A Comparison of Lung Nodule Segmentation Algorithms: Methods and Results from a Multi-institutional Study

Tumor volume estimation, as well as accurate and reproducible borders segmentation in medical images, are important in the diagnosis, staging, and assessment of response to cancer therapy. The goal of this study was to demonstrate the feasibility of a multi-institutional effort to assess the repeatability and reproducibility of nodule borders and volume estimate bias of computerized segmentation algorithms in CT images of lung cancer, and to provide results from such a study. The dataset used for this evaluation consisted of 52 tumors in 41 CT volumes (40 patient datasets and 1 dataset containing scans of 12 phantom nodules of known volume) from five collections available in The Cancer Imaging Archive. Three academic institutions developing lung nodule segmentation algorithms submitted results for three repeat runs for each of the nodules. We compared the performance of lung nodule segmentation algorithms by assessing several measurements of spatial overlap and volume measurement. Nodule sizes varied from 29 μl to 66 ml and demonstrated a diversity of shapes. Agreement in spatial overlap of segmentations was significantly higher for multiple runs of the same algorithm than between segmentations generated by different algorithms (p?<?0.05) and was significantly higher on the phantom dataset compared to the other datasets (p?<?0.05). Algorithms differed significantly in the bias of the measured volumes of the phantom nodules (p?<?0.05) underscoring the need for assessing performance on clinical data in addition to phantoms. Algorithms that most accurately estimated nodule volumes were not the most repeatable, emphasizing the need to evaluate both their accuracy and precision. There were considerable differences between algorithms, especially in a subset of heterogeneous nodules, underscoring the recommendation that the same software be used at all time points in longitudinal studies.     

Computer-aided diagnosis of pulmonary nodules on CT scans: segmentation and classification using 3D active contours

We are developing a computer-aided diagnosis (CAD) system to classify malignant and benign lung nodules found on CT scans. A fully automated system was designed to segment the nodule from its surrounding structured background in a local volume of interest (VOI) and to extract image features for classification. Image segmentation was performed with a three-dimensional (3D) active contour (AC) method. A data set of 96 lung nodules (44 malignant, 52 benign) from 58 patients was used in this study. The 3D AC model is based on two-dimensional AC with the addition of three new energy components to take advantage of 3D information: (1) 3D gradient, which guides the active contour to seek the object surface, (2) 3D curvature, which imposes a smoothness constraint in the z direction, and (3) mask energy, which penalizes contours that grow beyond the pleura or thoracic wall. The search for the best energy weights in the 3D AC model was guided by a simplex optimization method. Morphological and gray-level features were extracted from the segmented nodule. The rubber band straightening transform (RBST) was applied to the shell of voxels surrounding the nodule. Texture features based on run-length statistics were extracted from the RBST image. A linear discriminant analysis classifier with stepwise feature selection was designed using a second simplex optimization to select the most effective features. Leave-one-case-out resampling was used to train and test the CAD system. The system achieved a test area under the receiver operating characteristic curve (A(z)) of 0.83 +/- 0.04. Our preliminary results indicate that use of the 3D AC model and the 3D texture features surrounding the nodule is a promising approach to the segmentation and classification of lung nodules with CAD. The segmentation performance of the 3D AC model trained with our data set was evaluated with 23 nodules available in the Lung Image Database Consortium (LIDC). The lung nodule volumes segmented by the 3D AC model for best classification were generally larger than those outlined by the LIDC radiologists using visual judgment of nodule boundaries.     

A CAD system for nodule detection in low-dose lung CTs based on region growing and a new active contour model

A computer-aided detection (CAD) system for the selection of lung nodules in computer tomography (CT) images is presented. The system is based on region growing (RG) algorithms and a new active contour model (ACM), implementing a local convex hull, able to draw the correct contour of the lung parenchyma and to include the pleural nodules. The CAD consists of three steps: (1) the lung parenchymal volume is segmented by means of a RG algorithm; the pleural nodules are included through the new ACM technique; (2) a RG algorithm is iteratively applied to the previously segmented volume in order to detect the candidate nodules; (3) a double-threshold cut and a neural network are applied to reduce the false positives (FPs). After having set the parameters on a clinical CT, the system works on whole scans, without the need for any manual selection. The CT database was recorded at the Pisa center of the ITALUNG-CT trial, the first Italian randomized controlled trial for the screening of the lung cancer. The detection rate of the system is 88.5% with 6.6 FPs/CT on 15 CT scans (about 4700 sectional images) with 26 nodules: 15 internal and 11 pleural. A reduction to 2.47 FPs/CT is achieved at 80% efficiency.     

