检索结果-内蒙古大学图书馆

International Challenge on Segment Anything in Medical Images on Laptop held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024

作者： Kong, Youngbin Kim, Kwangtai Jeong, Seoi Lee, Kyu Eun Kong, Hyoun-Joong Interdisciplinary Program in Bioengineering Graduate School Seoul National University Seoul Korea Republic of Department of Transdisciplinary Medicine Seoul National University Hospital Seoul Korea Republic of Department of Surgery Seoul National University Hospital and College of Medicine Seoul Korea Republic of Department of Medicine Seoul National University College of Medicine Seoul Korea Republic of Innovative Medical Technology Research Institute Seoul National University Hospital Seoul Korea Republic of Interdisciplinary Program of Medical Informatics Seoul National University College of Medicine Seoul Korea Republic of

ISBN: (纸本)9783031818530

Medical image segmentation is a crucial step for accurate diagnosis and treatment planning, as it provides quantitative information about anatomical structures and pathological lesions in various clinical scenarios. However, the existing methodologies have limitations in terms of their generalizability and computational efficiency. In this study, we propose SwiftMedSAM, an ultra-lightweight prompt-based general model, to enable efficient medical image segmentation even in resource-constrained environments. Based on LiteMedSAM, we significantly reduced the model size and computational complexity through the hyperparameter optimization of the image encoder and mask decoder components. SwiftMedSAM showed remarkable performance across various imaging modalities enabling real-time inference in resource-limited computing environments. It achieved a validation score of 0.75 demonstrating that SwiftMedSAM outperformed the existing methodologies in terms of the trade-off between accuracy and efficiency. Owing to its unprecedented generalizability and low computational cost, SwiftMedSAM is expected to enable high-quality medical image analysis in resource-constrained settings, thereby contributing to advancements in precision medicine and telemedicine. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation

arXiv

引用

arXiv 2025年

作者： Jo, Sanghyun Lee, Seo Jin Lee, Seungwoo Hong, Seohyung Seo, Hyungseok Kim, Kyungsu OGQ Seoul Korea Republic of Laboratory of Cell & Gene Therapy Institute of Pharmaceutical Sciences College of Pharmacy Seoul National University Korea Republic of Department of Biomedical Science and Medical Research Center College of Pharmacy Seoul National University Korea Republic of School of Transdisciplinary Innovations Interdisciplinary Program in Bioengineering Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

Cell instance segmentation (CIS) is crucial for identifying individual cell morphologies in histopathological images, providing valuable insights for biological and medical research. While unsupervised CIS (UCIS) models aim to reduce the heavy reliance on labor-intensive image annotations, they fail to accurately capture cell boundaries, causing missed detections and poor performance. Recognizing the absence of error-free instances as a key limitation, we present COIN (COnfidence score-guided INstance distillation), a novel annotation-free framework with three key steps: (1) Increasing the sensitivity for the presence of error-free instances via unsupervised semantic segmentation with optimal transport, leveraging its ability to discriminate spatially minor instances, (2) Instance-level confidence scoring to measure the consistency between model prediction and refined mask and identify highly confident instances, offering an alternative to ground truth annotations, and (3) Progressive expansion of confidence with recursive self-distillation. Extensive experiments across six datasets show COIN outperforming existing UCIS methods, even surpassing semi- and weakly-supervised approaches across all metrics on the MoNuSeg and TNBC datasets. The code is available at https://***/shjo-april/COIN. © 2025, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Score-based Diffusion Model based Synthetic CT Generation from MR Images and Post-hoc Uncertainty Analysis

Score-based Diffusion Model based Synthetic CT Generation fr...

引用

Medical Imaging 2025: Image Processing

作者： Yie, Si Young Yoon, Siyeop Yang, Jaewon Kim, Kyungsang Lee, Jae Sung Li, Quanzheng Interdisciplinary Program in Bioengineering Seoul National University Seoul03080 Korea Republic of Center for Advanced Medical Computing and Analysis Massachusetts General Hospital Havard Medical School BostonMA02114 United States Department of Radiology University of Texas Southwestern DallasTX75390 United States

