Radiography Image Classification Using Deep Convolutional Neural Networks

Research has shown that chest radiography images of patients with different diseases, such as pneumonia, COVID-19, SARS, pneumothorax, etc., all exhibit some form of abnormality. Several deep learning techniques can be used to identify each of these anomalies in the chest x-ray images. Convolutional neural networks (CNNs) have shown great success in the fields of image recognition and image classification since there are numerous large-scale annotated image datasets available. The classification of medical images, particularly radiographic images, remains one of the biggest hurdles in medical diagnosis because of the restricted availability of annotated medical images. However, such difficulty can be solved by utilizing several deep learning strategies, including data augmentation and transfer learning. The aim was to build a model that would detect abnormalities in chest x-ray images with the highest probability. To do that, different models were built with different features. While making a CNN model, one of the main tasks is to tune the model by changing the hyperparameters and layers so that the model gives out good training and testing results. In our case, three different models were built, and finally, the last one gave out the best-predicted results. From that last model, we got 98% training accuracy, 84% validation, and 81% testing accuracy. The reason behind the final model giving out the best evaluation scores is that it was a well-fitted model. There was no overfitting or underfitting issues. Our aim with this project was to make a tool using the CNN model in R language, which will help detect abnormalities in radiography images. The tool will be able to detect diseases such as Pneumonia, Covid-19, Effusions, Infiltration, Pneumothorax, and others. Because of its high accuracy, this research chose to use supervised multi-class classification techniques as well as Convolutional Neural Networks (CNNs) to classify different chest x-ray images. CNNs are extremely efficient and successful at reducing the number of parameters while maintaining the quality of the primary model. CNNs are also trained to recognize the edges of various objects in any batch of images. CNNs automatically discover the relevant aspects in labeled data and learn the distinguishing features for each class by themselves.

Resolution analysis of thermal neutron radiography based on accelerator-driven compact neutron source

Owing to the immobility of traditional reactors and spallation neutron sources,the demand for compact thermal neutron radiography(CTNR)based on accelerator neutron sources has rapidly increased in industrial applications.Recently,thermal neutron radiography experiments based on a D-T neutron generator performed by Hefei Institutes of Physical Science indicated a significant resolution deviation between the experimental results and the values calculated using the traditional resolution model.The experimental result was up to 23%lower than the calculated result,which hinders the achievement of the design goal of a compact neutron radiography system.A GEANT4 Monte Carlo code was developed to simulate the CTNR process,aiming to identify the key factors leading to resolution deviation.The effects of a low collimation ratio and high-energy neutrons were analyzed based on the neutron beam environment of the CTNR system.The results showed that the deviation was primarily caused by geometric distortion at low collimation ratios and radiation noise induced by highenergy neutrons.Additionally,the theoretical model was modified by considering the imaging position and radiation noise factors.The modified theoretical model was in good agreement with the experimental results,and the maximum deviation was reduced to 4.22%.This can be useful for the high-precision design of CTNR systems.

胸部CT图像质量评价与辐射剂量的临床应用研究

目的:归纳和分析影响胸部CT图像质量的因素,进一步对照分析常规剂量组和低剂量组两组图像质量有无差异,以论证胸部CT低剂量检查的可行性。方法:选取150例胸部CT查体的患者,A组为常规剂量组,管电压120kV,管电流自动调节;B组为低剂量组,管电压100kV,管电流自动调节。参照胸部CT的图像质量评价标准对常规剂量组和低剂量组图像质量进一步作出主观评价。对辐射剂量、信噪比等客观数据进行统计学处理,以P<0.05为差异有统计学意义。并与主观评价相比较。结果:主、客观评价两组图像质量均无统计学意义,A组辐射剂量与B组辐射剂量有统计学意义。结论:影响图像质量的因素包括患者的因素、设备的因素以及操作者的因素,胸部CT采用100kV低剂量检查可以作为常规扫描方案,获得的图像可以满足影像诊断的要求,具有可行性。

