人工智能在心血管疾病研究和临床中的应用

本文从心血管疾病的诊断、预测、治疗和基础研究等多方面简述了人工智能(AI)在心血管疾病研究和临床中的应用,回顾了AI在这些领域的应用,分析了其面临的困难和未来前景。AI在心血管疾病的诊断和预测领域已经取得广泛进展,如AI结合心电图和心血管影像数据可实现精准诊断,AI联合心血管影像数据和其他临床数据可实现冠状动脉疾病、先天性心脏病、心力衰竭等心血管疾病的早期筛查和风险预测,但其适用范围仍有待进一步观察。此外,AI辅助的心血管介入治疗和临床决策等尚处于开发阶段,AI辅助的多组学研究也远未达到临床应用水平,是未来的主要研究方向。在此基础上,总结了AI在心血管疾病的诊断、预测、治疗和基础研究中所面临的问题,并对AI在心血管领域的应用前景进行了展望。     

多模态MRI影像组学在脑胶质瘤中的应用进展

影像组学在肿瘤的诊断、预后评估, 以及评价肿瘤对治疗的反应等方面均发挥着关键作用。多模态磁共振成像(MRI)影像组学可以将肿瘤的影像组学表现与其分子表型联系起来, 在脑胶质瘤的分级和治疗反应的预测和预后方面具有更大的优势。它利用常规和先进技术将脑肿瘤与非肿瘤性病变进行区分, 可用于脑胶质瘤的诊断和脑胶质瘤与脑转移瘤的鉴别;半自动和自动化的肿瘤分割技术也被开发用于评估脑胶质瘤的复发情况。主要对多模态MRI影像组学在预测胶质瘤重要分子生物学标志物、胶质瘤分级诊断、与脑转移瘤的鉴别诊断及评估术后复发方面的研究进展进行综述。     

人工智能技术在肺癌诊断中的研究进展和应用

随着科技的飞速发展,人工智能 （Artificial Intelligence,AI） 在医疗领域的应用愈发广泛,特别是在肺癌诊断方面备受瞩目。肺癌早期诊断对治疗和生存率至关重要,而 AI的应用有助于医生更精准地诊断肺癌,提高准确性和效率。 本文将详细介绍AI技术在肺癌诊断方面的研究进展,涵盖肺癌筛查、影像学诊断、基因突变检测、血液肿瘤标志物检测以及病理学检测等多个方面。然而,AI在肺癌诊断中的应用仍面临一些挑战,需要进一步的研究和改进。     

神经营养素与中枢神经退行性疾病

神经营养素是神经营养因子中一组形态和结构密切相关的蛋白质。近年来关于神经营养素在中枢神经退行疾病发病机制中的作用研究 ,及应用神经营养素治疗中枢神经退行性疾病的研究成为神经科学研究的一个热点。本文简述了神经营养素家族及其受体在CNS中的表达分布 ,以及其在中枢神经退行性疾病中的应用 ,为进一步应用神经营养素治疗中枢神经退行性疾病提供资料。     

几种新型神经上皮肿瘤病理学研究进展

不同类型的脑肿瘤在预后和治疗策略上有所不同，因此，脑肿瘤诊断中的分类十分重要。新版的ＷＨＯ中枢神经系统分类增加了多形性黄色星形细胞瘤、中枢神经细胞瘤、促纤维增生性婴儿型星形细胞瘤／神经节胶质瘤、胚胎发育不良性神经上皮肿瘤。这些肿瘤近年来国外报道逐渐增...     

人工智能在口腔疾病诊断中的研究进展

人工智能（AI）作为一种新兴的科学技术逐渐渗透到各个专业领域并开拓未知之地。目前,AI在医学领域推动智能医学的迅速发展,是现代医学未来的发展方向之一。文章简要阐述了AI的基本概念,综述了AI在口腔外科领域、口腔内科领域、口腔修复学领域、口腔正畸学领域诊断口腔疾病的发展现状和存在的问题及未来展望。现阶段AI辅助诊断处于初级阶段,随着临床诊疗数字化技术和便携式实验室诊断仪器的研发,将扩大AI学习的数据来源,使得数据不仅仅局限于传统的影像资料,还包括疾病生物标志物、各类光谱信号、大数据文本资料等,甚至是打破数据之间的壁垒,利用各类数据整合出混合数据库,建立临床大数据疾病预警系统,诊病于未病之时。     

