检索结果-内蒙古大学图书馆

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Ahmad, Zoheb Quasim, Danish Garg, Shreeya Kumar, Vinod Delhi Technological University Dept. of Software Engineering New Delhi India Delhi Technological University Dept. of Computer Engineering New Delhi India Iiit Delhi Dept. of Computer Engineering and Bioscience New Delhi India

ISBN: (纸本)9789380544472

YouTube's recommendation system is famous for its success in maintaining high retention rates. The cause of its success is its ability to learn and predict an individual user's preferences appropriately. An unintended consequence, however, is that users get stuck in what is known as their own 'echo chambers' when dealing with and feeding users back their preferences. These echo chambers can cause increasing perspective bias within users, making it difficult for users to understand differing opinions. This work aims to prepare a model that counteracts YouTube's recommendation system by forcefully exposing users to content from varying viewpoints. The SSKA pipeline (Suno Sabki, Karo Apni) is a complementary deep learning model that involves Natural Language Processing (NLP) and K-Means clustering. It utilizes modern software libraries such as the YouTube API (Application Programming Interface) for data collection and was trained and tested on a varied set of users. The results prove that the model is successful in decreasing the bias recommendation by exposing users to the content of varying opinions and helping them break away from their echo chambers. The proposed methodology of explicitly exposing users to the content of varying opinions can positively impact local societies and the global community. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Mitigating YouTube Recommendation Polarity using BERT and K-Means Clustering

Mitigating YouTube Recommendation Polarity using BERT and K-...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Zoheb Ahmad Danish Quasim Shreeya Garg Vinod Kumar Dept. of Software Engineering Delhi Technological University New Delhi India Dept. of Computer Engineering Delhi Technological University New Delhi India Dept. of Computer Engineering and Bioscience IIIT Delhi New Delhi India

YouTube's recommendation system is famous for its success in maintaining high retention rates. The cause of its success is its ability to learn and predict an individual user's preferences appropriately. An unintended consequence, however, is that users get stuck in what is known as their own “echo chambers” when dealing with and feeding users back their preferences. These echo chambers can cause increasing perspective bias within users, making it difficult for users to understand differing opinions. This work aims to prepare a model that counteracts YouTube's recommendation system by forcefully exposing users to content from varying viewpoints. The SSKA pipeline (Suno Sabki, Karo Apni) is a complementary deep learning model that involves Natural Language Processing (NLP) and K-Means clustering. It utilizes modern software libraries such as the YouTube API (Application Programming Interface) for data collection and was trained and tested on a varied set of users. The results prove that the model is successful in decreasing the bias recommendation by exposing users to the content of varying opinions and helping them break away from their echo chambers. The proposed methodology of explicitly exposing users to the content of varying opinions can positively impact local societies and the global community.

关键词： Adaptation models Video on demand Software libraries Social networking (online) Pipelines Psychology Transformers

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Predicting Metastasis on Melanoma Wsis

Deep Learning for Predicting Metastasis on Melanoma Wsis

引用

IEEE International Symposium on Biomedical Imaging

作者： Christopher Andreassen Saul Fuster Helga Hardardottir Emiel A.M. Janssen Kjersti Engan Dept. of Electrical Engineering and Computer Science University of Stavanger Stavanger Norway Dept. of Pathology Stavanger University Hospital Stavanger Norway Dept. of Chemistry Bioscience and Environmental Engineering University of Stavanger Stavanger Norway

Northern Europe has the second highest mortality rate of melanoma globally. In 2020, the mortality rate of melanoma rose to 1.9 per 100 000 habitants. Melanoma prognosis is based on a pathologist’s subjective visual analysis of the patient’s tumor. This methodology is heavily time-consuming, and the prognosis variability among experts is notable, drastically jeopardizing its reproducibility. Thus, the need for faster and more reproducible methods arises. Machine learning has paved its way into digital pathology, but so far, most contributions are on localization, segmentation, and diagnostics, with little emphasis on prognostics. This paper presents a convolutional neural network (CNN) method based on VGG16 to predict melanoma prognosis as the presence of metastasis within five years. Patches are extracted from regions of interest from Whole Slide Images (WSIs) at different magnification levels used in model training and validation. Results infer that utilizing WSI patches at 20x magnification level has the best performance, with an F1 score of 0.7667 and an AUC of 0.81.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DEEP LEARNING FOR PREDICTING METASTASIS ON MELANOMA WSIS

arXiv

引用

arXiv 2023年

作者： Andreassen, Christopher Fuster, Saul Hardardottir, Helga Janssen, Emiel A.M. Engan, Kjersti Dept. of Electrical Engineering and Computer Science University of Stavanger Stavanger4021 Norway Dept. of Pathology Stavanger University Hospital Stavanger4011 Norway Dept. of Chemistry Bioscience and Environmental Engineering University of Stavanger Stavanger4021 Norway

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Invasive Cancerous Area Detection in Non-Muscle Invasive Bladder Cancer Whole Slide Images

Invasive Cancerous Area Detection in Non-Muscle Invasive Bla...