MRI与X线联合评估乳腺非肿块样病变恶性风险的Logistic回归模型建立及应用评价

目的:基于MRI与X线特征建立乳腺非肿块样病变(Non-mass-like lesions,NML)恶性风险的预测模型,期望提高诊断准确率,为临床决策提供依据。方法:对我院2021年7月-2023年4月符合纳入标准的150例患者的资料进行回顾性分析,使用Logistic回归构建NML恶性风险预测模型及列线图,采用校准曲线评估模型准确度,用受试者工作特征(ROC)曲线评估模型的诊断效能。结果:多因素分析显示簇状环形强化、时间-信号强度曲线(TIC)类型、ADC值、线样及段样分布钙化等影像特征是预测病变恶性风险的因素。基于MRI特征的模型的ROC曲线下面积为0.941,灵敏度为88.7%,特异度为86.6%。基于MRI联合X线特征的模型的ROC曲线下面积为0.951,灵敏度为91.5%,特异度为91.4%,校准曲线预测准确度较好。结论 :基于MRI联合X线特征建立的乳腺NML恶性风险Logistic回归模型诊断效能较高,具有一定的应用潜力。

高能闪光照相阵列屏非一致性响应校正技术

阵列屏采用大量独立晶柱组合而成限制了可见光在转换屏内的扩散,能够在提高X光转换效率的同时保证照相系统有较高的空间分辨能力,是高能闪光照相系统中的重要器件。阵列屏由于各晶柱之间的转换系数不同而导致接收图像中存在非一致响应现象,必须将其校正才能对图像进行有效判读。研究了中阵列屏接收图像中非一致响应现象的校正方法,首先使用平板照相获得空场图像,然后对实验图像和空场图像扣除暗电流本底和消除脉冲噪声,最后将实验图像与空场图像进行像素相除运算。针对强振动环境下空场图像与实验图像不匹配问题,提出对空场图像进行位移的方法以实现空场图像与实验图像的重新匹配,采用校正后图像的标准差数据来判断两者的匹配性。实验结果表明位移后的空场图像能够校正强振动环境下阵列屏图像的非一致性响应。

股骨头坏死ARCO 3A期平片分期准确性及误分期原因分析

目的评估X线平片对股骨头坏死ARCO3A期分期的准确性,并分析其误分期的原因。方法回顾性分析2017年1月至2023年7月同期行髋关节正、蛙式位X线及CT检查,且髋关节CT分期为ARCO3A期的158例股骨头坏死患者,其中14例为双侧ARCO3A期,共计172例ARCO3A期股骨头坏死,F/M=67/91,平均年龄43.7±11.8岁。观察髋关节X线正、蛙式位图像进行ARCO分期并统计结果。结果髋关节X线分期为ARCO 3A期139例,误分期为ARCO 2期33例,准确率为80.8%;对照同期髋关节CT图像,X线误分期病例中未发现软骨下骨折6例(18.2%)、未发现坏死区骨折4例(12.1%)、未发现股骨头局限塌陷23例(69.7%)。结论X线对股骨头坏死ARCO 3A期分期的准确性高,但仍存在误分期的状况。在临床工作中,正位结合蛙式位,仔细观察关节面局部轻微不光整及软骨下、坏死区骨折等征象有助于提高X线平片对股骨头坏死ARCO3A期分期的准确性。

中国先进研究堆瞬发γ元素成像技术研究

无损分析样品内部的元素分布,对于材料、考古、地质科学等领域的研究具有重要意义。基于瞬发γ活化分析方法,结合中子照相技术,分析了模拟样品的结构和对称性,首次利用中国先进研究堆(CARR)水平孔道聚焦的微束中子束流,开展样品瞬发γ扫描分析和材料内部元素分布研究。通过蒙特卡罗软件(MCNP)对样品元素分布实验模型进行分析,模拟结果获得了样品不同区域的铜、铁、铝元素分布,基本实现了元素空间分辨。MCNP计算结果表明在瞬发γ扫描分析中,优化准直几何参数和提高中子通量能进一步提高元素空间分辨和元素测量准确度。

数字断层融合摄影技术在股骨干骨折内固定术后的应用研究

目的探讨数字断层融合摄影(DTS)在股骨干骨折内固定术后复查中的应用价值。方法收集90例股骨干骨折内固定术后患者,于术后6月时完成了数字化X线摄影(DR)及DTS检查。由两名放射科医师采用5分法对两种影像学检查方法所获图像进行图像质量评价及对比。同时由临床医师对DTS及DR的骨折愈合显示率进行对比。结果术后6月时,DTS图像质量评分为(3.689±1.148)分,DR图像质量评分为(2.778±1.197)分,两组差异具有统计学意义(P<0.05)。DTS图像骨折愈合情况显示率为95.56%(86/90),DR图像骨折愈合情况显示率为72.23%(65/90),差异具有统计学意义(P<0.05)。结论在股骨干骨折内固定术后复查中,DTS能清晰显示术区骨质结构,准确判断骨折愈合情况,图像质量较DR更优,可作为股骨干骨折内固定术后复查较为理想的影像学检查方法,临床实用性较强。

