Radiation Oncology Saint LouisMO United States

Purpose: Quantitative phase imaging (QPI) is a label-free technique that provides high-contrast images of tissues and cells without the use of chemicals or dyes. Accurate semantic segmentation of cells in QPI is essential for various biomedical applications. While DM-based segmentation has demonstrated promising results, the requirement for multiple sampling steps reduces efficiency. This study aims to enhance DM-based segmentation by introducing prior-guided content information into the starting noise, thereby minimizing inefficiencies associated with multiple sampling. Approach: A prior-guided mechanism is introduced into DM-based segmentation, replacing randomly sampled starting noise with noise informed by content information. This mechanism utilizes another trained DM and DDIM inversion to incorporate content information from the to-be-segmented images into the starting noise. An evaluation method is also proposed to assess the quality of the starting noise, considering both content and distribution information. Results: Extensive experiments on various QPI datasets for cell segmentation showed that the proposed method achieved superior performance in DM-based segmentation with only a single sampling. Ablation studies and visual analysis further highlighted the significance of content priors in DM-based segmentation. Conclusion: The proposed method effectively leverages prior content information to improve DM-based segmentation, providing accurate results while reducing the need for multiple samplings. The findings emphasize the importance of integrating content priors into DM-based segmentation methods for optimal performance. © 2024, CC BY-NC-ND.

关键词： Cells

Stain-free, rapid, and automated viral plaque assay using time-lapse holographic imaging and deep learning

学校读者我要写书评

暂无评论

Stain-free, rapid, and automated viral plaque assay using ti...

Frontiers in Optics + Laser Science 2023, FiO, LS 203: Part of Frontiers in Optics + Laser Science 2023

作者： Li, Yuzhu Liu, Tairan Koydemir, Hatice Ceylan Zhang, Yijie Yang, Ethan Eryilmaz, Merve Wang, Hongda Li, Jingxi Bai, Bijie Ma, Guangdong Ozcan, Aydogan Electrical and Computer Engineering Department University of California Los AngelesCA90095 United States Bioengineering Department University of California Los Angeles90095 United States University of California Los AngelesCA90095 United States Department of Biomedical Engineering Texas A&M University College StationTX77843 United States Center for Remote Health Technologies and Systems Texas A&M University College StationTX77843 United States Department of Mathematics University of California Los AngelesCA90095 United States

We report a rapid and automated viral plaque assay using time-lapse holographic imaging and deep learning, significantly reducing the detection time needed for traditional viral plaque assays and entirely eliminating ... 详细信息

ISBN: (纸本)9781957171296

关键词： Clinical applications Deep learning Imaging Laser systems Phase imaging Real time imaging