Sensitivity of Thoracic Digital Tomosynthesis (DTS) for the Identification of Lung Nodules

Thoracic computed tomography (CT) is considered the gold standard for detection lung pathology, yet its efficacy as a screening tool in regards to cost and radiation dose continues to evolve. Chest radiography (CXR) remains a useful and ubiquitous tool for detection and characterization of pulmonary pathology, but reduced sensitivity and specificity compared to CT. This prospective, blinded study compares the sensitivity of digital tomosynthesis (DTS), to that of CT and CXR for the identification and characterization of lung nodules. Ninety-five outpatients received a posteroanterior (PA) and lateral CXR, DTS, and chest CT at one care episode. The CXR and DTS studies were independently interpreted by three thoracic radiologists. The CT studies were used as the gold standard and read by a fourth thoracic radiologist. Nodules were characterized by presence, location, size, and composition. The agreement between observers and the effective radiation dose for each modality was objectively calculated. One hundred forty-five nodules of greatest diameter larger than 4 mm and 215 nodules less than 4 mm were identified by CT. DTS identified significantly more >4 mm nodules than CXR (DTS 32 % vs. CXR 17 %). CXR and DTS showed no significant difference in the ability to identify the smaller nodules or central nodules within 3 cm of the hilum. DTS outperformed CXR in identifying pleural nodules and those nodules located greater than 3 cm from the hilum. Average radiation dose for CXR, DTS, and CT were 0.10, 0.21, and 6.8 mSv, respectively. Thoracic digital tomosynthesis requires significantly less radiation dose than CT and nearly doubles the sensitivity of that of CXR for the identification of lung nodules greater than 4 mm. However, sensitivity and specificity for detection and characterization of lung nodules remains substantially less than CT. The apparent benefits over CXR, low cost, rapid acquisition, and minimal radiation dose of thoracic DTS suggest that it may be a useful procedure. Work-up of a newly diagnosed nodule will likely require CT, given its superior cross-sectional characterization. Further investigation of DTS as a diagnostic, screening, and surveillance tool is warranted.     

Biplane Correlation Imaging: A Feasibility Study Based on Phantom and Human Data

The objective of this study was to implement and evaluate the performance of a biplane correlation imaging (BCI) technique aimed to reduce the effect of anatomic noise and improve the detection of lung nodules in chest radiographs. Seventy-one low-dose posterior–anterior images were acquired from an anthropomorphic chest phantom with 0.28° angular separations over a range of ±10° along the vertical axis within an 11 s interval. Similar data were acquired from 19 human subjects with institutional review board approval and informed consent. The data were incorporated into a computer-aided detection (CAD) algorithm in which suspect lesions were identified by examining the geometrical correlation of the detected signals that remained relatively constant against variable anatomic backgrounds. The data were analyzed to determine the effect of angular separation, and the overall sensitivity and false-positives for lung nodule detection. The best performance was achieved for angular separations of the projection pairs greater than 5°. Within that range, the technique provided an order of magnitude decrease in the number of false-positive reports when compared with CAD analysis of single-view images. Overall, the technique yielded ~1.1 false-positive per patient with an average sensitivity of 75%. The results indicated that the incorporation of angular information can offer a reduction in the number of false-positives without a notable reduction in sensitivity. The findings suggest that the BCI technique has the potential for clinical implementation as a cost-effective technique to improve the detection of subtle lung nodules with lowered rate of false-positives.     

Impact of resolution and noise characteristics of digital radiographic detectors on the detectability of lung nodules

One of the unanswered questions in digital radiography is the connection between physical image quality metrics and clinical detection performance. In this paper, we examine the impact of two physical metrics, resolution and noise, on the detectability of nodules in a pulmonary background for specific digital radiographic detectors. A detection experiment was performed on a simulated image set using anatomical backgrounds from a high-quality lung radiograph and three different simulated nodule sizes (2-3.5 mm). The resolution and noise of the resulting images were modified using existing routines to simulate a selenium-based and a cesium iodide-based flat-panel detector at comparable exposures. A location-known-exactly (LKE) observer performance experiment was performed in which four experienced chest radiologists and three physicists specializing in chest radiology scored the images. The data from the observer experiment were analyzed by receiver operating characteristic (ROC) methodology. The detectability, as measured by the parameter Az, was higher for the selenium detector than the cesium iodide detector for all nodule sizes by an average of 8.5%. For one nodule size (2.75 mm), the difference between detectors was statistically significant (p < 0.01). The findings indicate that for the particular task studied, the superior resolution performance of the selenium-based detector provided better detectability of subtle lung nodules even though the images had greater noise than images obtained with the cesium iodide detector.     