俯卧与坐姿下籽骨轴位的X线影像质量的比较

目的:评估在坐姿下行籽骨轴位X线投照的影像质量。方法:收集2023年3—6月由于足部不适前来就诊的50例患者,对同一患者进行俯卧与坐姿两种姿势下籽骨轴位的DR检查,将获取的两组影像进行质量评估与比较。结果:俯卧与坐姿两种姿势下的影像合格率、EI、DAP在统计学上均不存在显著差异。结论:在拍摄籽骨轴位X线时,对于不能进行传统体位(俯卧)投照的患者,可在坐姿下进行投照,所获取的X线影像也能满足影像医生诊断需求。

Multi-distortion suppression for neutron radiographic images based on generative adversarial network

Neutron radiography is a crucial nondestructive testing technology widely used in the aerospace,military,and nuclear industries.However,because of the physical limitations of neutron sources and collimators,the resulting neutron radiographic images inevitably exhibit multiple distortions,including noise,geometric unsharpness,and white spots.Furthermore,these distortions are particularly significant in compact neutron radiography systems with low neutron fluxes.Therefore,in this study,we devised a multi-distortion suppression network that employs a modified generative adversarial network to improve the quality of degraded neutron radiographic images.Real neutron radiographic image datasets with various types and levels of distortion were built for the first time as multi-distortion suppression datasets.Thereafter,the coordinate attention mechanism was incorporated into the backbone network to augment the capability of the proposed network to learn the abstract relationship between ideally clear and degraded images.Extensive experiments were performed;the results show that the proposed method can effectively suppress multiple distortions in real neutron radiographic images and achieve state-of-theart perceptual visual quality,thus demonstrating its application potential in neutron radiography.

Robust Machine Learning Technique to Classify COVID-19 Using Fusion of Texture and Vesselness of X-Ray Images

Manual investigation of chest radiography(CXR)images by physicians is crucial for effective decision-making in COVID-19 diagnosis.However,the high demand during the pandemic necessitates auxiliary help through image analysis and machine learning techniques.This study presents a multi-threshold-based segmentation technique to probe high pixel intensity regions in CXR images of various pathologies,including normal cases.Texture information is extracted using gray co-occurrence matrix(GLCM)-based features,while vessel-like features are obtained using Frangi,Sato,and Meijering filters.Machine learning models employing Decision Tree(DT)and RandomForest(RF)approaches are designed to categorize CXR images into common lung infections,lung opacity(LO),COVID-19,and viral pneumonia(VP).The results demonstrate that the fusion of texture and vesselbased features provides an effective ML model for aiding diagnosis.The ML model validation using performance measures,including an accuracy of approximately 91.8%with an RF-based classifier,supports the usefulness of the feature set and classifier model in categorizing the four different pathologies.Furthermore,the study investigates the importance of the devised features in identifying the underlying pathology and incorporates histogrambased analysis.This analysis reveals varying natural pixel distributions in CXR images belonging to the normal,COVID-19,LO,and VP groups,motivating the incorporation of additional features such as mean,standard deviation,skewness,and percentile based on the filtered images.Notably,the study achieves a considerable improvement in categorizing COVID-19 from LO,with a true positive rate of 97%,further substantiating the effectiveness of the methodology implemented.

改良肺超声评分用于评估急性呼吸窘迫综合征严重程度

目的提出改良肺超声评分(LUS),观察其用于评估急性呼吸窘迫综合征(ARDS)严重程度的价值。方法回顾性分析33例突发ARDS患者肺超声及X线胸片等资料,根据氧合指数(OI)将患者归入中-重度组(n=16)及轻度组(n=17);比较组间LUS、改良LUS及肺水肿放射学(RALE)评分;绘制受试者工作特征(ROC)曲线,计算曲线下面积(AUC),分析影像学评分评估ARDS严重程度的效能;以Pearson相关分析观察ARDS患者影像学评分与OI的相关性,以及RALE评分与LUS及改良LUS的相关性。结果中-重度组LUS及改良LUS均高于轻度组(P均<0.05);RALE评分组间差异无统计学意义(P>0.05)。以LUS、改良LUS及RALE评分评估ARDS严重程度的AUC分别为0.809、0.853及0.640。ARDS患者LUS及改良LUS均与OI呈中度负相关(r=-0.570,P=0.001;r=-0.708,P<0.001),而RALE评分与OI无明显相关(r=-0.229,P=0.201)。ARDS患者RALE评分与LUS及改良LUS均呈中度正相关(r=0.588,P<0.001;r=0.502,P=0.003)。结论本研究提出的改良LUS可有效评估ARDS严重程度,且其效能优于LUS及RALE评分。

