Physiology for the pulmonary functional imager

Hybrid method for estimating lung ventilation from CT by combining intensity and motion information

BACKGROUND

Functional lung imaging modalities allow for capturing regional lung ventilation information. Computed Tomography based ventilation imaging (CTVI) has been proposed as a surrogate modality that relies on time-resolved anatomical data and image processing. However, generating accurate ventilation maps using solely computed tomography (CT) image information remains a challenging task, due to the need to derive functional information of ventilation from anatomical observations.

PURPOSE

We introduce the hybrid estimation of computed tomography obtained respiratory function (HECTOR) method that consists of two components: a volume- and a density-based ventilation estimate. For the first component, a deformable image registration (DIR)-based solution for accurate volumetric CTVI generation is proposed, integrating the physical characteristics of the lung deformations in its design. For the second component, an already established air-tissue density model is used. Furthermore, a novel method is developed for combining the two components.

METHODS

The proposed method consists of four principal steps: (1) Application of a specially tailored DIR algorithm to estimate respiratory motion between inhale and exhale phases. (2) Conversion of the motion information to volumetric change maps using a variation of the Jacobian determinant method. (3) Computation of a HU-based method that estimates the local product of air-tissue densities. (4) Combination of the metrics estimated in steps 2 and 3 by means of a smooth minimum function. The proposed approach is validated using the publicly available VAMPIRE dataset consisting of two subgroups: 25 subjects scanned with Galligas 4DPET/CT and 21 subjects scanned with DTPA-SPECT. Another dataset of 18 patients available at The Cancer Imaging Archive (TCIA) was used for further validation. All datasets contain inhale/exhale CT scans paired with ground-truth ventilation images (RefVIs). The CTVIs generated by the proposed HECTOR method were tested against the RefVIs using the Spearman correlation coefficient and Dice overlap of low- and high-function lung (DSC-low and DSC-high, respectively).

RESULTS

The proposed method achieved mean Spearman, DSC-high and DSC-low coefficients of 0.62, 0.55, and 0.59 on the Galligas PET subgroup and 0.49,0,48, and 0.50 on the DTPA-SPECT subgroup of the VAMPIRE dataset. This performance was better than the highest performing method reported in the original challenge. The same metrics for the TCIA dataset were 0.66, 0.60, and 0.60. The proposed hybrid ventilation method achieved higher Spearman correlation scores than the individual volume- and density-based components in all datasets. Additionally, the use of the specially tailored DIR algorithm was found to achieve higher scores than previously reported volume-based methods.

CONCLUSIONS

Our work provides a novel processing workflow for CT ventilation imaging that can consistently generate ventilation maps with high fidelity compared to reference approaches. This study also provides further insights into the benefits of combining different types of information to model the complex dynamics of respiratory function. Such information can be useful for potential applications in radiation therapy treatment planning and thoracic dose-response assessment.

Constructing Surrogate Lung Ventilation Maps From 4-Dimensional Computed Tomography-Derived Subregional Respiratory Dynamics

PURPOSE

To present a 2-stage framework that robustly extracts and maps reliable lung ventilation surrogates based on subregional respiratory dynamics (SRDs) measured from 4-dimensional computed tomography (4DCT) images, with comprehensive consideration of spatial and temporal heterogeneity in the ventilation process over the respiratory cycle.

METHODS AND MATERIALS

We retrospectively analyzed 3 subject cohorts from the Ventilation and Medical Pulmonary Image Registration Evaluation challenge containing 4DCT and reference ventilation imaging (RefVI) scans. Lung subregions were partitioned on the 4DCT end-of-exhale base phase using anatomically constrained simple linear iterative clustering, whereas sliding-preserved interphase image registrations were performed between the base and other phases. SRDs of breathing-induced volume and intensity changes were tracked across phases utilizing the displacement fields. Voxel-level representations integrating mechanical collapsibility and physiological tissue density (VSRD) were accordingly constructed from SRDs. Imaging performance of VSRD as the proposed surrogate ventilation map was studied against RefVI scans and compared with classical biphasic Jacobian maps. The dosimetric performance evaluation was also conducted to assess the clinical benefits of incorporating VSRD maps into functional lung avoidance radiation therapy (FLA-RT) planning.

RESULTS

The extracted SRD highlighted temporally varying subregional volume and computed tomography intensity changes related to underlying functional physiology and pathologies. For imaging performance, the median Spearman correlation coefficients between VSRD and RefVI scans were 0.600, 0.582, and 0.561 for the 3 cohorts, whereas median Dice similarity coefficients against RefVI scans showing the high (low)-functioning lung regions' concordances were 0.611 (0.626), 0.592 (0.620), and 0.601 (0.611), superior to biphasic Jacobian maps for both metrics. For dosimetric performance, VSRD-guided FLA-RT plans achieved significantly better dose sparing of high-functioning lung regions compared with FLA-RT plans based on biphasic Jacobian maps.

CONCLUSIONS

VSRD maps captured spatial and temporal heterogeneity in the ventilation process, providing improved ventilation representations compared with classical algorithms. The capability to extract multidimensional ventilation-correlated image information from widely available 4DCT images showed promise in enhancing personalized FLA-RT implementations.

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.