A Fully Automatic Method for Lung Parenchyma Segmentation and Repairing

Considering that the traditional lung segmentation algorithms are not adaptive for the situations that most of the juxtapleural nodules, which are excluded as fat, and lung are not segmented perfectly. In this paper, several methods are comprehensively utilized including optimal iterative threshold, three-dimensional connectivity labeling, three-dimensional region growing for the initial segmentation of the lung parenchyma, based on improved chain code, and Bresenham algorithms to repair the lung parenchyma. The paper thus proposes a fully automatic method for lung parenchyma segmentation and repairing. Ninety-seven lung nodule thoracic computed tomography scans and 25 juxtapleural nodule scans are used to test the proposed method and compare with the most-cited rolling-ball method. Experimental results show that the algorithm can segment lung parenchyma region automatically and accurately. The sensitivity of juxtapleural nodule inclusion is 100 %, the segmentation accuracy of juxtapleural nodule regions is 98.6 %, segmentation accuracy of lung parenchyma is more than 95.2 %, and the average segmentation time is 0.67 s/frame. The algorithm can achieve good results for lung parenchyma segmentation and repairing in various cases that nodules/tumors adhere to lung wall.     

非对称卷积核YOLO V2网络的CT影像肺结节检测

肺癌一直是严重威胁人类健康的疾病之一,肺结节作为早期肺癌的一个重要征象,在肺癌的早期诊断与治疗中具有重要的意义。传统的CT影像肺结节检测方法不仅步骤繁琐、处理速度慢,而且对于结节的检出率及定位精度都亟待提高。提出一种基于非对称卷积核YOLO V2网络的CT影像肺结节检测方法:首先将连续的CT序列叠加构造为伪彩色数据集,以增强病变和健康组织的差异;然后将含有非对称卷积核的inception V3模块引入到YOLO V2网络中,构造出一种适用于肺结节检测的深度网络,一方面利用YOLO V2网络在目标检测上的优势,另一方面通过inception V3模块在网络的宽度与深度上进行扩增,以提取更加丰富的特征;为进一步提高结节的定位精度,对损失函数的设计与计算方法也进行一定的改进。为验证所提检测模型的性能,从LIDC-IDRI数据集中选取1 010个病例的CT图像用于训练和测试,在大于3 mm的肺结节中,检测敏感度为94.25%,假阳性率为8.50%。实验表明,所提出的肺结节检测方法不仅可以简化肺部CT图像的处理过程,而且在结节检测率及定位精度方面均优于传统方法,可为肺结节检测提供一种新思路。     

Digital tomosynthesis of the chest for lung nodule detection: interim sensitivity results from an ongoing NIH-sponsored trial

The authors report interim clinical results from an ongoing NIH-sponsored trial to evaluate digital chest tomosynthesis for improving detectability of small lung nodules. Twenty-one patients undergoing computed tomography (CT) to follow up lung nodules were consented and enrolled to receive an additional digital PA chest radiograph and digital tomosynthesis exam. Tomosynthesis was performed with a commercial CsI/a-Si flat-panel detector and a custom-built tube mover. Seventy-one images were acquired in 11 s, reconstructed with the matrix inversion tomosynthesis algorithm at 5-mm plane spacing, and then averaged (seven planes) to reduce noise and low-contrast artifacts. Total exposure for tomosynthesis imaging was equivalent to that of 11 digital PA radiographs (comparable to a typical screen-film lateral radiograph or two digital lateral radiographs). CT scans (1.25-mm section thickness) were reviewed to confirm presence and location of nodules. Three chest radiologists independently reviewed tomosynthesis images and PA chest radiographs to confirm visualization of nodules identified by CT. Nodules were scored as: definitely visible, uncertain, or not visible. 175 nodules (diameter range 3.5-25.5 mm) were seen by CT and grouped according to size: < 5, 5-10, and > 10 mm. When considering as true positives only nodules that were scored definitely visible, sensitivities for all nodules by tomosynthesis and PA radiography were 70% (+/- 5%) and 22% (+/- 4%), respectively, (p < 0.0001). Digital tomosynthesis showed significantly improved sensitivity of detection of known small lung nodules in all three size groups, when compared to PA chest radiography.     

