人工智能云技术在乳腺癌患者心脏亚结构自动勾画中的应用

目的:评估人工智能云技术勾画平台（AI Contour）在乳腺癌患者心脏亚结构自动勾画中的准确性和可行性。方法:选取10例进行乳腺癌放射治疗患者的血管增强CT作为研究对象。在AI Contour上分别采用手动勾画、自动勾画和自动勾画后手动修改模式来完成10例患者的心脏亚结构勾画,包括左心房、右心房、左心室、右心室。比较Dice相似性系数（DSC）、Jaccard系数（JC）、Hausdorf距离（HD）、质心偏差（CMD）、包容性系数（IncI）、敏感性指数（SI）、勾画时间。结果:以手动勾画为金标准,自动勾画与手动勾画各心脏亚结构的DSC>0.8,JC>0.6,HD<9 mm,CMD<5 mm,IncI>0.8,SI>0.7。自动勾画后手动修改进一步提高了勾画精度,其中JC>0.8。自动勾画时间与手动勾画时间为（85.50±6.06） s vs （1 160.30±74.31） s,差异具有统计学意义（P<0.05）。自动勾画后手动修改总时间与手动勾画时间为（558.70±33.40） s vs （1 160.30±74.31） s,差异具有统计学意义（P<0.05）。结论:通过比较发现自动勾画技术能以较高的精度完成乳腺癌患者左心房、右心房、左心室、右心室的勾画,节省了大量时间,自动勾画后手动修改能进一步提高各心脏亚结构的勾画精度,同时云勾画平台具有远程协作的优势,值得推广运用。     

Evaluation of a Semi-automatic Right Ventricle Segmentation Method on Short-Axis MR Images

The purpose of this study was to evaluate a semi-automatic right ventricle segmentation method on short-axis cardiac cine MR images which segment all right ventricle contours in a cardiac phase using one seed contour. Twenty-eight consecutive short-axis, four-chamber, and tricuspid valve view cardiac cine MRI examinations of healthy volunteers were used. Two independent observers performed the manual and automatic segmentations of the right ventricles. Analyses were based on the ventricular volume and ejection fraction of the right heart chamber. Reproducibility of the manual and semi-automatic segmentations was assessed using intra- and inter-observer variability. Validity of the semi-automatic segmentations was analyzed with reference to the manual segmentations. The inter- and intra-observer variability of manual segmentations were between 0.8 and 3.2%. The semi-automatic segmentations were highly correlated with the manual segmentations (R² 0.79–0.98), with median difference of 0.9–4.8% and of 3.3% for volume and ejection fraction parameters, respectively. In comparison to the manual segmentation, the semi-automatic segmentation produced contours with median dice metrics of 0.95 and 0.87 and median Hausdorff distance of 5.05 and 7.35 mm for contours at end-diastolic and end-systolic phases, respectively. The inter- and intra-observer variability of the semi-automatic segmentations were lower than observed in the manual segmentations. Both manual and semi-automatic segmentations performed better at the end-diastolic phase than at the end-systolic phase. The investigated semi-automatic segmentation method managed to produce a valid and reproducible alternative to manual right ventricle segmentation.     

Quantifying the accuracy of automated structure segmentation in 4D CT images using a deformable image registration algorithm

