检索结果-内蒙古大学图书馆

Enhancing Bidirectional Encoder Representations From Transformers (BERT) With Frame Semantics to Extract Clinically Relevant Information From German Mammography Reports: Algorithm Development and Validation

引用

Journal of Medical Internet Research 2025年 27卷

作者： Reichenpfader, Daniel Knupp, Jonas von Däniken, Sandro Urs Gaio, Roberto Dennstädt, Fabio Cereghetti, Grazia Maria Sander, André Hiltbrunner, Hans Nairz, Knud Denecke, Kerstin Institute for Patient-centered Digital Health School of Engineering and Computer Science Bern University of Applied Sciences Biel/Bienne Switzerland PhD School of Life Sciences Faculty of Medicine University of Geneva Geneva Switzerland ID SUISSE AG St. Gallen Switzerland Department of Diagnostic Interventional and Pediatric Radiology Bern University Hospital University of Bern Bern Switzerland Department of Radiation Oncology Bern University Hospital University of Bern Bern Switzerland ID BERLIN Berlin Germany

Background: Structured reporting is essential for improving the clarity and accuracy of radiological information. Despite its benefits, the European Society of Radiology notes that it is not widely adopted. For example, while structured reporting frameworks such as the Breast Imaging Reporting and Data System provide standardized terminology and classification for mammography findings, radiology reports still mostly comprise free-text sections. This variability complicates the systematic extraction of key clinical data. Moreover, manual structuring of reports is time-consuming and prone to inconsistencies. Recent advancements in large language models have shown promise for clinical information extraction by enabling models to understand contextual nuances in medical text. However, challenges such as domain adaptation, privacy concerns, and generalizability remain. To address these limitations, frame semantics offers an approach to information extraction grounded in computational linguistics, allowing a structured representation of clinically relevant concepts. Objective: This study explores the combination of Bidirectional Encoder Representations from Transformers (BERT) architecture with the linguistic concept of frame semantics to extract and normalize information from free-text mammography reports. Methods: After creating an annotated corpus of 210 German reports for fine-tuning, we generate several BERT model variants by applying 3 pretraining strategies to hospital data. Afterward, a fact extraction pipeline is built, comprising an extractive question-answering model and a sequence labeling model. We quantitatively evaluate all model variants using common evaluation metrics (model perplexity, Stanford Question Answering Dataset 2.0 [SQuAD_v2], seqeval) and perform a qualitative clinician evaluation of the entire pipeline on a manually generated synthetic dataset of 21 reports, as well as a comparison with a generative approach following best practice prompting

关键词： annotation information extraction large language models mammography natural language processing quality control radiology structured reporting template filling

来源：评论

学校读者我要写书评

暂无评论

Thermoplastic Starch Films Reinforced with Electrospun PLLA Fibers and Oxidized Sucrose

SSRN

引用

SSRN 2025年

作者： Jakubska, Justyna Janik, Weronika Jakubski, Lukasz Polak, Martyna Stachewicz, Urszula Furgol, Simona Sabura, Ewa Gębura, Katarzyna Golombek, Klaudiusz Dudek, Gabriela Department of Physical Chemistry and Technology of Polymers Faculty of Chemistry Silesian University of Technology Strzody 9 Gliwice44-100 Poland Department of Physical Chemistry and Technology of Polymers PhD School Silesian University of Technology Akademicka 2A Gliwice44-100 Poland AGH University of Science and Technology of Krakow Faculty of Metals Engineering and Industrial Computer Science Al. A. Mickiewicza 30 Kraków30-059 Poland Lukasiewicz Research Network Institute of Heavy Organic Synthesis Blachownia Energetyków 9 Kędzierzyn-Koźle47-225 Poland Materials Research Laboratory Faculty of Mechanical Engineering Silesian University of Technology Konarskiego 18A Gliwice44-100 Poland

The increasing demand for eco-friendly packaging materials has driven extensive research into biodegradable alternatives. This paper focuses on enhancing starch-based films' mechanical and water barrier properties by incorporating electrospun PLLA fibers, with oxidized sucrose introduced as novel crosslinking agent. Varying oxidized sucrose concentrations (3–15 wt%) were examined for their impact on the films structure and performance. Results demonstrate that oxidized sucrose functionates as both an effective crosslinker and compatibilizer, improving integration between the starch matrix and PLLA fibers. This dual functionality contributes to a more cohesive and durable film structure, providing significant enhancements over non-crosslinked films. The formulation with 9 wt% oxidized sucrose exhibited a tensile strength of 1.8 MPa and an elongation at break of 40%, surpassing traditional alternatives. Additionally, water barrier properties reached the expected standards, positioning this film as highly promising for practical applications. These findings highlight the potential of oxidized sucrose to advance biodegradable packaging solutions. © 2025, The Authors. All rights reserved.