Development of a monochromatic crystal backlight imager for the recent double-cone ignition experiments

We developed a monochromatic crystal backlight imaging system for the double-cone ignition(DCI) scheme, employing a spherically bent quartz crystal. This system was used to measure the spatial distribution and temporal evolution of the head-on colliding plasma from the two compressing cones in the DCI experiments. The influence of laser parameters on the x-ray backlighter intensity and spatial resolution of the imaging system was investigated. The imaging system had a spatial resolution of 10 μm when employing a CCD detector. Experiments demonstrated that the system can obtain time-resolved radiographic images with high quality, enabling the precise measurement of the shape, size, and density distribution of the plasma.

基于深度学习的胸部X线图像清晰度评价方法

目的 构建深度学习模型对胸部X线图像进行清晰度评价,并与放射科医师的主观评价对比,验证模型的效能。资料与方法 回顾性收集2015年6月—2022年8月安徽省590家医院共9 135幅胸部X线图像,组织放射科医师采用五级评分法对图像清晰度进行多人多次评价,单人评价结果为A、B,多人评价结果为C。构建基于ResNet-50的深度学习模型对胸部X线图像进行清晰度评价,以结果 C作为模型训练和测试数据,模型评价结果为D。由1名放射质控专家对模型评价结果和医师多人评价结果进行审核评价作为图像清晰度的参考标准,评价结果为E。采用Spearman相关、均方根误差(RMSE)和准确率验证模型的效能。结果 与参考标准E相比,D的平均准确率为0.85,高于C的0.84。A、B、C、D与E的ρ分别为0.58(0.54,0.62)、0.59(0.55,0.63)、0.74(0.71,0.77)和0.80(0.78,0.82),D与E的相关性最好。A与B的ρ为0.45(0.41,0.49),两次单人主观评价清晰度相关性较差。A、B、C、D与E的RMSE分别为0.99、0.94、0.72和0.71,D与E的RMSE小于人工评价结果。结论 本研究构建的模型能够准确评价胸部X线图像清晰度,通过深度学习方法可以降低人工评价的主观干扰,为临床放射图像清晰度评价提供有效、客观的工具。

对比植入第二代无导线起搏器与传统双腔起搏器辐射剂量

目的对比植入第二代无导线起搏器(Micra AV)与传统双腔起搏器所致患者辐射剂量。方法回顾性分析74例因心动过缓接受植入起搏器患者,按照植入起搏器类型将其分为AV组(n=30)与传统组(n=44);比较2组透视时间、空气比释动能(AK)、剂量面积乘积(DAP)、电影序列数及电影合计帧数。结果AV组AK、电影DAP、电影序列数及电影合计帧数均高于传统组(P均<0.05);组间透视时间和透视DAP差异均无统计学意义(P均>0.05)。2组患者X线辐射投射范围基本一致,且多分布于躯体左半侧。结论相比植入传统双腔起搏器,植入Micra AV时患者所受电影采集辐射剂量更大,而透视所致辐射剂量无显著差异。

Deep learning automation of radiographic patterns for hallux valgus diagnosis

Artificial intelligence(AI)and deep learning are becoming increasingly powerful tools in diagnostic and radiographic medicine.Deep learning has already been utilized for automated detection of pneumonia from chest radiographs,diabetic retinopathy,breast cancer,skin carcinoma classification,and metastatic lymphadenopathy detection,with diagnostic reliability akin to medical experts.In the World Journal of Orthopedics article,the authors apply an automated and AIassisted technique to determine the hallux valgus angle(HVA)for assessing HV foot deformity.With the U-net neural network,the authors constructed an algorithm for pattern recognition of HV foot deformity from anteroposterior highresolution radiographs.The performance of the deep learning algorithm was compared to expert clinician manual performance and assessed alongside clinician-clinician variability.The authors found that the AI tool was sufficient in assessing HVA and proposed the system as an instrument to augment clinical efficiency.Though further sophistication is needed to establish automated algorithms for more complicated foot pathologies,this work adds to the growing evidence supporting AI as a powerful diagnostic tool.

