Voxel-Wise Comparison of Co-Registered Quantitative CT and Hyperpolarised Gas Diffusion-Weighted MRI Measurements in IPF.

The patterns of idiopathic pulmonary fibrosis (IPF) lung disease that directly correspond to elevated hyperpolarised gas diffusion-weighted (DW) MRI metrics are currently unknown. This study aims to develop a spatial co-registration framework for a voxel-wise comparison of hyperpolarised gas DW-MRI and CALIPER quantitative CT patterns. Sixteen IPF patients underwent 3He DW-MRI and CT at baseline, and eleven patients had a 1-year follow-up DW-MRI. Six healthy volunteers underwent 129Xe DW-MRI at baseline only. Moreover, 3He DW-MRI was indirectly co-registered to CT via spatially aligned 3He ventilation and structural 1H MRI. A voxel-wise comparison of the overlapping 3He apparent diffusion coefficient (ADC) and mean acinar dimension (LmD) maps with CALIPER CT patterns was performed at baseline and after 1 year. The abnormal lung percentage classified with the LmD value, based on a healthy volunteer 129Xe LmD, and CALIPER was compared with a Bland-Altman analysis. The largest DW-MRI metrics were found in the regions classified as honeycombing, and longitudinal DW-MRI changes were observed in the baseline-classified reticular changes and ground-glass opacities regions. A mean bias of -15.3% (95% interval -56.8% to 26.2%) towards CALIPER was observed for the abnormal lung percentage. This suggests DW-MRI may detect microstructural changes in areas of the lung that are determined visibly and quantitatively normal by CT.

PhysVENeT: a physiologically-informed deep learning-based framework for the synthesis of 3D hyperpolarized gas MRI ventilation.

Functional lung imaging modalities such as hyperpolarized gas MRI ventilation enable visualization and quantification of regional lung ventilation; however, these techniques require specialized equipment and exogenous contrast, limiting clinical adoption. Physiologically-informed techniques to map proton (1H)-MRI ventilation have been proposed. These approaches have demonstrated moderate correlation with hyperpolarized gas MRI. Recently, deep learning (DL) has been used for image synthesis applications, including functional lung image synthesis. Here, we propose a 3D multi-channel convolutional neural network that employs physiologically-informed ventilation mapping and multi-inflation structural 1H-MRI to synthesize 3D ventilation surrogates (PhysVENeT). The dataset comprised paired inspiratory and expiratory 1H-MRI scans and corresponding hyperpolarized gas MRI scans from 170 participants with various pulmonary pathologies. We performed fivefold cross-validation on 150 of these participants and used 20 participants with a previously unseen pathology (post COVID-19) for external validation. Synthetic ventilation surrogates were evaluated using voxel-wise correlation and structural similarity metrics; the proposed PhysVENeT framework significantly outperformed conventional 1H-MRI ventilation mapping and other DL approaches which did not utilize structural imaging and ventilation mapping. PhysVENeT can accurately reflect ventilation defects and exhibits minimal overfitting on external validation data compared to DL approaches that do not integrate physiologically-informed mapping.

Longitudinal Lung Function Assessment of Patients Hospitalized With COVID-19 Using 1H and 129Xe Lung MRI.

BACKGROUND: Microvascular abnormalities and impaired gas transfer have been observed in patients with COVID-19. The progression of pulmonary changes in these patients remains unclear. RESEARCH QUESTION: Do patients hospitalized with COVID-19 without evidence of architectural distortion on structural imaging exhibit longitudinal improvements in lung function measured by using 1H and 129Xe MRI between 6 and 52 weeks following hospitalization? STUDY DESIGN AND METHODS: Patients who were hospitalized with COVID-19 pneumonia underwent a pulmonary 1H and 129Xe MRI protocol at 6, 12, 25, and 51 weeks following hospital admission in a prospective cohort study between November 2020 and February 2022. The imaging protocol was as follows: 1H ultra-short echo time, contrast-enhanced lung perfusion, 129Xe ventilation, 129Xe diffusion-weighted, and 129Xe spectroscopic imaging of gas exchange. RESULTS: Nine patients were recruited (age 57 ± 14 [median ± interquartile range] years; six of nine patients were male). Patients underwent MRI at 6 (n = 9), 12 (n = 9), 25 (n = 6), and 51 (n = 8) weeks following hospital admission. Patients with signs of interstitial lung damage were excluded. At 6 weeks, patients exhibited impaired 129Xe gas transfer (RBC to membrane fraction), but lung microstructure was not increased (apparent diffusion coefficient and mean acinar airway dimensions). Minor ventilation abnormalities present in four patients were largely resolved in the 6- to 25-week period. At 12 weeks, all patients with lung perfusion data (n = 6) showed an increase in both pulmonary blood volume and flow compared with 6 weeks, although this was not statistically significant. At 12 weeks, significant improvements in 129Xe gas transfer were observed compared with 6-week examinations; however, 129Xe gas transfer remained abnormally low at weeks 12, 25, and 51. INTERPRETATION: 129Xe gas transfer was impaired up to 1 year following hospitalization in patients who were hospitalized with COVID-19 pneumonia, without evidence of architectural distortion on structural imaging, whereas lung ventilation was normal at 52 weeks.