ISBN: (纸本)9781510685901

PET/MRI and MR-guided radiotherapy have significantly advanced clinical diagnostics and treatment planning by integrating anatomy and function, while synthetic CT generation from MRI has emerged as a tool for extracting tissue density and attenuation properties. Despite these advances, generating synthetic CT from MRI remains challenging in the pelvic region due to substantial differences in tissue contrast and intensity between the two modalities. Traditional methods using dedicated MR sequences often fail to accurately represent bone structure. Recent deep learning models, including convolutional neural networks (CNNs) and generative adversarial networks (GANs), have improved the quality of synthetic CT generation, they typically lack uncertainty estimation, which limits their clinical utility. In this study, we propose a conditional diffusion model for generating pelvic CT from T1-weigted MR, enhanced by tissue segmentation extracted from TotalSegmentator-MR. We also investigated the self-explanatory characteristics of the diffusion model through uncertainty mapping from multiple realizations without requiring ground truth to enhance interpretability. Our results demonstrate that the diffusion model with tissue segmentation priors, produces higher-quality synthetic CTs and improved tissue differentiation compared to deterministic generative model and diffusion models conditioned only on MR data. Notably, the uncertainty map showed a strong spatial correlation with the ground truth-based error map. Furthermore, the inclusion of segmentation priors also reduces uncertainty, thereby improving the model's reliability. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

PET image reconstruction using diffusion priors and half-quadratic splitting

PET image reconstruction using diffusion priors and half-qua...

引用

Medical Imaging 2025: Physics of Medical Imaging

作者： Bae, Sangjin Yu, Boxiao Lee, Jae Sung Gong, Kuang Interdisciplinary Program in Bioengineering Seoul National University Seoul08826 Korea Republic of J. Crayton Pruitt Family Department of Biomedical Engineering University of Florida GainesvilleFL32611 United States Department of Nuclear Medicine Seoul National University Hospital Seoul03080 Korea Republic of

ISBN: (纸本)9781510685888

PET image reconstruction is an inverse problem that aims to reconstruct the radiotracer distribution inside the body. This process involves finding an image x that maximizes the likelihood of the observed data y. To further improve image quality, maximum a posteriori (MAP) reconstruction is developed to exploit prior information about x, which requires designing a regularizer. Recent advances in diffusion models, a powerful class of generative models, have demonstrated their ability to effectively approximate data distributions. These models traditionally use ancestral sampling to generate images. As research on diffusion models progresses, it has been shown that they can also be used to design robust regularizers for inverse problems that go beyond ancestral sampling. In this work, we explored diffusion models-based regularizers for PET image reconstruction. Given the computational complexity of directly solving PET reconstruction with such regularizers, half-quadratic splitting (HQS) was utilized to decouple the regularizer from the original PET reconstruction objective. Our simulation study demonstrated that the proposed approach could generate high-quality reconstructions based solely on a limited number of iterations when compared to other reference methods. © 2025 SPIE.

关键词： Positron emission tomography

来源：评论

学校读者我要写书评

暂无评论

YaleNLP @ PerAnsSumm 2025: Multi-Perspective Integration via Mixture-of-Agents for Enhanced Healthcare QA Summarization

arXiv

引用

arXiv 2025年

作者： Jang, Dongsuk Li, Alan Cohan, Arman Department of Computer Science Yale University United States Interdisciplinary Program for Bioengineering Seoul National University Korea Republic of Seoul National University Korea Republic of

Automated summarization of healthcare community question-answering forums is challenging due to diverse perspectives presented across multiple user responses to each question. The PerAnsSumm Shared Task was therefore proposed to tackle this challenge by identifying perspectives from different answers and then generating a comprehensive answer to the question. In this study, we address the PerAnsSumm Shared Task using two complementary paradigms: (i) a training-based approach through QLoRA fine-tuning of LLaMA-3.3-70B-Instruct, and (ii) agentic approaches including zero- and few-shot prompting with frontier LLMs (LLaMA-3.370B-Instruct and GPT-4o) and a Mixture-of-Agents (MoA) framework that leverages a diverse set of LLMs by combining outputs from multi-layer feedback aggregation. For perspective span identification/classification, GPT-4o zero-shot achieves an overall score of 0.57, substantially outperforming the 0.40 score of the LLaMA baseline. With a 2-layer MoA configuration, we were able to improve LLaMA performance up by 28% to 0.51. For perspective-based summarization, GPT-4o zero-shot attains an overall score of 0.42 compared to 0.28 for the best LLaMA zero-shot, and our 2-layer MoA approach boosts LLaMA performance by 32% to 0.37. Furthermore, in few-shot setting, our results show that the sentence-transformer embedding-based exemplar selection provides more gain than manually selected exemplars on LLaMA models, although the few-shot prompting is not always helpful for GPT-4o. The YaleNLP team’s approach ranked the overall second place in the shared task. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Engineering a Whitlockite-Containing Macroporous Composite Cryogel with Silica Hybrid for Enhanced Vascularized Bone Regeneration