Automatic Segmentation of Pulmonary Fissures in Computed Tomography Images Using 3D Surface Features

Pulmonary interlobar fissures are important anatomic structures in human lungs and are useful in locating and classifying lung abnormalities. Automatic segmentation of fissures is a difficult task because of their low contrast and large variability. We developed a fully automatic training-free approach for fissure segmentation based on the local bending degree (LBD) and the maximum bending index (MBI). The LBD is determined by the angle between the eigenvectors of two Hessian matrices for a pair of adjacent voxels. It is used to construct a constraint to extract the candidate surfaces in three-dimensional (3D) space. The MBI is a measure to discriminate cylindrical surfaces from planar surfaces in 3D space. Our approach for segmenting fissures consists of five steps, including lung segmentation, plane-like structure enhancement, surface extraction with LBD, initial fissure identification with MBI, and fissure extension based on local plane fitting. When applying our approach to 15 chest computed tomography (CT) scans, the mean values of the positive predictive value, the sensitivity, the root–mean square (RMS) distance, and the maximal RMS are 91 %, 88 %, 1.01 ± 0.99 mm, and 11.56 mm, respectively, which suggests that our algorithm can efficiently segment fissures in chest CT scans.     

Test–Retest Reproducibility Analysis of Lung CT Image Features

Quantitative size, shape, and texture features derived from computed tomographic (CT) images may be useful as predictive, prognostic, or response biomarkers in non-small cell lung cancer (NSCLC). However, to be useful, such features must be reproducible, non-redundant, and have a large dynamic range. We developed a set of quantitative three-dimensional (3D) features to describe segmented tumors and evaluated their reproducibility to select features with high potential to have prognostic utility. Thirty-two patients with NSCLC were subjected to unenhanced thoracic CT scans acquired within 15 min of each other under an approved protocol. Primary lung cancer lesions were segmented using semi-automatic 3D region growing algorithms. Following segmentation, 219 quantitative 3D features were extracted from each lesion, corresponding to size, shape, and texture, including features in transformed spaces (laws, wavelets). The most informative features were selected using the concordance correlation coefficient across test–retest, the biological range and a feature independence measure. There were 66 (30.14 %) features with concordance correlation coefficient ≥ 0.90 across test–retest and acceptable dynamic range. Of these, 42 features were non-redundant after grouping features with R²_Bet ≥ 0.95. These reproducible features were found to be predictive of radiological prognosis. The area under the curve (AUC) was 91 % for a size-based feature and 92 % for the texture features (runlength, laws). We tested the ability of image features to predict a radiological prognostic score on an independent NSCLC (39 adenocarcinoma) samples, the AUC for texture features (runlength emphasis, energy) was 0.84 while the conventional size-based features (volume, longest diameter) was 0.80. Test–retest and correlation analyses have identified non-redundant CT image features with both high intra-patient reproducibility and inter-patient biological range. Thus making the case that quantitative image features are informative and prognostic biomarkers for NSCLC.

Electronic supplementary material

The online version of this article (doi:10.1007/s10278-014-9716-x) contains supplementary material, which is available to authorized users.     

A Segmentation Framework of Pulmonary Nodules in Lung CT Images

Accurate segmentation of pulmonary nodules is a prerequisite for acceptable performance of computer-aided detection (CAD) system designed for diagnosis of lung cancer from lung CT images. Accurate segmentation helps to improve the quality of machine level features which could improve the performance of the CAD system. The well-circumscribed solid nodules can be segmented using thresholding, but segmentation becomes difficult for part-solid, non-solid, and solid nodules attached with pleura or vessels. We proposed a segmentation framework for all types of pulmonary nodules based on internal texture (solid/part-solid and non-solid) and external attachment (juxta-pleural and juxta-vascular). In the proposed framework, first pulmonary nodules are categorized into solid/part-solid and non-solid category by analyzing intensity distribution in the core of the nodule. Two separate segmentation methods are developed for solid/part-solid and non-solid nodules, respectively. After determining the category of nodule, the particular algorithm is set to remove attached pleural surface and vessels from the nodule body. The result of segmentation is evaluated in terms of four contour-based metrics and six region-based metrics for 891 pulmonary nodules from Lung Image Database Consortium and Image Database Resource Initiative (LIDC/IDRI) public database. The experimental result shows that the proposed segmentation framework is reliable for segmentation of various types of pulmonary nodules with improved accuracy compared to existing segmentation methods.     

