Lung Nodule Detection System Research Articles

Random forest based lung nodule classification aided by clustering

An automated lung nodule detection system can help spot lung abnormalities in CT lung images. Lung nodule detection can be achieved using template-based, segmentation-based, and classification-based methods. The existing systems that include a classification component in their structures have demonstrated better performances than their counterparts. Ensemble learners combine decisions of multiple classifiers to form an integrated output. To improve the performance of automated lung nodule detection, an ensemble classification aided by clustering (CAC) method is proposed. The method takes advantage of the random forest algorithm and offers a structure for a hybrid random forest based lung nodule classification aided by clustering. Several experiments are carried out involving the proposed method as well as two other existing methods. The parameters of the classifiers are varied to identify the best performing classifiers. The experiments are conducted using lung scans of 32 patients including 5721 images within which nodule locations are marked by expert radiologists. Overall, the best sensitivity of 98.33% and specificity of 97.11% have been recorded for proposed system. Also, a high receiver operating characteristic (ROC) A z of 0.9786 has been achieved.

Automatic Lung Segmentation in CT Images with Accurate Handling of the Hilar Region

A fully automated and three-dimensional (3D) segmentation method for the identification of the pulmonary parenchyma in thorax X-ray computed tomography (CT) datasets is proposed. It is meant to be used as pre-processing step in the computer-assisted detection (CAD) system for malignant lung nodule detection that is being developed by the Medical Applications in a Grid Infrastructure Connection (MAGIC-5) Project. In this new approach the segmentation of the external airways (trachea and bronchi), is obtained by 3D region growing with wavefront simulation and suitable stop conditions, thus allowing an accurate handling of the hilar region, notoriously difficult to be segmented. Particular attention was also devoted to checking and solving the problem of the apparent 'fusion' between the lungs, caused by partial-volume effects, while 3D morphology operations ensure the accurate inclusion of all the nodules (internal, pleural, and vascular) in the segmented volume. The new algorithm was initially developed and tested on a dataset of 130 CT scans from the Italung-CT trial, and was then applied to the ANODE09-competition images (55 scans) and to the LIDC database (84 scans), giving very satisfactory results. In particular, the lung contour was adequately located in 96% of the CT scans, with incorrect segmentation of the external airways in the remaining cases. Segmentation metrics were calculated that quantitatively express the consistency between automatic and manual segmentations: the mean overlap degree of the segmentation masks is 0.96 ± 0.02, and the mean and the maximum distance between the mask borders (averaged on the whole dataset) are 0.74 ± 0.05 and 4.5 ± 1.5, respectively, which confirms that the automatic segmentations quite correctly reproduce the borders traced by the radiologist. Moreover, no tissue containing internal and pleural nodules was removed in the segmentation process, so that this method proved to be fit for the use in the framework of a CAD system. Finally, in the comparison with a two-dimensional segmentation procedure, inter-slice smoothness was calculated, showing that the masks created by the 3D algorithm are significantly smoother than those calculated by the 2D-only procedure.

Computer-Aided Pulmonary Nodule Detection – Performance of Two CAD Systems at Different CT Dose Levels

To evaluate the impact of dose reduction on the performance of computer-aided lung nodule detection systems (CAD) of two manufacturers by comparing respective CAD results on ultra-low-dose computed tomography (ULD-CT) and standard dose CT (SD-CT). Multi-slice computed tomography (MSCT) data sets of 26 patients (13 male and 13 female, patients 31 - 74 years old) were retrospectively selected for CAD analysis. Indication for CT examination was staging of a known primary malignancy or suspected pulmonary malignancy. CT images were consecutively acquired at 5 mAs (ULD-CT) and 75 mAs (SD-CT) with 120 kV tube voltage (1 mm slice thickness). The standard of reference was determined by three experienced readers in consensus. CAD reading algorithms (pre-commercial CAD system, Philips, Netherlands: CAD-1; LungCARE, Siemens, Germany: CAD-2) were applied to the CT data sets. Consensus reading identified 253 nodules on SD-CT and ULD-CT. Nodules ranged in diameter between 2 and 41 mm (mean diameter 4.8 mm). Detection rates were recorded with 72 % and 62 % (CAD-1 vs. CAD-2) for SD-CT and with 73 % and 56 % for ULD-CT. Median false positive rates per patient were calculated with 6 and 5 (CAD-1 vs. CAD-2) for SD-CT and with 8 and 3 for ULD-CT. After separate statistical analysis of nodules with diameters of 5 mm and greater, the detection rates increased to 83 % and 61 % for SD-CT and to 89 % and 67 % for ULD-CT (CAD-1 vs. CAD-2). For both CAD systems there were no significant differences between the detection rates for standard and ultra-low-dose data sets (p > 0.05). Dose reduction of the underlying CT scan did not significantly influence nodule detection performance of the tested CAD systems.

