Detection and analysis of cerebral aneurysms based on X-ray rotational angiography - the CADA 2020 challenge.

The Cerebral Aneurysm Detection and Analysis (CADA) challenge was organized to support the development and benchmarking of algorithms for detecting, analyzing, and risk assessment of cerebral aneurysms in X-ray rotational angiography (3DRA) images. 109 anonymized 3DRA datasets were provided for training, and 22 additional datasets were used to test the algorithmic solutions. Cerebral aneurysm detection was assessed using the F2 score based on recall and precision, and the fit of the delivered bounding box was assessed using the distance to the aneurysm. The segmentation quality was measured using the Jaccard index and a combination of different surface distance measures. Systematic errors were analyzed using volume correlation and bias. Rupture risk assessment was evaluated using the F2 score. 158 participants from 22 countries registered for the CADA challenge. The U-Net-based detection solutions presented by the community show similar accuracy compared to experts (F2 score 0.92), with a small number of missed aneurysms with diameters smaller than 3.5 mm. In addition, the delineation of these structures, based on U-Net variations, is excellent, with a Jaccard score of 0.92. The rupture risk estimation methods achieved an F2 score of 0.71. The performance of the detection and segmentation solutions is equivalent to that of human experts. The best results are obtained in rupture risk estimation by combining different image-based, morphological, and computational fluid dynamic parameters using machine learning methods. Furthermore, we evaluated the best methods pipeline, from detecting and delineating the vessel dilations to estimating the risk of rupture. The chain of these methods achieves an F2-score of 0.70, which is comparable to applying the risk prediction to the ground-truth delineation (0.71).

The International Radiomics Platform - An Initiative of the German and Austrian Radiological Societies - First Application Examples. / Die Internationale Radiomics-Plattform ­ eine Initiative der Deutschen und Österreichischen Röntgengesellschaften ­ Erste Anwendungsbeispiele.

PURPOSE: The DRG-ÖRG IRP (Deutsche Röntgengesellschaft-Österreichische Röntgengesellschaft international radiomics platform) represents a web-/cloud-based radiomics platform based on a public-private partnership. It offers the possibility of data sharing, annotation, validation and certification in the field of artificial intelligence, radiomics analysis, and integrated diagnostics. In a first proof-of-concept study, automated myocardial segmentation and automated myocardial late gadolinum enhancement (LGE) detection using radiomic image features will be evaluated for myocarditis data sets. MATERIALS AND METHODS: The DRG-ÖRP IRP can be used to create quality-assured, structured image data in combination with clinical data and subsequent integrated data analysis and is characterized by the following performance criteria: Possibility of using multicentric networked data, automatically calculated quality parameters, processing of annotation tasks, contour recognition using conventional and artificial intelligence methods and the possibility of targeted integration of algorithms. In a first study, a neural network pre-trained using cardiac CINE data sets was evaluated for segmentation of PSIR data sets. In a second step, radiomic features were applied for segmental detection of LGE of the same data sets, which were provided multicenter via the IRP. RESULTS: First results show the advantages (data transparency, reliability, broad involvement of all members, continuous evolution as well as validation and certification) of this platform-based approach. In the proof-of-concept study, the neural network demonstrated a Dice coefficient of 0.813 compared to the expert's segmentation of the myocardium. In the segment-based myocardial LGE detection, the AUC was 0.73 and 0.79 after exclusion of segments with uncertain annotation.The evaluation and provision of the data takes place at the IRP, taking into account the FAT (fairness, accountability, transparency) and FAIR (findable, accessible, interoperable, reusable) criteria. CONCLUSION: It could be shown that the DRG-ÖRP IRP can be used as a crystallization point for the generation of further individual and joint projects. The execution of quantitative analyses with artificial intelligence methods is greatly facilitated by the platform approach of the DRG-ÖRP IRP, since pre-trained neural networks can be integrated and scientific groups can be networked.In a first proof-of-concept study on automated segmentation of the myocardium and automated myocardial LGE detection, these advantages were successfully applied.Our study shows that with the DRG-ÖRP IRP, strategic goals can be implemented in an interdisciplinary way, that concrete proof-of-concept examples can be demonstrated, and that a large number of individual and joint projects can be realized in a participatory way involving all groups. KEY POINTS: · The DRG-ÖRG IRP is a web/cloud-based radiomics platform based on a public-private partnership.. · The DRG-ÖRG IRP can be used for the creation of quality-assured, structured image data in combination with clinical data and subsequent integrated data analysis.. · First results show the applicability of left ventricular myocardial segmentation using a neural network and segment-based LGE detection using radiomic image features.. · The DRG-ÖRG IRP offers the possibility of integrating pre-trained neural networks and networking of scientific groups.. CITATION FORMAT: · Overhoff D, Kohlmann P, Frydrychowicz A et al. The International Radiomics Platform - An Initiative of the German and Austrian Radiological Societies. Fortschr Röntgenstr 2021; 193: 276 - 287.