基于肺部CT序列图像的肺实质三维分割

目的:肺实质分割是基于CT图像的肺结节计算机辅助检测技术必不可少的步骤。结合阈值技术、连通区域标记以及形态学技术,提出了一种简单有效的从CT图像中分割三维肺实质的方法,以期能为后续肺结节计算机辅助检测技术的研究奠定基础。方法:首先,将原图像二值化,并应用三维连通域标记去除背景及细小空洞;然后,经三维区域生长法去除气管;最后,经形态学滤波平滑肺边界得到肺部精确的三维模板,并采用该模板从CT序列图像中分割出肺实质。结果:根据对20组层厚2.0mm、每组约250个切片的肺部CT临床数据实验验证,其肺实质分割的平均正确度为91.55%,处理单组数据平均耗时167.4563s。结论:实验结果表明,本文方法能自动快速地从CT序列图像中分割出肺实质。     

Knowledge-based segmentation of thoracic computed tomography images for assessment of split lung function

The assessment of differential left and right lung function is important for patients under consideration for lung resection procedures such as single lung transplantation. We developed an automated, knowledge-based segmentation algorithm for purposes of deriving functional information from dynamic computed tomography (CT) image data. Median lung attenuation (HU) and area measurements were automatically calculated for each lung from thoracic CT images acquired during a forced expiratory maneuver as indicators of the amount and rate of airflow. The accuracy of these derived measures from fully automated segmentation was validated against those from segmentation using manual editing by an expert observer. A total of 1313 axial images were analyzed from 49 patients. The images were segmented using our knowledge-based system that identifies the chest wall, mediastinum, trachea, large airways and lung parenchyma on CT images. The key components of the system are an anatomical model, an inference engine and image processing routines, and segmentation involves matching objects extracted from the image to anatomical objects described in the model. The segmentation results from all images were inspected by the expert observer. Manual editing was required to correct 183 (13.94%) of the images, and the sensitivity, specificity, and accuracy of the knowledge-based segmentation were greater than 98.55% in classifying pixels as lung or nonlung. There was no significant difference between median lung attenuation or area values from automated and edited segmentations (p > 0.70). Using the knowledge-based segmentation method we can automatically derive indirect quantitative measures of single lung function that cannot be obtained using conventional pulmonary function tests.     

Effect of CT scanning parameters on volumetric measurements of pulmonary nodules by 3D active contour segmentation: a phantom study

The purpose of this study is to investigate the effects of CT scanning and reconstruction parameters on automated segmentation and volumetric measurements of nodules in CT images. Phantom nodules of known sizes were used so that segmentation accuracy could be quantified in comparison to ground-truth volumes. Spherical nodules having 4.8, 9.5 and 16 mm diameters and 50 and 100 mg cc(-1) calcium contents were embedded in lung-tissue-simulating foam which was inserted in the thoracic cavity of a chest section phantom. CT scans of the phantom were acquired with a 16-slice scanner at various tube currents, pitches, fields-of-view and slice thicknesses. Scans were also taken using identical techniques either within the same day or five months apart for study of reproducibility. The phantom nodules were segmented with a three-dimensional active contour (3DAC) model that we previously developed for use on patient nodules. The percentage volume errors relative to the ground-truth volumes were estimated under the various imaging conditions. There was no statistically significant difference in volume error for repeated CT scans or scans taken with techniques where only pitch, field of view, or tube current (mA) were changed. However, the slice thickness significantly (p < 0.05) affected the volume error. Therefore, to evaluate nodule growth, consistent imaging conditions and high resolution should be used for acquisition of the serial CT scans, especially for smaller nodules. Understanding the effects of scanning and reconstruction parameters on volume measurements by 3DAC allows better interpretation of data and assessment of growth. Tracking nodule growth with computerized segmentation methods would reduce inter- and intraobserver variabilities.     