Automated detection of lung nodules in CT scans: false-positive reduction with the radial-gradient index

We present a number of approaches based on the radial gradient index (RGI) to achieve false-positive reduction in automated CT lung nodule detection. A database of 38 cases was used that contained a total of 82 lung nodules. For each CT section, a complementary image known as an "RGI map" was constructed to enhance regions of high circularity and thus improve the contrast between nodules and normal anatomy. Thresholds on three RGI parameters were varied to construct RGI filters that sensitively eliminated false-positive structures. In a consistency approach, RGI filtering eliminated 36% of the false-positive structures detected by the automated method without the loss of any true positives. Use of an RGI filter prior to a linear discriminant classifier yielded notable improvements in performance, with the false-positive rate at a sensitivity of 70% being reduced from 0.5 to 0.28 per section. Finally, the performance of the linear discriminant classifier was evaluated with RGI-based features. RGI-based features achieved a substantial improvement in overall performance, with a 94.8% reduction in the false-positive rate at a fixed sensitivity of 70%. These results demonstrate the potential role of RGI analysis in an automated lung nodule detection method.     

Compare Display Schemes for Lung Nodule CT Screening

This study investigated the relative efficiencies of a stereographic display and two monoscopic display schemes for detecting lung nodules in chest computed tomography (CT). The ultimate goal was to determine whether stereoscopic display provides advantages for visualization and interpretation of three-dimensional (3D) medical image datasets. A retrospective study that compared lung nodule detection performances achieved using three different schemes for displaying 3D CT data was conducted. The display modes included slice-by-slice, orthogonal maximum intensity projection (MIP), and stereoscopic display. One hundred lung-cancer screening CT examinations containing 647 nodules were interpreted by eight radiologists, in each of the display modes. Reading times and displayed slab thickness versus time were recorded, as well as the probability, location, and size for each detected nodule. Nodule detection performance was analyzed using the receiver operating characteristic method. The stereo display mode provided higher detection performance with a shorter interpretation time, as compared to the other display modes tested in the study, although the difference was not statistically significant. The analysis also showed that there was no difference in the patterns of displayed slab thickness versus time between the stereo and MIP display modes. Most radiologists preferred reading the 3D data at a slab thickness that corresponded to five CT slices. Our results indicate that stereo display has the potential to improve radiologists' performance for detecting lung nodules in CT datasets. The experience gained in conducting the study also strongly suggests that further benefits can be achieved through providing readers with additional functionality.     

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.     

Sensitivity and Specificity of a CAD Solution for Lung Nodule Detection on Chest Radiograph with CTA Correlation

The objective of this research was to determine the sensitivity and specificity of a commercially available computer-aided detection (CAD) system for detection of lung nodule on posterior–anterior (PA) chest radiograph in a varied patient population who are referred to computed tomographic angiogram (CTA) of the chest as a reference standard. Patients who had a PA chest radiograph with concomitant CTA of the chest were included in this retrospective study. The PA chest radiograph was analyzed by a CAD device, and results were recorded. A qualitative assessment of the CAD results was performed using a 5-point Likert scale. The CTA was then reviewed to determine if there were correlative nodules. The presence of a correlative nodule between 0.5 cm and 1.5 cm was considered a positive result. The baseline sensitivity of the system was determined to be 0.707 (95% CI = 0.52–0.86), with a specificity of 0.50 (95% CI = 0.38–0.76). Positive predictive value was 0.30 (95% CI = 0.24–0.49), with a negative predictive value of 0.858 (95% CI = 0.82–0.95), and accuracy of 0.555 (95% CI = 0.40–0.66). When excluding nodules that were qualitatively determined by a thoracic radiologist to be false positives, the specificity was 0.781 (95% CI = 0.764–0.839), the positive predictive value was 0.564 (95% CI = 0.491–0.654), the negative predictive value was 0.829 (95% CI = 0.819–0.878), and the accuracy was 0.737 (95% CI = 0.721–0.801). The use of CAD for lung nodule detection on chest radiograph, when used in conjunction with an experienced radiologist, has a very good sensitivity, specificity, and accuracy.     