Four-dimensional (4D) radiotherapy is the explicit inclusion of the temporal changes in anatomy during the imaging, planning, and delivery of radiotherapy. One key component of 4D radiotherapy planning is the ability to automatically ("auto") create contours on all of the respiratory phase computed tomography (CT) datasets comprising a 4D CT scan, based on contours manually drawn on one CT image set from one phase. A tool that can be used to automatically propagate manually drawn contours to CT scans of other respiratory phases is deformable image registration. The purpose of the current study was to geometrically quantify the difference between automatically generated contours with manually drawn contours. Four-DCT data sets of 13 patients consisting of ten three-dimensional CT image sets acquired at different respiratory phases were used for this study. Tumor and normal tissue structures [gross tumor volume (GTV), esophagus, right lung, left lung, heart and cord] were manually drawn on each respiratory phase of each patient. Large deformable diffeomorphic image registration was performed to map each CT set from the peak-inhale respiration phase to the CT image sets corresponding with subsequent respiration phases. The calculated displacement vector fields were used to deform contours automatically drawn on the inhale phase to the other respiratory phase CT image sets. The code was interfaced to a treatment planning system to view the resulting images and to obtain the volumetric, displacement, and surface congruence information; 692 automatically generated structures were compared with 692 manually drawn structures. The auto- and manual methods showed similar trends, with a smaller difference observed between the GTVs than other structures. The auto-contoured structures agree with the manually drawn structures, especially in the case of the GTV, to within published interobserver variations. For the GTV, fractional volumes agree to within 0.2+/-0.1, center of mass displacements agree to within 0.5+/-1.5 mm, and agreement of surface congruence is 0.0+/-1.1 mm. The surface congruence between automatic and manual contours for the GTV, heart, left lung, right lung and esophagus was less than 5 mm in 99%, 94%, 94%, 91% and 89%, respectively. Careful assessment of the performance of automatic algorithms is needed in the presence of 4D CT artifacts.     

AN AUTOPSY CASE OF IDIOPATHIC ENLARGEMENT OF THE RIGHT ATRIUM, AND A REVIEW OF THE LITERATURE

A 69-year-old man in whom idiopathic enlargement of the right atrium was revealed at autopsy is described. The patient had had cardiomegaly of at least 19 years'duration prior to his death, even though cardiac symptoms were absent. Cause of death was pancreatic carcinoma. Postmortem examination revealed marked and diffuse dilatation of the right atrium and moderate dilatation of the left atrium. Measurement of the cardiac chambers showed that the right and left atria were 7.6 and 4.7 times as large as those of normal hearts, respectively. The volume of either ventricle was about twice the normal value. Histologically, widespread cardiac muscular degeneration and necrosis, diffuse fibrosis, and focal lymphocytic infiltration were found in the right atrium and also, to a lesser degree, in the left atrium. Such pathologic changes were not found in either of the ventricles. The etiology of these muscular changes, which might have been related to atrial enlargement, was unclear. The present case was thought to be consistent with idiopathic enlargement of the right atrium, and a brief review of the literature is given.     

Dynamics of the interventricular septum and free ventricular walls during selective left ventricular volume loading in dogs

A previous study suggested that a change in the position of the interventricular septum played an important role in regulating cardiac performance during selective right ventricular volume loading. In the present study the cardiac response to selective left ventricular volume loading induced by a shunt between the subclavian artery and the left atrium was examined in anesthetized open-chest dogs. Opening the shunt increased left and reduced right ventricular stroke volume, particularly after blood volume expansion. The end-diastolic transseptal pressure difference increased. Myocardial segment length in the septum and free walls of both ventricles and the distances between the septum and the free walls were measured by an ultrasonic technique. Comparisons at similar left ventricular stroke volume with the shunt open and closed showed that the Frank-Starling mechanisms of the free wall of the left ventricle and the septum were stimulated less with the shunt open. At similar right ventricular stroke volume the end-diastolic dimension of the right ventricular free wall was larger with the shunt open. The distance decreased across the right ventricle and increased across the left ventricle when the shunt was open. We conclude that a change in the position of the septum improves left and reduces right ventricular performance during selective left ventricular volume loading.     

An autopsy case of idiopathic enlargement of the right atrium, and a review of the literature

A 69-year-old man in whom idiopathic enlargement of the right atrium was revealed at autopsy is described. The patient had had cardiomegaly of at least 19 years' duration prior to his death, even though cardiac symptoms were absent. Cause of death was pancreatic carcinoma. Postmortem examination revealed marked and diffuse dilatation of the right atrium and moderate dilatation of the left atrium. Measurement of the cardiac chambers showed that the right and left atria were 7.6 and 4.7 times as large as those of normal hearts, respectively. The volume of either ventricle was about twice the normal value. Histologically, widespread cardiac muscular degeneration and necrosis, diffuse fibrosis, and focal lymphocytic infiltration were found in the right atrium and also, to a lesser degree, in the left atrium. Such pathologic changes were not found in either of the ventricles. The etiology of these muscular changes, which might have been related to atrial enlargement, was unclear. The present case was thought to be consistent with idiopathic enlargement of the right atrium, and a brief review of the literature is given.     