Quantitative CT analysis in patients with pulmonary emphysema: is lung function influenced by concomitant unspecific pulmonary fibrosis?

Purpose: Quantitative analysis of CT scans has proven to be a reproducible technique, which might help to understand the pathophysiology of chronic obstructive pulmonary disease (COPD) and combined pulmonary fibrosis and emphysema. The aim of this retrospective study was to find out if the lung function of patients with COPD with Global Initiative for Chronic Obstructive Lung Disease (GOLD) stages III or IV and pulmonary emphysema is measurably influenced by high attenuation areas as a correlate of concomitant unspecific fibrotic changes of lung parenchyma. Patients and methods: Eighty-eight patients with COPD GOLD stage III or IV underwent CT and pulmonary function tests. Quantitative CT analysis was performed to determine low attenuation volume (LAV) and high attenuation volume (HAV), which are considered to be equivalents of fibrotic (HAV) and emphysematous (LAV) changes of lung parenchyma. Both parameters were determined for the whole lung, as well as peripheral and central lung areas only. Multivariate regression analysis was used to correlate HAV with different parameters of lung function. Results: Unlike LAV, HAV did not show significant correlation with parameters of lung function. Even in patients with a relatively high HAV of more than 10%, in contrast to HAV (p=0.786) only LAV showed a significantly negative correlation with forced expiratory volume in 1 second (r=-0.309, R2=0.096, p=0.003). A severe decrease of DLCO% was associated with both larger HAV (p=0.045) and larger LAV (p=0.001). Residual volume and FVC were not influenced by LAV or HAV. Conclusion: In patients with COPD GOLD stage III-IV, emphysematous changes of lung parenchyma seem to have such a strong influence on lung function, which is a possible effect of concomitant unspecific fibrosis is overwhelmed.

Computed tomography quantification of tracheal abnormalities in COPD and their influence on airflow limitation.

PURPOSE: To present a method to automatically quantify tracheal morphology changes during breathing and investigate its contribution to airflow impairment when adding CT measures of emphysema, airway wall thickness, air trapping and ventilation. METHODS: Because tracheal abnormalities often occur localized, a method is presented that automatically determines the most abnormal trachea section based on automatically computed sagittal and coronal lengths. In this most abnormal section, trachea morphology is encoded using four equiangular rays from the center of the trachea and the normalized lengths of these rays are used as features in a classification scheme. Consequently, trachea measurements are used as input for classification into GOLD stages in addition to emphysema, air trapping and ventilation. A database of 200 subjects distributed across all GOLD stages is used to evaluate the classification with a k nearest neighbour algorithm. Performance is assessed in two experimental settings: (a) when only inspiratory scans are taken; (b) when both inspiratory and expiratory scans are available. RESULTS: Given only an inspiratory CT scan, measuring tracheal shape provides complementary information only to emphysema measurements. The best performing set in the inspiratory setting was a combination of emphysema and bronchial measurements. The best performing feature set in the inspiratory-expiratory setting includes measurements of emphysema, ventilation, air trapping, and trachea. Inspiratory and inspiratory-expiratory settings showed similar performance. CONCLUSIONS: The fully automated system presented in this study provides information on trachea shape at inspiratory and expiratory CT. Addition of tracheal morphology features improves the ability of emphysema and air trapping CT-derived measurements to classify COPD patients into GOLD stages and may be relevant when investigating different aspects of COPD.

