全文获取类型
收费全文 | 5359篇 |
免费 | 386篇 |
国内免费 | 65篇 |
专业分类
耳鼻咽喉 | 69篇 |
儿科学 | 17篇 |
妇产科学 | 21篇 |
基础医学 | 995篇 |
口腔科学 | 126篇 |
临床医学 | 760篇 |
内科学 | 196篇 |
皮肤病学 | 34篇 |
神经病学 | 257篇 |
特种医学 | 1474篇 |
外科学 | 369篇 |
综合类 | 521篇 |
预防医学 | 282篇 |
眼科学 | 84篇 |
药学 | 142篇 |
3篇 | |
中国医学 | 46篇 |
肿瘤学 | 414篇 |
出版年
2024年 | 3篇 |
2023年 | 73篇 |
2022年 | 118篇 |
2021年 | 145篇 |
2020年 | 140篇 |
2019年 | 109篇 |
2018年 | 115篇 |
2017年 | 133篇 |
2016年 | 138篇 |
2015年 | 152篇 |
2014年 | 342篇 |
2013年 | 293篇 |
2012年 | 300篇 |
2011年 | 334篇 |
2010年 | 261篇 |
2009年 | 314篇 |
2008年 | 332篇 |
2007年 | 312篇 |
2006年 | 270篇 |
2005年 | 224篇 |
2004年 | 188篇 |
2003年 | 175篇 |
2002年 | 168篇 |
2001年 | 154篇 |
2000年 | 135篇 |
1999年 | 144篇 |
1998年 | 104篇 |
1997年 | 97篇 |
1996年 | 81篇 |
1995年 | 93篇 |
1994年 | 79篇 |
1993年 | 63篇 |
1992年 | 49篇 |
1991年 | 49篇 |
1990年 | 14篇 |
1989年 | 23篇 |
1988年 | 13篇 |
1987年 | 10篇 |
1986年 | 7篇 |
1985年 | 15篇 |
1984年 | 9篇 |
1983年 | 3篇 |
1982年 | 4篇 |
1981年 | 7篇 |
1980年 | 6篇 |
1979年 | 5篇 |
1978年 | 3篇 |
1977年 | 1篇 |
1976年 | 2篇 |
1973年 | 1篇 |
排序方式: 共有5810条查询结果,搜索用时 15 毫秒
1.
We propose a Deep learning-based weak label learning method for analyzing whole slide images (WSIs) of Hematoxylin and Eosin (H&E) stained tumor tissue not requiring pixel-level or tile-level annotations using Self-supervised pre-training and heterogeneity-aware deep Multiple Instance LEarning (DeepSMILE). We apply DeepSMILE to the task of Homologous recombination deficiency (HRD) and microsatellite instability (MSI) prediction. We utilize contrastive self-supervised learning to pre-train a feature extractor on histopathology tiles of cancer tissue. Additionally, we use variability-aware deep multiple instance learning to learn the tile feature aggregation function while modeling tumor heterogeneity. For MSI prediction in a tumor-annotated and color normalized subset of TCGA-CRC (n=360 patients), contrastive self-supervised learning improves the tile supervision baseline from 0.77 to 0.87 AUROC, on par with our proposed DeepSMILE method. On TCGA-BC (n=1041 patients) without any manual annotations, DeepSMILE improves HRD classification performance from 0.77 to 0.81 AUROC compared to tile supervision with either a self-supervised or ImageNet pre-trained feature extractor. Our proposed methods reach the baseline performance using only 40% of the labeled data on both datasets. These improvements suggest we can use standard self-supervised learning techniques combined with multiple instance learning in the histopathology domain to improve genomic label classification performance with fewer labeled data. 相似文献
2.