关键词： Tensile strength

来源：评论

学校读者我要写书评

暂无评论

Statistical Power Analysis for Designing Bulk, Single-Cell, and Spatial Transcriptomics Experiments: Review, Tutorial, and Perspectives

arXiv

引用

arXiv 2023年

作者： Jeon, Hyeongseon Xie, Juan Jeon, Yeseul Jung, Kyeong Joo Gupta, Arkobrato Chang, Won Chung, Dongjun Department of Biomedical Informatics The Ohio State University ColumbusOH United States Pelotonia Institute for Immuno-Oncology The James Comprehensive Cancer Center The Ohio State University ColumbusOH43210 United States The Interdisciplinary PhD program in Biostatistics The Ohio State University ColumbusOH United States Department of Statistics and Data Science Yonsei University Seoul Korea Republic of Department of Applied Statistics Yonsei University Seoul Korea Republic of Department of Computer Science and Engineering The Ohio State University ColumbusOH United States Division of Statistics and Data Science University of Cincinnati CincinnatiOH United States

Gene expression profiling technologies have been used in various applications such as cancer biology. The development of gene expression profiling has expanded the scope of target discovery in transcriptomic studies, and each technology produces data with distinct characteristics. In order to guarantee biologically meaningful findings using transcriptomic experiments, it is important to consider various experimental factors in a systematic way through statistical power analysis. In this paper, we review and discuss the power analysis for three types of gene expression profiling technologies from a practical standpoint, including bulk RNA-seq, single-cell RNA-seq, and high-throughput spatial transcriptomics. Specifically, we describe the existing power analysis tools for each research objective for each of the bulk RNA-seq and scRNA-seq experiments, along with recommendations. On the other hand, since there are no power analysis tools for high-throughput spatial transcriptomics at this point, we instead investigate the factors that can influence power analysis. © 2023, CC BY-NC-ND.

关键词： RNA

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Genotype-Phenotype Maps Reveal Mutational Robustness of RNA Folding, Spin Glasses, and Quantum Circuits

arXiv

引用

arXiv 2023年

作者： Sappington, Anna Mohanty, Vaibhav Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Program for Health Sciences and Technology Harvard Medical School BostonMA02115 United States Massachusetts Institute of Technology CambridgeMA02139 United States Harvard/MIT MD-PhD Program Harvard Medical School BostonMA02115 United States Department of Chemistry and Chemical Biology Harvard University CambridgeMA02138 United States

Recent studies of genotype-phenotype (GP) maps have reported universally enhanced phenotypic robustness to genotype mutations, a feature essential to evolution. Virtually all of these studies make a simplifying assumption that each genotype—represented as a sequence—maps deterministically to a single phenotype, such as a discrete structure. Here, we introduce probabilistic genotype-phenotype (PrGP) maps, where each genotype maps to a vector of phenotype probabilities, as a more realistic and universal language for investigating robustness in a variety of physical, biological, and computational systems. We study three model systems to show that PrGP maps offer a generalized framework which can handle uncertainty emerging from various physical sources: (1) thermal fluctuation in RNA folding, (2) external field disorder in spin glass ground state finding, and (3) superposition and entanglement in quantum circuits, which are realized experimentally on IBM quantum computers. In all three cases, we observe a novel biphasic robustness scaling which is enhanced relative to random expectation for more frequent phenotypes and approaches random expectation for less frequent phenotypes. We derive an analytical theory for the behavior of PrGP robustness, and we demonstrate that the theory is highly predictive of empirical robustness. © 2023, CC BY.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Split-Net: Dual Transformer Encoder with Splitting Scene Text Image for Script Identification

