Samuel G. Armato

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.

Multicenter, Double-Blind, Placebo-Controlled, Randomized Phase II Trial of Gemcitabine/Cisplatin Plus Bevacizumab or Placebo in Patients With Malignant Mesothelioma

PURPOSE Gemcitabine plus cisplatin is active in malignant mesothelioma (MM), although single-arm phase II trials have reported variable outcomes. Vascular endothelial growth factor (VEGF) inhibitors have activity against MM in preclinical models. We added the anti-VEGF antibody bevacizumab to gemcitabine/cisplatin in a multicenter, double-blind, placebo-controlled randomized phase II trial in patients with previously untreated, unresectable MM. PATIENTS AND METHODS Eligible patients had an Eastern Cooperative Oncology Group (ECOG) performance status of 0 to 1 and no thrombosis, bleeding, or major blood vessel invasion. The primary end point was progression-free survival (PFS). Patients were stratified by ECOG performance status (0 v 1) and histologic subtype (epithelial v other). Patients received gemcitabine 1,250 mg/m(2) on days 1 and 8 every 21 days, cisplatin 75 mg/m(2) every 21 days, and bevacizumab 15 mg/kg or placebo every 21 days for six cycles, and then bevacizumab or placebo every 21 days until progression. RESULTS One hundred fifteen patients were enrolled at 11 sites; 108 patients were evaluable. Median PFS time was 6.9 months for the bevacizumab arm and 6.0 months for the placebo arm (P = .88). Median overall survival (OS) times were 15.6 and 14.7 months in the bevacizumab and placebo arms, respectively (P = .91). Partial response rates were similar (24.5% for bevacizumab v 21.8% for placebo; P = .74). A higher pretreatment plasma VEGF concentration (n = 56) was associated with shorter PFS (P = .02) and OS (P = .0066), independent of treatment arm. There were no statistically significant differences in toxicity of grade 3 or greater. CONCLUSION The addition of bevacizumab to gemcitabine/cisplatin in this trial did not significantly improve PFS or OS in patients with advanced MM.

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%.

Comparing and combining algorithms for computer-aided detection of pulmonary nodules in computed tomography scans: The ANODE09 study

Numerous publications and commercial systems are available that deal with automatic detection of pulmonary nodules in thoracic computed tomography scans, but a comparative study where many systems are applied to the same data set has not yet been performed. This paper introduces ANODE09 ( http://anode09.isi.uu.nl), a database of 55 scans from a lung cancer screening program and a web-based framework for objective evaluation of nodule detection algorithms. Any team can upload results to facilitate benchmarking. The performance of six algorithms for which results are available are compared; five from academic groups and one commercially available system. A method to combine the output of multiple systems is proposed. Results show a substantial performance difference between algorithms, and demonstrate that combining the output of algorithms leads to marked performance improvements.

Automated lung segmentation in digitized posteroanterior chest radiographs

RATIONALE AND OBJECTIVES The authors developed and tested a gray-level thresholding-based approach to automated lung segmentation in digitized posteroanterior chest radiographs. MATERIALS AND METHODS Gray-level histogram analysis was initially performed to establish a range of thresholds for use during an iterative global gray-level thresholding technique. Local gray-level threshold analysis was then performed on the output of global thresholding. The resulting contours were subjected to several smoothing processes, including a rolling-ball technique. The final contours closely approximated the boundaries of the aerated lung regions. The method was applied to a database of 600 posteroanterior chest images. Radiologists rated the accuracy and completeness of the contours with a five-point scale. RESULTS Results of the subjective rating evaluation indicated that this method was accurate, with 79% of the assigned ratings reflecting moderately or highly accurate segmentation and only 8% of the ratings indicating moderately or highly inaccurate segmentation. CONCLUSION This gray-level thresholding-based approach provides accurate automated lung segmentation in digital posteroanterior chest radiographs.

Measurement of mesothelioma on thoracic CT scans: a comparison of manual and computer-assisted techniques.

Our purpose in this study was to evaluate the variability of manual mesothelioma tumor thickness measurements in computed tomography (CT) scans and to assess the relative performance of six computerized measurement algorithms. The CT scans of 22 patients with malignant pleural mesothelioma were collected. In each scan, an initial observer identified up to three sites in each of three CT sections at which tumor thickness measurements were to be made. At each site, five observers manually measured tumor thickness through a computer interface. Three observers repeated these measurements during three separate sessions. Inter- and intra-observer variability in the manual measurement of tumor thickness was assessed. Six automated measurement algorithms were developed based on the geometric relationship between a specified measurement site and the automatically extracted lung regions. Computer-generated measurements were compared with manual measurements. The tumor thickness measurements of different observers were highly correlated (r > or = 0.99); however, the 95% limits of agreement for relative inter-observer difference spanned a range of 30%. Tumor thickness measurements generated by the computer algorithms also correlated highly with the average of observer measurements (r > or = 0.93). We have developed computerized techniques for the measurement of mesothelioma tumor thickness in CT scans. These techniques achieved varying levels of agreement with measurements made by human observers.