甲状腺结节AI超声辅助诊断系统在住院医师规范化培训教学中的应用

目的：探讨甲状腺结节AI超声辅助诊断系统在住院医师规范化培训教学中的应用效果。方法：选取2019年1月至2019年12月在广东省第二人民医院行甲状腺手术及超声检查的108名患者，共155个甲状腺结节，由两位2年级超声专业住院医师采用2017年美国放射学会发布的甲状腺影像报告与数据系统甲状腺结节超声指南（ACR TI-RADS）评估甲状腺结节；之后两位住院医师联合基于ACR TI-RADS超声特征的AI超声辅助诊断系统的预测结果再次评估上述结节。诊断标准以甲状腺结节手术病理结果作为金标准。结果：通过AI超声辅助诊断系统后，两位住院医师诊断甲状腺结节的AUC均有所提高。另外，两位住院医师联合AI超声辅助诊断系统在识别甲状腺结节的点状强回声方面的能力均得到提高，其中一位医师在识别甲状腺结构、回声、形状、分叶或不规则方面也有所提高。结论：与传统教学模式相比，应用甲状腺结节的AI超声辅助诊断系统可以帮助住院医师在较短的时间内提高掌握ACR TI-RADS指南的熟悉度，提高对结节超声特征的识别能力，缩短培训周期，起到辅助临床教学培训的作用。     

影像核医学在骨科中的应用研究

近年来,影像核医学技术发展迅速,这大大提高了诊断准确率,为人类健康事业做出巨大贡献.本文首先从影像核医学的定义以及发展历程出发,介绍了影像核医学的相关概念以及诊断仪器,以及几种主流的影像核医学技术应用概况,并着重探讨了影像核医学在骨科中的应用.并在最后对影响我国核医学的发展方向以及应用做出了总结展望.     

p53,c—erbB1,c—myc中p16基因蛋白产物在人脑胶质瘤中的表达

目的 为了探明癌基因ｃ－ｅｒｂＢ１、ｃ－ｍｙｃ，抑癌基因ｐ５３和ｐ１６在胶质瘤发生发展中的作用，以及上述基因蛋白检测对胶质瘤诊断、分级的临床意义。方法 用免疫组化ＡＢＣ法检测４种癌基因蛋白产物在６５例人脑胶质瘤中的表达，并分析与胶质瘤病理分级间的关系。结果 ｐ５３、ｃ－ｅｒｂＢ１、ｃ－ｍｙｃ过度表达率随胶质瘤级别升高而逐渐升高，前两者在胶质瘤良性组和高度恶性组间差异有显著性（Ｐ〈０．０５）；ｐ１６     

p53、c-erbB1、c-myc和p16基因蛋白产物在人脑胶质瘤中的表达

目的为了探明癌基因ｃ－ｅｒｂＢ１、ｃ－ｍｙｃ，抑癌基因ｐ５３和ｐ１６在胶质瘤发生发展中的作用，以及上述基因蛋白检测对胶质瘤诊断、分级的临床意义。方法用免疫组化ＡＢＣ法检测４种癌基因蛋白产物在６５例人脑胶质瘤中的表达，并分析与胶质瘤病理分级间的关系。结果ｐ５３、ｃ－ｅｒｂＢ１、ｃ－ｍｙｃ过度表达率随胶质瘤级别升高而逐渐升高，前两者在胶质瘤良性组和高度恶性组间差异有显著性（Ｐ＜０．０５）；ｐ１６在高度恶性组表达缺失率高于其它组，但差异不显著；４种癌基因、抑癌基因在胶质瘤中有协同表达。结论上述４种基因在胶质瘤的形成和发展中发挥着不同程度的作用，对ｐ５３、ｃ－ｅｒｂＢ１基因蛋白的检测或多种癌基因蛋白联合检测，对胶质瘤的病理分级和预后判断有积极的意义。     

颅内多发病变的临床病理学分析

目的 探讨颅内多发病变的临床病理学特征。方法 对2005年1月至2009年12月期间在首都医科大学宣武医院接受治疗病例中,影像学上为颅内多发病变的62例患者的临床、影像以及病理学资料进行回顾性分析。结果 62例中男32例,女30例,平均发病年龄37.4岁,平均病程11.6个月。病灶可累及大脑半球各叶、基底节区、脑干和小脑等部位,以幕上受累较为多见。病理检查结果为：胶质瘤13例,转移瘤13例,中枢神经系统感染12例,免疫介导的炎性脱髓鞘病8例,中枢神经系统原发淋巴瘤5例,血管炎3例,线粒体脑病2例,静脉窦血栓形成2例,Rosai-Dorfman病2例,放射性脑病2例。其中,线粒体脑病、静脉窦血栓形成以皮层受累为主,转移瘤和血源性感染主要累及灰白质交界区,胶质瘤、脱髓鞘疾病和放射性脑病以白质病变为主,血管炎表现为皮层和皮层下白质的病变。结论 多种肿瘤和非肿瘤性疾病在影像学上可以表现为颅内多发病变,其中以胶质瘤、转移瘤和中枢神经系统感染较为多见。积极开展颅内多发病变脑组织活检,临床、影像与病理学密切结合,是提高颅内多发病变诊断水平行之有效的方法。     