A hybrid model- and deep learning-based framework for functional lung image synthesis from multi-inflation CT and hyperpolarized gas MRI.

BACKGROUND: Hyperpolarized gas MRI is a functional lung imaging modality capable of visualizing regional lung ventilation with exceptional detail within a single breath. However, this modality requires specialized equipment and exogenous contrast, which limits widespread clinical adoption. CT ventilation imaging employs various metrics to model regional ventilation from non-contrast CT scans acquired at multiple inflation levels and has demonstrated moderate spatial correlation with hyperpolarized gas MRI. Recently, deep learning (DL)-based methods, utilizing convolutional neural networks (CNNs), have been leveraged for image synthesis applications. Hybrid approaches integrating computational modeling and data-driven methods have been utilized in cases where datasets are limited with the added benefit of maintaining physiological plausibility. PURPOSE: To develop and evaluate a multi-channel DL-based method that combines modeling and data-driven approaches to synthesize hyperpolarized gas MRI lung ventilation scans from multi-inflation, non-contrast CT and quantitatively compare these synthetic ventilation scans to conventional CT ventilation modeling. METHODS: In this study, we propose a hybrid DL configuration that integrates model- and data-driven methods to synthesize hyperpolarized gas MRI lung ventilation scans from a combination of non-contrast, multi-inflation CT and CT ventilation modeling. We used a diverse dataset comprising paired inspiratory and expiratory CT and helium-3 hyperpolarized gas MRI for 47 participants with a range of pulmonary pathologies. We performed six-fold cross-validation on the dataset and evaluated the spatial correlation between the synthetic ventilation and real hyperpolarized gas MRI scans; the proposed hybrid framework was compared to conventional CT ventilation modeling and other non-hybrid DL configurations. Synthetic ventilation scans were evaluated using voxel-wise evaluation metrics such as Spearman's correlation and mean square error (MSE), in addition to clinical biomarkers of lung function such as the ventilated lung percentage (VLP). Furthermore, regional localization of ventilated and defect lung regions was assessed via the Dice similarity coefficient (DSC). RESULTS: We showed that the proposed hybrid framework is capable of accurately replicating ventilation defects seen in the real hyperpolarized gas MRI scans, achieving a voxel-wise Spearman's correlation of 0.57 ± 0.17 and an MSE of 0.017 ± 0.01. The hybrid framework significantly outperformed CT ventilation modeling alone and all other DL configurations using Spearman's correlation. The proposed framework was capable of generating clinically relevant metrics such as the VLP without manual intervention, resulting in a Bland-Altman bias of 3.04%, significantly outperforming CT ventilation modeling. Relative to CT ventilation modeling, the hybrid framework yielded significantly more accurate delineations of ventilated and defect lung regions, achieving a DSC of 0.95 and 0.48 for ventilated and defect regions, respectively. CONCLUSION: The ability to generate realistic synthetic ventilation scans from CT has implications for several clinical applications, including functional lung avoidance radiotherapy and treatment response mapping. CT is an integral part of almost every clinical lung imaging workflow and hence is readily available for most patients; therefore, synthetic ventilation from non-contrast CT can provide patients with wider access to ventilation imaging worldwide.

Artificial Intelligence in Periodontology: A Scoping Review.