引用

ACS Applied Materials and Interfaces 2025年第21期17卷 30436-30453页

作者： Kuttappan, Shruthy Amirthalingam, Sivashanmugam Hennebert, Perrine M’Pemba Lee, Yoonho Ryu, Kyung Min Rajendran, Arun Kumar Kim, Jung Hun So, Kyoung-Ha Hwang, Nathaniel S. Jeon, Noo Li Institute of Advanced Machinery and Design Seoul National University Seoul 08826 South Korea Institute of Engineering Research Seoul National University Seoul 08826 South Korea School of Chemical and Biological Engineering Institute of Chemical Processes Seoul National University Seoul 08826 South Korea Interdisciplinary Program in Bioengineering Seoul National University Seoul 08826 South Korea Bio-MAX/N-Bio Institute Institute of Bio-Engineering Seoul National University Seoul 08826 South Korea School of Mechanical Engineering Seoul National University Seoul 08826 South Korea Qureator Inc. San Diego 92121 CA United States

Recognizing the complexity of the bone regeneration cascade and understanding the adverse effects of using growth factors, it is crucial to develop a growth factor-free scaffold with multiple functions to modulate various aspects of the regenerative process. This study explores a novel macroporous multifunctional bone graft for bone regeneration, aiming to overcome complications associated with current treatment modalities. The study reveals enhanced bone regeneration and vascularization by integrating silica hybrid and nano-whitlockite (nWH) into cryogel-based composite scaffolds. The physicochemical properties, in vitro angiogenic and osteogenic potential, three-dimensional (3D) vasculogenesis, osteoclastogenesis, and proinflammatory responses of the composite cryogels were systematically examined. Results showed augmented effects for nWH-containing silica hybrid cryogels, particularly notable in the 1:0.5 WH2.5 group. Cryogels promoted angio- and vasculogenesis, and osteogenic differentiation while reducing osteoclast formation and proinflammatory responses in vitro. Optimal composition analysis consistently favored the 1:0.5 WH2.5 group. Implantation in a critical-sized cranial defect model in mice demonstrated enhanced vascularization and new bone formation. Thus, this study demonstrates the synergistic effect of silica hybrid and nWH in critical-sized bone defects. © 2025 American Chemical Society.

关键词： bone regeneration cryogel silica hybrid vascularization whitlockite

来源：评论

学校读者我要写书评

暂无评论

BPS2025 - Studying self-assembly of bacterial proteins in cell-free protein synthesis systems

引用

Biophysical Journal 2025年第3期124卷 55a-55a页

作者： Jacob B. Miller Nolan W. Kennedy Danielle Tullman-Ercek Carolyn E. Mills Interdisciplinary Biological Sciences Program Northwestern University Evanston IL USA Department of Chemical and Biological Engineering Northwestern University Evanston IL USA Department of Bioengineering University of California Santa Barbara Santa Barbara CA USA

来源：评论

学校读者我要写书评

暂无评论

FET-based nanobiosensors for the detection of smell and taste

引用

Science China(Life Sciences) 2020年第8期63卷 1159-1167页

作者： Dongseok Moon Yeon Kyung Cha So-ong Kim Seongyeon Cho Hwi Jin Ko Tai Hyun Park School of Chemical and Biological Engineering Institute of Chemical ProcessesSeoul National UniversitySeoul 08826Republic of Korea Interdisciplinary Program for Bioengineering Seoul National UniversitySeoul 08826Republic of Korea

Various nanobiosensors composed of biomaterials and nanomaterials have been developed,due to their demonstrated advantage of showing high *** various biomaterials for biological recognition elements of the nanobiosensor,sensory receptors,such as olfactory and taste receptors,are promising biomaterials for developing nanobiosensors,because of their high selectivity to target ***-effect transistors(FET)with nanomaterials such as carbon nanotube(CNT),graphene,and conducting polymer nanotube(CPNT),can be combined with the biomaterials to enhance the sensitivity of ***,many efforts have been made to develop nanobiosensors using biomaterials,such as olfactory receptors and taste receptors for detecting various smells and *** review focuses on the biomaterials and nanomaterials used in nanobiosensor systems and studies of various types of nanobiosensor platforms that utilize olfactory receptors and taste receptors which could be applied to a wide range of industrial fields,including the food and beverage industry,environmental monitoring,the biomedical field,and anti-terrorism.

