Automated detection of lung nodules in CT scans: effect of image reconstruction algorithm

A narrative review of deep learning applications in lung cancer research: from screening to prognostication

Background and Objective

Deep learning (DL) algorithms have been developed for various tasks, including lung nodule detection on chest radiographs or lung cancer computed tomography screening, potential candidate selection in lung cancer screening, malignancy prediction for indeterminate pulmonary nodules, lung cancer staging, treatment response prediction, prognostication, and prediction of genetic mutations in lung cancer. Furthermore, these DL algorithms have been applied in various clinical settings in order for them to be generalized in real-world clinical practice. Multiple DL algorithms have been corroborated to be on par with experts or current clinical prediction models for several specific tasks. However, no article has yet comprehensively reviewed DL algorithms dedicated to lung cancer research. This narrative review presents an overview of the literature dealing with DL techniques applied in lung cancer research and briefly summarizes the results according to the DL algorithms’ clinical use cases.

Methods

we performed a narrative review by searching the Embase and OVID-MEDLINE databases for articles published in English from October, 2016 until September, 2021 and reviewing the bibliographies of key references to identify important literature related to DL in lung cancer research. The background, development, results, and clinical implications of each DL algorithm are briefly discussed. Lastly, we end this review article by highlighting future directions in lung cancer research using DL techniques.

Key Content and Findings

DL algorithms have been introduced to show comparable or higher performance than human experts in various clinical settings. Specifically, they have been actively applied to detect lung nodules in chest radiographs or computed tomography (CT) examinations, optimize candidate selection for lung cancer screening (LCS), predict the malignancy of lung nodules, stage lung cancer, and predict treatment response, patients’ prognoses, and genetic mutations in lung cancers.

Conclusions

DL algorithms have corroborated their potential value for various tasks, ranging from lung cancer screening to prognostication of lung cancer patients. Future research is warranted for the clinical application of these algorithms in daily clinical practice and verification of their real-world clinical usefulness.

Artificial intelligence in thoracic surgery: a narrative review

OBJECTIVE

The aim of this article is to review the current applications of artificial intelligence in thoracic surgery, from diagnosis and pulmonary disease management, to preoperative risk-assessment, surgical planning, and outcomes prediction.

BACKGROUND

Artificial intelligence implementation in healthcare settings is rapidly growing, though its widespread use in clinical practice is still limited. The employment of machine learning algorithms in thoracic surgery is wide-ranging, including all steps of the clinical pathway.

METHODS

We performed a narrative review of the literature on Scopus, PubMed and Cochrane databases, including all the relevant studies published in the last ten years, until March 2021.

CONCLUSION

Machine learning methods are promising encouraging results throughout the key issues of thoracic surgery, both clinical, organizational, and educational. Artificial intelligence-based technologies showed remarkable efficacy to improve the perioperative evaluation of the patient, to assist the decision-making process, to enhance the surgical performance, and to optimize the operating room scheduling. Still, some concern remains about data supply, protection, and transparency, thus further studies and specific consensus guidelines are needed to validate these technologies for daily common practice.

KEYWORDS

Artificial intelligence (AI); thoracic surgery; machine learning; lung resection; perioperative medicine.

Applications of artificial intelligence in the thorax: a narrative review focusing on thoracic radiology

OBJECTIVE

This review will focus on how AI-and, specifically, deep learning-can be applied to complement aspects of the current healthcare system. We describe how AI-based tools can augment existing clinical workflows by discussing the applications of AI to worklist prioritization and patient triage, the performance-boosting effects of AI as a second reader, and the use of AI to facilitate complex quantifications. We also introduce prominent examples of recent AI applications, such as tuberculosis screening in resource-constrained environments, the detection of lung cancer with screening CT, and the diagnosis of COVID-19. We also provide examples of prognostic predictions and new discoveries beyond existing clinical practices.

BACKGROUND

Artificial intelligence (AI) has shown promising performance for thoracic diseases, particularly in the field of thoracic radiology. However, it has not yet been established how AI-based image analysis systems can help physicians in clinical practice.

METHODS

This review included peer-reviewed research articles on AI in the thorax published in English between 2015 and 2021.

CONCLUSIONS

With advances in technology and appropriate preparation of physicians, AI could address various clinical problems that have not been solved due to a lack of clinical resources or technological limitations.

