基于定量影像组学的乳腺肿瘤良恶性诊断

乳腺癌是女性致死率最高的恶性肿瘤之一。为提高诊断效率,提供给医生更加客观和准确的诊断结果。借助影像组学的方法,利用公开数据集BreaKHis中82例患者的乳腺肿瘤病理图像,提取乳腺肿瘤病理图像的灰度特征、Haralick纹理特征、局部二值模式(LBP)特征和Gabor特征共139维影像组学特征,并用主成分分析(PCA)对影像组学特征进行降维,然后利用随机森林(RF)、极限学习机(ELM)、支持向量机(SVM)、k最近邻(kNN)等4种不同的分类器构建乳腺肿瘤良恶性的诊断模型,并对上述不同的特征集进行评估。结果表明,基于支持向量机的影像组学特征的分类效果最好,准确率能达到88.2%,灵敏性达到86.62%,特异性达到89.82%。影像组学方法可为乳腺肿瘤良恶性预测提供一种新型的检测手段,使乳腺肿瘤良恶性临床诊断的准确率得到很大提升。     

新型冠状病毒肺炎患者临床及CT影像特点分析

目的:探讨新型冠状病毒肺炎（coronavirus disease 19,COVID-19）患者临床及CT影像特点。方法:回顾性分析2020年1—3月广安市收治的30例COVID-19患者的临床资料和胸部CT影像学资料。将23例普通型患者设为普通组,7例重型或危重型患者设为重症组。分析30例COVID-19患者的胸部影...     

基于影像组学的肺癌分型预测

目的 基于影像组学特征对肺癌中的两大亚型分类（小细胞肺癌与非小细胞肺癌）进行分型预测。 方法 在131名小细胞肺癌与非小细胞肺癌患者中(其中训练集包含119人,测试集中包含12人),从手动分割的病灶区域提取107维组学特征,使用R统计学软件中的FSelector包对影像组学特征进行关键特征筛选,构建支持向量机模型和k折交叉验证模型对肺癌患者的病理进行表型分类和验证,通过绘制受试者工作特征曲线（ROC曲线）图和计算曲线下面积（AUC）数值来对训练集和测试集中的肺癌分型预测效果进行评估。 结果 挑选出20个主要的影像组学特征用于小细胞肺癌与非小细胞肺癌的分型鉴别,这些特征对于训练集和测试集中的小细胞肺癌与非小细胞肺癌均有较好的区分能力。在测试集中,预肺癌亚型分类的准确率为75%,组学特征的AUC结果为0.69。 结论 通过构建独特的影像组学特征,以用作区分小细胞肺癌与非小细胞肺癌的诊断因素。这对实现非侵入性的肺癌病理有效分型预测,指导肺癌患者后续治疗方案的选择具有重要指导意义。     

新型冠状病毒肺炎患者急诊科转运路径

2019年12月以来,武汉市暴发新型冠状病毒肺炎(COVID-19),并迅速蔓延至全国各地。为了有效防控疾病的蔓延,大部分省市均启动限制交通、出入等措施,这给患者的急诊转运流程带来了巨大的挑战。为了有效促使患者顺利入院接受救治,四川大学华西医院急诊科采用了一种创新医疗隔离运输系统以转运新型冠状病毒肺炎患者,并应用于首例患者的急诊转运,最终使该患者顺利入院,且转运途中病情稳定,按计划进行治疗,未发生二次感染病例。     

基于影像组学和剂量组学的放射性肺炎预测研究

目的：旨在利用影像组学和剂量组学的多组学方法,建立并验证一个有效的基于CT图像的放射性肺炎（RP）预测模型。方法：对2019年至2021年在广州医科大学附属肿瘤医院接受放疗的91例非小细胞肺癌患者进行回顾性分析。将除去临床靶区的全肺（Lung-CTV）作为感兴趣区域,从Lung-CTV区域的CT图像和剂量分布中提取影像组学和剂量组学特征。将单独的剂量体积直方图（DVH）特征、影像组学结合DVH(radio+DVH)特征、影像组学结合剂量组学（radio+dose）特征,分别输入11个不同的分类器来构建预测模型,采用五倍交叉验证法来完成分类实验。利用接受者操作特征（ROC）曲线下的面积（AUC）、准确性、精确性、召回率和F1值来评估预测模型的性能。结果：与DVH模型相比,radio+DVH和radio+dose的AUC值更高,差异有统计学意义（P<0.05）。与DVH和radio+DVH模型相比,radio+dose的准确率和F1值更高,差异有统计学意义（P<0.05）。结论：使用基于机器学习的影像组学和剂量组学的多组学方法预测RP的性能更好,有望为临床治疗提供指导。     

新型冠状病毒肺炎疫情下医学生的参与及其启示

新型冠状病毒肺炎(COVID-19)疫情流行期间,医学教育受到了很大的影响.关于医学生是否应该以及通过何种方式参与疫情防控,全球争议不断.本文对COVID-19疫情期间医学生所面临的困境以及实际的参与情况进行回顾与总结,为医学教育对重大公共卫生事件的应对提供参考.     