Computer-aided detection of lung nodules on multidetector row computed tomography using three-dimensional analysis of nodule candidates and their surroundings

Purpose We have been developing a computer-aided detection (CAD) system for lung nodules on multidetector row computed tomography (MDCT). The scheme for nodule detection in this system is featured by three-dimensional analysis for nodule detection in nodules and their surroundings, which is designed to discriminate nodules from blood vessels. The purpose of this study was to evaluate the CAD system.

Computer-aided diagnosis in breast tomosynthesis and chest CT.

Computer-aided diagnosis (CAD), in the general sense, includes computer-aided detection and characterization of abnormalities on medical images. The usefulness of CAD for assisting radiologists in detection of breast cancer in screening mammography has been demonstrated by a number of prospective clinical trials in recent years. The development of CAD in other areas is also being actively pursued by researchers. In this talk, the recent work in two areas of CAD, digital breast tomosynthesis (DBT) and chest computed tomography (CT), in the CAD Research Laboratory at the University of Michigan will be reviewed. DBT is a new modality under development for breast imaging. The quasi-3D information in DBT alleviates the problem of overlapping tissue in mammography and holds the promise to improve the sensitivity for cancer detection. DBT image analysis can be performed in the 3D reconstructed volume of the 2D projection view (PV) images. DBT image quality depend on the image acquisition parameters, reconstruction method and parameters. The flexibility in image processing approaches makes CAD development for DBT interesting and challenging. out early experiences in the development of image segmentation and features extraction technique for mass detection and characterization in DBT will be discussed. The performances of the CAD systems using the 2D, 3D, and combined 2D and 3D approaches will be compared. CT has been shown to be superior to chest x-ray in detection of small lung nodules and thus lung cancer screening with CT is still being debated, many research groups are developing CAD methods for detection and characterization of lung nodules in chest CT scans. The specific prescreening, segmentation, and feature extraction techniques designed for our lung nodule detection and characterization systems will be discussed. The effects of CAD on radiologists' accuracy in nodules detection and characterization in CT scans will be demonstrated by results of observer ROC studies. There are similarities in the approaches to developing CAD methods in 3D image volumes such as DBT and CT, these experiences will facilitate the development of CAD systems for other diseases in 3D modalities.

Computer-aided detection of lung nodules on multidetector row computed tomography using three-dimensional analysis of nodule candidates and their surroundings

We have been developing a computer-aided detection (CAD) system for lung nodules on multidetector row computed tomography (MDCT). The scheme for nodule detection in this system is featured by three-dimensional analysis of nodule candidates [corrected] and their surroundings, which is designed to discriminate nodules from blood vessels. The purpose of this study was to evaluate the CAD system. MDCT images from 30 patients with lung nodules were read twice, 3 weeks apart by a chest radiologist to detect noncalcified nodules of > or = 4 mm. The first reading was without CAD, and the second reading was with CAD. Based on the reference standard later determined by another chest radiologist, the sensitivity of the former chest radiologist without or with CAD was obtained; the sensitivity and false-positive rate of the system alone were also obtained. The reference standard consisted of 66 nodules. The sensitivity of the chest radiologist was 77% (51/66) without CAD and 91% (60/66) with CAD, showing a significant improvement. The CAD system alone showed a sensitivity of 79% (52/66) with the false-positive rate of 4.5 per patient. Although preliminary, these results indicate the efficacy of the CAD system.