KEYWORDS

Artificial intelligence (AI); deep learning (DL); computer aided diagnosis (CAD); thoracic radiology; pulmonary medicine.

Effect of Hybrid Kernel and Iterative Reconstruction on Objective and Subjective Analysis of Lung Nodule Calcification in Low-Dose Chest CT

Objective

To evaluate the differences in subjective calcification detection rates and objective calcium volumes in lung nodules according to different reconstruction methods using hybrid kernel (FC13-H) and iterative reconstruction (IR).

Materials and Methods

Overall, 35 patients with small (< 4 mm) calcified pulmonary nodules on chest CT were included. Raw data were reconstructed using filtered back projection (FBP) or IR algorithm (AIDR-3D; Canon Medical Systems Corporation), with three types of reconstruction kernel: conventional lung kernel (FC55), FC13-H and conventional soft tissue kernel (FC13). The calcium volumes of pulmonary nodules were quantified using the modified Agatston scoring method. Two radiologists independently interpreted the role of each nodule calcification on the six types of reconstructed images (FC55/FBP, FC55/AIDR-3D, FC13-H/FBP, FC13-H/AIDR-3D, FC13/FBP, and FC13/AIDR-3D).

Results

Seventy-eight calcified nodules detected on FC55/FBP images were regarded as reference standards. The calcium detection rates of FC55/AIDR-3D, FC13-H/FBP, FC13-H/AIDR-3D, FC13/FBP, and FC13/AIDR-3D protocols were 80.7%, 15.4%, 6.4%, 52.6%, and 28.2%, respectively, and FC13-H/AIDR-3D showed the smallest calcium detection rate. The calcium volume varied significantly with reconstruction protocols and FC13/AIDR-3D showed the smallest calcium volume (0.04 ± 0.22 mm³), followed by FC13-H/AIDR-3D.

Conclusion

Hybrid kernel and IR influence subjective detection and objective measurement of calcium in lung nodules, particularly when both techniques (FC13-H/AIDR-3D) are combined.

The utilisation of convolutional neural networks in detecting pulmonary nodules: a review

Lung cancer is one of the leading causes of cancer-related fatality in the world. Patients display few or even no signs or symptoms in the early stages, resulting in up to 75% of patients diagnosed in the later stages of the disease. Consequently, there has been a call for lung cancer screening amongst at-risk populations. The early detection of malignant pulmonary nodules in CT is one of the suggested methods proposed to diagnose early-stage lung cancer; however, the reported sensitivity of radiologists' ability to accurately detect pulmonary nodules ranges widely from 30 to 97%. 2012 saw Alex Krizhevsky present a paper titled "ImageNet Classification with Deep Convolutional Networks" in which a multilayered convolutional computational model known as a convolutional neural network (CNN) was confirmed competent in identifying and classifying 1.2 million images to a previously unseen level of accuracy. Since then, CNNs have gained attention as a potential tool in aiding radiologists' detection of pulmonary nodules in CT imaging. This review found the use of CNN is a viable strategy to increase the overall sensitivity of pulmonary nodule detection. Small, non-validated data sets, computational constraints, and incomparable studies are currently limited factors of the existing research.

Automatic Lung Segmentation With Juxta-Pleural Nodule Identification Using Active Contour Model and Bayesian Approach

OBJECTIVE

chest computed tomography (CT) images and their quantitative analyses have become increasingly important for a variety of purposes, including lung parenchyma density analysis, airway analysis, diaphragm mechanics analysis, and nodule detection for cancer screening. Lung segmentation is an important prerequisite step for automatic image analysis. We propose a novel lung segmentation method to minimize the juxta-pleural nodule issue, a notorious challenge in the applications.

METHOD

we initially used the Chan-Vese (CV) model for active lung contours and adopted a Bayesian approach based on the CV model results, which predicts the lung image based on the segmented lung contour in the previous frame image or neighboring upper frame image. Among the resultant juxta-pleural nodule candidates, false positives were eliminated through concave points detection and circle/ellipse Hough transform. Finally, the lung contour was modified by adding the final nodule candidates to the area of the CV model results.