Artificial intelligence (AI) is the development of computer systems whereby machines can mimic human actions. This is increasingly used as an assistive tool to help clinicians diagnose and treat diseases. Periodontitis is one of the most common diseases worldwide, causing the destruction and loss of the supporting tissues of the teeth. This study aims to assess current literature describing the effect AI has on the diagnosis and epidemiology of this disease. Extensive searches were performed in April 2022, including studies where AI was employed as the independent variable in the assessment, diagnosis, or treatment of patients with periodontitis. A total of 401 articles were identified for abstract screening after duplicates were removed. In total, 293 texts were excluded, leaving 108 for full-text assessment with 50 included for final synthesis. A broad selection of articles was included, with the majority using visual imaging as the input data field, where the mean number of utilised images was 1666 (median 499). There has been a marked increase in the number of studies published in this field over the last decade. However, reporting outcomes remains heterogeneous because of the variety of statistical tests available for analysis. Efforts should be made to standardise methodologies and reporting in order to ensure that meaningful comparisons can be drawn.

Implementable Deep Learning for Multi-sequence Proton MRI Lung Segmentation: A Multi-center, Multi-vendor, and Multi-disease Study.

BACKGROUND: Recently, deep learning via convolutional neural networks (CNNs) has largely superseded conventional methods for proton (1 H)-MRI lung segmentation. However, previous deep learning studies have utilized single-center data and limited acquisition parameters. PURPOSE: Develop a generalizable CNN for lung segmentation in 1 H-MRI, robust to pathology, acquisition protocol, vendor, and center. STUDY TYPE: Retrospective. POPULATION: A total of 809 1 H-MRI scans from 258 participants with various pulmonary pathologies (median age (range): 57 (6-85); 42% females) and 31 healthy participants (median age (range): 34 (23-76); 34% females) that were split into training (593 scans (74%); 157 participants (55%)), testing (50 scans (6%); 50 participants (17%)) and external validation (164 scans (20%); 82 participants (28%)) sets. FIELD STRENGTH/SEQUENCE: 1.5-T and 3-T/3D spoiled-gradient recalled and ultrashort echo-time 1 H-MRI. ASSESSMENT: 2D and 3D CNNs, trained on single-center, multi-sequence data, and the conventional spatial fuzzy c-means (SFCM) method were compared to manually delineated expert segmentations. Each method was validated on external data originating from several centers. Dice similarity coefficient (DSC), average boundary Hausdorff distance (Average HD), and relative error (XOR) metrics to assess segmentation performance. STATISTICAL TESTS: Kruskal-Wallis tests assessed significances of differences between acquisitions in the testing set. Friedman tests with post hoc multiple comparisons assessed differences between the 2D CNN, 3D CNN, and SFCM. Bland-Altman analyses assessed agreement with manually derived lung volumes. A P value of <0.05 was considered statistically significant. RESULTS: The 3D CNN significantly outperformed its 2D analog and SFCM, yielding a median (range) DSC of 0.961 (0.880-0.987), Average HD of 1.63 mm (0.65-5.45) and XOR of 0.079 (0.025-0.240) on the testing set and a DSC of 0.973 (0.866-0.987), Average HD of 1.11 mm (0.47-8.13) and XOR of 0.054 (0.026-0.255) on external validation data. DATA CONCLUSION: The 3D CNN generated accurate 1 H-MRI lung segmentations on a heterogenous dataset, demonstrating robustness to disease pathology, sequence, vendor, and center. EVIDENCE LEVEL: 4. TECHNICAL EFFICACY: Stage 1.

129 Xe and Free-Breathing 1 H Ventilation MRI in Patients With Cystic Fibrosis: A Dual-Center Study.

BACKGROUND: Free-breathing 1 H ventilation MRI shows promise but only single-center validation has yet been performed against methods which directly image lung ventilation in patients with cystic fibrosis (CF). PURPOSE: To investigate the relationship between 129 Xe and 1 H ventilation images using data acquired at two centers. STUDY TYPE: Sequence comparison. POPULATION: Center 1; 24 patients with CF (12 female) aged 9-47 years. Center 2; 7 patients with CF (6 female) aged 13-18 years, and 6 healthy controls (6 female) aged 21-31 years. Data were acquired in different patients at each center. FIELD STRENGTH/SEQUENCE: 1.5 T, 3D steady-state free precession and 2D spoiled gradient echo. ASSESSMENT: Subjects were scanned with 129 Xe ventilation and 1 H free-breathing MRI and performed pulmonary function tests. Ventilation defect percent (VDP) was calculated using linear binning and images were visually assessed by H.M., L.J.S., and G.J.C. (10, 5, and 8 years' experience). STATISTICAL TESTS: Correlations and linear regression analyses were performed between 129 Xe VDP, 1 H VDP, FEV1 , and LCI. Bland-Altman analysis of 129 Xe VDP and 1 H VDP was carried out. Differences in metrics were assessed using one-way ANOVA or Kruskal-Wallis tests. RESULTS: 129 Xe VDP and 1 H VDP correlated strongly with; each other (r = 0.84), FEV1 z-score (129 Xe VDP r = -0.83, 1 H VDP r = -0.80), and LCI (129 Xe VDP r = 0.91, 1 H VDP r = 0.82). Bland-Altman analysis of 129 Xe VDP and 1 H VDP from both centers had a bias of 0.07% and limits of agreement of -16.1% and 16.2%. Linear regression relationships of VDP with FEV1 were not significantly different between 129 Xe and 1 H VDP (P = 0.08), while 129 Xe VDP had a stronger relationship with LCI than 1 H VDP. DATA CONCLUSION: 1 H ventilation MRI shows large-scale agreement with 129 Xe ventilation MRI in CF patients with established lung disease but may be less sensitive to subtle ventilation changes in patients with early-stage lung disease. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 2.

