检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Shiman Zhao, Jiayue Liu, Shaolei Dai, Xiaokun Zhang, Chenxi Song, Zhijian The School of Basic Medical Science Fudan University 200433 China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention 200032 China The Academy for Engineering and Technology Fudan University 200433 China

Deep learning-based medical image segmentation helps assist diagnosis and accelerate the treatment process while the model training usually requires large-scale dense annotation datasets. Weakly semi-supervised medical image segmentation is an essential application because it only requires a small amount of scribbles and a large number of unlabeled data to train the model, which greatly reduces the clinician’s effort to fully annotate images. To handle the inadequate supervisory information challenge in weakly semi-supervised segmentation (WSSS), a SuperPixel-Propagated Pseudo-label (SP3) learning method is proposed, using the structural information contained in superpixel for supplemental information. Specifically, the annotation of scribbles is propagated to superpixels and thus obtains a dense annotation for supervised training. Since the quality of pseudo-labels is limited by the low-quality annotation, the beneficial superpixels selected by dynamic thresholding are used to refine pseudo-labels. Furthermore, aiming to alleviate the negative impact of noise in pseudo-label, superpixel-level uncertainty is incorporated to guide the pseudo-label supervision for stable learning. Our method achieves state-of-the-art performance on both tumor and organ segmentation datasets under the WSSS setting, using only 3% of the annotation workload compared to fully supervised methods and attaining approximately 80% Dice score. Additionally, our method outperforms eight weakly and semi-supervised methods under both weakly supervised and semi-supervised settings. Results of extensive experiments validate the effectiveness and annotation efficiency of our weakly semi-supervised segmentation, which can assist clinicians in achieving automated segmentation for organs or tumors quickly and ultimately benefit patients. © 2024, CC BY.

关键词： Superpixels

来源：评论

学校读者我要写书评

暂无评论

Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You Need

arXiv

引用

arXiv 2023年

作者： Qu, Linhao Ma, Yingfan Luo, Xiaoyuan Guo, Qinhao Wang, Manning Song, Zhijian Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai200032 China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China Department of Gynecologic Oncology Fudan University Shanghai Cancer Center 270 Dong-An Road Shanghai200032 China

Weakly supervised whole slide image classification is usually formulated as a multiple instance learning (MIL) problem, where each slide is treated as a bag, and the patches cut out of it are treated as instances. Existing methods either train an instance classifier through pseudo-labeling or aggregate instance features into a bag feature through attention mechanisms and then train a bag classifier, where the attention scores can be used for instance-level classification. However, the pseudo instance labels constructed by the former usually contain a lot of noise, and the attention scores constructed by the latter are not accurate enough, both of which affect their performance. In this paper, we propose an instance-level MIL framework based on contrastive learning and prototype learning to effectively accomplish both instance classification and bag classification tasks. To this end, we propose an instance-level weakly supervised contrastive learning algorithm for the first time under the MIL setting to effectively learn instance feature representation. We also propose an accurate pseudo label generation method through prototype learning. We then develop a joint training strategy for weakly supervised contrastive learning, prototype learning, and instance classifier training. Extensive experiments and visualizations on four datasets demonstrate the powerful performance of our method. Codes are available at https://***/miccaiif/INS. Copyright © 2023, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Combined Transcranial and Endoscopic Endonasal Approach for Resecting a Giant Intracranial and Extracranial Communicating Meningioma:A Case Report

引用

Clinical Cancer Bulletin 2022年第3期1卷 167-171页

作者： Ye GU Kai XUE Quan LIU Huankang ZHANG Hongmeng YU Department of Neurosurgery Eye&ENT HospitalFudan UniversityShanghaiChina Department of Otolaryngology Eye&ENT HospitalFudan UniversityShanghaiChina Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention Fudan UniversityShanghaiChina Research Units of New Technologies of Endoscopic Surgery in Skull Base Tumor Chinese Academy of Medical SciencesShanghaiChina

Objective Although intracranial and extracranial communicating meningiomas are uncommon in clinical settings,they pose a considerable challenge for ***,one-stage surgery should be more comprehensively explained as it is not frequently reported as a first-line *** report A 27-year-old man with a massive intracranial and extracranial communicating meningioma was admitted with nasal congestion and mild numbness on the left side of his face.A combined transcranial and endoscopic endonasal approach was performed in a single day aided by preoperative tumor *** tumor was nearly completely removed without any serious ***-up revealed the disappearance of diplopia,with the patient having a normal ***,no tumor progression was *** The combined transcranial and endoscopic endonasal approach is feasible for removing certain massive intracranial and extracranial communicating *** techniques,such as embolization,microscopic,and endoscopic manipulation,are indispensable tools for treating such cases.