Effect of Multiscale Processing in Digital Chest Radiography on Automated Detection of Lung Nodule with a Computer Assistance System

The aim of this study is to evaluate the effect of multiscale processing in digital chest radiography on automated detection of lung nodule with a computer-aided diagnosis (CAD) system. The study involved 58 small-nodule patient cases and 58 normal cases. The 58 patient cases included a total of 64 noncalcified lung nodules up to 15 mm in diameter. Each case underwent an examination with a digital radiography system (Digital Diagnost, Philips Medical Systems), and the acquired image was processed by the following three types of multiscale processing (Unique Image Processing Package, Philips Medical Systems) respectively: (1) standard image from the default processing parameter (structure preference, 0.0), (2) high-pass image with structure preference of 0.4, (3) low-pass image with structure preference of ?0.4. The CAD output images were produced with a real-time computer assistance system (IQQA?-Chest, EDDA Technology). Two experienced chest radiologists established the nodule gold standard by consensus reading according to computed tomography results, and analyzed and recorded the detection of lung nodules and false-positive detections of these CAD output images. For the entire cases involved (each case with three types of different processing), a total of 348 observations were evaluated by the receiver operating characteristic (ROC) analysis. The mean area under the ROC curve (A _z ) value was 0.700 for the standard images, 0.587 for the high-pass images, and 0.783 for the low-pass images. There were statistically significant A _z values among these three types of processed images (p?<?0.01). Multiscale processing in digital chest radiography can affect the automated detection of lung nodule by CAD, which is consistent with effects from visual inspection.     

An automated CT based lung nodule detection scheme using geometric analysis of signed distance field

The authors present a new computerized scheme to automatically detect lung nodules depicted on computed tomography (CT) images. The procedure is performed in the signed distance field of the CT images. To obtain an accurate signed distance field, CT images are first interpolated linearly along the axial direction to form an isotropic data set. Then a lung segmentation strategy is applied to smooth the lung border aiming to include as many juxtapleural nodules as possible while minimizing over segmentations of the lung regions. Potential nodule regions are then detected by locating local maximas of signed distances in each subvolume with values and the sizes larger than the smallest nodule of interest in the three-dimensional space. Finally, all detected candidates are scored by computing the similarity distance of their medial axis-like shapes obtained through a progressive clustering strategy combined with a marching cube algorithm from a sphere based shape. A free-response receiver operating characteristics curve is computed to assess the scheme performance. A performance test on 52 low-dose CT screening examinations that depict 184 verified lung nodules showed that during the initial stage the scheme achieved an asymptotic maximum sensitivity of 95.1% (175/184) with an average of 1200 suspicious voxels per CT examination. The nine missed nodules included two small solid nodules (with a diameter < or =3.1 mm) and seven nonsolid nodules. The final performance level after the similarity scoring stage was an absolute sensitivity level, namely, including the nine missed during the initial stage, of 81.5% (150/184) with 6.5 false-positive identifications per CT examination. This preliminary study demonstrates the feasibility of applying a simple and robust geometric model using the signed distance field to identify suspicious lung nodules. In the authors' data set the sensitivity of this scheme is not affected by nodule size. In addition to potentially being a stand alone approach, the signed distance field based method can be easily implemented as an initial filtering step in other computer-aided detection schemes.     

Automated lung nodule classification following automated nodule detection on CT: a serial approach

We have evaluated the performance of an automated classifier applied to the task of differentiating malignant and benign lung nodules in low-dose helical computed tomography (CT) scans acquired as part of a lung cancer screening program. The nodules classified in this manner were initially identified by our automated lung nodule detection method, so that the output of automated lung nodule detection was used as input to automated lung nodule classification. This study begins to narrow the distinction between the "detection task" and the "classification task." Automated lung nodule detection is based on two- and three-dimensional analyses of the CT image data. Gray-level-thresholding techniques are used to identify initial lung nodule candidates, for which morphological and gray-level features are computed. A rule-based approach is applied to reduce the number of nodule candidates that correspond to non-nodules, and the features of remaining candidates are merged through linear discriminant analysis to obtain final detection results. Automated lung nodule classification merges the features of the lung nodule candidates identified by the detection algorithm that correspond to actual nodules through another linear discriminant classifier to distinguish between malignant and benign nodules. The automated classification method was applied to the computerized detection results obtained from a database of 393 low-dose thoracic CT scans containing 470 confirmed lung nodules (69 malignant and 401 benign nodules). Receiver operating characteristic (ROC) analysis was used to evaluate the ability of the classifier to differentiate between nodule candidates that correspond to malignant nodules and nodule candidates that correspond to benign lesions. The area under the ROC curve for this classification task attained a value of 0.79 during a leave-one-out evaluation.     