正常国人心表面积256层动脉期增强CT测量

目的： 通过手动分割重建心多层螺旋CT（ MSCT）动脉期图像,定量测量正常国人心表面积并建立不同 年龄范围心表面积数据库。方法： 采用回顾性横断面研究方法,自2016 年1 月～ 2019 年12 月在本院行256 层心 增强CT检查的受检者中,筛选无心、大血管病变,且心各房室显示优良者,按照不同年龄范围分为5 组。将正 常心动脉期薄层数据导入3D Slicer 软件,手动逐层勾画各心房、心室进行三维体数据的图像分割标注,重建全心 及各心房、心室模型,并通过Marching Cubes 算法分别测量。观测不同年龄阶段心表面积、左心房及左心室表面积、 右心房及右心室表面积。结果： 正常受检者心表面积为（598.45±49.97）cm2,其中左心房表面积（154.46±34.33） cm2,左心室表面积（220.06±38.72）cm2,右心房表面积（179.07±36.61）cm2,右心室表面积（190.06±36.61） cm2。男性、女性心表面积分别为（610.50±42.75）cm2、（580.86±47.13）cm2。随着年龄增长,心表面积及各心房、 心室表面积均有增大。结论：基于手动分割重建心多层螺旋CT技术可获得正常国人心表面积测量值,为心脏疾 病的诊断和治疗提供依据。     

A new approach towards volumetric assessment of left ventricular function with MSCT

Cardiovascular CT is considered the diagnostic standard for establishing the presence of a functional and dynamic imaging system. It is difficult, however, to estimate the ventricular motion and volumes that are processed using hundreds and thousands of CT images, in a few moments.The main concept and design of our work are two fold - the development of effective semi-automatic tools for measuring the sequential left ventricular volumes from the hundreds or thousands of cardiac trans-axial images, and providing a simple interface with an interactive diagnostic tool for the volumetry of left ventricle and valuable cardiac 4D visualisation.We converted ten and more sequential volume data sets of the heart acquired from retrospective ECG-gating helical scan into 3D images by volume rendering. These sequential 3D images could be displayed as a movie (4D cardiac image) file. Furthermore, we developed a method for semi-automatic calculation of ejection fraction (EF) and cardiac cycle (%)-volume (ml) curve for estimation of the motion and the volume of the left ventricle. This method involved the use an interactive selection tool in the region of interest (ROI). All 3D processing methods, such as, cutting objects, segmentation, and image fusion were based on mask processing data. We now describe the software developed for cardiac 4D imaging and the estimation of ventricular volume.     

Endocardial Border Detection in Cardiac Magnetic Resonance Images Using Level Set Method

Segmentation of the left ventricle in MRI images is a task with important diagnostic power. Currently, the evaluation of cardiac function involves the global measurement of volumes and ejection fraction. This evaluation requires the segmentation of the left ventricle contour. In this paper, we propose a new method for automatic detection of the endocardial border in cardiac magnetic resonance images, by using a level set segmentation-based approach. To initialize this level set segmentation algorithm, we propose to threshold the original image and to use the binary image obtained as initial mask for the level set segmentation method. For the localization of the left ventricular cavity, used to pose the initial binary mask, we propose an automatic approach to detect this spatial position by the evaluation of a metric indicating object’s roundness. The segmentation process starts by the initialization of the level set algorithm and ended up through a level set segmentation. The validation process is achieved by comparing the segmentation results, obtained by the automated proposed segmentation process, to manual contours traced by tow experts. The database used was containing one automated and two manual segmentations for each sequence of images. This comparison showed good results with an overall average similarity area of 97.89%.     