RESULTS

to evaluate the proposed method, we collected chest CT digital imaging and communications in medicine images of 84 anonymous subjects, including 42 subjects with juxta-pleural nodules. There were 16 873 images in total. Among the images, 314 included juxta-pleural nodules. Our method exhibited a disc similarity coefficient of 0.9809, modified hausdorff distance of 0.4806, sensitivity of 0.9785, specificity of 0.9981, accuracy of 0.9964, and juxta-pleural nodule detection rate of 96%. It outperformed existing methods, such as the CV model used alone, the normalized CV model, and the snake algorithm. Clinical impact: the high accuracy with the juxta-pleural nodule detection in the lung segmentation can be beneficial for any computer aided diagnosis system that uses lung segmentation as an initial step.

Technical Note: Image filtering to make computer-aided detection robust to image reconstruction kernel choice in lung cancer CT screening

PURPOSE

In lung cancer computed tomography (CT) screening, the performance of a computer-aided detection (CAD) system depends on the selection of the image reconstruction kernel. To reduce this dependence on reconstruction kernels, the authors propose a novel application of an image filtering method previously proposed by their group.

METHODS

The proposed filtering process uses the ratio of modulation transfer functions (MTFs) of two reconstruction kernels as a filtering function in the spatial-frequency domain. This method is referred to as MTFratio filtering. Test image data were obtained from CT screening scans of 67 subjects who each had one nodule. Images were reconstructed using two kernels: fSTD (for standard lung imaging) and fSHARP (for sharp edge-enhancement lung imaging). The MTFratio filtering was implemented using the MTFs measured for those kernels and was applied to the reconstructed fSHARP images to obtain images that were similar to the fSTD images. A mean filter and a median filter were applied (separately) for comparison. All reconstructed and filtered images were processed using their prototype CAD system.

RESULTS

The MTFratio filtered images showed excellent agreement with the fSTD images. The standard deviation for the difference between these images was very small, ∼6.0 Hounsfield units (HU). However, the mean and median filtered images showed larger differences of ∼48.1 and ∼57.9 HU from the fSTD images, respectively. The free-response receiver operating characteristic (FROC) curve for the fSHARP images indicated poorer performance compared with the FROC curve for the fSTD images. The FROC curve for the MTFratio filtered images was equivalent to the curve for the fSTD images. However, this similarity was not achieved by using the mean filter or median filter.

CONCLUSIONS

The accuracy of MTFratio image filtering was verified and the method was demonstrated to be effective for reducing the kernel dependence of CAD performance.

Initial phantom study comparing image quality in computed tomography using adaptive statistical iterative reconstruction and new adaptive statistical iterative reconstruction v

PURPOSE

The purpose of this study was to assess the image quality of a novel advanced iterative reconstruction (IR) method called as "adaptive statistical IR V" (ASIR-V) by comparing the image noise, contrast-to-noise ratio (CNR), and spatial resolution from those of filtered back projection (FBP) and adaptive statistical IR (ASIR) on computed tomography (CT) phantom image.

MATERIALS AND METHODS

We performed CT scans at 5 different tube currents (50, 70, 100, 150, and 200 mA) using 3 types of CT phantoms. Scanned images were subsequently reconstructed in 7 different scan settings, such as FBP, and 3 levels of ASIR and ASIR-V (30%, 50%, and 70%). The image noise was measured in the first study using body phantom. The CNR was measured in the second study using contrast phantom and the spatial resolutions were measured in the third study using a high-resolution phantom. We compared the image noise, CNR, and spatial resolution among the 7 reconstructed image scan settings to determine whether noise reduction, high CNR, and high spatial resolution could be achieved at ASIR-V.

RESULTS

At quantitative analysis of the first and second studies, it showed that the images reconstructed using ASIR-V had reduced image noise and improved CNR compared with those of FBP and ASIR (P < 0.001). At qualitative analysis of the third study, it also showed that the images reconstructed using ASIR-V had significantly improved spatial resolution than those of FBP and ASIR (P < 0.001).

CONCLUSIONS

Our phantom studies showed that ASIR-V provides a significant reduction in image noise and a significant improvement in CNR as well as spatial resolution. Therefore, this technique has the potential to reduce the radiation dose further without compromising image quality.

Quantifying tumour heterogeneity with CT

Heterogeneity is a key feature of malignancy associated with adverse tumour biology. Quantifying heterogeneity could provide a useful non-invasive imaging biomarker. Heterogeneity on computed tomography (CT) can be quantified using texture analysis which extracts spatial information from CT images (unenhanced, contrast-enhanced and derived images such as CT perfusion) that may not be perceptible to the naked eye. The main components of texture analysis can be categorized into image transformation and quantification. Image transformation filters the conventional image into its basic components (spatial, frequency, etc.) to produce derived subimages. Texture quantification techniques include structural-, model- (fractal dimensions), statistical- and frequency-based methods. The underlying tumour biology that CT texture analysis may reflect includes (but is not limited to) tumour hypoxia and angiogenesis. Emerging studies show that CT texture analysis has the potential to be a useful adjunct in clinical oncologic imaging, providing important information about tumour characterization, prognosis and treatment prediction and response.