Investigating the low-dose limits of multidetector CT in lung nodule surveillance

The purpose of this study was to evaluate the factors limiting nodule detection in thoracic computed tomography (CT) and to determine whether prior knowledge of nodule size and attenuation, available from a baseline CT study, influences the minimum radiation dose at which nodule surveillance CT scans can be performed while maintaining current levels of nodule detectability. Multiple nodules varying in attenuation (-509 to + 110 HU) and diameter (1.6 to 9.5 mm) were layered in random and ordered sequences within 2 lung cylinders made of Rando lung material and suspended within a custom-built CT phantom. Multiple CT scans were performed at varying kVp (120, 100, and 80), mA (200, 150, 100, 50, 20, and 10), and beam collimation (5, 2.5, and 1.25 mm) on a four-row multidetector scanner (Lightspeed, General Electric, Milwaukee, WI) using 0.8 s gantry rotation. The corresponding range of radiation dose over which images were acquired was 0.3-26.4 mGy. Nine observers independently performed three specific tasks, namely: (1) To detect a 3.2 mm nodule of 23 HU; (2) To detect 3.2 mm nodules of varying attenuation (-509 to -154 HU); and (3) To detect nodules varying in size (1.6-9 mm) and attenuation (-509 to 110 HU). A two-alternative forced-choice test was used in order to determine the limits of nodule detection in terms of the proportion of correct responses (Pcorr, related to the area under the ROC curve) as a summary metric of observer performance. The radiation dose levels for detection of 99% of nodules in each task were as follows: Task 1 (1 mGy); Task 2 (5 mGy); and Task 3 (7 mGy). The corresponding interobserver confidence limits were 1, 5, and 10 mGy for Tasks 1, 2, and 3, respectively. There was a fivefold increase in the radiation dose required for detection of lower-density nodules (Tasks 1 to 2). Absence of prior knowledge of the nodule size and density (Task 3) corresponds to a significant increase in the minimum required radiation dose. Significant image degradation and reduction in observer performance for all tasks occur at a dose of < or = 1 mGy. It is concluded that the size and attenuation of a nodule strongly influence the radiation dose required for confident evaluation with a minimum threshold value of 1-2 mGy (minimum dose CT). A prior knowledge of nodule size and attenuation is available from the baseline CT scan and is an important consideration in minimizing the radiation exposure required for nodule detection with surveillance CT.     

Computer-aided diagnostic scheme for the detection of lung nodules on chest radiographs: localized search method based on anatomical classification

We developed an advanced computer-aided diagnostic (CAD) scheme for the detection of various types of lung nodules on chest radiographs intended for implementation in clinical situations. We used 924 digitized chest images (992 noncalcified nodules) which had a 500 x 500 matrix size with a 1024 gray scale. The images were divided randomly into two sets which were used for training and testing of the computerized scheme. In this scheme, the lung field was first segmented by use of a ribcage detection technique, and then a large search area (448 x 448 matrix size) within the chest image was automatically determined by taking into account the locations of a midline and a top edge of the segmented ribcage. In order to detect lung nodule candidates based on a localized search method, we divided the entire search area into 7 x 7 regions of interest (ROIs: 64 x 64 matrix size). In the next step, each ROI was classified anatomically into apical, peripheral, hilar, and diaphragm/heart regions by use of its image features. Identification of lung nodule candidates and extraction of image features were applied for each localized region (128 x 128 matrix size), each having its central part (64 x 64 matrix size) located at a position corresponding to a ROI that was classified anatomically in the previous step. Initial candidates were identified by use of the nodule-enhanced image obtained with the average radial-gradient filtering technique, in which the filter size was varied adaptively depending on the location and the anatomical classification of the ROI. We extracted 57 image features from the original and nodule-enhanced images based on geometric, gray-level, background structure, and edge-gradient features. In addition, 14 image features were obtained from the corresponding locations in the contralateral subtraction image. A total of 71 image features were employed for three sequential artificial neural networks (ANNs) in order to reduce the number of false-positive candidates. All parameters for ANNs, i.e., the number of iterations, slope of sigmoid functions, learning rate, and threshold values for removing the false positives, were determined automatically by use of a bootstrap technique with training cases. We employed four different combinations of training and test image data sets which was selected randomly from the 924 cases. By use of our localized search method based on anatomical classification, the average sensitivity was increased to 92.5% with 59.3 false positives per image at the level of initial detection for four different sets of test cases, whereas our previous technique achieved an 82.8% of sensitivity with 56.8 false positives per image. The computer performance in the final step obtained from four different data sets indicated that the average sensitivity in detecting lung nodules was 70.1% with 5.0 false positives per image for testing cases and 70.4% sensitivity with 4.2 false positives per image for training cases. The advanced CAD scheme involving the localized search method with anatomical classification provided improved detection of pulmonary nodules on chest radiographs for 924 lung nodule cases.     