Respiratory Invariant Textures From Static Computed Tomography Scans for Explainable Lung Function Characterization

PURPOSE

The inherent characteristics of lung tissue independent of breathing maneuvers may provide fundamental information for function assessment. This paper attempted to correlate textural signatures from computed tomography (CT) with pulmonary function measurements.

MATERIALS AND METHODS

Twenty-one lung cancer patients with thoracic 4-dimensional CT, DTPA-single-photon emission CT ventilation ( VNM ) scans, and available spirometry measurements (forced expiratory volume in 1 s, FEV 1 ; forced vital capacity, FVC; and FEV 1 /FVC) were collected. In subregional feature discovery, function-correlated candidates were identified from 79 radiomic features based on the statistical strength to differentiate defected/nondefected lung regions. Feature maps (FMs) of selected candidates were generated on 4-dimensional CT phases for a voxel-wise feature distribution study. Quantitative metrics were applied for validations, including the Spearman correlation coefficient (SCC) and the Dice similarity coefficient for FM- VNM spatial agreement assessments, intraclass correlation coefficient for FM interphase robustness evaluations, and FM-spirometry comparisons.

RESULTS

At the subregion level, 8 function-correlated features were identified (effect size>0.330). The FMs of candidates yielded moderate-to-strong voxel-wise correlations with the reference VNM . The FMs of gray level dependence matrix dependence nonuniformity showed the highest robust (intraclass correlation coefficient=0.96 and P <0.0001) spatial correlation, with median SCCs ranging from 0.54 to 0.59 throughout the 10 breathing phases. Its phase-averaged FM achieved a median SCC of 0.60, a median Dice similarity coefficient of 0.60 (0.65) for high (low) functional lung volumes, and a correlation of 0.565 (0.646) between the spatially averaged feature values and FEV 1 (FEV 1 /FVC).

CONCLUSIONS

The results provide further insight into the underlying association of specific pulmonary textures with both local ( VNM ) and global (FEV 1 /FVC, FEV 1 ) functions. Further validations of the FM generalizability and the standardization of implementation protocols are warranted before clinically relevant investigations.

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.

A super-voxel-based method for generating surrogate lung ventilation images from CT

Purpose: This study aimed to develop and evaluate CTVISVD , a super-voxel-based method for surrogate computed tomography ventilation imaging (CTVI). Methods and Materials: The study used four-dimensional CT (4DCT) and single-photon emission computed tomography (SPECT) images and corresponding lung masks from 21 patients with lung cancer obtained from the Ventilation And Medical Pulmonary Image Registration Evaluation dataset. The lung volume of the exhale CT for each patient was segmented into hundreds of super-voxels using the Simple Linear Iterative Clustering (SLIC) method. These super-voxel segments were applied to the CT and SPECT images to calculate the mean density values (D _mean) and mean ventilation values (Vent _mean), respectively. The final CT-derived ventilation images were generated by interpolation from the D _mean values to yield CTVISVD. For the performance evaluation, the voxel- and region-wise differences between CTVISVD and SPECT were compared using Spearman's correlation and the Dice similarity coefficient index. Additionally, images were generated using two deformable image registration (DIR)-based methods, CTVIHU and CTVIJac, and compared with the SPECT images. Results: The correlation between the D _mean and Vent _mean of the super-voxel was 0.59 ± 0.09, representing a moderate-to-high correlation at the super-voxel level. In the voxel-wise evaluation, the CTVISVD method achieved a stronger average correlation (0.62 ± 0.10) with SPECT, which was significantly better than the correlations achieved with the CTVIHU (0.33 ± 0.14, p < 0.05) and CTVIJac (0.23 ± 0.11, p < 0.05) methods. For the region-wise evaluation, the Dice similarity coefficient of the high functional region for CTVISVD (0.63 ± 0.07) was significantly higher than the corresponding values for the CTVIHU (0.43 ± 0.08, p < 0.05) and CTVIJac (0.42 ± 0.05, p < 0.05) methods. Conclusion: The strong correlation between CTVISVD and SPECT demonstrates the potential usefulness of this novel method of ventilation estimation for surrogate ventilation imaging.

Pulmonary Functional Imaging: Part 1-State-of-the-Art Technical and Physiologic Underpinnings

Over the past few decades, pulmonary imaging technologies have advanced from chest radiography and nuclear medicine methods to high-spatial-resolution or low-dose chest CT and MRI. It is currently possible to identify and measure pulmonary pathologic changes before these are obvious even to patients or depicted on conventional morphologic images. Here, key technological advances are described, including multiparametric CT image processing methods, inhaled hyperpolarized and fluorinated gas MRI, and four-dimensional free-breathing CT and MRI methods to measure regional ventilation, perfusion, gas exchange, and biomechanics. The basic anatomic and physiologic underpinnings of these pulmonary functional imaging techniques are explained. In addition, advances in image analysis and computational and artificial intelligence (machine learning) methods pertinent to functional lung imaging are discussed. The clinical applications of pulmonary functional imaging, including both the opportunities and challenges for clinical translation and deployment, will be discussed in part 2 of this review. Given the technical advances in these sophisticated imaging methods and the wealth of information they can provide, it is anticipated that pulmonary functional imaging will be increasingly used in the care of patients with lung disease. © RSNA, 2021 Online supplemental material is available for this article.