A Dual-Channel Deep Learning Approach for Lung Cavity Estimation From Hyperpolarized Gas and Proton MRI.

BACKGROUND: Hyperpolarized gas MRI can quantify regional lung ventilation via biomarkers, including the ventilation defect percentage (VDP). VDP is computed from segmentations derived from spatially co-registered functional hyperpolarized gas and structural proton (1 H)-MRI. Although acquired at similar lung inflation levels, they are frequently misaligned, requiring a lung cavity estimation (LCE). Recently, single-channel, mono-modal deep learning (DL)-based methods have shown promise for pulmonary image segmentation problems. Multichannel, multimodal approaches may outperform single-channel alternatives. PURPOSE: We hypothesized that a DL-based dual-channel approach, leveraging both 1 H-MRI and Xenon-129-MRI (129 Xe-MRI), can generate LCEs more accurately than single-channel alternatives. STUDY TYPE: Retrospective. POPULATION: A total of 480 corresponding 1 H-MRI and 129 Xe-MRI scans from 26 healthy participants (median age [range]: 11 [8-71]; 50% females) and 289 patients with pulmonary pathologies (median age [range]: 47 [6-83]; 51% females) were split into training (422 scans [88%]; 257 participants [82%]) and testing (58 scans [12%]; 58 participants [18%]) sets. FIELD STRENGTH/SEQUENCE: 1.5-T, three-dimensional (3D) spoiled gradient-recalled 1 H-MRI and 3D steady-state free-precession 129 Xe-MRI. ASSESSMENT: We developed a multimodal DL approach, integrating 129 Xe-MRI and 1 H-MRI, in a dual-channel convolutional neural network. We compared this approach to single-channel alternatives using manually edited LCEs as a benchmark. We further assessed a fully automatic DL-based framework to calculate VDPs and compared it to manually generated VDPs. STATISTICAL TESTS: Friedman tests with post hoc Bonferroni correction for multiple comparisons compared single-channel and dual-channel DL approaches using Dice similarity coefficient (DSC), average boundary Hausdorff distance (average HD), and relative error (XOR) metrics. Bland-Altman analysis and paired t-tests compared manual and DL-generated VDPs. A P value < 0.05 was considered statistically significant. RESULTS: The dual-channel approach significantly outperformed single-channel approaches, achieving a median (range) DSC, average HD, and XOR of 0.967 (0.867-0.978), 1.68 mm (37.0-0.778), and 0.066 (0.246-0.045), respectively. DL-generated VDPs were statistically indistinguishable from manually generated VDPs (P = 0.710). DATA CONCLUSION: Our dual-channel approach generated LCEs, which could be integrated with ventilated lung segmentations to produce biomarkers such as the VDP without manual intervention. EVIDENCE LEVEL: 4. TECHNICAL EFFICACY: Stage 1.

Image Phenotyping of Preterm-Born Children Using Hyperpolarized 129Xe Lung Magnetic Resonance Imaging and Multiple-Breath Washout.