Detection of interstitial lung abnormalities on picture archive and communication system video monitors

The purpose of this study was to compare the detection of interstitial lung abnormalities on video display workstation monitors between radiologists experienced with video image interpretation and radiologists who lack this experience. Twenty-four patients with interstitial lung abnormalities documented by high-resolution computed tomography (HRCT) and lung biopsy, and 26 control patients with no history of pulmonary disease or a normal HRCT and normal chest radiographs were studied. Images were acquired using storage phosphor digital radiography and displayed on 1,640×2,048 pixel resolution video monitors. Five board-certified radiologists evaluated the images in a blinded and randomized manner by using a six-point presence of abnormality grading scale. Three radiologists were from 1 to 4 years out of residency and considered to be experienced workstation monitor readers with between 1 to 3 years of video monitor image interpretation. For the inexperienced readers, one radiologist had no prior experience with reading images from a video monitor and was direct out of residency, and the other radiologist had less than 4 months of intermittent exposure and was 1 year out of residency. Sensitivity and specificity were determined for individual readers. Positive predictive values, negative predictive values, accuracy, and receiver-operating curves were alsoggenerated. A comparison was made between experienced and inexperienced readers. For readers experienced with video monitor image interpretation, the sensitivity ranged from 87.5% to 92%, specificity from 69% to 92%, positive predictive value (PPV) from 73% to 87.5%, negative predictive value (NPV) from 87% to 90%, and accuracy from 80% to 88%. For inexperienced readers, these values were sensitivity 58%, specificity 50% to 65% PPV 52% to 61%, NPV 56.5% to 63%, and accuracy 54% to 62%. Comparing image interpretation between experienced and inexperienced readers, there were statistically significant differences for sensitivity (P<.01), specificity (P<.01), PPV (P<.05), NPV (P<.05), accuracy (P<.05), and area under the receiver operator curve (Az) (P<.01). Within the respective experienced and inexperienced groups, no statistical significant differences were present. Our results show that digitally acquired chest radiographs displayed on high-resolution workstation monitors are adequate for the detection of interstitial lung abnormalities when the images are interpreted by radiologists experienced with video image interpretation. Radiologists inexperienced with video monitor image interpretation, however, cannot reliably interpret images for the detection of interstitial lung abnormalities.     

Management of small pulmonary nodules in patients with sarcoma

Small pulmonary nodules in patients with sarcoma are problematic, because it is difficult to distinguish such small metastatic nodules from benign. The purpose of this study was to establish management guidelines for such small pulmonary nodules in patients with sarcoma. Pulmonary nodules were detected in 70 of 206 patients with sarcoma. About 55 patients were classified as having pulmonary metastasis. Seventeen of these 55 patients with pulmonary metastases were excluded from the imaging review because they did not undergo the required imaging examination. This study reviewed 38 patients with metastatic nodules and 15 patients with benign nodules. A statistically significant relationship was observed between the size of the nodules and final clinical decision. The patients with pulmonary nodules which did not exceed 5 mm in size showed significantly better cumulative overall survival rate after the detection of pulmonary nodules than those with larger nodules (5-years: 58.4 vs. 20.4%). There was no significant difference in the overall survival rate between the patients with smaller pulmonary benign lesions which did not exceed 5 mm in size and those with a normal chest CT (5-years: 92.3 vs. 85.3%). The only factor to diagnose in a metastatic pulmonary lesion is the size of the nodules. If the nodule remains ≦5 mm in size for more than 6 months, the nodule will be a benign lesion. On the contrary, if the nodule becomes larger than 5 mm within 6 months, a surgical excision of the nodules is recommended.     

