检索结果-南通市图书馆

Designing a High-Performance Deep Learning Theoretical Model for Biomedical Image Segmentation by Using Key Elements of the Latest U-Net-Based Architectures

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Computer and Communications 2021年第7期9卷 8-20页

作者： Andreea Roxana Luca Tudor Florin Ursuleanu Liliana Gheorghe Roxana Grigorovici Stefan Iancu Maria Hlusneac Cristina Preda Alexandru Grigorovici Faculty of General Medicine “Grigore T. Popa” University of Medicine and Pharmacy Iasi Romania Departament obstetrics and gynecology Integrated Ambulatory of Hospital “Sf. Spiridon” Iasi Romania Department of Surgery VI “Sf. Spiridon” Hospital Iasi Romania Iasi Departament of Surgery I Regional Institute of Oncology Iasi Romania Department of Radiology “Sf. Spiridon” Hospital Iasi Romania Department of Endocrinology “Sf. Spiridon” Hospital Iasi Romania

Deep learning (DL) has experienced an exponential development in recent years, with major impact in many medical fields, especially in the field of medical image and, respectively, as a specific task, in the segmentation of the medical image. We aim to create a computer assisted diagnostic method, optimized by the use of deep learning (DL) and validated by a randomized controlled clinical trial, is a highly automated tool for diagnosing and staging precancerous and cervical cancer and thyroid cancers. We aim to design a high-performance deep learning model, combined from convolutional neural network (U-Net)-based architectures, for segmentation of the medical image that is independent of the type of organs/tissues, dimensions or type of image (2D/3D) and to validate the DL model in a randomized, controlled clinical trial. We used as a methodology primarily the analysis of U-Net-based architectures to identify the key elements that we considered important in the design and optimization of the combined DL model, from the U-Net-based architectures, imagined by us. Secondly, we will validate the performance of the DL model through a randomized controlled clinical trial. The DL model designed by us will be a highly automated tool for diagnosing and staging precancers and cervical cancer and thyroid cancers. The combined model we designed takes into account the key features of each of the architectures Overcomplete Convolutional Network Kite-Net (Kite-Net), Attention gate mechanism is an improvement added on convolutional network architecture for fast and precise segmentation of images (Attention U-Net), Harmony Densely Connected Network-Medical image Segmentation (HarDNet-MSEG). In this regard, we will create a comprehensive computer assisted diagnostic methodology validated by a randomized controlled clinical trial. The model will be a highly automated tool for diagnosing and staging precancers and cervical cancer and thyroid cancers. This would help drastically minimize the time and effort that specialists put into

关键词： Combined Model of U-Net-Based Architectures Medical Image Segmentation 2D/3D/CT/RMN Images

Meta analysis on the relationship between gene polymorphisms of vascular endothelial growth factorand retinal prognosis risk of prematurity

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Ophthalmology(English edition) 2012年第3期5卷 397-400页

作者： Jun Zhai, Ying-Pu Sun Reproductive Center the First Affiliated Hospital of Zhengzhou University Zhengzhou 450052 Henan Province China Department of Gynaecology and obstetrics People's Hospital of Zhengzhou Zhengzhou 450003 Henan Province China

AIM: To explore the relationship between gene polymorphisms of (VEGF) and retinopathy of prematurity (ROP). METHODS: Literature materials related to gene polymorphisms of VEGF and ROP in PubMed, EMBASE, Cochrane and CBM database were retrieved. These materials were screened according to inclusion and exclusion standards. Patients diagnosed with ROP in clinic were regarded as control group and ROP patients who were in treatment were regarded as observation group. The indexes in two groups were matched except birth weight (BW), gender and gestational weeks. Meta5.1 was used to analyze the relationship between gene polymorphisms of VEGF and ROP. RESULTS: Four random control tests (RCT) were included in this research, including 2611 patients. Met) analysis results showed that VEGF affected ROP, having statistical significance. The combined ratio was 0.44 (95% CI, 0.07, 0.80), 0.42 (95%CI, 0.09, 0.74) and 0.75 (95%CI, 0.02, 1.49), respectively. Carrying +405 allele might increase the premature infants risk of having ROP. CONCLUSION: ROP may be related to its carrying of +405 allele. Large-scale, multi-factor RCT researches are still needed in order to identify the relation between VEGF and ROP.

关键词： polymorphisms of vascular endothelial growth factor premature infant retinopathy Meta analysis

应用三维能量多普勒(3DPD)超声诊断并随访胎儿血管异常

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

世界核心医学期刊文摘（妇产科学分册） 2006年第4期2卷 14-14页

作者： Sciaky-Tamir Y. Cohen S.M. Hochner-Celnikier D. 李奎 Department of obstetrics and gynecology Hadassah University HospitalMt. Scopus Jerusalem Israel Dr.