基于影像组学的脑脊液细胞分类方法

目的：基于影像组学构建出更为高效、准确的脑脊液细胞判别模型。方法：回顾性收集3331张脑脊液细胞显微图像,其中吞噬细胞167张、单核细胞332张、淋巴细胞1081张、中性粒细胞1751张。首先在显微图像上分割出细胞核、细胞核凸包区域和细胞核凸包区域的部分细胞质,然后设计3种细胞核形状特征,即圆度、凸度、坚固性。针对细胞核、凸包区域和凸包区域的部分细胞质设计48种颜色特征。基于细胞核凸包区域提取4 676种纹理特征。结果：共提取了4 727个影像组学特征,在经过ANOVA和LASSO特征选择之后,保留了519个特征,且形状特征和颜色特征都得到了较高比例的保留（100.0%, 66.7%）。特征选择之后,利用SMOTE数据增强和SVM分类器在测试集上进行预测,各项评价指标Accuracy、Sensitivity、Specificity、Precision、F1＿score、AUC高达0.953、0.948、0.990、0.961、0.955、0.996。结论：本文提出的新的细胞显微图像特征提取方案和分类模型对细胞分类问题非常有效,且避免了细胞质分割的难题,无需分割细胞,只需分割细胞核和细胞...     

阿尔茨海默病海马结构异常的影像组学研究

目的 探讨阿尔茨海默病 (AD) 患者的左右侧海马影像组学特征,建立和比较左右侧海马的影像组学分类模型,并分析其在AD患者诊断中的价值。方法 前瞻性对照研究。纳入2016年9月—2018年6月在浙江省人民医院记忆专科门诊就诊的59例AD患者为AD组,健康促进中心44名志愿者为正常对照组(NC组)。采用 GE 3.0 T MR成像系统对两组受试者行全脑扫描,分别获取三维磁化准备快速梯度回波成像序列 (MPRAGE)。使用一种基于学习的可变形模型对左右侧海马进行分割。对分割后的左右侧海马两组数据分别进行特征计算和特征选择,基于选择的特征建立logistic回归模型。结果 经过计算后两组数据分别得到385个特征。左右侧海马数据经过特征选择后分别剩下5个特征。右侧海马logistic回归模型评价指标的准确性、曲线下面积、特异度、灵敏度、阳性预测值、阴性预测值分别为0.69、0.74、50%、83%、68%、70%,左侧海马分别为0.75、0.83、79%、72%、81%、69%。结论 海马的影像组学特征具有作为诊断AD的生物标志物的潜力。左侧和右侧的海马影像组学模型有助于AD的诊断,其中左侧海马模型的诊断价值高于右侧。     

基于超声影像组学的原发性肝细胞癌分级预测

目的:针对原发性肝细胞癌（HCC）肿瘤分级预测难题,提出一种基于灰阶超声成像的影像组学预测模型。方法:首先,由超声医生对肿瘤区域进行手动分割,其次,采用影像组学方法对肿瘤区域提取形状、一阶统计、纹理特征,计算特征间Pearson相关系数剔除冗余特征,最后通过单变量分析筛选得到特征子集,采用LASSO构建HCC分级预测模型;利用留一法计算模型的受试者操作特性曲线下的面积（AUC）评估模型对HCC分级的预测能力。结果:利用43例经手术病理证实的HCC患者的灰阶超声图像构建HCC分级预测模型,所建模型由6个与分级高度相关的影像特征组成,模型具有较强的预测能力（AUC=0.76）。结论:基于灰阶超声成像的影像特征与HCC分级高度相关,所建影像组学模型能够较好地预测HCC分级。     

新型冠状病毒肺炎武汉一线支援队华西医疗队驻地管理

随着新型冠状病毒肺炎(简称新冠肺炎)(COVID-19)确诊病例的增加,武汉疫情防控难度增大,四川大学华西医院再次派出第三批医疗队到武汉支援。为了确保医疗队员在紧张繁重的新冠肺炎救治工作后有一个安全安心的休息环境,做好医疗队驻地的全方位管理至关重要。现总结华西医疗队驻地的管理经验,为抗击疫情的支援医疗团队提供参考。     