Follow-up of CT-derived airway wall thickness: Correcting for changes in inspiration level improves reliability.

OBJECTIVES: Airway wall thickness (AWT) is affected by changes in lung volume. This study evaluated whether correcting AWT on computed tomography (CT) for differences in inspiration level improves measurement agreement, reliability, and power to detect changes over time. METHODS: Participants of the Dutch-Belgian lung cancer screening trial who underwent 3-month repeat CT for an indeterminate pulmonary nodule were included. AWT on CT was calculated by the square root of the wall area at a theoretical airway with an internal perimeter of 10mm (Pi10). The scan with the highest lung volume was labelled as the reference scan and the scan with the lowest lung volume was labelled as the comparison scan. Pi10 derived from the comparison scan was corrected by multiplying it with the ratio of CT lung volume of the comparison scan to CT lung volume on the reference scan. Agreement of uncorrected and corrected Pi10 was studied with the Bland-Altman method, reliability with intra-class correlation coefficients (ICC), and power to detect changes over time was calculated. RESULTS: 315 male participants were included. Limit of agreement and reliability for Pi10 was -0.61 to 0.57mm (ICC=0.87), which improved to -0.38 to 0.37mm (ICC=0.94) after correction for inspiration level. To detect a 15% change over 3 months, 71 subjects are needed for Pi10 and 26 subjects for Pi10 adjusted for inspiration level. CONCLUSIONS: Correcting Pi10 for differences in inspiration level improves reliability, agreement, and power to detect changes over time.

Algorithm Variability in the Estimation of Lung Nodule Volume From Phantom CT Scans: Results of the QIBA 3A Public Challenge.

RATIONALE AND OBJECTIVES: Quantifying changes in lung tumor volume is important for diagnosis, therapy planning, and evaluation of response to therapy. The aim of this study was to assess the performance of multiple algorithms on a reference data set. The study was organized by the Quantitative Imaging Biomarker Alliance (QIBA). MATERIALS AND METHODS: The study was organized as a public challenge. Computed tomography scans of synthetic lung tumors in an anthropomorphic phantom were acquired by the Food and Drug Administration. Tumors varied in size, shape, and radiodensity. Participants applied their own semi-automated volume estimation algorithms that either did not allow or allowed post-segmentation correction (type 1 or 2, respectively). Statistical analysis of accuracy (percent bias) and precision (repeatability and reproducibility) was conducted across algorithms, as well as across nodule characteristics, slice thickness, and algorithm type. RESULTS: Eighty-four percent of volume measurements of QIBA-compliant tumors were within 15% of the true volume, ranging from 66% to 93% across algorithms, compared to 61% of volume measurements for all tumors (ranging from 37% to 84%). Algorithm type did not affect bias substantially; however, it was an important factor in measurement precision. Algorithm precision was notably better as tumor size increased, worse for irregularly shaped tumors, and on the average better for type 1 algorithms. Over all nodules meeting the QIBA Profile, precision, as measured by the repeatability coefficient, was 9.0% compared to 18.4% overall. CONCLUSION: The results achieved in this study, using a heterogeneous set of measurement algorithms, support QIBA quantitative performance claims in terms of volume measurement repeatability for nodules meeting the QIBA Profile criteria.

Inter-Method Performance Study of Tumor Volumetry Assessment on Computed Tomography Test-Retest Data.