A novel computer-aided lung nodule detection system for CT images

PURPOSE

The paper presents a complete computer-aided detection (CAD) system for the detection of lung nodules in computed tomography images. A new mixed feature selection and classification methodology is applied for the first time on a difficult medical image analysis problem.

METHODS

The CAD system was trained and tested on images from the publicly available Lung Image Database Consortium (LIDC) on the National Cancer Institute website. The detection stage of the system consists of a nodule segmentation method based on nodule and vessel enhancement filters and a computed divergence feature to locate the centers of the nodule clusters. In the subsequent classification stage, invariant features, defined on a gauge coordinates system, are used to differentiate between real nodules and some forms of blood vessels that are easily generating false positive detections. The performance of the novel feature-selective classifier based on genetic algorithms and artificial neural networks (ANNs) is compared with that of two other established classifiers, namely, support vector machines (SVMs) and fixed-topology neural networks. A set of 235 randomly selected cases from the LIDC database was used to train the CAD system. The system has been tested on 125 independent cases from the LIDC database.

RESULTS

The overall performance of the fixed-topology ANN classifier slightly exceeds that of the other classifiers, provided the number of internal ANN nodes is chosen well. Making educated guesses about the number of internal ANN nodes is not needed in the new feature-selective classifier, and therefore this classifier remains interesting due to its flexibility and adaptability to the complexity of the classification problem to be solved. Our fixed-topology ANN classifier with 11 hidden nodes reaches a detection sensitivity of 87.5% with an average of four false positives per scan, for nodules with diameter greater than or equal to 3 mm. Analysis of the false positive items reveals that a considerable proportion (18%) of them are smaller nodules, less than 3 mm in diameter.

CONCLUSIONS

A complete CAD system incorporating novel features is presented, and its performance with three separate classifiers is compared and analyzed. The overall performance of our CAD system equipped with any of the three classifiers is well with respect to other methods described in literature.

Hybrid convolution kernel: optimized CT of the head, neck, and spine

OBJECTIVE

Conventional CT requires generation of separate images utilizing different convolution kernels to optimize lesion detection. Our goal was to develop and test a hybrid CT algorithm to simultaneously optimize bone and soft-tissue characterization, potentially halving the number of images that need to be stored, transmitted, and reviewed.

MATERIALS AND METHODS

CT images generated with separate high-pass (bone) and low-pass (soft tissue) kernels were retrospectively combined so that low-pass algorithm pixels less than -150 HU or greater than 150 HU are substituted with corresponding high-pass kernel reconstructed pixels. A total of 38 CT examinations were reviewed using the hybrid technique, including 20 head, eight spine, and 10 head and neck scans. Three neuroradiologists independently reviewed all 38 hybrid cases, comparing them to both standard low-pass and high-pass kernel convolved images for characterization of anatomy and pathologic abnormalities. The conspicuity of bone, soft tissue, and related anatomy were compared for each CT reconstruction technique.

RESULTS

For the depiction of bone, in all 38 cases, the three neuroradiologists scored the hybrid images as being equivalent to high-pass kernel reconstructions but superior to the low-pass kernel. For depiction of extracranial soft tissues and brain, the hybrid kernel was rated equivalent to the low-pass kernel but superior to that of the high-pass kernel.

CONCLUSION

The hybrid convolution kernel is a promising technique affording optimized bone and soft tissue evaluation while potentially halving the number of images needed to be transmitted, stored, and reviewed.