Rationale: Preterm birth is associated with low lung function in childhood, but little is known about the lung microstructure in childhood. Objectives: We assessed the differential associations between the historical diagnosis of bronchopulmonary dysplasia (BPD) and current lung function phenotypes on lung ventilation and microstructure in preterm-born children using hyperpolarized 129Xe ventilation and diffusion-weighted magnetic resonance imaging (MRI) and multiple-breath washout (MBW). Methods: Data were available from 63 children (aged 9-13 yr), including 44 born preterm (⩽34 weeks' gestation) and 19 term-born control subjects (⩾37 weeks' gestation). Preterm-born children were classified, using spirometry, as prematurity-associated obstructive lung disease (POLD; FEV1 < lower limit of normal [LLN] and FEV1/FVC < LLN), prematurity-associated preserved ratio of impaired spirometry (FEV1 < LLN and FEV1/FVC ⩾ LLN), preterm-(FEV1 ⩾ LLN) and term-born control subjects, and those with and without BPD. Ventilation heterogeneity metrics were derived from 129Xe ventilation MRI and SF6 MBW. Alveolar microstructural dimensions were derived from 129Xe diffusion-weighted MRI. Measurements and Main Results: 129Xe ventilation defect percentage and ventilation heterogeneity index were significantly increased in preterm-born children with POLD. In contrast, mean 129Xe apparent diffusion coefficient, 129Xe apparent diffusion coefficient interquartile range, and 129Xe mean alveolar dimension interquartile range were significantly increased in preterm-born children with BPD, suggesting changes of alveolar dimensions. MBW metrics were all significantly increased in the POLD group compared with preterm- and term-born control subjects. Linear regression confirmed the differential effects of obstructive disease on ventilation defects and BPD on lung microstructure. Conclusion: We show that ventilation abnormalities are associated with POLD, and BPD in infancy is associated with abnormal lung microstructure.

Large-scale investigation of deep learning approaches for ventilated lung segmentation using multi-nuclear hyperpolarized gas MRI.

Respiratory diseases are leading causes of mortality and morbidity worldwide. Pulmonary imaging is an essential component of the diagnosis, treatment planning, monitoring, and treatment assessment of respiratory diseases. Insights into numerous pulmonary pathologies can be gleaned from functional lung MRI techniques. These include hyperpolarized gas ventilation MRI, which enables visualization and quantification of regional lung ventilation with high spatial resolution. Segmentation of the ventilated lung is required to calculate clinically relevant biomarkers. Recent research in deep learning (DL) has shown promising results for numerous segmentation problems. Here, we evaluate several 3D convolutional neural networks to segment ventilated lung regions on hyperpolarized gas MRI scans. The dataset consists of 759 helium-3 (3He) or xenon-129 (129Xe) volumetric scans and corresponding expert segmentations from 341 healthy subjects and patients with a wide range of pathologies. We evaluated segmentation performance for several DL experimental methods via overlap, distance and error metrics and compared them to conventional segmentation methods, namely, spatial fuzzy c-means (SFCM) and K-means clustering. We observed that training on combined 3He and 129Xe MRI scans using a 3D nn-UNet outperformed other DL methods, achieving a mean ± SD Dice coefficient of 0.963 ± 0.018, average boundary Hausdorff distance of 1.505 ± 0.969 mm, Hausdorff 95th percentile of 5.754 ± 6.621 mm and relative error of 0.075 ± 0.039. Moreover, limited differences in performance were observed between 129Xe and 3He scans in the testing set. Combined training on 129Xe and 3He yielded statistically significant improvements over the conventional methods (p < 0.0001). In addition, we observed very strong correlation and agreement between DL and expert segmentations, with Pearson correlation of 0.99 (p < 0.0001) and Bland-Altman bias of - 0.8%. The DL approach evaluated provides accurate, robust and rapid segmentations of ventilated lung regions and successfully excludes non-lung regions such as the airways and artefacts. This approach is expected to eliminate the need for, or significantly reduce, subsequent time-consuming manual editing.

Xenon ventilation MRI in difficult asthma: initial experience in a clinical setting.