《Cancer radiothérapie》2022,26(8):1008-1015
PurposeDeep learning (DL) techniques are widely used in medical imaging and in particular for segmentation. Indeed, manual segmentation of organs at risk (OARs) is time-consuming and suffers from inter- and intra-observer segmentation variability. Image segmentation using DL has given very promising results. In this work, we present and compare the results of segmentation of OARs and a clinical target volume (CTV) in thoracic CT images using three DL models.Materials and methodsWe used CT images of 52 patients with breast cancer from a public dataset. Automatic segmentation of the lungs, the heart and a CTV was performed using three models based on the U-Net architecture. Three metrics were used to quantify and compare the segmentation results obtained with these models: the Dice similarity coefficient (DSC), the Jaccard coefficient (J) and the Hausdorff distance (HD).ResultsThe obtained values of DSC, J and HD were presented for each segmented organ and for the three models. Examples of automatic segmentation were presented and compared to the corresponding ground truth delineations. Our values were also compared to recent results obtained by other authors.ConclusionThe performance of three DL models was evaluated for the delineation of the lungs, the heart and a CTV. This study showed clearly that these 2D models based on the U-Net architecture can be used to delineate organs in CT images with a good performance compared to other models. Generally, the three models present similar performances. Using a dataset with more CT images, the three models should give better results. 相似文献
3.
4.
目的探讨多排螺旋CT(MSCT)对气管憩室的诊断价值。方法选取分析68例气管憩室的临床及影像学资料。结果本组68例共发现气管憩室82个,其中59例为单发,9例为多发(≥2个),单发占86.76%,多发占13.24%,多发气管憩室中5例为2个憩室,3例为3个憩室,1例为4个憩室;本组气管憩室大小不等,其中最大直径44.00 mm,最小直径1.50 mm,平均直径为26(23~35)mm。82个气管憩室形状多样,圆形或类圆形(囊腔样)为62个,气泡样10个,烧瓶样6个,凹槽样2个,三角样2个;MSCT能显示气管憩室与气管为单一细管或多个管道相通,其中2例气管憩室合并感染,本组68例中有慢性支气管炎、肺气肿或慢性支气管炎合并肺气肿的病例共为38例,占55.88%。结论MSCT可以清晰显示气管憩室与气管的通道、气管憩室的部位、数量、形状和内容物等情况,对气管憩室的诊断有重要价值。 相似文献
5.
目的 建立本单位应用光学表面监测系统(OSMS)门控技术在左侧乳腺癌深吸气屏气(DIBH)放疗的基本流程,比较应用OSMS与CBCT确定左侧乳腺癌DIBH放疗摆位误差的一致性。方法 20例左侧乳腺癌患者采用DIBH方法治疗,OSMS与模拟定位DIBH体表外轮廓配准,CBCT扫描与模拟定位CT配准各记录得到误差数据,数据包括左右(x)、上下(y)、前后(z)方向平移误差和旋转误差Rx、Ry、Rz。采用Pearson法分析两者相关性,Bland-Altman法检验两者一致性。结果 两种方法呈正相关,x、y、z方向平移误差以及Rx、Ry、Rz方向旋转误差的相关系数分别为0.84、0.74、0.84、0.65、0.41、0.54(P<0.01),95%CI值分别为-0.37~0.42 cm、-0.39~0.41 cm、-0.29~0.49cm和-2.9°~1.4°、-2.6°~1.4°、-2.4°~2.5°,均<5mm和3°。20例左侧乳腺癌DIBH放疗患者系统误差<0.18cm,随机误差<0.24cm。结论 左侧乳腺癌DIBH放疗中应用OSMS与CBCT两种方式确定与模拟定位状态误差具有一致性,CBCT图像引导基础上使用无辐射的OSMS验证位置信息是安全可靠的。 相似文献
6.