经食管超声评价微创外科房间隔缺损封堵术中患者心功能及血流动力学

目的运用经食管超声对微创外科房间隔缺损封堵术中患者心功能及血流动力学的变化进行评价,探讨超声在微创外科房间隔缺损封堵术中的应用价值。方法门诊筛查选择适合经微创外科封堵术治疗的房间隔缺损患者50例,于术中及手术前后对患者进行经食管超声和经胸超声心动图检查,分别测量左、右室心功能及血流动力学指标,并对手术前后结果进行对照比较。结果术后左、右房室腔的径线与术前比较明显减小（P〈0．05）,右心室舒张末期容积（RVEDV）、右心室每搏输出量（RVSV）、右心排血量（CO）均较封堵前明显减小,左心室舒张末期容积（LVEDV）、每搏输出量（LVSV）及排血量（CO）均较封堵前增加,两者具有显著差异（P〈0．05）。而左心室收缩末期容积（LVESV）和右心室收缩末期容积（RVESV）以及左室和右室射血分数无显著变化。术后肺动脉瓣上最大血流速度、三尖瓣口E峰流速、三尖瓣反流最大流速及肺动脉收缩压与术前比较均显著减小（P〈0．05）,二尖瓣口E峰流速显著增大（P〈0．05）。结论经食管超声可及时反映微创外科房间隔缺损封堵术前后患者心功能及血流动力学变化,为临床评价手术效果提供参考。     

An Image-Based Comprehensive Approach for Automatic Segmentation of Left Ventricle from Cardiac Short Axis Cine MR Images

Segmentation of the left ventricle is important in the assessment of cardiac functional parameters. Manual segmentation of cardiac cine MR images for acquiring these parameters is time-consuming. Accuracy and automation are the two important criteria in improving cardiac image segmentation methods. In this paper, we present a comprehensive approach to segment the left ventricle from short axis cine cardiac MR images automatically. Our method incorporates a number of image processing and analysis techniques including thresholding, edge detection, mathematical morphology, and image filtering to build an efficient process flow. This process flow makes use of various features in cardiac MR images to achieve high accurate segmentation results. Our method was tested on 45 clinical short axis cine cardiac images and the results are compared with manual delineated ground truth (average perpendicular distance of contours near 2 mm and mean myocardium mass overlapping over 90%). This approach provides cardiac radiologists a practical method for an accurate segmentation of the left ventricle.     

Quantitative volumetric analysis of cardiac morphogenesis assessed through micro-computed tomography.

We present a method to generate quantitative embryonic cardiovascular volumes at extremely high resolution without tissue shrinkage using micro-computed tomography (Micro-CT). A CT dense polymer (Microfil, Flow Tech, Inc.) was used to perfuse avian embryonic hearts from Hamburger and Hamilton stage (HH) 15 through HH36, which solidified to create a cast within the luminal space. Hearts were then scanned at 10.5 mum(3) voxel resolution using a VivaCT scanner, digital slices were contoured for regions of interest, and computational analysis was conducted to quantify morphogenetic parameters. The three-dimensional morphology was compared with that of scanning electron microscopy (SEM) images and serial section reconstruction of similarly staged hearts. We report that Microfil-perfused hearts swelled to maximum end-diastolic volume with negligible shrinking after polymerization. Comparison to SEM revealed good agreement of cardiac chamber proportions and intracardiac tissue structures (i.e., valves and septa) at the stages of development assessed. Quantification of changes in chamber volume over development revealed several notable results that confirm earlier hypotheses. Heart chamber volumes grow over two orders of magnitude during the 1-week developmental period analyzed. The atrioventricular canal comprised a significant proportion of the early heart volume. While left atrium/left ventricular volume ratios approached 1 in later development, right atrium/right ventricle ratios increase to over 2.5. Quantification of trabeculation patterns confirmed that the right and left ventricles are similarly trabeculated before HH27, after which the right ventricle became quantitatively coarser than that of the left ventricle. These results demonstrate that Micro-CT can be used to image and quantify cardiovascular structures during development.     