BACKGROUND: Hyperpolarised gas magnetic resonance imaging (MRI) can be used to assess ventilation patterns. Previous studies have shown the image-derived metric of ventilation defect per cent (VDP) to correlate with forced expiratory volume in 1 s (FEV1)/forced vital capacity (FVC) and FEV1 in asthma. OBJECTIVES: The aim of this study was to explore the utility of hyperpolarised xenon-129 (129Xe) ventilation MRI in clinical care and examine its relationship with spirometry and other clinical metrics in people seen in a severe asthma service. METHODS: 26 people referred from a severe asthma clinic for MRI scanning were assessed by contemporaneous 129Xe MRI and spirometry. A subgroup of 18 patients also underwent reversibility testing with spirometry and MRI. Quantitative MRI measures of ventilation were calculated, VDP and the ventilation heterogeneity index (VHI), and compared to spirometry, Asthma Control Questionnaire 7 (ACQ7) and blood eosinophil count. Images were reviewed by a multidisciplinary team. RESULTS: VDP and VHI correlated with FEV1, FEV1/FVC and forced expiratory flow between 25% and 75% of FVC but not with ACQ7 or blood eosinophil count. Discordance of MRI imaging and symptoms and/or pulmonary function tests also occurred, prompting diagnostic re-evaluation in some cases. CONCLUSION: Hyperpolarised gas MRI provides a complementary method of assessment in people with difficult to manage asthma in a clinical setting. When used as a tool supporting clinical care in a severe asthma service, occurrences of discordance between symptoms, spirometry and MRI scanning indicate how MRI scanning may add to a management pathway.

Patterns of regional lung physiology in cystic fibrosis using ventilation magnetic resonance imaging and multiple-breath washout.

Hyperpolarised helium-3 (3He) ventilation magnetic resonance imaging (MRI) and multiple-breath washout (MBW) are sensitive methods for detecting lung disease in cystic fibrosis (CF). We aimed to explore their relationship across a broad range of CF disease severity and patient age, as well as assess the effect of inhaled lung volume on ventilation distribution.32 children and adults with CF underwent MBW and 3He-MRI at a lung volume of end-inspiratory tidal volume (EIV T). In addition, 28 patients performed 3He-MRI at total lung capacity. 3He-MRI scans were quantitatively analysed for ventilation defect percentage (VDP), ventilation heterogeneity index (VHI) and the number and size of individual contiguous ventilation defects. From MBW, the lung clearance index, convection-dependent ventilation heterogeneity (Scond) and convection-diffusion-dependent ventilation heterogeneity (Sacin) were calculated.VDP and VHI at EIV T strongly correlated with lung clearance index (r=0.89 and r=0.88, respectively), Sacin (r=0.84 and r=0.82, respectively) and forced expiratory volume in 1 s (FEV1) (r=-0.79 and r=-0.78, respectively). Two distinct 3He-MRI patterns were highlighted: patients with abnormal FEV1 had significantly (p<0.001) larger, but fewer, contiguous defects than those with normal FEV1, who tended to have numerous small volume defects. These two MRI patterns were delineated by a VDP of ∼10%. At total lung capacity, when compared to EIV T, VDP and VHI reduced in all subjects (p<0.001), demonstrating improved ventilation distribution and regions of volume-reversible and nonreversible ventilation abnormalities.

Automated aorta segmentation in low-dose chest CT images.

PURPOSE: Abnormalities of aortic surface and aortic diameter can be related to cardiovascular disease and aortic aneurysm. Computer-based aortic segmentation and measurement may aid physicians in related disease diagnosis. This paper presents a fully automated algorithm for aorta segmentation in low-dose non-contrast CT images. METHODS: The original non-contrast CT scan images as well as their pre-computed anatomy label maps are used to locate the aorta and identify its surface. First a seed point is located inside the aortic lumen. Then, a cylindrical model is progressively fitted to the 3D image space to track the aorta centerline. Finally, the aortic surface is located based on image intensity information. This algorithm has been trained and tested on 359 low-dose non-contrast CT images from VIA-ELCAP and LIDC public image databases. Twenty images were used for training to obtain the optimal set of parameters, while the remaining images were used for testing. The segmentation result has been evaluated both qualitatively and quantitatively. Sixty representative testing images were used to establish a partial ground truth by manual marking on several axial image slices. RESULTS: Compared to ground truth marking, the segmentation result had a mean Dice Similarity Coefficient of 0.933 (maximum 0.963 and minimum 0.907). The average boundary distance between manual segmentation and automatic segmentation was 1.39 mm with a maximum of 1.79 mm and a minimum of 0.83 mm. CONCLUSION: Both qualitative and quantitative evaluations have shown that the presented algorithm is able to accurately segment the aorta in low-dose non-contrast CT images.

Three-dimensional DNA image cytometry by optical projection tomographic microscopy for early cancer diagnosis.