Epidemiological analysis of COVID-19 and practical experience from China

The rapid spread of the epidemic has aroused widespread concern in the international community. Severe acute respiratory syndrome coronavirus 2 (SARS-COV-2) was first reported in China, with bats as the likely original hosts and pangolins as potential intermediate hosts. The current source of the disease is mainly patients infected with SARS-COV-2. Patients in the incubation period may also become sources of infection. The virus is mainly transmitted via respiratory droplets and contact, and the population is generally susceptible. The epidemic has progressed through the local outbreak stage and community transmission stage due to exposure at Wuhan's Huanan wholesale seafood market and is now in the stage of large-scale transmission due to the spread of the epidemic. The basic productive number (R0) at the beginning of the epidemic was 2.2, with an average incubation period of 5.2 days. The proportion of critically ill patients was 23.4%, the mortality rate was lower than those of SARS and Middle East respiratory syndrome, and 96.5% of deaths occurred in Hubei Province, where the outbreak occurred first. Among them, elderly men with underlying diseases had a higher mortality rate. Chinese medical staff have summarized a set of effective strategies and methods in the diagnosis and treatment of this disease that are worthy of reference for their international counterparts. With powerful government intervention and the efforts of Chinese medical staff, China's outbreak has gradually improved.     

基于机器学习的新型冠状病毒(COVID-19)疫情分析及预测

本研究采用数学建模的方式,在有限的数据下,通过机器学习对近期爆发的新型冠状病毒(COVID-19)肺炎确诊人数趋势进行了预测,根据有关部门发布的信息,预测了疫情拐点出现的时间,并对比了各省预计最终确诊人数所占的比例,以此为依据,大致划分了疫情的严重程度,对各省市人民防护工作有指导意义。     

Understanding of COVID-19 based on current evidence

Since December 2019, a series of unexplained pneumonia cases have been reported in Wuhan, China. On 12 January 2020, the World Health Organization (WHO) temporarily named this new virus as the 2019 novel coronavirus (2019-nCoV). On 11 February 2020, the WHO officially named the disease caused by the 2019-nCoV as coronavirus disease (COVID-19). The COVID-19 epidemic is spreading all over the world, especially in China. Based on the published evidence, we systematically discuss the characteristics of COVID-19 in the hope of providing a reference for future studies and help for the prevention and control of the COVID-19 epidemic.     

Characteristics of inflammatory factors and lymphocyte subsets in patients with severe COVID-19

To investigate the inflammatory factors and lymphocyte subsets which play an important role in the course of severe coronavirus disease 2019 (COVID-19). A total of 27 patients with severe COVID-19 who were admitted to Tongji Hospital in Wuhan from 1 to 21 February 2020 were recruited to the study. The characteristics of interleukin-1β (IL-1β), IL-2 receptor (IL-2R), IL-6, IL-8, IL-10, tumor necrosis factor-α (TNF)-α, C-reactive protein (CRP), serum ferritin and procalcitonin (PCT), and lymphocyte subsets of these patients were retrospectively compared before and after treatment. Before treatment, there was no significant difference in most inflammatory factors (IL-1β, IL-2R, IL-6, IL-8, IL-10, CRP, and serum ferritin) between male and female patients. Levels of IL-2R, IL-6, TNF-α, and CRP decreased significantly after treatment, followed by IL-8, IL-10, and PCT. Serum ferritin was increased in all patients before treatment but did not decrease significantly after treatment. IL-1β was normal in most patients before treatment. Lymphopenia was common among these patients with severe COVID-19. Analysis of lymphocyte subsets showed that CD4+ and particularly CD8+ T lymphocytes increased significantly after treatment. However, B lymphocytes and natural killer cells showed no significant changes after treatment. A pro-inflammatory response and decreased level of T lymphocytes were associated with severe COVID-19.     

Secondary organizing pneumonia after recovery of mild COVID-19 infection

A 36-year-old male with diffuse large B-cell lymphoma on maintenance rituximab therapy presented to the emergency department with high fever and fatigue. A chest X-ray showed a lobar infiltrate, 40 days before admission the patient suffered from a mild coronavirus disease 2019 (COVID-19) infection and fully recovered. PCR nasopharyngeal swab was negative for COVID-19. Comprehensive biochemical, radiological, and pathological evaluation including 18-fluorodeoxyglucose positron emission tomography with computed tomography and transbronchial lung biopsy found no pathogen or lymphoma recurrence. Treatment for pneumonia with antibiotic and antifungal agents was nonbeneficial. A diagnosis of secondary organizing pneumonia (OP) was made after pneumonia migration and a rapid response to corticosteroids. OP secondary to a viral respiratory infection has been well described. Raising awareness for post-COVID-19 OP has therapeutic and prognostic importance because those patients benefit from steroid therapy. We believe the condition described here is underdiagnosed and undertreated by doctors worldwide. Because of the ongoing global pandemic we are now encountering a new kind of patient, patients that have recovered from COVID-19. We hope that this case may contribute to gaining more knowledge about this growing patient population.     