Texture analysis of non-small cell lung cancer on unenhanced computed tomography: initial evidence for a relationship with tumour glucose metabolism and stage

The aim was to undertake an initial study of the relationship between texture features in computed tomography (CT) images of non-small cell lung cancer (NSCLC) and tumour glucose metabolism and stage. This retrospective pilot study comprised 17 patients with 18 pathologically confirmed NSCLC. Non-contrast-enhanced CT images of the primary pulmonary lesions underwent texture analysis in 2 stages as follows: (a) image filtration using Laplacian of Gaussian filter to differentially highlight fine to coarse textures, followed by (b) texture quantification using mean grey intensity (MGI), entropy (E) and uniformity (U) parameters. Texture parameters were compared with tumour fluorodeoxyglucose (FDG) uptake (standardised uptake value (SUV)) and stage as determined by the clinical report of the CT and FDG-positron emission tomography imaging. Tumour SUVs ranged between 2.8 and 10.4. The number of NSCLC with tumour stages I, II, III and IV were 4, 4, 4 and 6, respectively. Coarse texture features correlated with tumour SUV (E: r = 0.51, p = 0.03; U: r = −0.52, p = 0.03), whereas fine texture features correlated with tumour stage (MGI: r_s = 0.71, p = 0.001; E: r_s = 0.55, p = 0.02; U: r_s = −0.49, p = 0.04). Fine texture predicted tumour stage with a kappa of 0.7, demonstrating 100% sensitivity and 87.5% specificity for detecting tumours above stage II ( p = 0.0001). This study provides initial evidence for a relationship between texture features in NSCLC on non-contrast-enhanced CT and tumour metabolism and stage. Texture analysis warrants further investigation as a potential method for obtaining prognostic information for patients with NSCLC undergoing CT.

Computer-aided detection of lung nodules: influence of the image reconstruction kernel for computer-aided detection performance

OBJECTIVE

To evaluate the relationship between a computed tomographic reconstruction kernel and the sensitivity of a computer-aided detection (CAD) system for lung nodule detection.

METHODS

We retrospectively studied 36 consecutive patients with no known pulmonary nodules who underwent low-dose computed tomography for lung cancer screening with 3 different reconstruction kernels (B, C, and L). All series were reviewed with a commercial CAD system for lung nodule detection.

RESULTS

The 36 scans showed 231 uncalcified nodules (170 micronodules and 61 nodules). There was little variation of sensitivities for each series (82%, 88%, and 82% for the nodules of B, C, and L, respectively). When the results of 2 series were combined, sensitivities were boosted (B + C, 89%; B + L, 95%; and C + L, 96% for the nodules).

CONCLUSIONS

Sensitivity of the CAD system was influenced by the selection of the reconstruction kernel. By combining data from 2 different kernels, CAD sensitivity can be elevated without further patient radiation exposure.

A novel multithreshold method for nodule detection in lung CT

Multislice computed tomography (MSCT) is a valuable tool for lung cancer detection, thanks to its ability to identify noncalcified nodules of small size (from about 3 mm). Due to the large number of images generated by MSCT, there is much interest in developing computer-aided detection (CAD) systems that could assist radiologists in the lung nodule detection task. A complete multistage CAD system, including lung boundary segmentation, regions of interest (ROIs) selection, feature extraction, and false positive reduction is presented. The selection of ROIs is based on a multithreshold surface-triangulation approach. Surface triangulation is performed at different threshold values, varying from a minimum to a maximum value in a wide range. At a given threshold value, a ROI is defined as the volume inside a connected component of the triangulated isosurface. The evolution of a ROI as a function of the threshold can be represented by a treelike structure. A multithreshold ROI is defined as a path on this tree, which starts from a terminal ROI and ends on the root ROI. For each ROI, the volume, surface area, roundness, density, and moments of inertia are computed as functions of the threshold and used as input to a classification system based on artificial neural networks. The method is suitable to detect different types of nodules, including juxta-pleural nodules and nodules connected to blood vessels. A training set of 109 low-dose MSCT scans made available by the Pisa center of the Italung-CT trial and annotated by expert radiologists was used for the algorithm design and optimization. The system performance was tested on an independent set of 23 low-dose MSCT scans coming from the Pisa Italung-CT center and on 83 scans made available by the Lung Image Database Consortium (LIDC) annotated by four expert radiologists. On the Italung-CT test set, for nodules having a diameter greater than or equal to 3 mm, the system achieved 84% and 71% sensitivity at false positive/scan rates of 10 and 4, respectively. For nodules having a diameter greater than or equal to 4 mm, the sensitivities were 97% and 80% at false positive/scan rates of 10 and 4, respectively. On the LIDC data set, the system achieved a 79% sensitivity at a false positive/scan rate of 4 in the detection of nodules with a diameter greater than or equal to 3 mm that have been annotated by all four radiologists.