Aneuploidy is typically assessed by flow cytometry (FCM) and image cytometry (ICM). We used optical projection tomographic microscopy (OPTM) for assessing cellular DNA content using absorption and fluorescence stains. OPTM combines some of the attributes of both FCM and ICM and generates isometric high-resolution three-dimensional (3-D) images of single cells. Although the depth of field of the microscope objective was in the submicron range, it was extended by scanning the objective's focal plane. The extended depth of field image is similar to a projection in a conventional x-ray computed tomography. These projections were later reconstructed using computed tomography methods to form a 3-D image. We also present an automated method for 3-D nuclear segmentation. Nuclei of chicken, trout, and triploid trout erythrocyte were used to calibrate OPTM. Ratios of integrated optical densities extracted from 50 images of each standard were compared to ratios of DNA indices from FCM. A comparison of mean square errors with thionin, hematoxylin, Feulgen, and SYTOX green was done. Feulgen technique was preferred as it showed highest stoichiometry, least variance, and preserved nuclear morphology in 3-D. The addition of this quantitative biomarker could further strengthen existing classifiers and improve early diagnosis of cancer using 3-D microscopy.

The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans.

PURPOSE: The development of computer-aided diagnostic (CAD) methods for lung nodule detection, classification, and quantitative assessment can be facilitated through a well-characterized repository of computed tomography (CT) scans. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI) completed such a database, establishing a publicly available reference for the medical imaging research community. Initiated by the National Cancer Institute (NCI), further advanced by the Foundation for the National Institutes of Health (FNIH), and accompanied by the Food and Drug Administration (FDA) through active participation, this public-private partnership demonstrates the success of a consortium founded on a consensus-based process. METHODS: Seven academic centers and eight medical imaging companies collaborated to identify, address, and resolve challenging organizational, technical, and clinical issues to provide a solid foundation for a robust database. The LIDC/IDRI Database contains 1018 cases, each of which includes images from a clinical thoracic CT scan and an associated XML file that records the results of a two-phase image annotation process performed by four experienced thoracic radiologists. In the initial blinded-read phase, each radiologist independently reviewed each CT scan and marked lesions belonging to one of three categories ("nodule > or =3 mm," "nodule <3 mm," and "non-nodule > or =3 mm"). In the subsequent unblinded-read phase, each radiologist independently reviewed their own marks along with the anonymized marks of the three other radiologists to render a final opinion. The goal of this process was to identify as completely as possible all lung nodules in each CT scan without requiring forced consensus. RESULTS: The Database contains 7371 lesions marked "nodule" by at least one radiologist. 2669 of these lesions were marked "nodule > or =3 mm" by at least one radiologist, of which 928 (34.7%) received such marks from all four radiologists. These 2669 lesions include nodule outlines and subjective nodule characteristic ratings. CONCLUSIONS: The LIDC/IDRI Database is expected to provide an essential medical imaging research resource to spur CAD development, validation, and dissemination in clinical practice.

A comparison of ground truth estimation methods.

PURPOSE: Knowledge of the exact shape of a lesion, or ground truth (GT), is necessary for the development of diagnostic tools by means of algorithm validation, measurement metric analysis, accurate size estimation. Four methods that estimate GTs from multiple readers' documentations by considering the spatial location of voxels were compared: thresholded Probability-Map at 0.50 (TPM(0.50)) and at 0.75 (TPM(0.75)), simultaneous truth and performance level estimation (STAPLE) and truth estimate from self distances (TESD). METHODS: A subset of the publicly available Lung Image Database Consortium archive was used, selecting pulmonary nodules documented by all four radiologists. The pair-wise similarities between the estimated GTs were analyzed by computing the respective Jaccard coefficients. Then, with respect to the readers' marking volumes, the estimated volumes were ranked and the sign test of the differences between them was performed. RESULTS: (a) the rank variations among the four methods and the volume differences between STAPLE and TESD are not statistically significant, (b) TPM(0.50) estimates are statistically larger (c) TPM(0.75) estimates are statistically smaller (d) there is some spatial disagreement in the estimates as the one-sided 90% confidence intervals between TPM(0.75) and TPM(0.50), TPM(0.75) and STAPLE, TPM(0.75) and TESD, TPM(0.50) and STAPLE, TPM(0.50) and TESD, STAPLE and TESD, respectively, show: [0.67, 1.00], [0.67, 1.00], [0.77, 1.00], [0.93, 1.00], [0.85, 1.00], [0.85, 1.00]. CONCLUSIONS: The method used to estimate the GT is important: the differences highlighted that STAPLE and TESD, notwithstanding a few weaknesses, appear to be equally viable as a GT estimator, while the increased availability of computing power is decreasing the appeal afforded to TPMs. Ultimately, the choice of which GT estimation method, between the two, should be preferred depends on the specific characteristics of the marked data that is used with respect to the two elements that differentiate the method approaches: relative reliabilities of the readers and the reliability of the region boundaries.