关键词： meningioma transcranial approach endoscopic endonasal approach

来源：评论

学校读者我要写书评

暂无评论

Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation

Separate and Conquer: Decoupling Co-occurrence via Decomposi...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhiwei Yang Kexue Fu Minghong Duan Linhao Qu Shuo Wang Zhijian Song Academy for Engineering and Technology Fudan University Digital Medical Research Center School of Basic Medical Sciences Fudan University Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shandong Computer Science Center (National Supercomputer Center in Jinan)

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Weakly supervised semantic segmentation (WSSS) with image-level labels aims to achieve segmentation tasks with-out dense annotations. However, attributed to the frequent coupling of co-occurring objects and the limited supervision from image-level labels, the challenging co-occurrence problem is widely present and leads to false activation of objects in WSSS. In this work, we devise a ‘Separate and Conquer’ scheme SeCo to tackle this issue from di-mensions of image space and feature space. In the im-age space, we propose to ‘separate’ the co-occurring ob-jects with image decomposition by subdividing images into patches. Importantly, we assign each patch a category tag from Class Activation Maps (CAMs), which spatially helps remove the co-context bias and guide the subsequent rep-resentation. In the feature space, we propose to ‘conquer’ the false activation by enhancing semantic representation with multi-granularity knowledge contrast. To this end, a dual-teacher-single-student architecture is designed and tag-guided contrast is conducted, which guarantee the cor-rectness of knowledge and further facilitate the discrepancy among co-contexts. We streamline the multi-staged WSSS pipeline end-to-end and tackle this issue without external supervision. Extensive experiments are conducted, validating the efficiency of our method and the superiority over previous single-staged and even multi-staged competitors on PASCAL VOC and MS COCO. Code is available here.

关键词： Couplings computer vision Codes Semantic segmentation Semantics Pipelines Noise reduction

来源：评论

学校读者我要写书评

暂无评论

2d-3d Hierarchical Feature Fusion Network For Segmentation Of Bone Structure In Knee Mr Image

2d-3d Hierarchical Feature Fusion Network For Segmentation O...

引用

IEEE International Symposium on Biomedical imaging

作者： Hui Wang Demin Yao Jiayi Chen Yanjing Liu Wensheng Li Yonghong Shi Digital Medical Research Center School of Basic Medical Sciences Fudan University Shanghai China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Fudan University Shanghai China. Histology and Embryology School of Basic Medical Sciences Fudan University Shanghai China.

ISBN: (纸本)9781665412469;9781665429474

Automatic segmentation of knee bone structures is an important task in orthopedics diagnosis of knee disease based on MRI images. Inspired by doctors' diagnosis of knee in sagittal plane of MR image, we propose to first calculate the sagittal maximum intensity projection (MIP) of MR image, then construct a high precision 2D-3D hierarchical feature fusion network for automatic segmentation of knee based on convolutional encoding and decoding architecture. It includes: 1) A 2D bypass network extracting global features based on MIP; 2) A 3D backbone network calculating local details based on MR volume; 3) A feature fusion module integrating 2D global context and 3D local details hierarchically. Particularly, the global features as anchor points will be fused with the local details at each level of the encoding path to enrich the context of local details and improve the segmentation accuracy. Our method is verified on SKI10 dataset. The average dice coefficients of femur, femoral cartilage, tibia and tibia cartilage are 0.978, 0.848, 0.979 and 0.848, respectively, and the segmentation performance is far better than the state-of-the-art methods.

关键词： Image segmentation Three-dimensional displays Image coding Magnetic resonance imaging Semantics medical services Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Differential GR Expression and Translocation in the Hippocampus Mediates Susceptibility vs. Resilience to Chronic Social Defeat Stress

Differential GR Expression and Translocation in the Hippocam...