Recent progress in computer-aided diagnosis of lung nodules on thin-section CT

Computer-aided diagnosis (CAD) provides a computer output as a "second opinion" in order to assist radiologists in the diagnosis of various diseases on medical images. Currently, a significant research effort is being devoted to the detection and characterization of lung nodules in thin-section computed tomography (CT) images, which represents one of the newest directions of CAD development in thoracic imaging. We describe in this article the current status of the development and evaluation of CAD schemes for the detection and characterization of lung nodules in thin-section CT. We also review a number of observer performance studies in which it was attempted to assess the potential clinical usefulness of CAD schemes for nodule detection and characterization in thin-section CT. Whereas current CAD schemes for nodule characterization have achieved high performance levels and would be able to improve radiologists' performance in the characterization of nodules in thin-section CT, current schemes for nodule detection appear to report many false positives, and, therefore, significant efforts are needed in order further to improve the performance levels of current CAD schemes for nodule detection in thin-section CT.

Computer-aided detection of solid lung nodules in lossy compressed multidetector computed tomography chest exams

RATIONALE AND OBJECTIVES

To assess the effect of three-dimensional (3D) lossy image compression of multidetector computed tomography chest scans on computer-aided detection (CAD) of solid lung nodules greater than 4 mm in size.

MATERIALS AND METHODS

A total of 120 cases, acquired with 1.25-mm collimation, were collected from 5 different sites, of which 66/120 were low-dose cases. Two chest radiologists established that 37 cases had no actionable lung nodules; the remaining 83 cases contained 169 nodules (range 3.8-35.0 mm, mean 5.8 mm +/- 3.0 [SD]). All cases were compressed using the 3D Set Partitioning in Hierarchical Trees algorithm to 24:1, 48:1, and 96:1 levels. A study of the effect of compression on computer-aided detection (CAD) sensitivity was performed at operating points of 2.5 false marks (FM), 5 FM, and 10 FM per case using McNemar's test. Logistic regression models were used to evaluate the impact on CAD sensitivity by compression level on nodule and image characteristics.

RESULTS

Compared with no compression, there was no significant degradation in CAD sensitivity found at any of the studied compression levels and operating points. However, between compression levels, there was marginal association with sensitivity. Specifically, 24:1 level was significantly better than 96:1 at all operating points, and occasionally better than no compression at 10 FM/case. Based on multivariate analysis, nodule location was found to be a significant predictor (P = .01) with a lower sensitivity associated with juxtapleural nodules. Nodule size, dose, reconstruction filter, and contrast medium were not significant predictors.

CONCLUSION

CAD detection performance of solid lung nodules did not suffer until 48:1 compression.

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.

Computerized mass detection for digital breast tomosynthesis directly from the projection images

Digital breast tomosynthesis (DBT) has recently emerged as a new and promising three-dimensional modality in breast imaging. In DBT, the breast volume is reconstructed from 11 projection images, taken at source angles equally spaced over an arc of 50 degrees. Reconstruction algorithms for this modality are not fully optimized yet. Because computerized lesion detection in the reconstructed breast volume will be affected by the reconstruction technique, we are developing a novel mass detection algorithm that operates instead on the set of raw projection images. Mass detection is done in three stages. First, lesion candidates are obtained for each projection image separately, using a mass detection algorithm that was initially developed for screen-film mammography. Second, the locations of a lesion candidate are backprojected into the breast volume. In this feature volume, voxel intensities are a combined measure of detection frequency (e.g., the number of projections in which a given lesion candidate was detected), and a measure of the angular range over which a given lesion was detected. Third, features are extracted after reprojecting the three-dimensional (3-D) locations of lesion candidates into projection images. Features are combined using linear discriminant analysis. The database used to test the algorithm consisted of 21 mass cases (13 malignant, 8 benign) and 15 cases without mass lesions. Based on this database, the algorithm yielded a sensitivity of 90% at 1.5 false positives per breast volume. Algorithm performance is positively biased because this dataset was used for development, training, and testing, and because the number of algorithm parameters was approximately the same as the number.of patient cases. Our results indicate that computerized mass detection in the sequence of projection images for DBT may be effective despite the higher noise level in those images.

Pulmonary nodules: estimation of malignancy at thin-section helical CT--effect of computer-aided diagnosis on performance of radiologists

PURPOSE

To evaluate the effect of a computer-aided diagnosis (CAD) system on the diagnostic performance of radiologists for the estimation of the malignancy of pulmonary nodules on thin-section helical computed tomographic (CT) scans.