引用

Pattern Recognition Letters 2025年

作者： Ayush Roy Shivakumara Palaiahnakote Umapada Pal Cheng-Lin Liu PhD Department of Computer Science and Engineering State University of New York Buffalo USA School of Science Engineering and Environment University of Salford Manchester UK Computer Vision and Pattern Recognition Indian Statistical Institute Kolkata India State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of the Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Script identification is vital for understanding scenes and video images. It is challenging due to high variations in physical appearance, typeface design, complex background, distortion, and significant overlap in the characteristics of different scripts. Unlike existing models, which aim to tackle the script images utilizing the scene text image as a whole, we propose to split the image into upper and lower halves to capture the intricate differences in stroke and style of various scripts. Motivated by the accomplishments of the transformer, a modified script-style-aware Mobile-Vision Transformer (M-ViT) is explored for encoding visual features of the images. To enrich the features of the transformer blocks, a novel Edge Enhanced Style Aware Channel Attention Module (EESA-CAM) has been integrated with M-ViT. Furthermore, the model fuses the features of the dual encoders (extracting features from the upper and the lower half of the images) by a dynamic weighted average procedure utilizing the gradient information of the encoders as the weights. In experiments on three standard datasets, MLe2e, CVSI2015, and SIW-13, the proposed model yielded superior performance compared to state-of-the-art models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatial atlas of the mouse central nervous system at molecular resolution (vol 622, pg 552, 2023)

引用

NATURE 2024年第7993期625卷 E6-E6页

作者： Shi, Hailing He, Yichun Zhou, Yiming Huang, Jiahao Maher, Kamal Wang, Brandon Tang, Zefang Luo, Shuchen Tan, Peng Wu, Morgan Lin, Zuwan Ren, Jingyi Thapa, Yaman Tang, Xin Chan, Ken Y. Deverman, Benjamin E. Shen, Hao Liu, Albert Liu, Jia Wang, Xiao Broad Institute of MIT and Harvard Cambridge MA USA Department of Chemistry Massachusetts Institute of Technology Cambridge MA USA John A. Paulson School of Engineering and Applied Sciences Harvard University Boston MA USA Computational and Systems Biology PhD Program Massachusetts Institute of Technology Cambridge MA USA Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA Department of Biology Massachusetts Institute of Technology Cambridge MA USA Klarman Cell Observatory Broad Institute of MIT and Harvard Cambridge MA USA Department of Chemistry and Chemical Biology Harvard University Cambridge MA USA Stanley Center for Psychiatric Research Broad Institute of MIT and Harvard Cambridge MA USA

来源：评论

学校读者我要写书评

暂无评论

Bi-path Architecture of CNN Segmentation and Classification Method for Cervical Cancer Disorders Based on Pap-smear Images

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2021年第3期48卷 1-9页

作者： Desiani, Anita Erwin, Member Suprihatin, Bambang Yahdin, Sugandi Putri, Ajeng I. Husein, Fathur R. Assistant Professor of Mathematics Department and Phd candidate of Mathematics and Natural Science Faculty Universitas Sriwijaya Indralaya30662 Indonesia Associate Professor of Computer Engineering Department Computer Science Faculty Universitas Sriwijaya Indralaya30662 Indonesia Associate Professor of Mathematics Department Mathematics and Natural Science Faculty Universitas Sriwijaya Indralaya30662 Indonesia Head of Mathematics Department Mathematics and Natural Science Faculty Universitas Sriwijaya Indralaya30662 Indonesia Undergraduate student of Mathematics Department Mathematics and Natural Science Faculty Universitas Sriwijaya Indralaya30662 Indonesia An undergraduate student of Mathematics Department Mathematics and Natural Science Faculty Universitas Sriwijaya Indralaya30662 Indonesia

This paper is concern about segmentation on pap smear images to use for classification cervical cancer. A cervical cancer screening by recognizing the cell shape pattern on the Pap-smear image can provide information about the presence of cervical cancer Pap-smear. The manual screening process for classifying cells is a challenging endeavor prone to the risk of error. There are several studies on the classification of cervical cell images which are sometimes not segmented first. Segmentation is very important to get the features contained in the image of cervical cells including the cell nucleus and cytoplasm. However, the segmentation results are also determined by the quality of images. This study proposed 2 paths that had a combination of image segmentation and classification. Before segmentation, image enhancement was carried out to improve image quality using Normalization, CLAHE and Adaptive Gamma Correction. The first path, the segmentation based on the CNN architecture. The second path is a classification process to test the segmentation results used by applying the KNN and ANN methods. The accuracy (ACC) result at the segmentation path was used to measure the match between the location of the segmented pixels and the results on ground truth, while the accuracy at the classification path was the success of the machine in classifying or predicting the segmentation results based on the class label for each group according normal and abnormal Pap-smear's label. The ACC result obtained in segmentation was only 0.77. However, the results of the segmentation when used in classification to classify which Pap-smears were normal and which are abnormal could provide excellent accuracy results, which were above 0.9. The results of the performance of Sensitivity (SN), Specificity (SP) and F1-score on the segmentation path also only gave results below 0.72, but the performance on the classification path that used the results on the segmentation path gave well results, wh