RATIONALE AND OBJECTIVES: Tumor volume change has potential as a biomarker for diagnosis, therapy planning, and treatment response. Precision was evaluated and compared among semiautomated lung tumor volume measurement algorithms from clinical thoracic computed tomography data sets. The results inform approaches and testing requirements for establishing conformance with the Quantitative Imaging Biomarker Alliance (QIBA) Computed Tomography Volumetry Profile. MATERIALS AND METHODS: Industry and academic groups participated in a challenge study. Intra-algorithm repeatability and inter-algorithm reproducibility were estimated. Relative magnitudes of various sources of variability were estimated using a linear mixed effects model. Segmentation boundaries were compared to provide a basis on which to optimize algorithm performance for developers. RESULTS: Intra-algorithm repeatability ranged from 13% (best performing) to 100% (least performing), with most algorithms demonstrating improved repeatability as the tumor size increased. Inter-algorithm reproducibility was determined in three partitions and was found to be 58% for the four best performing groups, 70% for the set of groups meeting repeatability requirements, and 84% when all groups but the least performer were included. The best performing partition performed markedly better on tumors with equivalent diameters greater than 40 mm. Larger tumors benefitted by human editing but smaller tumors did not. One-fifth to one-half of the total variability came from sources independent of the algorithms. Segmentation boundaries differed substantially, not ony in overall volume but also in detail. CONCLUSIONS: Nine of the 12 participating algorithms pass precision requirements similar to what is indicated in the QIBA Profile, with the caveat that the present study was not designed to explicitly evaluate algorithm profile conformance. Change in tumor volume can be measured with confidence to within ±14% using any of these nine algorithms on tumor sizes greater than 10 mm. No partition of the algorithms was able to meet the QIBA requirements for interchangeability down to 10 mm, although the partition comprising best performing algorithms did meet this requirement for a tumor size of greater than approximately 40 mm.

Quantitative Emphysema Distribution in Anatomic and Non-anatomic Lung Regions.

PURPOSE: The change of emphysema distribution with increasing COPD severity is not yet assessed. Especially, involvement of the upper aspect of the lower lobe is unknown. The primary aim was to quantitatively determine regional distribution of emphysema in anatomically (lung lobes) and non-anatomically defined lung regions (upper/lower lung halves as well as core and rind regions) in a cohort covering equally all COPD severity stages using CT. MATERIAL AND METHODS: Basically 100 CT data sets were quantitatively evaluated for regional distribution of emphysema. Emphysema characteristics (emphysema index, mean lung density and 15th percentile of the attenuation values of lung voxels) were compared (t-test) in: upper lobes vs. upper halves, lower lobes vs. lower halves, core vs. rind region. RESULTS: In patients with ≤ GOLD II, a significantly higher emphysema burden was found in the upper lobes as compared to upper halves. In subjects with GOLD III/IV the differences were not significant for all emphysema characteristics. A high difference between lobes and halves in subjects with ≤ GOLD II was found, in contrast to low difference in higher GOLD stages. CONCLUSIONS: Lobar segmentation provides improved characterization of cranio-caudal emphysema distribution compared to a non-anatomic approach in subjects up to GOLD stage II.

Automatic lung segmentation method for MRI-based lung perfusion studies of patients with chronic obstructive pulmonary disease.

PURPOSE: A novel fully automatic lung segmentation method for magnetic resonance (MR) images of patients with chronic obstructive pulmonary disease (COPD) is presented. The main goal of this work was to ease the tedious and time-consuming task of manual lung segmentation, which is required for region-based volumetric analysis of four-dimensional MR perfusion studies which goes beyond the analysis of small regions of interest. METHODS: The first step in the automatic algorithm is the segmentation of the lungs in morphological MR images with higher spatial resolution than corresponding perfusion MR images. Subsequently, the segmentation mask of the lungs is transferred to the perfusion images via nonlinear registration. Finally, the masks for left and right lungs are subdivided into a user-defined number of partitions. Fourteen patients with two time points resulting in 28 perfusion data sets were available for the preliminary evaluation of the developed methods. RESULTS: Resulting lung segmentation masks are compared with reference segmentations from experienced chest radiologists, as well as with total lung capacity (TLC) acquired by full-body plethysmography. TLC results were available for thirteen patients. The relevance of the presented method is indicated by an evaluation, which shows high correlation between automatically generated lung masks with corresponding ground-truth estimates. CONCLUSION: The evaluation of the developed methods indicates good accuracy and shows that automatically generated lung masks differ from expert segmentations about as much as segmentations from different experts.

Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images.

Subsolid pulmonary nodules occur less often than solid pulmonary nodules, but show a much higher malignancy rate. Therefore, accurate detection of this type of pulmonary nodules is crucial. In this work, a computer-aided detection (CAD) system for subsolid nodules in computed tomography images is presented and evaluated on a large data set from a multi-center lung cancer screening trial. The paper describes the different components of the CAD system and presents experiments to optimize the performance of the proposed CAD system. A rich set of 128 features is defined for subsolid nodule candidates. In addition to previously used intensity, shape and texture features, a novel set of context features is introduced. Experiments show that these features significantly improve the classification performance. Optimization and training of the CAD system is performed on a large training set from one site of a lung cancer screening trial. Performance analysis on an independent test from another site of the trial shows that the proposed system reaches a sensitivity of 80% at an average of only 1.0 false positive detections per scan. A retrospective analysis of the output of the CAD system by an experienced thoracic radiologist shows that the CAD system is able to find subsolid nodules which were not contained in the screening database.

Segmentation-based partial volume correction for volume estimation of solid lesions in CT.

In oncological chemotherapy monitoring, the change of a tumor's size is an important criterion for assessing cancer therapeutics. Measuring the volume of a tumor requires its delineation in 3-D. This is called segmentation, which is an intensively studied problem in medical image processing. However, simply counting the voxels within a binary segmentation result can lead to significant differences in the volume, if the lesion has been segmented slightly differently by various segmentation procedures or in different scans, for example due to the limited spatial resolution of computed tomography (CT) or partial volume effects. This variability limits the sensitivity of size measurements and thus of therapy response assessments and it can even lead to misclassifications. We present a fast, generic algorithm for measuring the volume of solid, compact tumors in CT that considers partial volume effects at the border of a given segmentation result. The algorithm is an extension of the segmentation-based partial volume analysis proposed by Kuhnigk for the volumetry of solid lung lesions , such that it can be applied to inhomogeneous lesions and lesions with inhomogeneous surroundings. Our generalized segmentation-based partial volume correction is based on a spatial subdivision of the segmentation result, from which the fraction of tumor for each voxel is computed. It has been evaluated on phantom data, 1516 lesion segmentation pairs (lung nodules, liver metastases and lymph nodes) as well as 1851 lung nodules from the LIDC-IDRI database. The evaluations of our algorithm show a more accurate estimation of the real volume and its ability to reduce inter- and intra-observer variability significantly for each entity. Overall, the variability (interquartile range) for phantom data is reduced by 49% ( p ≪ 0.001) and the variability between different readers is reduced by 28% ( p ≪ 0.001). The average computation time is 0.2 s.

Determination of lung segments in computed tomography images using the Euclidean distance to the pulmonary artery.

PURPOSE: Computed tomography (CT) imaging is the modality of choice for lung cancer diagnostics. With the increasing number of lung interventions on sublobar level in recent years, determining and visualizing pulmonary segments in CT images and, in oncological cases, reliable segment-related information about the location of tumors has become increasingly desirable. Computer-assisted identification of lung segments in CT images is subject of this work. METHODS: The authors present a new interactive approach for the segmentation of lung segments that uses the Euclidean distance of each point in the lung to the segmental branches of the pulmonary artery. The aim is to analyze the potential of the method. Detailed manual pulmonary artery segmentations are used to achieve the best possible segment approximation results. A detailed description of the method and its evaluation on 11 CT scans from clinical routine are given. RESULTS: An accuracy of 2-3 mm is measured for the segment boundaries computed by the pulmonary artery-based method. On average, maximum deviations of 8 mm are observed. 135 intersegmental pulmonary veins detected in the 11 test CT scans serve as reference data. Furthermore, a comparison of the presented pulmonary artery-based approach to a similar approach that uses the Euclidean distance to the segmental branches of the bronchial tree is presented. It shows a significantly higher accuracy for the pulmonary artery-based approach in lung regions at least 30 mm distal to the lung hilum. CONCLUSIONS: A pulmonary artery-based determination of lung segments in CT images is promising. In the tests, the pulmonary artery-based determination has been shown to be superior to the bronchial tree-based determination. The suitability of the segment approximation method for application in the planning of segment resections in clinical practice has already been verified in experimental cases. However, automation of the method accompanied by an evaluation on a larger number of test cases is required before application in the daily clinical routine.