引用

IEEE IVMSP Workshop

作者： Saul Fuster Farbod Khoraminia Umay Kiraz Neel Kanwal Vebjø rn Kvikstad Trygve Eftestø l Tahlita C.M. Zuiverloon Emiel A.M. Janssen Kjersti Engan Dept. of Electrical Engineering and Computer Science University of Stavanger Stavanger Norway Dept. of Urology Erasmus MC Cancer Institute University Medical Center GD Rotterdam The Netherlands Dept. of Pathology Stavanger University Hospital Stavanger Norway Dept. of Chemistry Bioscience and Environmental Engineering University of Stavanger Stavanger Norway

Bladder cancer patients’ stratification into risk groups relies on grade, stage and clinical factors. For non-muscle invasive bladder cancer, T1 tumours that invade the subepithelial tissue are high-risk lesions with a high probability to progress into an aggressive muscle-invasive disease. Detecting invasive cancerous areas is the main factor for dictating the treatment strategy for the patient. However, defining invasion is often subject to intra/interobserver variability among pathologists, thus leading to over or undertreatment. computer-aided diagnosis systems can help pathologists reduce overheads and erratic reproducibility. We propose a multi-scale model that detects invasive cancerous areas patterns across the whole slide image. The model extracts tiles of different tissue types at multiple magnification levels and processes them to predict invasive patterns based on local and regional information for accurate T1 staging. Our proposed method yields an F1 score of 71.9, in controlled settings 74.9, and without infiltration 90.0.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-Contrastive Weakly Supervised Learning Framework for Prognostic Prediction Using Whole Slide Images

arXiv

引用

arXiv 2024年

作者： Fuster, Saul Khoraminia, Farbod Silva-Rodríguez, Julio Kiraz, Umay van Leenders, Geert J.L.H. Eftestøl, Trygve Naranjo, Valery Janssen, Emiel A.M. Zuiverloon, Tahlita C.M. Engan, Kjersti Dept. of Electrical Engineering and Computer Science University of Stavanger Stavanger4021 Norway Dept. of Urology Erasmus MC Cancer Institute University Medical Center Rotterdam3015 GD Netherlands ÉTS Montréal MontréalQC1011 Canada Dept. of Pathology Stavanger University Hospital Stavanger4011 Norway Dept. of Chemistry Bioscience and Environmental Engineering University of Stavanger Stavanger4021 Norway Dept. of Pathology and Clinical Bioinformatics Erasmus MC Cancer Institute University Medical Center Rotterdam Rotterdam3015 GD Netherlands Universitat Politècnica de València Valencia46022 Spain

We present a pioneering investigation into the application of deep learning techniques to analyze histopathological images for addressing the substantial challenge of automated prognostic prediction. Prognostic prediction poses a unique challenge as the ground truth labels are inherently weak, and the model must anticipate future events that are not directly observable in the image. To address this challenge, we propose a novel three-part framework comprising of a convolutional network based tissue segmentation algorithm for region of interest delineation, a contrastive learning module for feature extraction, and a nested multiple instance learning classification module. Our study explores the significance of various regions of interest within the histopathological slides and exploits diverse learning scenarios. The pipeline is initially validated on artificially generated data and a simpler diagnostic task. Transitioning to prognostic prediction, tasks become more challenging. Employing bladder cancer as use case, our best models yield an AUC of 0.721 and 0.678 for recurrence and treatment outcome prediction respectively. © 2024, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional quantitative phase imaging evaluating glioblastoma targeting CAR T-cell efficacy 11

Three-dimensional quantitative phase imaging evaluating glio...