MATERIALS AND METHODS

The institutional review board approved use of the CT database; informed specific study-related consent was waived. The institutional review board approved participation of radiologists; informed consent was obtained from all observers. Thirty-three (18 malignant, 15 benign) pulmonary nodules of less than 3.0 cm in maximal diameter were evaluated. Receiver operating characteristic (ROC) analysis with a continuous rating scale was used to compare observer performance for the estimation of the likelihood of malignancy first without and then with the CAD system. The participants were 10 board-certified radiologists and nine radiology residents.

RESULTS

For all 19 participants, the mean area under the best-fit ROC curve (A(z)) values achieved without and with the CAD system were 0.843 +/- 0.097 (standard deviation) and 0.924 +/- 0.043, respectively. The difference was significant (P = .021). The mean A(z) values achieved without and with the CAD system were 0.910 +/- 0.052 and 0.944 +/- 0.040, respectively, for the 10 board-certified radiologists (P = .190) and 0.768 +/- 0.078 and 0.901 +/- 0.036, respectively, for the nine radiology residents (P = .009).

CONCLUSION

Use of the CAD system significantly (P = .009) improved the diagnostic performance of radiology residents for assessment of the malignancy of pulmonary nodules; however, it did not improve that of board-certified radiologists.

Autonomous detection of pulmonary nodules on CT images with a neural network-based fuzzy system

In this paper, a novel extension of neural network-based fuzzy model has been proposed to detect lung nodules. The proposed model can automatically identify a set of appropriate fuzzy inference rules, and refine the membership functions through the steepest gradient descent-learning algorithm. Twenty-nine clinical cases involving 583 thick section CT images were tested in this study. Receiver operating characteristic (ROC) analysis was used to evaluate the proposed autonomous pulmonary nodules detection system and yielded an area under the ROC curve of Azs=0.963. The overall detection sensitivity of the proposed method was 89.3% (with p-value less than 0.001), and the false positive was as low as 0.2 per image. This result demonstrates that the proposed neural network-based fuzzy system resolves the most suitable fuzzy rules, improves the detection rate, and reduces false positives compared to other approaches. The proposed system is fully automated with fast processing speed. The studies have shown a high potential for implementation of this system in clinical practice as a CAD tool.

Lung Nodule Detection and Characterization With Multi-Slice CT

The influence of MSCT on nodule detection and characterization will be discussed. The objective is to improve understanding of the clinical issues involved in nodule detection, characterization, and management in light of technological advances. Topics to be covered are noninvasive characterization techniques, such as morphologic and density inspection on CT, nodule enhancement techniques, CT-PET, temporal nodule size assessment, and computer aided diagnosis for both detection and characterization.

Vessel tree reconstruction in thoracic CT scans with application to nodule detection

Vessel tree reconstruction in volumetric data is a necessary prerequisite in various medical imaging applications. Specifically, when considering the application of automated lung nodule detection in thoracic computed tomography (CT) scans, vessel trees can be used to resolve local ambiguities based on global considerations and so improve the performance of nodule detection algorithms. In this study, a novel approach to vessel tree reconstruction and its application to nodule detection in thoracic CT scans was developed by using correlation-based enhancement filters and a fuzzy shape representation of the data. The proposed correlation-based enhancement filters depend on first-order partial derivatives and so are less sensitive to noise compared with Hessian-based filters. Additionally, multiple sets of eigenvalues are used so that a distinction between nodules and vessel junctions becomes possible. The proposed fuzzy shape representation is based on regulated morphological operations that are less sensitive to noise. Consequently, the vessel tree reconstruction algorithm can accommodate vessel bifurcation and discontinuities. A quantitative performance evaluation of the enhancement filters and of the vessel tree reconstruction algorithm was performed. Moreover, the proposed vessel tree reconstruction algorithm reduced the number of false positives generated by an existing nodule detection algorithm by 38%.

Accuracy of segmentation of a commercial computer-aided detection system for mammography

PURPOSE

To assess the accuracy of segmentation in a commercially available computer-aided detection (CAD) system.