改进知识蒸馏Transformer的新冠肺炎医学影像分类

针对在筛查新型冠状病毒感染肺炎患者时核酸检测假阴性率较高的问题,提出了一种DRPL-ViT计算机辅助诊断网络。在Vision Transformer的基础上首先引入知识蒸馏机制,使Transformer结构在小数据集上训练取得更好的拟合效果;然后,在patches的位置信息编码上,通过更适合视觉任务的相对位置编码方式,使tokens之间的依赖关系能够被更好地捕捉;为了关注到更多的局部特征,在Transformer Encoder模块中引入了传统的卷积模块提取局部特征。实验在四分类测试集上平均分类准确率达到92.11%,对新冠肺炎分类准确率达到97.85%。实验结果表明,所提出的网络对新冠肺炎及其他肺部病变分类准确率较高,有一定的临床应用价值。

基于X线影像组学特征的预测模型对膝关节周围骨肿瘤的诊断价值

目的探讨基于数字化X线影像组学特征,并联合常规临床信息构建的预测模型鉴别膝关节周围骨肿瘤良恶性的临床应用价值。方法回顾性收集433例经手术病理证实的膝关节周围良恶性骨肿瘤病人的术前X线影像及临床资料。根据WHO骨肿瘤分类将病人分为良性组(303例)和恶性组(130例)。病人按照7∶3的比例随机分为训练集(303例)及测试集(130例)。采用ITK-SNAP软件在术前膝关节正侧位X线影像上的病灶区域手动勾画感兴趣区(ROI)并提取影像组学特征,利用最小绝对收缩和选择算子(LASSO)回归算法进行特征选择,并采用决策树(DT)、随机森林(RF)、极端梯度提升(XGB)、逻辑回归(LR)、支持向量机(SVM)和K最邻近(KNN)分类器构建单纯影像组学模型,以及整合了临床信息的联合预测模型。采用受试者操作特征(ROC)曲线下面积(AUC)评估各模型的预测效能,并采用DeLong检验比较各模型之间预测效能的差异。利用SHAP值评估模型纳入的各个特征对诊断结果的重要性。结果恶性组的红细胞沉降率(ESR)大于良性组,且关节活动受限多于良性组(均P<0.05),将ESR、关节活动度作为临床特征。基于6种分类器,分别构建单纯影像组学模型(18个组学特征)和联合预测模型(16个组学特征和2个临床特征)。6种分类器构建的影像组学模型和联合模型的诊断效能均较高(均AUC>0.8),其中XGB联合模型的AUC值最高(0.905)。DeLong检验结果显示,XGB、LR和SVM联合模型的AUC值均高于相应的组学模型(均P<0.05)。其中,XGB联合模型的效能最优。通过SHAP值发现组学特征中灰度依赖矩阵(GLDM)为模型提供了重要的预测信息。结论基于膝关节X线影像组学特征和临床信息构建的XGB联合模型可以在术前有效鉴别良恶性骨肿瘤。

Al-20%Cu多晶粒竞争生长的原位观测及汇聚型枝晶淘汰模型构建

采用同步辐射成像技术研究Al-20%Cu(质量分数)亚共晶合金的晶粒竞争生长动力学,并建立与实验结果相一致的数学模型。结果表明,对于发散型竞争生长,遵循“正常淘汰”规则。对于汇聚型竞争生长,成分过冷的作用加速非择优取向晶粒中一次枝晶臂的生长速度,导致非择优取向枝晶出现“异常淘汰”现象,淘汰择优取向枝晶。探讨汇聚型竞争生长的“正常淘汰”与“异常淘汰”之间的临界条件,建立枝晶生长速率、枝晶臂间距和枝晶倾斜角之间的数学关系,又称“二次枝晶臂阻挡模型”,可以快速预测晶界位相和淘汰类型。

犬含牙囊肿病例报告

本院接诊了1例乳齿未脱、右下颌恒犬齿缺失的患犬病例,将患犬麻醉后采用口腔探查和X线检查的方法进行诊断,初步诊断该患犬为含牙囊肿,即由未萌出的右下颌恒犬齿发育过程中相关的残留上皮所形成。手术拔除未萌发犬齿,使用刮匙将囊壁完整去除,用金刚砂车针打磨囊壁齿槽骨并使用生理盐水冲洗囊腔,结节缝合齿龈黏膜,术后恢复良好。患犬于术后3个月复查,镇静后拍摄口腔X线片,可见有新骨生成,无囊肿复发表现。表明治疗含牙囊肿时,拔除未萌发的牙齿并将囊壁清理干净,可获得良好的预后,但需要结合口腔X线和组织病理学检查结果进行诊断,后续需要进行影像学监测。