引用

Quantitative Phase Imaging XI 2025

作者： Serafini, Caroline E. Davarzani, Amin Cappabianca, Dan Collazos, Daniela Baez Li, Zhenmin Mamaghani, Deniz Tommasi, Anna Sarko, Lauren La Vonne Denne, Nina Mao, Leidong Saha, Krishanu Karumbaiah, Lohitash Robles, Francisco E. George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology AtlantaGA United States Wallace H. Coulter Dept. of Biomedical Engineering Georgia Institute of Technology Emory University AtlantaGA United States School of Electrical and Computer Engineering College of Engineering University of Georgia AthensGA United States Regenerative Bioscience Center University of Georgia AthensGA United States Department of Biomedical Engineering University of Wisconsin-Madison MadisonWI United States Wisconsin Institute for Discovery University of Wisconsin-Madison MadisonWI United States School of Electrical and Computer Engineering Georgia Institute of Technology 266 Ferst Drive AtlantaGA United States Department of Cellular Biology University of Georgia AthensGA United States Division of Neuroscience Biomedical and Translational Sciences Institute University of Georgia AthensGA United States Edgar L. Rhodes Center for Animal and Dairy Science College of Agriculture and Environmental Science University of Georgia AthensGA United States

ISBN: (纸本)9781510684065

Glioblastoma (GBM) is a highly aggressive brain tumor with limited treatment options and poor patient outcomes. While patient-derived spheroids offer a platform for studying GBM treatment, existing imaging modalities are often destructive or limited to endpoint analyses. Here, we present quantitative Oblique Back- illumination Microscopy (qOBM) as a novel, label-free imaging technique for real-time, non-invasive monitoring of GBM spheroids treated with tumor targeting chimeric antigen receptor T-cells (CAR T-cells). qOBM overcomes existing imaging limitations by providing high-resolution, 3D quantitative phase imaging through epi-illumination, enabling longitudinal visualization of cellular and subcellular processes within thick spheroids. Here, we apply qOBM to monitor the responses of GBM spheroids derived from three unique patient cell lines to targeted CAR T-cell immunotherapy and non-targeted controls. With this, we capture changes in the spheroids over 72 hours of treatment, allowing for visualization of processes such as CAR T-cell infiltration, mitosis, and apoptosis. Further, using images from GBM/CAR T cell cocultures, we develop a machine learning model for predicting spheroid cytotoxicity rates. Our findings establish qOBM as a powerful, non-destructive tool for longitudinal GBM spheroid toxicity monitoring and demonstrate its potential to advance personalized cancer therapy by providing real-time insight into treatment efficacy. © 2025 SPIE.

关键词： T-cells

来源：评论

学校读者我要写书评

暂无评论

Tracking cellular and subcellular dynamics with quantitative oblique back-illumination microscopy 10

Tracking cellular and subcellular dynamics with quantitative...

引用

Quantitative Phase Imaging X 2024

作者： Filan, Caroline E. Bharadwaj, Srinidhi Casteleiro Costa, Paloma Davarzani, Amin Cappabianca, Dan Tommasi, Anna Sarko, Lauren La Vonne Denne, Nina Mao, Leidong Saha, Krishanu Karumbaiah, Lohitash Robles, Francisco E. George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology 801 Ferst Dr. NW AtlantaGA United States Wallace H. Coulter Dept. of Biomedical Engineering Georgia Institute of Technology and Emory University 313 Ferst Dr. NW AtlantaGA United States School of Electrical and Computer Engineering Georgia Institute of Technology 266 Ferst Drive AtlantaGA United States School of Electrical and Computer Engineering College of Engineering University of Georgia AthensGA United States Regenerative Bioscience Center University of Georgia AthensGA United States Department of Biomedical Engineering University of Wisconsin-Madison MadisonWI United States Wisconsin Institute for Discovery University of Wisconsin-Madison MadisonWI United States Division of Neuroscience Biomedical and Health Sciences Institute University of Georgia AthensGA United States Edgar L. Rhodes Center for Animal and Dairy Science College of Agriculture and Environmental Science University of Georgia AthensGA United States

ISBN: (纸本)9781510669635

Quantitative oblique back-illumination microscopy (qOBM) is a label-free imaging technique that enables tomographic phase imaging of thick scattering samples with epi-illumination. Here, we propose the use of two forms of functional imaging with qOBM to study tissue and cell cultures. In doing so, we obtain the spatiotemporal and quantitative functional information associated with the phase values extrapolated from qOBM imaging. We have applied this process to study the efficacy of individual immune T cells to kill glioblastoma spheroid cultures in 3D spheroids. Data show that we can effectively distinguish between cell phenotypes and characterize the dynamic motion of these cells in 3D cultures. This work offers a distinct advantage in tracking 3D cellular dynamics in thick tissue as many function imaging modalities are limited to 2D samples. Further, this technology can be expanded to analyze a wide variety of cellular and subcellular dynamics non-invasively in thick tissue. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Development of a Low-Cost Hydrophone for Research, Education, and Community Science

Development of a Low-Cost Hydrophone for Research, Education...