目的 探讨迭代算法对超低剂量CT肺部扫描图像质量的影响。方法 采用不同方案对胸部仿真体模行CT扫描。超低剂量方案:管电压分为80和100 kV组,每组分别采用10、15、20、25、30 mAs扫描。常规低剂量方案:120 kV、30 mAs。各方案均采用滤波反投影法(FBP组)和迭代算法重建(迭代组)。比较各方案的肺组织噪声和有效剂量(E)。结果 管电流和管电压一定时,迭代组的肺组织噪声均低于FBP组,差异均有统计学意义(t=1.102~8.070,P<0.05)。管电流一定时,80 kV时FBP组的肺组织噪声均高于100 kV时FBP组,80 kV时迭代组的肺组织噪声均低于100 kV时FBP组,差异均有统计学意义(t=-8.639~7.841,P<0.05)。与常规低剂量方案FBP组相比,各超低剂量方案FBP组的肺组织噪声明显增加,80 kV时10、15、20 mAs迭代组的肺组织噪声明显增加,100 kV时15、20、25、30 mAs迭代组的肺组织噪声明显降低,差异均有统计学意义(t=-8.140~23.028,P<0.05)。80 kV时25、30 mAs和100 kV时10 mAs迭代组的肺组织噪声与常规低剂量方案FBP组比较,差异均无统计学意义(P>0.05)。80 kV时25、30 mAs和100 kV时10、15、20、25、30 mAs的E较常规低剂量组分别降低了75.9%、71.0%、79.8%、70.4%、60.3%、50.2%、40.0%。结论 超低剂量方案(100 kV、10 mAs)迭代算法组的图像质量与常规低剂量方案FBP组相当,且辐射剂量明显降低。 相似文献
7.
8.
9.
B.R. Mussmann S.D. Mørup P.M. Skov S. Foley A.S. Brenøe F. Eldahl G.M. Jørgensen H. Precht 《Radiography》2021,27(1):1-7
IntroductionOrgan-based tube current modulation (OBTCM) is designed for anterior dose reduction in Computed Tomography (CT). The purpose was to assess dose reduction capability in chest CT using three organ dose modulation systems at different kVp settings. Furthermore, noise, diagnostic image quality and tumour detection was assessed.MethodsA Lungman phantom was scanned with and without OBTCM at 80–135/140 kVp using three CT scanners; Canon Aquillion Prime, GE Revolution CT and Siemens Somatom Flash. Thermo-luminescent dosimeters were attached to the phantom surface and all scans were repeated five times. Image noise was measured in three ROIs at the level of the carina. Three observers visually scored the images using a fivestep scale. A Wilcoxon Signed-Rank test was used for statistical analysis of differences.ResultsUsing the GE revolution CT scanner, dose reductions between 1.10 mSv (12%) and 1.56 mSv (24%) (p < 0.01) were found in the anterior segment and no differences posteriorly and laterally. Total dose reductions between 0.64 (8%) and 0.91 mSv (13%) were found across kVp levels (p < 0.00001). Maximum noise increase with OBTCM was 0.8 HU. With the Canon system, anterior dose reductions of 6–10% and total dose reduction of 0.74–0.76 mSv across kVp levels (p < 0.001) were found with a maximum noise increase of 1.1 HU. For the Siemens system, dose increased by 22–51% anteriorly; except at 100 kVp where no dose difference was found. Noise decreased by 1 to 1.5 HU.ConclusionOrgan based tube current modulation is capable of anterior and total dose reduction with minimal loss of image quality in vendors that do not increase posterior dose.Implications for practiceThis research highlights the importance of being familiar with dose reduction technologies. 相似文献
10.
《Radiography》2022,28(4):1080-1086
IntroductionImage interpretation is a required capability for all UK pre-registration programmes in diagnostic radiography to meet the needs of graduate practice. It also provides a potential educational foundation for future advanced clinical practice. The aim of this study was to explore how image interpretation education is designed, delivered, and assessed within contemporary UK pre-registration diagnostic radiography programmes.MethodsQualitative content analysis of open-source image interpretation curriculum data extracted from UK Higher Education Institute (HEI) websites.ResultsExtracted search data was initially coded and three overarching themes emerged, image interpretation education vision, operationalisation, and delivery and assessment.ConclusionThis study identified significant heterogeneity in all aspects of UK pre-registration image interpretation education which may suggest an equal heterogeneity can be expected in the image interpretation knowledge, skill, confidence between newly registered practitioners.Implications for practiceThere may be a need for clearer expectations on HEIs by professional and regulatory bodies to ensure consistency in pre-registration image interpretation education. 相似文献