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Thermalization of fluorescent protein exciton-polaritons at room temperature

arXiv

引用

arXiv 2022年

作者： Satapathy, Sitakanta Liu, Bin Deshmukh, Prathmesh Molinaro, Paul M. Dirnberger, Florian Khatoniar, Mandeep Koder, Ronald L. Menon, Vinod M. Department of Physics Center for Discovery and Innovation The City College of New York 85 St. Nicholas Terrace New YorkNY10031 United States The PhD Program in Physics The Graduate Center of the City University of New York 365 5th Ave New YorkNY10016 United States Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States

Fluorescent proteins (FPs) have recently emerged as a serious contender for realizing ultra-low threshold room temperature exciton-polariton condensation and lasing. Our contribution investigates the thermalization of FP microcavity exciton-polaritons upon optical pumping under ambient conditions. We realize polariton cooling using a new FP molecule, called mScarlet, coupled strongly to the optical modes in a Fabry-Pérot cavity. Interestingly, at the threshold excitation energy (fluence) of ~9 nJ/pulse (15.6 mJ/cm2), we observe an effective temperature, Teff ~350 ± 35 K close to the lattice temperature indicative of strongly thermalized exciton-polaritons at equilibrium. This efficient thermalization results from the interplay of radiative pumping facilitated by the energetics of the lower polariton branch and the cavity Qfactor. Direct evidence for dramatic switching from an equilibrium state into a metastable state is observed for the organic cavity polariton device at room temperature via deviation from the Maxwell-Boltzmann statistics at k1 = 0 above the threshold. Thermalized polariton gases in organic systems at equilibrium hold substantial promise for designing room temperature polaritonic circuits, switches, and lattices for analog simulation. © 2022, CC BY-NC-SA.

关键词： Polariton

来源：评论

学校读者我要写书评

暂无评论

AN ALGEBRAIC CHARACTERIZATION OF k–COLORABILITY

arXiv

引用

arXiv 2020年

作者： Flores, Ramón Kahrobaei, Delaram Koberda, Thomas Department of Geometry and Topology University of Seville Spain Department of Computer Science University of York UK New York University Tandon School of Engineering PhD Program in Computer Science CUNY Graduate Center Mathematics Department University of Virginia CharlottesvilleVA22904

We characterize k–colorability of a simplicial graph via the intrinsic algebraic structure of the associated right-angled Artin group. As a consequence, we show that a certain problem about the existence of homomorphisms from right-angled Artin groups to products of free groups is NP–complete. Copyright © 2020, The Authors. All rights reserved.

关键词： Algebra

来源：评论

学校读者我要写书评

暂无评论

Identification and Prevention of Glaucoma Through Digital Processing of Biomedical Imaging by the Relationship Between Volume of Nerve Fibers and Intraocular Pressure

Identification and Prevention of Glaucoma Through Digital Pr...

引用

AHFE Virtual Conference on Human Factors and Ergonomics in Healthcare and Medical Devices, and the International Conference on Human Factors in Aging and Special Needs, 2020

作者： Pinos-Vélez, Eduardo Chazi, Marlon Cajamarca, Christian Robles-Bykbaev, Vladimir Chacón, Carlos Luis Ipanaqué, William Serpa-Andrade, Luis GIIATA Research Group on Artificial Intelligence and Assistive Technologies and GIIB Research Group on Biomedical Engineering Universidad Politécnica Salesiana Cuenca Ecuador GIIATA Research Group on Artificial Intelligence and Assistive Technologies Universidad Politécnica Salesiana Cuenca Ecuador Ecuadorian Society of Glaucoma Clinical Santa Lucía Quito Ecuador PhD of Engineering Computer Science and Control DICOP Universidad de Piura Piura Peru

ISBN: (纸本)9783030508371

Glaucoma is the second leading cause of blindness worldwide and the first in an irreversible way, many of the studies and investigations are concentrated in methods of control and treatment, however, there are few studies carried out in the areas of prevention and early detection of glaucoma, so, in this research presents the effect of increased intraocular pressure in the optic nerve, especially in damage caused in the layer of nerve fibers and their impact with the visual field, To do this, you work with background images of human eye, obtained from the Clinic "Santa Lucia", digital image processing to characterize parameters that determine a presumptive diagnosis of glaucoma suspect, the results are presented to specialists for a medical diagnosis. © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Optical tomography

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：