Comparability of skeletal fibulae surfaces generated by different source scanning (dual‐energy CT scan vs. high resolution laser scanning) and 3D geometric morphometric validation

This work aims to test accuracy and comparability of 3D models of human skeletal fibulae generated by clinical CT and laser scanner virtual acquisitions. Mesh topology, segmentation and smoothing protocols were tested to assess variation among meshes generated with different scanning methods and procedures, and to evaluate meshes‐interchangeability in 3D geometric morphometric analysis. A sample of 13 left human fibulae were scanned separately with Revolution Discovery CT dual energy (0.625 mm resolution) and ARTEC Space Spider 3D structured light laser scanner (0.1 mm resolution). Different segmentation methods, including half‐maximum height (HMH) and MIA‐clustering protocols, were compared to their high‐resolution standard generated with laser‐scanner by calculating topological surface deviations. Different smoothing algorithms were also evaluated, such as Laplacian and Taubin smoothing. A total of 142 semilandmarks were used to capture the shape of both proximal and distal fibular epiphyses. After Generalized Procrustes superimposition, the Procrustes coordinates of the proximal and distal fibular epiphyses were used separately to assess variation due to scanning methods and the operator error. Smoothing algorithms at low iteration do not provide significant variation among reconstructions, but segmentation protocol may influence final mesh quality (0.09–0.24 mm). Mean deviation among CT‐generated meshes that were segmented with MIA‐clustering protocol, and laser scanner‐generated ones, is optimal (0.42 mm, ranging 0.35–0.56 mm). Principal component analysis reveals that homologous samples scanned with the two methods cluster together for both the proximal and distal fibular epiphyses. Similarly, Procrustes ANOVA reveals no shape differences between scanning methods and replicates, and only 1.38–1.43% of shape variation is due to scanning device. Topological similarities support the comparability of CT‐ and laser scanner‐generated meshes and validate its simultaneous use in shape analysis with potential clinical relevance. We precautionarily suggest that dedicated trials should be performed in each study when merging different data sources prior to analyses.     

Automated detection of lung nodules in CT scans: preliminary results

We have developed a fully automated computerized method for the detection of lung nodules in helical computed tomography (CT) scans of the thorax. This method is based on two-dimensional and three-dimensional analyses of the image data acquired during diagnostic CT scans. Lung segmentation proceeds on a section-by-section basis to construct a segmented lung volume within which further analysis is performed. Multiple gray-level thresholds are applied to the segmented lung volume to create a series of thresholded lung volumes. An 18-point connectivity scheme is used to identify contiguous three-dimensional structures within each thresholded lung volume, and those structures that satisfy a volume criterion are selected as initial lung nodule candidates. Morphological and gray-level features are computed for each nodule candidate. After a rule-based approach is applied to greatly reduce the number of nodule candidates that corresponds to nonnodules, the features of remaining candidates are merged through linear discriminant analysis. The automated method was applied to a database of 43 diagnostic thoracic CT scans. Receiver operating characteristic (ROC) analysis was used to evaluate the ability of the classifier to differentiate nodule candidates that correspond to actual nodules from false-positive candidates. The area under the ROC curve for this categorization task attained a value of 0.90 during leave-one-out-by-case evaluation. The automated method yielded an overall nodule detection sensitivity of 70% with an average of 1.5 false-positive detections per section when applied to the complete 43-case database. A corresponding nodule detection sensitivity of 89% with an average of 1.3 false-positive detections per section was achieved with a subset of 20 cases that contained only one or two nodules per case.     

Automated 3D Ιnterstitial Lung Disease Εxtent Quantification: Performance Evaluation and Correlation to PFTs