引用

中国神经科学学会第十二届全国学术会议

作者： Huimei Wang Qiu-Qin Han Liu Yang Hui-Jie Huang Ya-Lin Wang Rui Yu Jing Wang Xiaorong Chen Adam Pilot Gen-Cheng Wu Qiong Liu Jin Yu Department of Integrative Medicine and Neurobiology State Key Laboratory of Medical Neurobiology School of Basic Medical Sciences Institutes of Brain ScienceBrain Science Collaborative Innovation Center Shanghai Medical College Fudan University Department of Anatomy Histology and EmbryologySchool of Basic Medical Sciences Shanghai Medical College Fudan University Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai

While social stress exposure is a common risk factor for affective disorders, most individuals exposed to it can maintain normal physical and psychological functioning. However, factors that determine

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimating mean trabecular bone spacing based on the combination of Hilbert transform and fundamental frequency estimation

引用

Science Foundation in China 2017年第3期25卷 57-71页

作者：李颖徐峰刘成成许凯亮他得安王威琪 Department of Electronic Engineering Fudan UniversityShanghai 200433China Institute of Acoustics Tongji UniversityShanghai 200092China Sorbonne Université UPMC Univ Paris 06INSERM UMR-S 1146CNRS UMR 7371Laboratoired'ImagerieBiomédicaleF-75006ParisFrance State Key Laboratory of ASIC and System Fudan UniversityShanghai 200433China Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention(MICCAI)of Shanghai Shanghai 200032China

Ultrasonic backscatter signals from cancellous bone are sensitive to the microstructure of trabecular bone,and thus enable the feasibility to extract microstructural information of trabecular *** mean trabecular bone spacing(MTBS)is an important parameter for characterizing bone *** paper proposes an MTBS estimation method based on the combination of Hilbert transform and fundamental frequency estimation(CHF). The CHF was verified with ultrasonic backscatter signals from simulations and in vitro measurements at a central frequency of *** CHF method was compared with the simplified inverse filter tracking(SIFT)method,Simons' Quadratic Transformation(QT)method,Singular Spectrum Analysis(SSA)method,and Spectral Autocorrelation(SAC)***-Carlo simulations were performed by varying the MTBS,signal-to-noise ratio(SNR),standard deviation of regular spacing(SDRS),amplitude ratio of diffuse scattering to regular scattering(Ad)and frequency dependent attenuation(nBUA).The simulation results showed that the CHF method had a better performance in MTBS estimation under almost all the examination conditions except for *** estimation percentage correct(EPC)was greater than 90% when the MTBS was in the range of 0.4to *** the in vitro measurements,the estimated EPC by the CHF method was91.25±7.81%(mean±standard deviation).A significant correlation was observed for the CHF-estimated MTBS and micro-computed tomography(μ-CT)-measured values(R^2=0.75,p<0.01).These results demonstrate that the CHF method is anti-interference for MTBS estimation and can be used to estimate trabecular bone spacing.

关键词： Ultrasonic backscatter Mean trabecular bone spacing estimation Hilbert transform and fundamental frequency estimation Cancellous bone microstructure

来源：评论

学校读者我要写书评

暂无评论

USFM: A Universal Ultrasound Foundation Model Generalized to Tasks and Organs towards label Efficient Image Analysis

arXiv

引用

arXiv 2023年

作者： Jiao, Jing Zhou, Jin Li, Xiaokang Xia, Menghua Huang, Yi Huang, Lihong Wang, Na Zhang, Xiaofan Zhou, Shichong Wang, Yuanyuan Guo, Yi Department of Electronic Engineering School of Information Science and Technology Fudan University Shanghai China Fudan University Shanghai Cancer Center Shanghai China Department of Radiology and Biomedical Imaging Yale School of Medicine New HavenCT United States SenseTime Research Shanghai China Shanghai Artificial Intelligence Laboratory Shanghai China Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Shanghai China