Ultra-Low-Dose MDCT of the Chest: Influence on Automated Lung Nodule Detection

ObjectiveTo evaluate the relationship between CT dose and the performance of a computer-aided diagnosis (CAD) system, and to determine how best to minimize patient exposure to ionizing radiation while maintaining sufficient image quality for automated lung nodule detection, by the use of lung cancer screening CT.Materials and MethodsTwenty-five asymptomatic volunteers participated in the study. Each volunteer underwent a low-dose CT scan without contrast enhancement (multidetector CT with 16 detector rows, 1.25 mm section thickness, 120 kVp, beam pitch 1.35, 0.6 second rotation time, with 1.25 mm thickness reconstruction at 1.25 mm intervals) using four different amperages 32, 16, 8, and 4 mAs. All series were analyzed using a commercially available CAD system for automatic lung nodule detection and the results were reviewed by a consensus reading by two radiologists. The McNemar test and Kappa analysis were used to compare differences in terms of the abilities to detect pulmonary nodules.ResultsA total of 78 non-calcified true nodules were visualized in the 25 study subjects. The sensitivities for nodule detection were as follows: 72% at 32 mAs, 64% at 16 mAs, 59% at 8 mAs, and 40% at 4 mAs. Although the overall nodule-detecting performance was best at 32 mAs, no significant difference in nodule detectability was observed between scans at 16 mAs or 8 mAs versus 32 mAs. However, scans performed at 4 mAs were significantly inferior to those performed at 32 mAs (p < 0.001).ConclusionReducing the radiation dose (i.e. reducing the amperage) lowers lung nodule detectability by CAD. However, relatively low dose scans were found to be acceptable and to cause no significant reduction in nodule detectability versus usual low-dose CT.

A KNOWLEDGE-BASED LUNG NODULE DETECTION SYSTEM FOR HELICAL CT IMAGES

In this paper, we describe a knowledge-based system for segmenting and labeling lung nodule on helical CT images. The system was developed under a blackboard environment that incorporates a lung knowledge model, image processing model, inference engine and a blackboard. Lung model, which contains both analogical and propositional knowledge about lung in the form of semantic networks, was used to guide the interpretation process. The system works in a hierarchical structure, from large structures to the final nodule candidates by focusing on the interested region step by step. The symbolic variables, introduced to accomplish high-level inference, were defined by fuzzy confidence functions in the lung model. Composite fuzzy functions were applied to evaluate the plausibility of the mapping between the image and lung model objects. Anatomical lung segments knowledge was embedded in the system to direct 3D validation of suspicious objects. Structures were identified and abnormal objects were reported. The experimental results obtained demonstrate the proof of concept and the potential of the automated knowledge-based lung nodule detection system.

Computer-aided Lung Nodule Detection in CT: Results of Large-Scale Observer Test 1

The objective is to study the incremental effects of using a computer-aided lung nodule detection (CAD) system on the performance of a large pool of observers. A set of eight thin-section computed tomographic data sets with limited longitudinal coverage, containing a total of 22 lung nodules, was analyzed by using the automated nodule detection system. When applied to all eight cases, the CAD system alone achieved a detection rate of 86.4%, with 2.64 false-positive results per case. This study included 202 observers at a national radiology meeting: 39 thoracic radiologists, 95 non-thoracic radiologists, and 68 non-radiologists. Each participant read from one to eight cases in random order, first without and then with CAD system output available. Observer performance in nodule detection was measured before and after CAD was made available. Differences in performance of groups of observers before and after CAD were tabulated by mean, median, and SD in detection rate and number of false-positive results and tested by using nonparametric methods. In an analysis involving only the first randomly selected case read by all 202 participants, there were statistically significant increases in nodule detection rates and numbers of false-positive results for all types of observers. There was a significant difference in detection rates between radiologists and non-radiologists before CAD, but after CAD, there was no significant difference in detection rates between these observer types. In a second analysis involving 13 participants who read all eight cases, mean detection rates were 64.0% before CAD and 81.9% after CAD. Mean numbers of false-positive results were 0.144 per case before CAD and 0.173 after CAD. In a large observer study, use of a CAD system for nodule detection resulted in an incremental increase in detection rate, but also led to an increase in number of false-positive results. Also, CAD appears to be an equalizer of detection rates between observers of different levels of experience.