Computer-aided segmentation and volumetry of artificial ground-glass nodules at chest CT.

OBJECTIVE: The purpose of this study was to investigate a new software program for semiautomatic measurement of the volume and mass of ground-glass nodules (GGNs) in a chest phantom and to investigate the influence of CT scanner, reconstruction filter, tube voltage, and tube current. MATERIALS AND METHODS: We used an anthropomorphic chest phantom with eight artificial GGNs with two different CT attenuations and four different volumes. CT scans were obtained with four models of CT scanner at 120 kVp and 25 mAs with a soft and a sharp reconstruction filter. On the 256-MDCT scanner, the tube current-exposure time product and tube voltage settings were varied. GGNs were measured with software that automatically segmented the nodules. Absolute percentage error (APE) was calculated for volume, mass, and density. Wilcoxon signed rank, Mann-Whitney U, and Kruskal-Wallis tests were used for analysis. RESULTS: Volume and mass did not differ significantly from the true values. When measurements were expressed as APE, the error range was 2-36% for volume and 5-46% for mass, which was significantly different from no error. We did not find significant differences in APE between CT scanners with filters for lower tube current for volume or lower tube voltage for mass. CONCLUSION: Computer-aided segmentation and mass and volume measurements of GGNs with the prototype software had promising results in this study.

CT-based weight assessment of lung lobes: comparison with ex vivo measurements.

PURPOSE: We aimed to evaluate the validity of lung lobe weight assessment via computed tomography (CT) by comparing CT-derived and ex vivo measurements. MATERIALS AND METHODS: Unenhanced CT scanning was performed in 30 consecutive patients before lobectomy for lung cancer. The CT images were analyzed using research software after allowing for lobar weight quantitation. The lobar weight estimated by CT was then compared with that measured after surgery using a precision scale (ex vivo measurement). Comparisons as well as assessment of intra- and interoperator variability were conducted using the Bland-Altman method and the coefficient of repeatability (CR). Correlations were examined using Pearson's correlation analysis. RESULTS: Comparison analyses were feasible for 28 cases. The ex vivo lobe weight was 186.2±57.3 g, whereas the weights measured by the two operators by CT were 190.0±55 and 182.4±58.2 g, respectively. As compared with ex vivo weights, the CR was 36.4 for operator 1 and 50.4 for operator 2; the mean differences were 3.8 and -3.8 for operators 1 and 2, respectively. The intraoperator and interoperator CR were 20.9 and 36.6, respectively. The mean differences for the intra- and interoperator analysis were -1.5 and -7.5, respectively. The correlation was very high between CT-based and ex vivo measurements (r=0.95 and r=0.90 for operators 1 and 2, respectively; P < 0.001). CONCLUSION: Estimation of lung lobe weight by semi-automated CT analysis is sufficiently reproducible and in agreement with ex vivo measurements.

PET-based delineation of tumour volumes in lung cancer: comparison with pathological findings.