Inadequate generality across different organs and tasks constrains the application of ultrasound (US) image analysis methods in smart healthcare. Building a universal US foundation model holds the potential to address these issues. Nevertheless, the development of such foundational models encounters intrinsic challenges in US analysis, i.e., insufficient databases, low quality, and ineffective features. In this paper, we present a universal US foundation model, named USFM, generalized to diverse tasks and organs towards label efficient US image analysis. First, a large-scale Multi-organ, Multi-center, and Multi-device US database was built, comprehensively containing over two million US images. Organ-balanced sampling was employed for unbiased learning. Then, USFM is self-supervised pre-trained on the sufficient US database. To extract the effective features from low-quality US images, we proposed a spatial-frequency dual masked image modeling method. A productive spatial noise addition-recovery approach was designed to learn meaningful US information robustly, while a novel frequency band-stop masking learning approach was also employed to extract complex, implicit grayscale distribution and textural variations. Extensive experiments were conducted on the various tasks of segmentation, classification, and image enhancement from diverse organs and diseases. Comparisons with representative US image analysis models illustrate the universality and effectiveness of USFM. The label efficiency experiments suggest the USFM obtains robust performance with only 20% annotation, laying the groundwork for the rapid development of US models in clinical practices. Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

超声背散射松质骨诊断仪及其在新生儿骨质评价中的应用

引用

Engineering 2015年第3期 123-137页

作者：刘成成张蓉李颖徐峰他得安王威琪 Department of Electronic Engineering Fudan University Department of Neonatology Children’s Hospital of Fudan University Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention (MICCAI) of Shanghai

超声背散射技术在松质骨骨质无损评价中极具前景。本文介绍了一种新型超声背散射骨质诊断仪(UBBD)及其在新生儿骨质状况评价中的应用。超声背散射骨质诊断仪具有无损、无电离辐射、便携及操作简便等优点,可以在短时间内(5 s)获得人体松... 详细信息

超声背散射技术在松质骨骨质无损评价中极具前景。本文介绍了一种新型超声背散射骨质诊断仪(UBBD)及其在新生儿骨质状况评价中的应用。超声背散射骨质诊断仪具有无损、无电离辐射、便携及操作简便等优点,可以在短时间内(5 s)获得人体松质骨背散射信号。笔者共采集了467例新生儿(268男/199女)左侧跟骨处的背散射信号,所用探头中心频率为3.5 MHz。逐步调节背散射有效信号(SOI)的延迟(T1)和长度(T2),计算表观积分背散射(AIB)、表观背散射频率斜率(FSAB)及零频率截距(FIAB)和频谱质心偏移量(SCS)等参数。结果表明,背散射有效信号的选取对背散射测量有直接的影响。当T1较短时(<8μs),AIB和FIAB与新生儿胎龄有显著的正相关性(|R|=0.45,P<0.001);而当T1较长时(>10μs),AIB和FIAB负相关于新生儿胎龄(|R|=0.56,P<0.001),还可以观察到FSAB和SCS与新生儿胎龄有中度的正相关性(|R|=0.45,P<0.001)。T2对背散射测量的影响较小,引起相关系数的波动较小。本文通过自制的松质骨超声诊断仪证明超声背散射信号用于评价新生儿骨质状况的可行性。本文还提出了明确的背散射有效信号选取规则及新生儿骨质评价标准。

关键词：超声背散射松质骨评价有效信号背散射仪器新生儿骨质

来源：评论

学校读者我要写书评

暂无评论

Clomipramine inhibits microglial NLRP3 inflammasome in the hippocampus of depressive rats

Clomipramine inhibits microglial NLRP3 inflammasome in the h...

引用

中国解剖学会2021年年会

作者： Wang Yalin Zhang Shanshan Yue Na Liu Guixue Huang Huijie Han Qiuqin Gong Wenqing Chen Xiaorong Zhang Yaodong Yu Jin Xiao Honglei Qin Song Li Wensheng Liu Qiong Department of Integrative Medicine and Neurobiology School of Basic Medical Sciences Fudan University Department of Anatomy Histology and EmbryologySchool of Basic Medical SciencesFudan University Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Children's Hospital Affiliated to Zhengzhou University Henan Neural Development Engineering Research Center

Neuroinflammation is implicated in the pathophysiology of *** reduction of hippocampal volume in depression remains controversial because of interindividual variability in clinical ***,we studied the effects of clomipramine,a tricyclic antidepressant (TCA) that modulates serotonin and norepinephrine uptake,on chronic mild unpredictable stress (CMS)-induced depressive-like behaviors,hippocampal neuroinflammation, and hippocampal volume.

关键词： CMS Clomipramine inhibits microglial NLRP3 inflammasome in the hippocampus of depressive rats

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：