Objective: This study was undertaken to examine the value of 3-dimensional power Doppler (3DPD) ultrasound imaging in diagnosis and follow-up of fetal vascular anomalies. Study design: In 174 women undergoing early second-trimester targeted organ scanning, followed by a midtrimester second scan in a university hospital setting, 3DPD was applied to the fetal intraabdominal and intrathoracic vessels. Results: In 137 of 174 fetuses (75%) in the earlier scan, and in 164 of 174 fetuses (95%) in the later scan, 3DPD ultrasound successfully visualized the fetal vessels. In an additional 9 cases, anomalous vascularity was identified: fetal intra-abdominal umbilicalvein varix (2), persistent right umbilical vein (1), agenesis of ductus venosus (2), eventration of diaphragm (1), parenchymal and vascular lung anomaly (1), sacrococcygeal teratoma (1), and chorioangioma (1). 3DPD improved diagnostic precision, aided our understanding of anomalous structure, and added information on the vascular volume of lesions in some cases. Conclusion: 3DPD improved ultrasound visualization of the fetal vessels of the abdomen and thorax in normal and anomalous cases.

关键词：胎儿血 PD 超声诊断胎儿腹腔骶尾部畸胎瘤脐静脉曲张绒毛膜血管瘤发育不全超声检查血管检

Outcome of Assisted Reproduction Treatment in Women with Extremely Low Antimullerian Hormone (AMH) Levels

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Open Journal of obstetrics and gynecology 2014年第15期4卷 961-966页

作者： Munawar Hussain David J. Cahill Valentine Akande Uma Gordon St. Michael’s hospital University Hospital Bristol NHS Foundation Trust Bristol UK Academic Unit of obstetrics and Gynaecology School of clinical sciences University of Bristol & St. Michael’s Hospital Bristol UK Bristol Centre for Reproductive Medicine North Bristol NHS Trust Bristol UK

Purpose: To evaluate age related ovarian response to controlled ovarian hyperstimulation, clinical pregnancy and ongoing pregnancy rates beyond 20 weeks in women undergoing assisted reproduction treatment (ART) with antimullerian hormone (AMH) levels of 38 years of age. Non parametric variables were expressed as median (Interquartile range) and compared by Kruskal-Wallis test. Categorical variables were expressed as numbers with proportions (%) and compared by Fisher’s exact test. Results: There was no statistical difference in body max index, level of antimullerian hormone (AMH), follicle stimulating hormone (FSH), dose of gonadotrophins used and cycles cancellation rate in two groups. Although number of oocytes retrieved (median 5), clinical pregnancy (18.4%) and ongoing pregnancy rate beyond 20 weeks (18.4%) was higher in group 1, there was no statistical difference between the two groups. There was one miscarriage in group 2. Conclusion: Women with extremely low-serum AMH levels can still have clinical pregnancy and ongoing pregnancies beyond 20 weeks after ART, though chances will be lower than women with normal ovarian reserve.

关键词： Extremely Low Antimullerian Hormone Assisted Reproduction Treatment Clinical Pregnancy Ongoing Pregnancy Miscarriage Rate

Labetalol versus Hydralazine in the Management of Severe Pre-Eclampsia at Tertiary hospitals in a Low-Resource Setting: A Randomised Controlled Trial

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Open Journal of obstetrics and gynecology 2023年第6期13卷 1058-1067页

作者： Uzoma Otutoaja Adeyemo Olabisi Timothy Emmanuel Olumide Adewara Olufunmilayo Victoria Adebara Augustine Adebayo Adeniyi Babatunde Sunday Awoyinka Raymond Akujuobi Okere Idowu Oluseyi Adebara Adewumi Bakare Mojisola Olumide Ayankunle Department of obstetrics and Gynaecology Ado-Ekiti/Federal Teaching Hospital Afe Babalola University Ido-Ekiti Nigeria Department of Paediatrics Ado-Ekiti/Federal Teaching Hospital Afe Babalola University Ido-Ekiti Nigeria

Objective: Intravenous labetalol and hydralazine are both considered first-line medications for the management of acute-onset, severe hypertension in pregnant and postpartum women. The study compared the efficacy and safety profile of intravenous labetalol and hydralazine in the control hypertension in severe pre-eclampsia. Materials and Methods: One hundred patients who presented with severe pre-eclampsia were randomized into two study groups. The fifty patients in each arm of the study received either intravenous labetalol or intravenous hydralazine for the control of blood pressure. Results: The mean age of the labetalol subjects was 28.6 ± 5.47 years while that of their hydralazine counterparts was 29.12 ± 5.77 years. The majority of respondents in both groups were primigravidae (76% vs. 78%) (P = 0.813). The number of doses of drug needed to significantly lower the mean systolic blood pressure was slightly lower in the labetalol group (2 doses) compared to the hydralazine group (5 doses) (t = 0.803Y, P = 0.977). The incidence of headaches which were the commonest complaints was comparable in both groups 8% and 10% of respondents respectively (P > 0.05). Conclusion: Although both intravenous labetalol and hydralazine are useful in patients with severe pre-eclampsia, the response to labetalol was better with comparable side effects.