Primary lymphoma of the heart: case report and literature review

Primary cardiac lymphoma (PCL) is a rare and usually fatal neoplasma. A case of PCL in a 78-year-old man who complained of exertional dyspnea and peripheral edema is presented. Echocardiography revealed a mass in the right atrium and a diagnosis of low-grade B-cell lymphoma was obtained with the surgically resected tumor. The lesion appeared to have originated in the right atrium and involved the right ventricle. The patient died of bronchopneumonia 8 months after the initial consultation. The present case and 39 patients with PCL reported between 1995 and 2002 were reviewed. Forty patients showed various and non-specific symptoms such as dyspnea, edema, arrhythmia and pericardial effusion. Primary cardiac lymphoma occurred slightly more often in male patients (M : F = 23:17) and in the elderly in general (mean age, 67 years), with lesions found in the following locations, listed in order of frequency: right atrium, pericardium, right ventricle, left atrium, left ventricle, and other sites. Antemortem diagnosis was obtained in 37 of the 40 patients. Thirty-seven cases were of B-cell lineage and two cases were of T-cell lineage. Complete remission was obtained in only 15 of the 40 patients. Although PCL antemortem diagnoses have been made in the majority of recent cases, the prognosis still remains poor.     

心房同形位畸形：8例尸检报告

本文报告心房同形位畸形8例。其中7例属右同形位,1例属左同形位。根据肺的分叶、主支气管的形态、主支气管与肺动脉的关系和心耳的形态进行分析,并对畸形心脏按节段分析方法进行全面分析。结果认为右同形位心脏的畸形远较左同形位复杂,前者?例中6例为右室型单心室,1例为完全性房室管畸形;而后者为单心房例。心房同形位畸形亦常伴腹腔脏器异位,由于尸检不全面或尸检记录不完善,难以作为依据进行分析,只有待今后工作改善而进一步研究。     

Right ventricular protection with coronary sinus retrograde cardioplegia

Fifteen consecutive patients having open heart surgery using retrograde cardioplegia were studied to demonstrate that important venous collateralization exists between the coronary sinus (CS) and its left ventricular branches and the right ventricle (RV). The venous collateralization makes possible RV myocardial protection during retrograde cardioplegia. Right ventricular venous drainage principally occurs via anterior cardiac veins, which drain into the right atrium, and thebesian veins, which drain into both the RV and the atrium, generally without connection to the CS. Retrograde cardioplegia used during open heart surgery should, therefore, give inadequate myocardial protection to the RV. Two RV temperature probes used as markers for RV perfusion were monitored continuously during cardiac arrest. Systemic temperature while on cardiopulmonary bypass was 25°C, and the retrograde perfusate solution temperature was 4°C. Coronary sinus pressure during the bypass procedure was maintained between 20 torr and 50 torr. Mean temperatures at the two probe sites were 16.1°C and 14.5°C. We conclude that a complex network of venous collaterals between the coronary sinus and left ventricle and the right ventricle allow excellent myocardial protection during retrograde cardioplegia. © 1994 Wiley-Liss, Inc.     

Semiautomated four-dimensional computed tomography segmentation using deformable models

The purpose of this work is to demonstrate a proof of feasibility of the application of a commercial prototype deformable model algorithm to the problem of delineation of anatomic structures on four-dimensional (4D) computed tomography (CT) image data sets. We acquired a 4D CT image data set of a patient's thorax that consisted of three-dimensional (3D) image data sets from eight phases in the respiratory cycle. The contours of the right and left lungs, cord, heart, and esophagus were manually delineated on the end inspiration data set. An interactive deformable model algorithm, originally intended for deforming an atlas-based model surface to a 3D CT image data set, was applied in an automated fashion. Triangulations based on the contours generated on each phase were deformed to the CT data set on the succeeding phase to generate the contours on that phase. Deformation was propagated through the eight phases, and the contours obtained on the end inspiration data set were compared with the original manually delineated contours. Structures defined by high-density gradients, such as lungs, cord, and heart, were accurately reproduced, except in regions where other gradient boundaries may have confused the algorithm, such as near bronchi. The algorithm failed to accurately contour the esophagus, a soft-tissue structure completely surrounded by tissue of similar density, without manual interaction. This technique has the potential to facilitate contour delineation in 4D CT image data sets; and future evolution of the software is expected to improve the process.     