MATERIALS AND METHODS

Approval for this study was obtained from the authors' institutional review board. Informed consent was not required by the board for this review, as data were stripped of patient identifiers. Two thousand twenty mammograms from 507 women were analyzed with the hardware and software of a commercial CAD system. The accuracy of the segmentation process was determined semiquantitatively and categorized as near perfect if the skin line of the breast was accurately detected, acceptable if only subcutaneous fat was excluded, or unacceptable if any breast parenchyma was excluded from consideration. The accuracy of segmentation was compared for different breast densities and film sizes by using logistic regression (P < .05).

RESULTS

Overall, segmentation was near perfect or acceptable in almost 96.8% of images. However, segmentation defects were significantly more common in mammograms with heterogeneously dense breast tissue (8% unacceptable) than in those with fatty replaced (0% unacceptable), scattered (1.2% unacceptable), or extremely dense (1.8% unacceptable) breast parenchyma (P < .05). For images with unacceptable segmentation, the average percentage of breast parenchyma excluded was almost 25% (range, 5%-100%), with no significant differences among breast densities.

CONCLUSION

For one commercial CAD system, segmentation was usually near perfect or acceptable but was unacceptable more than five times more frequently for mammograms of breasts with heterogeneously dense parenchyma than for those with all other breast densities. On average, one-quarter of the breast parenchyma was excluded from CAD analysis for images with unacceptable segmentation.

Evaluation of automated lung nodule detection on low-dose computed tomography scans from a lung cancer screening program(1)

RATIONALE AND OBJECTIVES

The purpose of this study was to evaluate the performance of a fully automated lung nodule detection method in a large database of low-dose computed tomography (CT) scans from a lung cancer screening program. Because nodules demonstrate a spectrum of radiologic appearances, the performance of the automated method was evaluated on the basis of nodule malignancy status, size, subtlety, and radiographic opacity.

MATERIALS AND METHODS

A database of 393 thick-section (10 mm) low-dose CT scans was collected. Automated lung nodule detection proceeds in two phases: gray-level thresholding for the initial identification of nodule candidates, followed by the application of a rule-based classifier and linear discriminant analysis to distinguish between candidates that correspond to actual lung nodules and candidates that correspond to non-nodules. Free-response receiver operating characteristic analysis was used to evaluate the performance of the method based on a jackknife training/testing approach.

RESULTS

An overall nodule detection sensitivity of 70% (330 of 470) was attained with an average of 1.6 false-positive detections per section. At the same false-positive rate, 83% (57 of 69) of the malignant lung nodules in the database were detected. When the method was trained specifically for malignant nodules, a sensitivity of 80% (55 of 69) was attained with 0.85 false-positives per section.

CONCLUSION

We have evaluated an automated lung nodule detection method with a large number of low-dose CT scans from a lung cancer screening program. An overall sensitivity of 80% for malignant nodules was achieved with 0.85 false-positive detections per section. Such a computerized lung nodule detection method is expected to become an important part of CT-based lung cancer screening programs.

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.

Automated lung segmentation for thoracic CT impact on computer-aided diagnosis

RATIONALE AND OBJECTIVES

Automated lung segmentation in thoracic computed tomography scans is essential for the development of computer-aided diagnostic (CAD) methods. A core segmentation method may be developed for general application; however, modifications may be required for specific clinical tasks.

MATERIALS AND METHODS

An automated lung segmentation method has been applied (1) as preprocessing for automated lung nodule detection and (2) as the foundation for computer-assisted measurements of pleural mesothelioma tumor thickness. The core method uses gray-level thresholding to segment the lungs within each computed tomography section. The segmentation is revised through separation of right and left lungs along the anterior junction line, elimination of the trachea and main bronchi from the lung segmentation regions, and suppression of the diaphragm. Segmentation modifications required for nodule detection include a rolling ball algorithm to include juxtapleural nodules and morphologic erosion to eliminate partial volume pixels at the boundary of the segmentation regions.

RESULTS

For automated lung nodule detection, 4 of 82 actual nodules (4.9%) were excluded from the lung segmentation regions when the core segmentation method was modified compared with 14 nodules (17.1%) excluded without modifications. The computer-assisted quantification of mesothelioma method achieved a correlation coefficient of 0.990 with 134 manual measurements when the core segmentation method was used alone; correlation was reduced to 0.977 when the segmentation modifications, as adapted for the lung nodule detection task, were applied to the mesothelioma measurement task.

CONCLUSION

Different CAD applications impose different requirements on the automated lung segmentation process. The specific approach to lung segmentation must be adapted to the particular CAD task.

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.

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.