The use of neuroimaging to guide the histologic diagnosis of central nervous system lesions

Recent advances in neuroimaging techniques, particularly in magnetic resonance imaging, have led to substantially improved spatial anatomic resolution such that subtle or small central nervous system lesions, which could go undetected on gross examination of brain sections, are now readily identified on imaging. Although neuroimaging is generally considered the surrogate of gross neuropathology, it is still not a substitute for tissue diagnosis. Rather, it can be a valuable tool for the surgical pathologist in the process of formulating a differential diagnosis based on location and imaging features, as well as in identifying radiologic/pathologic discordance, such as the possible undersampling of a heterogenous glioma, which could lead to underestimation of the tumor grade. The following review focuses on the application of neuroimaging techniques, mainly magnetic resonance imaging, to the histologic diagnosis of central nervous system lesions, and the correlation of imaging features of infiltrative gliomas with histologic findings pertinent to tumor grading. The use of advanced functional magnetic resonance methods, specifically diffusion-weighted imaging, perfusion-weighted imaging, and magnetic resonance spectroscopy is also discussed, as well as the common pitfalls in imaging interpretation.     

Introduction of autopsy imaging redefines the concept of autopsy: 37 cases of clinical experience

A new autopsy imaging (AI) system was introduced at the Research Center Hospital for Charged Particle Therapy (RCCPT) in January 2000. Autopsy imaging is a postmortem and preautopsy diagnostic procedure using magnetic resonance imaging (MRI). Scanning is performed with a 1.5 Tesla MRI system before autopsy. The AI results are reported to the pathologist and, in light of this information, autopsy is performed with minute precision. Autopsy imaging was performed on 37 cancer cases. In seven cases, AI was less informative than the autopsy, but in 30 cases, more precise reports on the final diagnosis were available with the combined application of autopsy and AI than autopsy alone, particularly in eight limited autopsy cases. Thus, AI provides critical and supplementary information for autopsy; furthermore, AI itself is a unique imaging system of great importance.     

人工智能在泌尿疾病诊断中的应用现状与趋势

近年来,随着数据储存、图像处理、模式识别和机器学习等技术的进步,人工智能在泌尿疾病的诊疗方面得到了广泛的应用。基于影像学和组织病理学等海量的生物医学大数据,人工智能技术可以让医务工作者对泌尿系肿瘤、泌尿系结石、泌尿系感染、泌尿功能异常和勃起功能障碍等几类泌尿疾病的诊断更为精准,让治疗更加个性化。然而,目前人工智能诊疗大多处于研究阶段,在实际的应用中尚存在一些问题。本文以辅助诊断为线索,对人工智能方法在前列腺癌、膀胱癌、肾癌、尿路结石、尿频、勃起功能障碍等常见泌尿疾病的应用和研究情况予以综述,并进一步探讨其存在的问题和未来发展方向。     

Mesenchymal, IMon-Meningothelial Tumors of the Central Nervous System

The spectrum of non-meningothelial mesenchymal tumors that may arise within the central nervous system is presented, based on the current classification of soft tissue tumors. Among malignant types, hemangiopericytoma, rhabdomyosarcoma, mesenchymal chondrosarcoma, and malignant fibrous histiocytoma are the most frequent ones. Rare tumor entities are mentioned. As in soft tissue sarcomas, diagnosis is mainly based on light and electron microscopy, while immunohistochemistry can improve accuracy of diagnosis.     

中枢神经系统真菌感染诊断治疗进展

中枢神经系统真菌感染发生率近年有逐渐增高之趋势,颅内真菌感染可分为弥漫性感染和局灶性感染,临床表现多为脑膜炎、脑膜脑炎引起的发热和颅高压症状,以及由颅内占位性病变所致的局灶性神经缺损症状。中枢神经系统真菌感染的诊断需将病史、流行病学、基础疾病、临床表现、影像学表现和各项实验室检查结果等综合分析,脑组织或脑脊液标本中找到真菌是诊断的金标准。中枢神经系统真菌感染的治疗原则是有效控制致病危险因素,使用有效抗真菌药物,对真菌脓肿、肉芽肿等进行积极手术干预。同时应积极探索新的诊断、治疗方法,以期改善患者预后。     

The new WHO classification of tumors of the nervous system 2000. Pathology and genetics