Diagnosis of COVID-19 pneumonia despite missing detection of viral nucleic acid and initially inconspicuous radiologic findings

The diagnosis of coronavirus disease 2019 (COVID-19) is mainly based on a positive severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) polymerase chain reaction (PCR) result. PCR samples are obtained from upper or lower respiratory tract specimens. However, the sensitivity of PCR is known to have some limitations. We report on a patient who was admitted to our hospital with dyspnea, fever, cough, and history of contact with a SARS-CoV-2 infected relative. The initial chest computed tomography (CT) showed only minimal changes and SARS-CoV-2 PCR from a nasopharyngeal swab sample was negative. PCR results obtained from further nasopharyngeal swabs, qualified sputum samples, and from a lower respiratory tract specimen also remained negative. At day 13 after admission, a second chest CT showed radiological findings suspicious for viral pneumonia. Finally, serologic results showed high levels of immunoglobulin G and immunoglobulin A antibodies against the S1 domain of the SARS-CoV-2 spike protein, and the patient was diagnosed with COVID-19 pneumonia.     

Pathophysiology of Methicillin-Resistant Staphylococcus aureus Superinfection in COVID-19 Patients

The global spread of the coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), has infected humans in all age groups, deteriorated host immune responses, and caused millions of deaths. The reasons for individuals succumbing to COVID-19 were not only the SARS-CoV-2 infection but also associated bacterial infections. Antibiotics were largely used to prevent bacterial infections during COVID-19 illness, and many bacteria became resistant to conventional antibiotics. Although COVID-19 was considered the main culprit behind the millions of deaths, bacterial coinfections and superinfections were the major factors that increased the mortality rate in hospitalized patients. In the present study, we assessed the pathophysiology of methicillin-resistant Staphylococcus aureus (MRSA) superinfection in COVID-19 patients in Pakistan. A total of 3492 COVID-19 hospitalized patients were screened among which 224 strain were resistant to methicillin; 110 strains were tazobactam-resistant; 53 strains were ciprofloxacin-resistant; 23 strains were gentamicin-resistant; 11 strains were azithromycin-resistant; 3 strains were vancomycin-resistant. A high frequency of MRSA was detected in patients aged ≥50 with a prevalence of 7.33%, followed by patients aged >65 with a prevalence of 5.48% and a 5.10% prevalence in patients aged <50. In addition, pneumonia was detected in the COVID-19-associated MRSA (COVID-MRSA) that showed decreased levels of lymphocytes and albumin and increased the mortality rate from 2.3% to 25.23%. Collectively, an MRSA superinfection was associated with increased mortality in COVID-19 after 12 to 18 days of hospitalization. The study assessed the prevalence of MRSA, mortality rate, pneumonia, and the emergence of antibiotic resistance as the main outcomes. The study summarized that COVID-MRSA aggravated the treatment and recovery of patients and suggested testing MRSA as critical for hospitalized patients.     

Impact of COVID-19 on Pregnancy

Coronavirus disease 2019 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and is an emerging disease. There has been a rapid increase in cases and deaths since it was identified in Wuhan, China, in early December 2019, with over 4,000,000 cases of COVID-19 including at least 250,000 deaths worldwide as of May 2020. However, limited data about the clinical characteristics of pregnant women with COVID-19 have been reported. Given the maternal physiologic and immune function changes during pregnancy, pregnant women may be at a higher risk of being infected with SARS-CoV-2 and developing more complicated clinical events. Information on severe acute respiratory syndrome (SARS) and Middle East respiratory syndrome (MERS) may provide insights into the effects of COVID-19''s during pregnancy. Even though SARS and MERS have been associated with miscarriage, intrauterine death, fetal growth restriction and high case fatality rates, the clinical course of COVID-19 pneumonia in pregnant women has been reported to be similar to that in non-pregnant women. In addition, pregnant women do not appear to be at a higher risk of catching COVID-19 or suffering from more severe disease than other adults of similar age.Moreover, there is currently no evidence that the virus can be transmitted to the fetus during pregnancy or during childbirth. Babies and young children are also known to only experience mild forms of COVID-19. The aims of this systematic review were to summarize the possible symptoms, treatments, and pregnancy outcomes of women infected with COVID-19 during pregnancy.