Lung Texture in Serial Thoracic Computed Tomography Scans: Correlation of Radiomics-based Features With Radiation Therapy Dose and Radiation Pneumonitis Development

PURPOSE To assess the relationship between radiation dose and change in a set of mathematical intensity- and texture-based features and to determine the ability of texture analysis to identify patients who develop radiation pneumonitis (RP). METHODS AND MATERIALS A total of 106 patients who received radiation therapy (RT) for esophageal cancer were retrospectively identified under institutional review board approval. For each patient, diagnostic computed tomography (CT) scans were acquired before (0-168 days) and after (5-120 days) RT, and a treatment planning CT scan with an associated dose map was obtained. 32- × 32-pixel regions of interest (ROIs) were randomly identified in the lungs of each pre-RT scan. ROIs were subsequently mapped to the post-RT scan and the planning scan dose map by using deformable image registration. The changes in 20 feature values (ΔFV) between pre- and post-RT scan ROIs were calculated. Regression modeling and analysis of variance were used to test the relationships between ΔFV, mean ROI dose, and development of grade ≥2 RP. Area under the receiver operating characteristic curve (AUC) was calculated to determine each features ability to distinguish between patients with and those without RP. A classifier was constructed to determine whether 2- or 3-feature combinations could improve RP distinction. RESULTS For all 20 features, a significant ΔFV was observed with increasing radiation dose. Twelve features changed significantly for patients with RP. Individual texture features could discriminate between patients with and those without RP with moderate performance (AUCs from 0.49 to 0.78). Using multiple features in a classifier, AUC increased significantly (0.59-0.84). CONCLUSIONS A relationship between dose and change in a set of image-based features was observed. For 12 features, ΔFV was significantly related to RP development. This study demonstrated the ability of radiomics to provide a quantitative, individualized measurement of patient lung tissue reaction to RT and assess RP development.

The Reference Image Database to Evaluate Response to Therapy in Lung Cancer (RIDER) Project: A Resource for the Development of Change-Analysis Software

Critical to the clinical evaluation of effective novel therapies for lung cancer is the early and accurate determination of tumor response, which requires an understanding of the sources of uncertainty in tumor measurement and subsequent attempts to minimize their effects on the assessment of the therapeutic agent. The Reference Image Database to Evaluate Response (RIDER) project seeks to develop a consensus approach to the optimization and benchmarking of software tools for the assessment of tumor response to therapy and to provide a publicly available database of serial images acquired during lung cancer drug and radiation therapy trials. Images of phantoms and patient images acquired under situations in which tumor size or biology is known to be unchanged also will be provided. The RIDER project will create standardized methods for benchmarking software tools to reduce sources of uncertainty in vital clinical assessments such as whether a specific tumor is responding to therapy.

Variability in Mesothelioma Tumor Response Classification

OBJECTIVE The objective of our study was to evaluate observer variability in the measurement of temporal change in mesothelioma tumor thickness and in the resulting tumor response classification from CT scans. In addition, the performance of a semiautomated measurement method was evaluated. MATERIALS AND METHODS Four observers individually used an interface that displayed two serial CT scans from the same patient to measure mesothelioma tumor thickness on the follow-up CT scans of 22 patients based on baseline scan measurements. During one session, observers acquired measurements on the follow-up scans based on written reports of baseline scan measurements; in another session, baseline scan measurements were superimposed on the baseline scan for direct visual comparison. Follow-up scan measurements also were obtained from a semiautomated method. Measurement variability and tumor response classification concordance were evaluated for manual measurements acquired in both modes and for semiautomated measurements. RESULTS Although only a small increase in tumor response classification concordance rate was obtained with the visual approach (84.8%) relative to the more standard written-report approach (82.6%), the actual measurements acquired by observers were statistically significantly different between the two approaches (p = 0.03). Both the semiautomated measurements and the resulting tumor response classifications were consistent with manual measurements. CONCLUSION The presentation of baseline scan tumor measurements affects measurements acquired on follow-up scans and could influence tumor response classification. The potential utility of semiautomated tumor thickness measurements was shown in the context of measuring tumor response.

Automatic detection of pulmonary nodules in low-dose screening thoracic CT examinations

Computed tomography of the chest can be used as a screening method for lung cancer in a high-risk population. However, the detection of lung nodules is a difficult and time-consuming task for radiologists. The developed technique should improve the sensitivity of the detection of lung nodules without showing too many false positive nodules. In a study, which should evaluate the feasibility of screening lung cancer, about 1400 thoracic studies were acquired. Scanning parameters were 120 kVp, 5 mm collimation pitch of 2, and a reconstruction index of 5 mm. This results in a data set of about 60 to 70 images per exam. In the images the detection technique first eliminates all air outside the patient, then soft tissue and bony structures are removed. In the remaining lung fields a three-dimensional region detection is performed and rule-based analysis is used to detect possible lung nodules. This technique was applied to a small subset (n equals 17) of above studies. Computation time is about 5 min on an O2 workstation. The use of low-dose exams proved not be a hindrance in the detection of lung nodules. All of the nodules (n equals 23), except one with a size of 3 mm, were detected. The false positive rate was less than 0.3 per image. We have developed a technique, which might help the radiologist in the detection of pulmonary nodules in CT exams of the chest.