基于收敛指数滤波和Hessian矩阵的肺结节检测算法

肺癌的早期形态多以肺结节的形式出现,对其正确检测有助于提高肺癌病人的存活率.针对肺部高分辨率CT图像中肺结节与血管横断面难以区分的问题,提出了一种基于收敛指数滤波和Hessian矩阵的肺结节检测算法.首先对基于向量域的收敛指数滤波器进行量化产生候选肺结节,然后设计基于三阶Hessian矩阵特征值的血管检测滤波器对血管进行检测标记.最后从候选肺结节中剔除血管横断面得到真阳性肺结节.实验结果 表明,本文提出的检测算法具有较高的灵敏性和低假阳性.     

Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography

In this study, we investigated a pattern-recognition technique based on an artificial neural network (ANN), which is called a massive training artificial neural network (MTANN), for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography (CT) images. The MTANN consists of a modified multilayer ANN, which is capable of operating on image data directly. The MTANN is trained by use of a large number of subregions extracted from input images together with the teacher images containing the distribution for the "likelihood of being a nodule." The output image is obtained by scanning an input image with the MTANN. The distinction between a nodule and a non-nodule is made by use of a score which is defined from the output image of the trained MTANN. In order to eliminate various types of non-nodules, we extended the capability of a single MTANN, and developed a multiple MTANN (Multi-MTANN). The Multi-MTANN consists of plural MTANNs that are arranged in parallel. Each MTANN is trained by using the same nodules, but with a different type of non-nodule. Each MTANN acts as an expert for a specific type of non-nodule, e.g., five different MTANNs were trained to distinguish nodules from various-sized vessels; four other MTANNs were applied to eliminate some other opacities. The outputs of the MTANNs were combined by using the logical AND operation such that each of the trained MTANNs eliminated none of the nodules, but removed the specific type of non-nodule with which the MTANN was trained, and thus removed various types of non-nodules. The Multi-MTANN consisting of nine MTANNs was trained with 10 typical nodules and 10 non-nodules representing each of nine different non-nodule types (90 training non-nodules overall) in a training set. The trained Multi-MTANN was applied to the reduction of false positives reported by our current computerized scheme for lung nodule detection based on a database of 63 low-dose CT scans (1765 sections), which contained 71 confirmed nodules including 66 biopsy-confirmed primary cancers, from a lung cancer screening program. The Multi-MTANN was applied to 58 true positives (nodules from 54 patients) and 1726 false positives (non-nodules) reported by our current scheme in a validation test; these were different from the training set. The results indicated that 83% (1424/1726) of non-nodules were removed with a reduction of one true positive (nodule), i.e., a classification sensitivity of 98.3% (57 of 58 nodules). By using the Multi-MTANN, the false-positive rate of our current scheme was improved from 0.98 to 0.18 false positives per section (from 27.4 to 4.8 per patient) at an overall sensitivity of 80.3% (57/71).     

Characterization of Radiologists’ Search Strategies for Lung Nodule Detection: Slice-Based Versus Volumetric Displays

The goal of this study was to assess whether radiologists’ search paths for lung nodule detection in chest computed tomography (CT) between different rendering and display schemes have reliable properties that can be exploited as an indicator of ergonomic efficiency for the purpose of comparing different display paradigms. Eight radiologists retrospectively viewed 30 lung cancer screening CT exams, containing a total of 91 nodules, in each of three display modes [i.e., slice-by-slice, orthogonal maximum intensity projection (MIP) and stereoscopic] for the purpose of detecting and classifying lung nodules. Radiologists’ search patterns in the axial direction were recorded and analyzed along with the location, size, and shape for each detected feature, and the likelihood that the feature is an actual nodule. Nodule detection performance was analyzed by employing free-response receiver operating characteristic methods. Search paths were clearly different between slice-by-slice displays and volumetric displays but, aside from training and novelty effects, not between MIP and stereographic displays. Novelty and training effects were associated with the stereographic display mode, as evidenced by differences between the beginning and end of the study. The stereo display provided higher detection and classification performance with less interpretation time compared to other display modes tested in the study; however, the differences were not statistically significant. Our preliminary results indicate a potential role for the use of radiologists’ search paths in evaluating the relative ergonomic efficiencies of different display paradigms, but systematic training and practice is necessary to eliminate training curve and novelty effects before search strategies can be meaningfully compared.