PURPOSE: The objective of the study was to validate an adaptive, contrast-oriented thresholding algorithm (COA) for tumour delineation in (18)F-fluorodeoxyglucose (FDG) positron emission tomography (PET) for non-small cell lung cancer (NSCLC) in comparison with pathological findings. The impact of tumour localization, tumour size and uptake heterogeneity on PET delineation results was also investigated. METHODS: PET tumour delineation by COA was compared with both CT delineation and pathological findings in 15 patients to investigate its validity. Correlations between anatomical volume, metabolic volume and the pathology reference as well as between the corresponding maximal diameters were determined. Differences between PET delineations and pathological results were investigated with respect to tumour localization and uptake heterogeneity. RESULTS: The delineated volumes and maximal diameters measured on PET and CT images significantly correlated with the pathology reference (both r > 0.95, p < 0.0001). Both PET and CT contours resulted in overestimation of the pathological volume (PET 32.5 ± 26.5%, CT 46.6 ± 27.4%). CT volumes were larger than those delineated on PET images (CT 60.6 ± 86.3 ml, PET 48.3 ± 61.7 ml). Maximal tumour diameters were similar for PET and CT (51.4 ± 19.8 mm for CT versus 53.4 ± 19.1 mm for PET), slightly overestimating the pathological reference (mean difference CT 4.3 ± 3.2 mm, PET 6.2 ± 5.1 mm). PET volumes of lung tumours located in the lower lobe were significantly different from those determined from pathology (p = 0.037), whereas no significant differences were observed for tumours located in the upper lobe (p = 0.066). Only minor correlation was found between pathological tumour size and PET heterogeneity (r = -0.24). CONCLUSION: PET tumour delineation by COA showed a good correlation with pathological findings. Tumour localization had an influence on PET delineation results. The impact of tracer uptake heterogeneity on PET delineation should be considered carefully and individually in each patient. Altogether, PET tumour delineation by COA for NSCLC patients is feasible and reliable with the potential for routine clinical application.

Intra- and interoperator variability of lobar pulmonary volumes and emphysema scores in patients with chronic obstructive pulmonary disease and emphysema: comparison of manual and semi-automated segmentation techniques.

PURPOSE: We aimed to compare the intra- and interoperator variability of lobar volumetry and emphysema scores obtained by semi-automated and manual segmentation techniques in lung emphysema patients. MATERIALS AND METHODS: In two sessions held three months apart, two operators performed lobar volumetry of unenhanced chest computed tomography examinations of 47 consecutive patients with chronic obstructive pulmonary disease and lung emphysema. Both operators used the manual and semi-automated segmentation techniques. The intra- and interoperator variability of the volumes and emphysema scores obtained by semi-automated segmentation was compared with the variability obtained by manual segmentation of the five pulmonary lobes. RESULTS: The intra- and interoperator variability of the lobar volumes decreased when using semi-automated lobe segmentation (coefficients of repeatability for the first operator: right upper lobe, 147 vs. 96.3; right middle lobe, 137.7 vs. 73.4; right lower lobe, 89.2 vs. 42.4; left upper lobe, 262.2 vs. 54.8; and left lower lobe, 260.5 vs. 56.5; coefficients of repeatability for the second operator: right upper lobe, 61.4 vs. 48.1; right middle lobe, 56 vs. 46.4; right lower lobe, 26.9 vs. 16.7; left upper lobe, 61.4 vs. 27; and left lower lobe, 63.6 vs. 27.5; coefficients of reproducibility in the interoperator analysis: right upper lobe, 191.3 vs. 102.9; right middle lobe, 219.8 vs. 126.5; right lower lobe, 122.6 vs. 90.1; left upper lobe, 166.9 vs. 68.7; and left lower lobe, 168.7 vs. 71.6). The coefficients of repeatability and reproducibility of emphysema scores also decreased when using semi-automated segmentation and had ranges that varied depending on the target lobe and selected threshold of emphysema. CONCLUSION: Semi-automated segmentation reduces the intra- and interoperator variability of lobar volumetry and provides a more objective tool than manual technique for quantifying lung volumes and severity of emphysema.

Increased mean lung density: another independent predictor of lung cancer?