In this study, the performance of a recently proposed computer-aided diagnosis (CAD) scheme in detection and 3D quantification of reticular and ground glass pattern extent in chest computed tomography of interstitial lung disease (ILD) patients is evaluated. CAD scheme performance was evaluated on a dataset of 37 volumetric chest scans, considering five representative axial anatomical levels per scan. CAD scheme reliability analysis was performed by estimating agreement (intraclass correlation coefficient, ICC) of automatically derived ILD pattern extent to semi-quantitative disease extent assessment in terms of 29-point rating scale provided by two expert radiologists. Receiver operating characteristic (ROC) analysis was employed to assess CAD scheme accuracy in ILD pattern detection in terms of area under ROC curve (A_z). Correlation of reticular and ground glass volumetric pattern extent to pulmonary function tests (PFTs) was also investigated. CAD scheme reliability was substantial for ILD extent (ICC = 0.809) and distinct reticular pattern extent (0.806) and moderate for distinct ground glass pattern extent (0.543), performing within inter-observer agreement. CAD scheme demonstrated high accuracy in detecting total ILD (A_z = 0.950 ± 0.018), while accuracy in detecting distinct reticular and ground glass patterns was 0.920 ± 0.023 and 0.883 ± 0.024, respectively. Moderate and statistically significant negative correlation was found between reticular volumetric pattern extent and diffusing capacity, forced expiratory volume in 1 s, forced vital capacity, and total lung capacity (R = −0.581, −0.513, −0.494, and −0.446, respectively), similar to correlations found between radiologists’ semi-quantitative ratings with PFTs. CAD-based quantification of disease extent is in agreement with radiologists’ semi-quantitative assessment and correlates to specific PFTs, suggesting a potential imaging biomarker for ILD staging and management.     

Correction of segmented lung boundary for inclusion of pleural nodules and pulmonary vessels in chest CT images

We propose a new curvature-based method for correcting the segmented lung boundary. Our method consists of the following steps. First, the lungs are extracted from chest CT images by the automatic segmentation method. Second, the segmented lung contours are corrected by lung smoothing in each axial slice. Our scan line search provides an efficient contour tracing and curvature calculation. Finally, the smoothed lung contours are corrected by 3D VOI refinement. This increases the smoothness in the z-axis without distortion of the lung boundary. Experimental results show that our method effectively incorporates the pleural nodules and pulmonary vessels into the segmentation results.     

Semi-automated Phalanx Bone Segmentation Using the Expectation Maximization Algorithm

Medical imaging technologies have allowed for in vivo exploration and evaluation of the human musculoskeletal system. Three-dimensional bone models generated using image-segmentation techniques provide a means to optimize individualized orthopedic surgical procedures using engineering analyses. However, many of the current segmentation techniques are not clinically practical due to the required time and human intervention. As a proof of concept, we demonstrate the use of an expectation maximization (EM) algorithm to segment the hand phalanx bones, and hypothesize that this semi-automated technique will improve the efficiency while providing similar definitions as compared to a manual rater. Our results show a relative overlap of the proximal, middle, and distal phalanx bones of 0.83, 0.79, and 0.72 for the EM technique when compared to validated manual segmentations. The EM segmentations were also compared to 3D surface scans of the cadaveric specimens, which resulted in distance maps showing an average distance for the proximal, middle, and distal phalanx bones of 0.45, 0.46, and 0.51 mm, respectively. The EM segmentation improved on the segmentation speed of the manual techniques by a factor of eight. Overall, the manual segmentations had greater relative overlap metric values, which suggests that the manual segmentations are a better fit to the actual surface of the bone. As shown by the comparison to the bone surface scans, the EM technique provides a similar representation of the anatomic structure and offers an increase in efficiency that could help to reduce the time needed for defining anatomical structures from CT scans.     

Unmasking Myocardial Dysfunction in Patients Hospitalized for Community-Acquired Pneumonia Using a 4-Chamber 3-Dimensional Volume/Strain Analysis