Cardiac Image Segmentation from Cine Cardiac MRI Using Graph Cuts and Shape Priors

In this paper, we propose a novel method for segmentation of the left ventricle, right ventricle, and myocardium from cine cardiac magnetic resonance images of the STACOM database. Our method incorporates prior shape information in a graph cut framework to achieve segmentation. Poor edge information and large within-patient shape variation of the different parts necessitates the inclusion of prior shape information. But large interpatient shape variability makes it difficult to have a generalized shape model. Therefore, for every dataset the shape prior is chosen as a single image clearly showing the different parts. Prior shape information is obtained from a combination of distance functions and orientation angle histograms of each pixel relative to the prior shape. To account for shape changes, pixels near the boundary are allowed to change their labels by appropriate formulation of the penalty and smoothness costs. Our method consists of two stages. In the first stage, segmentation is performed using only intensity information which is the starting point for the second stage combining intensity and shape information to get the final segmentation. Experimental results on different subsets of 30 real patient datasets show higher segmentation accuracy in using shape information and our method's superior performance over other competing methods.     

Combined left and right ventricular volume determination by radionuclide angiocardiography using double bolus and equilibrium technique

Eighteen patients with ischaemic heart disease were studied. Left and right ventricular volumes including cardiac output (forward flow) were determined by radionuclide angiocardiography using a double bolus and equilibrium technique. As reference, cardiac output was simultaneously measured by indicator dilution. The radionuclide technique comprised four steps: (1) a first-pass study of right ventricle; (2) a bolus study of left ventricle; (3) an equilibrium study of left ventricle; (4) determination of the distribution volume of red blood cells. Absolute volumes of left ventricle were determined from steps 2 + 3 + 4. Absolute volumes of right ventricle were calculated from stroke volume and right ventricular ejection fraction (EF) which in turn was determined from step 1 by creating composite systolic and composite diastolic images. There was an acceptable agreement between stroke volume determinations by radionuclide angiocardiography and indicator dilution (r = 0.74; P less than 0.001). Stroke volume determination by radionuclide was 83 +/- 20 ml (mean +/- SD) and by indicator dilution 84 +/- 20 ml with a difference of -1 +/- 15 ml (NS). Cardiac output determination by radionuclide was 5.24 +/- 1.37 l min-1 and by indicator dilution 5.28 +/- 1.23 l min-1 with a difference of -0.04 +/- 0.95 l min-1 (NS). Left ventricular EF was 0.44 +/- 0.14 and right ventricular EF 0.57 +/- 0.10. The intra-observer coefficient of variation for duplicate calculations of the radionuclide determinations was 5.5% for stroke volume, 2.5% for left ventricular EF and 4.8% for right ventricular EF.     

Fast prostate segmentation in 3D TRUS images based on continuity constraint using an autoregressive model

In this article a new slice-based 3D prostate segmentation method based on a continuity constraint, implemented as an autoregressive (AR) model is described. In order to decrease the propagated segmentation error produced by the slice-based 3D segmentation method, a continuity constraint was imposed in the prostate segmentation algorithm. A 3D ultrasound image was segmented using the slice-based segmentation method. Then, a cross-sectional profile of the resulting contours was obtained by intersecting the 2D segmented contours with a coronal plane passing through the midpoint of the manually identified rotational axis, which is considered to be the approximate center of the prostate. On the coronal cross-sectional plane, these intersections form a set of radial lines directed from the center of the prostate. The lengths of these radial lines were smoothed using an AR model. Slice-based 3D segmentations were performed in the clockwise and in the anticlockwise directions, where clockwise and anticlockwise are defined with respect to the propagation directions on the coronal view. This resulted in two different segmentations for each 2D slice. For each pair of unmatched segments, in which the distance between the contour generated clockwise and that generated anticlockwise was greater than 4 mm, a method was used to select the optimal contour. Experiments performed using 3D prostate ultrasound images of nine patients demonstrated that the proposed method produced accurate 3D prostate boundaries without manual editing. The average distance between the proposed method and manual segmentation was 1.29 mm. The average intraobserver coefficient of variation (i.e., the standard deviation divided by the average volume) of the boundaries segmented by the proposed method was 1.6%. The average segmentation time of a 352 x 379 x 704 image on a Pentium IV 2.8 GHz PC was 10 s.