关键词： Blood Pressure Hydralazine Labetalol Low-Resource Setting Severe Pre-Eclampsia Side Effects

Unified Analysis Specific to the Medical Field in the Interpretation of Medical Images through the Use of Deep Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

E-Health Telecommunication Systems and Networks 2021年第2期10卷 41-74页

作者： Tudor Florin Ursuleanu Andreea Roxana Luca Liliana Gheorghe Roxana Grigorovici Stefan Iancu Maria Hlusneac Cristina Preda Alexandru Grigorovici Faculty of General Medicine “Grigore T. Popa” University of Medicine and Pharmacy Iasi Romania Department of Surgery VI “Sf. Spiridon” Hospital Iasi Romania Department of Surgery I Regional Institute of Oncology Iasi Romania Department of obstetrics and gynecology Integrated Ambulatory of Hospital “Sf. Spiridon” Iasi Romania Department of Radiology “Sf. Spiridon” Hospital Iasi Romania Department of Endocrinology “Sf. Spiridon” Hospital Iasi Romania

Deep learning (DL) has seen an exponential development in recent years, with major impact in many medical fields, especially in the field of medical image. The purpose of the work converges in determining the importance of each component, describing the specificity and correlations of these elements involved in achieving the precision of interpretation of medical images using DL. The major contribution of this work is primarily to the updated characterisation of the characteristics of the constituent elements of the deep learning process, scientific data, methods of knowledge incorporation, DL models according to the objectives for which they were designed and the presentation of medical applications in accordance with these tasks. Secondly, it describes the specific correlations between the quality, type and volume of data, the deep learning patterns used in the interpretation of diagnostic medical images and their applications in medicine. Finally presents problems and directions of future research. Data quality and volume, annotations and labels, identification and automatic extraction of specific medical terms can help deep learning models perform image analysis tasks. Moreover, the development of models capable of extracting unattended features and easily incorporated into the architecture of DL networks and the development of techniques to search for a certain network architecture according to the objectives set lead to performance in the interpretation of medical images.

关键词： Medical Image Analysis Data Types Labels Deep Learning Models

Single-nucleus transcriptomic landscape of primate hippocampal aging

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Protein & Cell 2021年第9期12卷 695-716页

作者： Hui Zhang Jiaming Li Jie Ren Shuhui Sun Shuai Ma Weiqi Zhang Yang Yu Yusheng Cai Kaowen Yan Wei Li Baoyang Hu Piu Chan Guo-Guang Zhao Juan Carlos Izpisua Belmonte Qi Zhou Jing Qu Si Wang Guang-Hui Liu State Key Laboratory of Membrane Biology Institute of ZoologyChinese Academy of SciencesBeijing 100101China State Key Laboratory of Stem Cell and Reproductive Biology Institute of ZoologyChinese Academy of SciencesBeijing 100101China Advanced Innovation Center for Human Brain Protection National Clinical Research Center for Geriatric DisordersXuanwu Hospital Capital Medical UniversityBeijing 100053China CAS Key Laboratory of Genomic and Precision Medicine Beijing Institute of GenomicsChinese Academy of SciencesBeijing 100101China Institute for Stem Cell and Regeneration Chinese Academy of SciencesBeijing 100101China University of Chinese Academy of Sciences Beijing 100049China China National Center for Bioinformation Beijing 100101China Aging Translational Medicine Center Xuanwu HospitalCapital Medical UniversityBeijing 100053China Department of Neurosurgery Xuanwu HospitalCapital Medical UniversityBeijing 100053China Sino Danish CollegeUniversity of Chinese Academy of SciencesBeijing 101408China Sino Danish Center for Education and ResearchBeijing 101408China Department of obstetrics and gynecology Center for Reproductive MedicinePeking University Third HospitalBeijing 100191China Beijing Institute for Stem Cell and Regenerative Medicine Beijing 100101China Stem Cell Research Center Peking University Third HospitalBeijing 100191China Gene Expression Laboratory Salk Institute for Biological StudiesLa JollaCAUSA