引用

OCEANS 2024 - Halifax, OCEANS 2024

作者： Chapuis, Lucille Burca, Mihai Gridley, Tess Mouy, Xavier Nath, Artash Nedelec, Sophie Seeyave, Sophie Theriault, Jim Urban, Ed Williams, Rob Zimmer, Walter M.X. School of Biological Sciences University of Bristol BristolBS8 1TQ United Kingdom National Institute of Oceanography and Applied Geophysics Ogs Sgonico Italy University of Cape Town Dept. of Statistical Science Cape Town South Africa Applied Ocean Physics And Engineering Woods Hole Oceanographic Institution Woods HoleMA United States Computer Science and Envoronment Stanford University StanfordCA United States Bioscience Hatherly Laboraties University of Exeter ExeterEX4 4PS United Kingdom Partnership for Observation of the Global Ocean Plymouth United Kingdom Ocean Environmental Consulting Theriault Environmental Consulting HalifaxNS Canada NewarkDE United States Oceans Intitiative SeattleWA United States Center for Maritime Research and Experimentation Nato Science and Technology Office La Spezia Italy

ISBN: (纸本)9798331540081

In an effort to support the widespread use of passive acoustic monitoring devices in marine environments, a Task Team on Low-Cost Hydrophones for Research, Education, and Community Science was launched under the auspices of the Partnership for Observation of the Global Ocean and the International Quiet Ocean Experiment. To this aim, the Task Team is developing an open-source Low-Cost Marine Acoustic REcorder (LC-MARE), including hydrophone ceramics with a frequency response range of 10 Hz to 100 kHz, an effective sensitivity of at least -180 dB re V/µPa and an endurance exceeding one week of continuous recording. To minimise costs, the proposed deployment dept. will be limited to 100 m and the pressure housing will be made of commercially available PVC tubes and fittings. The envisioned price tag of less than US$200 makes the suggested marine acoustic recorder affordable in low-budget educational and community science contexts, as well as scientific applications where finances are limiting (for example in developing countries and for entry-level researchers). © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

High-throughput segmentation of unmyelinated axons by deep learning

Research Square

引用

Research Square 2021年

作者： Plebani, Emanuele Biscola, Natalia P. Havton, Leif A. Rajwa, Bartek Shemonti, Abida Sanjana Jaffey, Deborah Powley, Terry Keast, Janet R. Lu, Kun-Han Dundar, M. Murat Dept. of Computer & Information Sciences Indiana University - Purdue University IndianapolisIN46202 United States Dept. of Neurology Icahn School of Medicine at Mount Sinai New YorkNY10029 United States Dept. of Neuroscience Icahn School of Medicine at Mount Sinai New YorkNY10029 United States James J. Peters Department of Veterans Affairs Medical Center BronxNY10468 United States Bindley Bioscience Center Purdue University West LafayetteIN47906 United States Dept. of Computer Science Purdue University West LafayetteIN47906 United States Dept. of Psychological Sciences Purdue University West LafayetteIN47907 United States Dept. of Anatomy and Physiology The University of Melbourne MelbourneVIC3010 Australia Weldon School of Biomedical Engineering Purdue University West LafayetteIN47907 United States

Axonal characterizations of connectomes in healthy and disease phenotypes are surprisingly incomplete and biased because unmyelinated axons, the most prevalent type of fibers in the nervous system, have largely been ignored as their quantitative assessment quickly becomes unmanageable as the number of axons increases. Herein, we introduce the first prototype of a high-throughput processing pipeline for automated segmentation of unmyelinated fibers. Our team has used transmission electron microscopy images of vagus and pelvic nerves in rats. All unmyelinated axons in these images are individually annotated and used as labeled data to train and validate a deep instance segmentation network. We investigate the effect of different training strategies on the overall segmentation accuracy of the network. We extensively validate the segmentation algorithm as a stand-alone segmentation tool as well as in an expert-in-the-loop hybrid segmentation setting with preliminary, albeit remarkably encouraging results. Our algorithm achieves an instance-level F1 score of between 0.7 and 0.9 on various test images in the stand-alone mode and reduces expert annotation labor by 80% in the hybrid setting. We hope that this new high-throughput segmentation pipeline will enable quick and accurate characterization of unmyelinated fibers at scale and become instrumental in significantly advancing our understanding of connectomes in both the peripheral and the central nervous systems. © 2021, CC BY.

关键词： Fibers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：