Lower respiratory infection was reported as the most common fatal infectious disease. Community-acquired pneumonia (CAP) and myocardial injury are associated; yet, true prevalence of myocardial injury is probably underestimated. We assessed the rate and severity of myocardial dysfunction in patients with CAP. Admitted patients diagnosed with CAP were prospectively recruited. All the patients had C-reactive protein (CRP), brain natriuretic peptide (BNP), and high-sensitivity cardiac troponin (hs-cTnl) tests added to their routine workup. 2D/3D Doppler echocardiography was done on a Siemens Acuson SC2000 machine ≤ 24 h of diagnosis. 3D datasets were blindly analyzed for 4-chamber volumes/strains using EchobuildR 3D-Volume Analysis prototype software, v3.0 2019, Siemens-Medical Solutions. Volume/strain parameters were correlated with admission clinical and laboratory findings. The cohort included 34 patients, median age 60 years (95% CI 55–72). The cohort included 18 (53%) patients had hypertension, 9 (25%) had diabetes mellitus, 7 (21%) were smokers, 7 (21%) had previous myocardial infarction, 4 (12%) had chronic renal failure, and 1 (3%) was on hemodialysis treatment. 2D/Doppler echocardiography findings showed normal ventricular size/function (LVEF 63 ± 9%), mild LV hypertrophy (104 ± 36 g/m²), and LA enlargement (41 ± 6 mm). 3D volumes/strains suggested bi-atrial and right ventricular dysfunction (global longitudinal strain RVGLS =  − 8 ± 4%). Left ventricular strain was normal (LVGLS =  − 18 ± 5%) and correlated with BNP (r = 0.40, p = 0.024). The patients with LVGLS >  − 17% had higher admission blood pressure and lower SaO₂ (144 ± 33 vs. 121 ± 20, systolic, mmHg, p = 0.02, and 89 ± 4 vs. 94 ± 4%, p = 0.006, respectively). hs-cTnl and CRP were not different. Using novel 3D volume/strain software in CAP patients, we demonstrated diffuse global myocardial dysfunction involving several chambers. The patients with worse LV GLS had lower SaO₂ and higher blood pressure at presentation. LV GLS correlated with maximal BNP level and did not correlate with inflammation or myocardial damage markers.     

Segmentation of nodules on chest computed tomography for growth assessment

Several segmentation methods to evaluate growth of small isolated pulmonary nodules on chest computed tomography (CT) are presented. The segmentation methods are based on adaptively thresholding attenuation levels and use measures of nodule shape. The segmentation methods were first tested on a realistic chest phantom to evaluate their performance with respect to specific nodule characteristics. The segmentation methods were also tested on sequential CT scans of patients. The methods' estimation of nodule growth were compared to the volume change calculated by a chest radiologist. The best method segmented nodules on average 43% smaller or larger than the actual nodule when errors were computed across all nodule variations on the phantom. Some methods achieved smaller errors when examined with respect to certain nodule properties. In particular, on the phantom individual methods segmented solid nodules to within 23% of their actual size and nodules with 60.7 mm3 volumes to within 14%. On the clinical data, none of the methods examined showed a statistically significant difference in growth estimation from the radiologist.     

Impact of a Computer-Aided Detection (CAD) System Integrated into a Picture Archiving and Communication System (PACS) on Reader Sensitivity and Efficiency for the Detection of Lung Nodules in Thoracic CT Exams

The objective of this study is to assess the impact on nodule detection and efficiency using a computer-aided detection (CAD) device seamlessly integrated into a commercially available picture archiving and communication system (PACS). Forty-eight consecutive low-dose thoracic computed tomography studies were retrospectively included from an ongoing multi-institutional screening study. CAD results were sent to PACS as a separate image series for each study. Five fellowship-trained thoracic radiologists interpreted each case first on contiguous 5 mm sections, then evaluated the CAD output series (with CAD marks on corresponding axial sections). The standard of reference was based on three-reader agreement with expert adjudication. The time to interpret CAD marking was automatically recorded. A total of 134 true-positive nodules, measuring 3 mm and larger were included in our study; with 85 ≥ 4 and 50 ≥ 5 mm in size. Readers detection improved significantly in each size category when using CAD, respectively, from 44 to 57 % for ≥3 mm, 48 to 61 % for ≥4 mm, and 44 to 60 % for ≥5 mm. CAD stand-alone sensitivity was 65, 68, and 66 % for nodules ≥3, ≥4, and ≥5 mm, respectively, with CAD significantly increasing the false positives for two readers only. The average time to interpret and annotate a CAD mark was 15.1 s, after localizing it in the original image series. The integration of CAD into PACS increases reader sensitivity with minimal impact on interpretation time and supports such implementation into daily clinical practice.     