The hippocampus plays a crucial role in learning and memory,and its progressive deterioration with age is functionally linked to a variety of human neurodegenerative diseases.Yet a systematic profiling of the aging effects on various hippocampal cell types in primates is still missing.Here,we reported a variety of new aging-associated phenotypic changes of the primate hippocampus.These include,in particular,increased DNA damage and heterochromatin erosion with time,alongside loss of proteostasis and elevated inflammation.To understand their cellular and molecular causes,we established the first single-nucleus transcriptomic atlas of primate hippocampal aging.Among the 12 identified cell types,neural transiently amplifying progenitor cell(TAPC)and microglia were most affected by aging.In-depth dissection of gene-expression dynamics revealed impaired TAPC division and compromised neuronal function along the neurogenesis trajectory;additionally elevated pro-inflammatory responses in the aged microglia and oligodendrocyte,as well as dysregulated coagulation pathways in the aged endothelial cells may contribute to a hostile microenvironment for neurogenesis.This rich resource for understanding primate hippocampal aging may provide potential diagnostic biomarkers and therapeutic interventions against age-related neurodegenerative diseases.

关键词： aging hippocampus primate single-cell RNA sequencing

Study of Differential Expression of COP9,JAK2,HSPs and NADH Genes in Taxol-Resistant Ovarian Carcinoma Tissues

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Clinical Oncology 2008年第5期5卷 373-378页

作者： Hongxia Li Department of obstetrics ＆ Gynaecology Beijing Shijitan Hospital Beijing 100038 China

OBJECTIVE To study the differential expression of COP9,JAK2,HSPS and NADH genes and their relationship with taxol resistance in ovarian carcinoma.METHODS The up-regulated genes for JAK2,HSPs and NADH,and the down-regulated COP9 gene,which have been demonstrated by a micro-array from our previous study,were examined by the reverse transcription-polymerase chain reaction(RT-PCR) and real-time-PCR in 33 tissue samples from ovarian cancer patients who previously had received taxol-based chemotherapy(Group1),and from 21 ovarian cancer cases who had never received chemotherapy before operation(Group2).RESULTS The expression rate of COP9 in Group 1 was shown to be markedly lower compared to Group 2(P = 0.000).However the expression rates of JAK2,HSPs and NADH in Group 1 were significantly higher than those in Group 2(all P = 0.000).The expression of COP9,HSPs and NADH showed no significant differences related to the histological grade.However,signifi cant higher expression of JAK2 was seen in Grade 3 compared to Grade 1～2(P = 0.000).We performed real-time PCR to conf irm the above fi ndings showing that the level of COP9 gene copies of Group 1 was much lower than that of Group 2(P = 0.007).Similarly,HSPs and NADH had significantly higher copy numbers in Group 1 compared to those patients who had not undergone chemotherapy(Group 2)(P = 0.018,P = 0.024,respectively).We also found that the JAK2 gene copy concentration in a TAX group was higher than in a non-TAX group(P = 0.001).In addition,we conf irmed a higher copy concentration of the JAK2 gene in Grade 3 compared to Grade 1～2 tumors(P = 0.000),though no signifi cant difference in the expression rates and gene copy concentrations of the 4 genes were seen among variable tumor types.CONCLUSION The down-regulation of COP9 and up-regulation of JAK2,HSPs,and NADH genes are related to the mechanism of drug-resistance in ovarian cancers.

关键词：实时的PCR 卵巢癌临床研究治疗措施

Umbilical Vein Oxytocin Injection versus Umbilical Cord Drainage in Management of Third Stage of Normal Vaginal Delivery: A Randomized Controlled Trial

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Open Journal of obstetrics and gynecology 2020年第5期10卷 634-643页

作者： Mohamed El-Bakry Lashin Department of obstetrics and gynecology Faculty of Medicine Zagazig University Zagazig Egypt

Objectives: Postpartum hemorrhage is an important cause of maternal morbidity and mortality worldwide. Different preventive strategies were tried to determine the best approach for the management of the 3rd stage of labour. We aim to determine the effect of umbilical vein oxytocin injection and umbilical cord drainage in the management of third stage of labour in normal vaginal delivery. Patients and Methods: One hundred twenty three (123) females were enrolled into this randomized controlled trial. They were aligned into three groups: 1st group (I) (cord drainage group), 2nd group (II) (oxytocin group) and 3rd group (III) (control cord traction group). The primary outcomes were duration of 3rd stage and blood loss. Results: Both group I and II had statistically significant shorter third stage duration than patients of group III (p < 0.001). Mean ± SD (7.3 ± 3.45, 4.6 ± 1.74, 9.4 ± 3.67) respectively for groups I, II, III. Also, both group I and II had statistically significant less blood loss than patients of group III (p < 0.001). Conclusion: The current study demonstrated that umbilical vein oxytocin injection and umbilical cord drainage significantly reduce the duration and amount of blood loss in the 3rd stage of labour, thus, reducing the risk of post partum hemorrhage.

关键词： Umbilical Cord Drainage Umbilical Vein Oxytocin Injection Third Stage of Labour