OBJECTIVES: To investigate the relationship between emphysema phenotype, mean lung density (MLD), lung function and lung cancer by using an automated multiple feature analysis tool on thin-section computed tomography (CT) data. METHODS: Both emphysema phenotype and MLD evaluated by automated quantitative CT analysis were compared between outpatients and screening participants with lung cancer (n=119) and controls (n=989). Emphysema phenotype was defined by assessing features such as extent, distribution on core/peel of the lung and hole size. Adjusted multiple logistic regression models were used to evaluate independent associations of CT densitometric measurements and pulmonary function test (PFT) with lung cancer risk. RESULTS: No emphysema feature was associated with lung cancer. Lung cancer risk increased with decreasing values of forced expiratory volume in 1s (FEV1) independently of MLD (OR 5.37, 95% CI: 2.63-10.97 for FEV1<60% vs. FEV1≥90%), and with increasing MLD independently of FEV1 (OR 3.00, 95% CI: 1.60-5.63 for MLD>-823 vs. MLD<-857 Hounsfield units). CONCLUSION: Emphysema per se was not associated with lung cancer whereas decreased FEV1 was confirmed as being a strong and independent risk factor. The cross-sectional association between increased MLD and lung cancer requires future validations.

Automatic segmentation of the pulmonary lobes from chest CT scans based on fissures, vessels, and bronchi.

Segmentation of the pulmonary lobes is relevant in clinical practice and particularly challenging for cases with severe diseases or incomplete fissures. In this work, an automated segmentation approach is presented that performs a marker-based watershed transformation on computed tomography (CT) scans to subdivide the lungs into lobes. A cost image for the watershed transformation is computed by combining information from fissures, bronchi, and pulmonary vessels. The lobar markers are calculated by an analysis of the automatically labeled bronchial tree. By integration of information from several anatomical structures the segmentation is made robust against incomplete fissures. For evaluation the method was compared to a recently published method on 20 CT scans with no or mild disease. The average distances to the reference segmentation were 0.69, 0.67, and 1.21 mm for the left major, right major, and right minor fissure, respectively. In addition the results were submitted to LOLA11, an international lung lobe segmentation challenge with publically available data including cases with severe diseases. The average distances to the reference for the 55 CT scans provided by LOLA11 were 0.98, 3.97, and 3.09 mm for the left major, right major, and right minor fissure. Moreover, an analysis of the relation between segmentation quality and fissure completeness showed that the method is robust against incomplete fissures.

Relationship and prognostic value of modified coronary artery calcium score, FEV1, and emphysema in lung cancer screening population: the MILD trial.

PURPOSE: To assess the relationship between a modified coronary artery calcium (mCAC) score and both forced expiratory volume in 1 second (FEV1) and pulmonary emphysema and the associations of such factors with all-cause mortality and cardiovascular events (CVEs) in a lung cancer computed tomographic (CT) screening trial. MATERIALS AND METHODS: In this institutional review board-approved study, both clinical and low-dose CT data were evaluated in a cohort of heavy smokers consecutively recruited by the Multicentric Italian Lung Detection, or MILD, trial. Low-dose CT images were analyzed by using software that allowed quantification of mCAC, mean lung attenuation (MLA), and total extent of emphysema. The correlations between mCAC, percentage predicted FEV1, MLA, and emphysema extent were tested by using the Pearson correlation coefficient. Adjusted multiple logistic regression models were applied to assess the relationships between mCAC, FEV1, MLA, and emphysema extent and all-cause mortality and CVEs. RESULTS: The final study cohort consisted of 1159 smokers. There were no significant correlations between mCAC score and FEV1 (r=-0.03, P=.4), MLA (r=-0.01, P=.7), or emphysema extent (r=0.02, P=.6). An mCAC score greater than 400 was the only factor that was independently associated with both all-cause mortality (odds ratio [OR]: 3.73; 95% confidence interval [CI]: 1.05, 13.32; P=.04) and CVEs (OR: 2.87; 95% CI: 1.13, 7.27; P=.03). CONCLUSION: mCAC is a better predictor of CVE and all-cause mortality than FEV1 and emphysema extent and may contribute to the identification of high-risk individuals in a lung cancer screening setting.