关键词： nanobiosensor olfactory receptor taste receptor field-effect transistor(FET)

来源：评论

学校读者我要写书评

暂无评论

High performance gamma-ray spectrometer based on Cs3Cu2I5 single crystal grown by room-temperature vacuum solvent-evaporation method

引用

Journal of Alloys and Compounds 2025年 1027卷

作者： Seo, Jiwon Song, Seungho Park, Minhwan Byun, Jangwon Park, Beomjun Park, Chansun Jang, Mee Yeom, Jung-Yeol Dept. of Health and Safety Convergence Science Korea University Seoul02841 Korea Republic of Interdisciplinary Program in Precision Public Health Korea University Seoul02841 Korea Republic of Dept. of Bioengineering Korea University Seoul02841 Korea Republic of Dept. of Materials Science and Engineering Korea University Seoul02841 Korea Republic of The Institute for High Technology Materials and Devices Korea University Seoul02841 Korea Republic of Global Health Technology Center Korea University Seoul02841 Korea Republic of Daejeon34057 Korea Republic of School of Biomedical Engineering Korea University Seoul02841 Korea Republic of

In this study, the properties of Cs3Cu2I5 (CCI) crystals grown using the Slow Vacuum Evaporation Technique (SVET) were examined. Crystals were grown at room temperature (300 K, 27 °C) under vacuum conditions, producing single crystals with maximum diameter of 13 mm over 23 days. We confirmed excellent crystallinity via X-ray diffraction (XRD), compositional uniformity via X-ray photoelectron spectroscopy (XPS), and homogeneity via electron probe micro analyzer (EPMA). UV-Vis measurements indicated a high transmittance of 83 % and a bandgap of 3.64 eV. The Stokes shift of 110 nm, smaller than previously reported values, contributed to faster decay times and improved low-energy detection feasibility. Time-resolved photoluminescence (TR-PL) showed a rapid decay component (4.1 ns), accounting for 95.11 % of the total decay, demonstrating superior properties compared to existing reports. The gamma-ray detection capabilities of the CCI crystals were evaluated using six radioactive sources (Am-241, Ba-133, Co-57, Na-22, Cs-137, and Mn-54), achieving excellent energy resolution, including 5.2 % at 662 keV. The crystals displayed a highly linear response to gamma radiation (R² = 0.99998) with a light yield of 55,613 photons/MeV. Moreover, assessments of multiple crystals grown under identical conditions showed consistent performance with a coefficient of variation (CV) of 1.23 %. These findings confirm that SVET is a highly effective and cost-efficient method for producing high-quality CCI crystals, offering significant advantages over other growth techniques. © 2025 Elsevier B.V.

关键词： Gamma ray spectrometers

来源：评论

学校读者我要写书评

暂无评论

Verification of Geant4-DNA step-by-step-reaction-diffusion master equation model for long-term radiolysis simulation

引用

Physica Medica 2025年 133卷 104983-104983页

作者： Yoon, Euntaek Tran, Ngoc Hoang Incerti, Sebastien Choi, Chang Heon Interdisciplinary Program in Bioengineering Seoul National University Seoul 08826 Cuba Biomedical Research Institute Seoul National University Hospital Seoul 03080 Cuba Univ. Bordeaux CNRS LP2I UMR 5797 Gradignan F-33170 France Department of Radiation Oncology Seoul National University Hospital Seoul 03080 Cuba Institute of Radiation Medicine Seoul National University Medical Research Center Seoul 03080 Cuba Department of Radiation Oncology Seoul National University College of Medicine Seoul 03080 Cuba

Purpose: This paper describes the verification of the step-by-step-reaction-diffusion Master Equation (SBS-RDME) model, implemented in Geant4-DNA, for long-term radiolysis simulations in the Fricke dosimeter. Methods: Scaling for reaction rate constants due to the high acidity of the Fricke solution was applied. The secondary electrons generated by gamma irradiation from Co-60 were used as the radiation source for the simulations. Model parameters were optimized by observing changes in output and computation time in response to variations in the starting time t and initial voxel resolution ℎ of the compartment-based simulation. The yields of ferric ion G(Fe³⁺) and chemical species influencing its formation were calculated using the SBS-RDME model and using the IRT method for comparison. The time evolution of the yields of Fe³⁺, ^[rad]OH, H^[rad], HO₂^[rad], H₂O₂, and H₂ were compared, and the reactions affecting the yield of each chemical species were analyzed. Results: The model parameters were set to t = 5 ns and h = 12.5 nm. The yield trends over time for chemical species were consistent between the SBS-RDME model and the IRT method. At 50 s, the G(Fe³⁺) from the two calculations agreed within 3.2 %. Contribution analysis of the reactions affecting the generation/removal of each chemical species indicated that the main reason for this discrepancy between the two calculations might be the inability of the SBS method to consider specific reaction types during simulation. Conclusions: The SBS-RDME model was verified for long-term simulations by comparing its results to those obtained from the IRT method. © 2025 Associazione Italiana di Fisica Medica e Sanitaria

关键词： Fricke dosimetry Geant4-DNA RDME Water radiolysis

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：