New developments in neuro-oncology have prompted an update of the World Health Organization (WHO) classification of tumors of the nervous system. Major changes include the addition of new entities and the refinement of criteria for the diagnosis and grading of various neoplasms, in particular the meningiomas. As novel clinico-pathological entities, the chordoid glioma of the third ventricle, the atypical teratoid/rhabdoid tumor (AT/RT), the solitary fibrous tumor, and the perineurioma have been listed. The former lipomatous medulloblastoma of the cerebellum, previously incorporated in the family of embryonal tumors, is now classified as cerebellar liponeurocytoma. The term mixed pineocytoma/pineoblastoma has been replaced by pineal parenchymal tumor of intermediate differentiation. Furthermore, the large cell medulloblastoma and the tanycytic ependymoma were established as novel tumor variants. A separate chapter on the peripheral neuroblastic tumors has now been included in the classification. Substantial revisions were introduced in the meningioma chapter. For both atypical meningioma WHO grade II and anaplastic meningioma WHO grade III, histopathological criteria are now precisely defined. An important new addition to the WHO 2000 classification of nervous system tumors is the inclusion of molecular pathology findings. With this combination of pathology and genetics it has set the stage for a new format of the WHO tumor classification series.     

A metabolomic data fusion approach to support gliomas grading

Magnetic resonance imaging (MRI) is the current gold standard for the diagnosis of brain tumors. However, despite the development of MRI techniques, the differential diagnosis of central nervous system (CNS) primary pathologies, such as lymphoma and glioblastoma or tumor‐like brain lesions and glioma, is often challenging. MRI can be supported by in vivo magnetic resonance spectroscopy (MRS) to enhance its diagnostic power and multiproject‐multicenter evaluations of classification of brain tumors have shown that an accuracy around 90% can be achieved for most of the pairwise discrimination problems. However, the survival rate for patients affected by gliomas is still low. The High‐Resolution Magic‐Angle‐Spinning Nuclear Magnetic Resonance (HR‐MAS NMR) metabolomics studies may be helpful for the discrimination of gliomas grades and the development of new strategies for clinical intervention. Here, we propose to use T₂‐filtered, diffusion‐filtered and conventional water‐presaturated spectra to try to extract as much information as possible, fusing the data gathered by these different NMR experiments and applying a chemometric approach based on Multivariate Curve Resolution (MCR). Biomarkers important for glioma's discrimination were found. In particular, we focused our attention on cystathionine (Cyst) that shows promise as a biomarker for the better prognosis of glioma tumors.     

Single myelin fiber imaging in living rodents without labeling by deep optical coherence microscopy

Myelin sheath disruption is responsible for multiple neuropathies in the central and peripheral nervous system. Myelin imaging has thus become an important diagnosis tool. However, in vivo imaging has been limited to either low-resolution techniques unable to resolve individual fibers or to low-penetration imaging of single fibers, which cannot provide quantitative information about large volumes of tissue, as required for diagnostic purposes. Here, we perform myelin imaging without labeling and at micron-scale resolution with >300-μm penetration depth on living rodents. This was achieved with a prototype [termed deep optical coherence microscopy (deep-OCM)] of a high-numerical aperture infrared full-field optical coherence microscope, which includes aberration correction for the compensation of refractive index mismatch and high-frame-rate interferometric measurements. We were able to measure the density of individual myelinated fibers in the rat cortex over a large volume of gray matter. In the peripheral nervous system, deep-OCM allows, after minor surgery, in situ imaging of single myelinated fibers over a large fraction of the sciatic nerve. This allows quantitative comparison of normal and Krox20 mutant mice, in which myelination in the peripheral nervous system is impaired. This opens promising perspectives for myelin chronic imaging in demyelinating diseases and for minimally invasive medical diagnosis.     

La classification de l’OMS 2021 des tumeurs du système nerveux central

Rapid technical advances in molecular biology allowed for the identification of key genetic alterations in central nervous system (CNS) tumors. Our ever-expanding knowledge of brain tumor genetics and the development of new technologies, such as DNA-methylation profiling, required an update of the 2016 fourth edition of the WHO classification of CNS tumors. Updates were regularly published by the Consortium to Inform Molecular Practical Approaches to CNS Tumor Taxonomy-Not Official WHO (c-IMPACT-NOW) until the publication of the fifth edition of the WHO classification of CNS tumors in 2021. In that edition, new types and subtypes are introduced and criteria for histo-molecular diagnostic and grading are refined, especially for diffuse gliomas. The definition of a broad category “diffuse glioma, pediatric subtype” (low or high grade) is a major improvement of the classification. Moreover, the nomenclature was simplified and aligned with that of other blue books. The 2021 edition truly advances the role of molecular diagnostics in CNS tumor classification. Methyloma profiling may become a cornerstone of CNS tumor diagnostic. The new WHO classification will lead to better management of brain tumor patients.