Automated nodule location and size estimation using a multi-scale Laplacian of Gaussian filtering approach.

Estimation of nodule location and size is an important pre-processing step in some nodule segmentation algorithms to determine the size and location of the region of interest. Ideally, such estimation methods will consistently find the same nodule location regardless of where the the seed point (provided either manually or by a nodule detection algorithm) is placed relative to the "true" center of the nodule, and the size should be a reasonable estimate of the true nodule size. We developed a method that estimates nodule location and size using multi-scale Laplacian of Gaussian (LoG) filtering. Nodule candidates near a given seed point are found by searching for blob-like regions with high filter response. The candidates are then pruned according to filter response and location, and the remaining candidates are sorted by size and the largest candidate selected. This method was compared to a previously published template-based method. The methods were evaluated on the basis of stability of the estimated nodule location to changes in the initial seed point and how well the size estimates agreed with volumes determined by a semi-automated nodule segmentation method. The LoG method exhibited better stability to changes in the seed point, with 93% of nodules having the same estimated location even when the seed point was altered, compared to only 52% of nodules for the template-based method. Both methods also showed good agreement with sizes determined by a nodule segmentation method, with an average relative size difference of 5% and -5% for the LoG and template-based methods respectively.

Estimation of anatomical locations using standard frame of reference in chest CT scans.

We propose a method to establish the standard chest frame of reference (CFOR) using the rib cage in a lung CT scan. Such a reference frame is essential for referring to a certain location within a chest region and may facilitate the registration across multiple scans of a given subject as well as the comparative studies within a cohort of subjects. The robustness of the established CFOR was evaluated by estimating the anatomical locations within chest in the follow-up scan given the location in the first scan. Specifically, tracheal bifurcation point of airway tree and the center of pulmonary nodule were used as the anatomical points of interest. The CFOR was also used for exploring the spatial distribution of the anatomical location for a large number of individuals. The results show that on average the point of interest can be estimated accurately within 10.3 mm for the bifurcation point and within 12.5 mm for the pulmonary nodule's center point. Further analyzing the spatial distribution of the CFOR coordinates across 86 subjects shows that we can localize the bifurcation point to the small subregion within the CFOR.

The Lung Image Database Consortium (LIDC): a comparison of different size metrics for pulmonary nodule measurements.

RATIONALE AND OBJECTIVES: The goal was to investigate the effects of choosing between different metrics in estimating the size of pulmonary nodules as a factor both of nodule characterization and of performance of computer aided detection systems, because the latter are always qualified with respect to a given size range of nodules. MATERIALS AND METHODS: This study used 265 whole-lung CT scans documented by the Lung Image Database Consortium (LIDC) using their protocol for nodule evaluation. Each inspected lesion was reviewed independently by four experienced radiologists who provided boundary markings for nodules larger than 3 mm. Four size metrics, based on the boundary markings, were considered: a unidimensional and two bidimensional measures on a single image slice and a volumetric measurement based on all the image slices. The radiologist boundaries were processed and those with four markings were analyzed to characterize the interradiologist variation, while those with at least one marking were used to examine the difference between the metrics. RESULTS: The processing of the annotations found 127 nodules marked by all of the four radiologists and an extended set of 518 nodules each having at least one observation with three-dimensional sizes ranging from 2.03 to 29.4 mm (average 7.05 mm, median 5.71 mm). A very high interobserver variation was observed for all these metrics: 95% of estimated standard deviations were in the following ranges for the three-dimensional, unidimensional, and two bidimensional size metrics, respectively (in mm): 0.49-1.25, 0.67-2.55, 0.78-2.11, and 0.96-2.69. Also, a very large difference among the metrics was observed: 0.95 probability-coverage region widths for the volume estimation conditional on unidimensional, and the two bidimensional size measurements of 10 mm were 7.32, 7.72, and 6.29 mm, respectively. CONCLUSIONS: The selection of data subsets for performance evaluation is highly impacted by the size metric choice. The LIDC plans to include a single size measure for each nodule in its database. This metric is not intended as a gold standard for nodule size; rather, it is intended to facilitate the selection of unique repeatable size limited nodule subsets.