The potential contribution of a computer-aided detection system for lung nodule detection in multidetector row computed tomography.

We sought to evaluate the potential benefits of a computer-aided detection (CAD) system for detecting lung nodules in multidetector row CT (MDCT) scans. A CAD system was developed for detecting lung nodules on MDCT scans and was applied to the data obtained from 15 patients. Two chest radiologists in consensus established the reference standard. The nodules were categorized according to their size and their relationship to the surrounding structures (nodule type). The differences in the sensitivities between an experienced chest radiologist and a CAD system without user interaction were evaluated using a chi2 analysis. The differences in the sensitivities also were compared in terms of the nodule size and the nodule type. A total of 309 nodules were identified as the reference standard. The sensitivity of a CAD system (81%) was not significantly different from that of a radiologist (85%; P > 0.05). The sensitivities of the CAD system for detecting nodules < or = 5 mm in diameter as well as detecting isolated nodules were higher than those of a radiologist (83% vs. 75%, P > 0.05; 93% vs. 76%, P < 0.001). The sensitivities of a radiologist for detecting nodules >5 mm and the nodules attached to other structures were higher than those of a CAD system (98% vs. 79%, P < 0.001; 91% vs. 71%, P < 0.001). There were 28.8 false-positive results of CAD per CT study. The CAD system developed in this study performed the nodule detection task in different ways to that of a radiologist in terms of the nodule size and the nodule type, which suggests that the CAD system can play a complementary role to a radiologist in detecting nodules from large CT data sets.

Evaluation of computer-aided detection performance using mathematically simulated lung nodules

The goal of this paper is to assess the performance of a Computer-Aided Detection (CAD) system for lung nodule detection in MDCT examinations of the chest (ImageChecker CT™, R2 Technology), using an objective reference database of computer-generated nodules that mimic the range of nodule characteristics typically found in the chest.

Image annotation for conveying automated lung nodule detection results to radiologists

Rationale and objectives The author investigated the ability of automated techniques to convey the results of an automated lung nodule detection method for human visualization. Materials and methods Automated nodule detection begins with gray-level thresholding techniques to create a segmented lung volume within which nodule candidates are identified. Morphologic and gray-level features are computed for each candidate. To distinguish between candidates that represent actual nodules and those that represent non-nodules, a rule-based scheme is combined with linear discriminant analysis. For output visualization, final detection results are represented as circles around computer-detected structures in a single section in which each structure appears. Consequently, an inappropriate choice of section could result in an actual nodule detected by the computer but not properly indicated to the radiologist, thus reducing the potential positive impact of that detection on the radiologist’s decision-making process. Results The automated nodule detection method achieved 71% sensitivity with 0.5 false positives per section on 38 CT scans; however, when these results were converted to annotations on the images output for human visualization, only 91% of the computer-detected true-positive nodules received annotations that encompassed a portion of the actual nodule. Thus, the “effective sensitivity” of the automated detection method was reduced. Conclusion The “effective sensitivity” of an automated lung nodule detection system considers the eventual human interaction with system output. Differences between reported computer sensitivity and “effective sensitivity” may be reduced through proper consideration of the assessment of “truth,” of the manner in which computer results are scored, and of the complete segmentation of candidates for automated nodule detection.

Hybrid Lung Nodule Detection (HLND) system

A Hybrid Lung Nodule Detection (HLND) system is developed for improving detection accuracy and speed for lung cancerous pulmonary radiology. The configuration of the HLND system includes (i) pre-processing, in order to enhance the figure-background contrast based upon the energy content of nodule; (ii) quick selection of nodule suspects based upon the most prominent feature of nodules, the disc shape; and (iii) complete feature space determination and neural network classification of nodules, based on the characteristics of edges in nodules. Nodule suspects are captured and stored in 32 × 32 images after first two processing phases. Eight categories, including true nodule, rib-crossing, rib-vessel crossing, end vessel, vessel cluster, bone, rib edge, and vessel, are identified for further neural analysis and classification. A supervised back propagation artificial neural network architecture is developed for traning and recognition of feature curves of nodules. Results show that this detection system is able to identify true nodule at accuracy up to 93% with false detection reduced down to 7%.