Method for Segmentation of Knee Articular Cartilages Based on Contrast-Enhanced CT Images

Segmentation of contrast-enhanced computed tomography (CECT) images enables quantitative evaluation of morphology of articular cartilage as well as the significance of the lesions. Unfortunately, automatic segmentation methods for CECT images are currently lacking. Here, we introduce a semiautomated technique to segment articular cartilage from in vivo CECT images of human knee. The segmented cartilage geometries of nine knee joints, imaged using a clinical CT-scanner with an intra-articular contrast agent, were compared with manual segmentations from CT and magnetic resonance (MR) images. The Dice similarity coefficients (DSCs) between semiautomatic and manual CT segmentations were 0.79–0.83 and sensitivity and specificity values were also high (0.76–0.86). When comparing semiautomatic and manual CT segmentations, mean cartilage thicknesses agreed well (intraclass correlation coefficient?=?0.85–0.93); the difference in thickness (mean?±?SD) was 0.27?±?0.03 mm. Differences in DSC, when MR segmentations were compared with manual and semiautomated CT segmentations, were statistically insignificant. Similarly, differences in volume were not statistically significant between manual and semiautomatic CT segmentations. Semiautomation decreased the segmentation time from 450?±?190 to 42?±?10 min per joint. The results reveal that the proposed technique is fast and reliable for segmentation of cartilage. Importantly, this is the first study presenting semiautomated segmentation of cartilage from CECT images of human knee joint with minimal user interaction.     

Segmentation of pulmonary nodules in three-dimensional CT images by use of a spiral-scanning technique

Accurate segmentation of pulmonary nodules in computed tomography (CT) is an important and difficult task for computer-aided diagnosis of lung cancer. Therefore, the authors developed a novel automated method for accurate segmentation of nodules in three-dimensional (3D) CT. First, a volume of interest (VOI) was determined at the location of a nodule. To simplify nodule segmentation, the 3D VOI was transformed into a two-dimensional (2D) image by use of a key "spiral-scanning" technique, in which a number of radial lines originating from the center of the VOI spirally scanned the VOI from the "north pole" to the "south pole." The voxels scanned by the radial lines provided a transformed 2D image. Because the surface of a nodule in the 3D image became a curve in the transformed 2D image, the spiral-scanning technique considerably simplified the segmentation method and enabled reliable segmentation results to be obtained. A dynamic programming technique was employed to delineate the "optimal" outline of a nodule in the 2D image, which corresponded to the surface of the nodule in the 3D image. The optimal outline was then transformed back into 3D image space to provide the surface of the nodule. An overlap between nodule regions provided by computer and by the radiologists was employed as a performance metric for evaluating the segmentation method. The database included two Lung Imaging Database Consortium (LIDC) data sets that contained 23 and 86 CT scans, respectively, with 23 and 73 nodules that were 3 mm or larger in diameter. For the two data sets, six and four radiologists manually delineated the outlines of the nodules as reference standards in a performance evaluation for nodule segmentation. The segmentation method was trained on the first and was tested on the second LIDC data sets. The mean overlap values were 66% and 64% for the nodules in the first and second LIDC data sets, respectively, which represented a higher performance level than those of two existing segmentation methods that were also evaluated by use of the LIDC data sets. The segmentation method provided relatively reliable results for pulmonary nodule segmentation and would be useful for lung cancer quantification, detection, and diagnosis.     

基于深度学习的危及器官自动勾画软件系统DeepViewer在放疗中的应用及评估

目的:将一款基于深度学习的危及器官自动勾画软件系统DeepViewer应用于临床,实现自动勾画肿瘤患者治疗计划中危及器官的功能。方法:DeepViewer使用改进后的全卷积神经网络U-Net来实现自动勾画患者CT扫描部位所包含的危及器官,并使用Dice相似性系数（DSC）对比分析这22种危及器官自动勾画与手动勾画的差异。结果:11种危及器官DSC平均值在0.9以上,5种危及器官DSC平均值为0.8~0.9,5种器官DSC平均值为0.7~0.8,视交叉DSC平均值最低,为0.676。总体结果表明DeepViewer系统能够较准确地自动勾画出危及器官,特别是左、右肺、膀胱、脑干等器官,已基本满足临床需求。结论:DeepViewer软件系统可以实现放疗肿瘤患者危及器官的自动勾画,准确性较高。同时,DeepViewer系统勾画完毕后,可以通过网络系统自动传输RTStructure DICOM3.0文件,无需其他操作,能极大地提高临床医生工作效率,降低治疗计划流程中的勾画总时间。