A deep learning method for producing ventilation images from 4DCT: First comparison with technegas SPECT ventilation

Deep learning-based combination of [18F]-FDG PET and CT images for producing pulmonary perfusion image

BACKGROUND

The main application of [18F] FDG-PET (18 FDG-PET) and CT images in oncology is tumor identification and quantification. Combining PET and CT images to mine pulmonary perfusion information for functional lung avoidance radiation therapy (FLART) is desirable but remains challenging.

PURPOSE

To develop a deep-learning-based (DL) method to combine 18 FDG-PET and CT images for producing pulmonary perfusion images (PPI).

METHODS

Pulmonary technetium-99 m-labeled macroaggregated albumin SPECT (PPISPECT ), 18 FDG-PET, and CT images obtained from 53 patients were enrolled. CT and PPISPECT images were rigidly registered, and registration displacement was subsequently used to align 18 FDG-PET and PPISPECT images. The left/right lung was separated and rigidly registered again to improve the registration accuracy. A DL model based on 3D Unet architecture was constructed to directly combine multi-modality 18 FDG-PET and CT images for producing PPI (PPIDLM ). 3D Unet architecture was used as the basic architecture, and the input was expanded from a single-channel to a dual-channel to combine multi-modality images. For comparative evaluation, 18 FDG-PET images were also used alone to generate PPIDLPET . Sixty-seven samples were randomly selected for training and cross-validation, and 36 were used for testing. The Spearman correlation coefficient (rs ) and multi-scale structural similarity index measure (MS-SSIM) between PPIDLM /PPIDLPET and PPISPECT were computed to assess the statistical and perceptual image similarities. The Dice similarity coefficient (DSC) was calculated to determine the similarity between high-/low- functional lung (HFL/LFL) volumes.

RESULTS

The voxel-wise rs and MS-SSIM of PPIDLM /PPIDLPET were 0.78 ± 0.04/0.57 ± 0.03, 0.93 ± 0.01/0.89 ± 0.01 for cross-validation and 0.78 ± 0.11/0.55 ± 0.18, 0.93 ± 0.03/0.90 ± 0.04 for testing. PPIDLM /PPIDLPET achieved averaged DSC values of 0.78 ± 0.03/0.64 ± 0.02 for HFL and 0.83 ± 0.01/0.72 ± 0.03 for LFL in the training dataset and 0.77 ± 0.11/0.64 ± 0.12, 0.82 ± 0.05/0.72 ± 0.06 in the testing dataset. PPIDLM yielded a stronger correlation and higher MS-SSIM with PPISPECT than PPIDLPET (p < 0.001).

CONCLUSIONS

The DL-based method integrates lung metabolic and anatomy information for producing PPI and significantly improved the accuracy over methods based on metabolic information alone. The generated PPIDLM can be applied for pulmonary perfusion volume segmentation, which is potentially beneficial for FLART treatment plan optimization.

The Past, Present, and Future Role of Artificial Intelligence in Ventilation/Perfusion Scintigraphy: A Systematic Review

Ventilation-perfusion (V/Q) lung scans constitute one of the oldest nuclear medicine procedures, remain one of the few studies performed in the acute setting, and are amongst the few performed in the emergency setting. V/Q studies have witnessed a long fluctuation in adoption rates in parallel to continuous advances in image processing and computer vision techniques. This review provides an overview on the status of artificial intelligence (AI) in V/Q scintigraphy. To clearly assess the past, current, and future role of AI in V/Q scans, we conducted a systematic Ovid MEDLINE(R) literature search from 1946 to August 5, 2022 in addition to a manual search. The literature was reviewed and summarized in terms of methodologies and results for the various applications of AI to V/Q scans. The PRISMA guidelines were followed. Thirty-one publications fulfilled our search criteria and were grouped into two distinct categories: (1) disease diagnosis/detection (N = 22, 71.0%) and (2) cross-modality image translation into V/Q images (N = 9, 29.0%). Studies on disease diagnosis and detection relied heavily on shallow artificial neural networks for acute pulmonary embolism (PE) diagnosis and were primarily published between the mid-1990s and early 2000s. Recent applications almost exclusively regard image translation tasks from CT to ventilation or perfusion images with modern algorithms, such as convolutional neural networks, and were published between 2019 and 2022. AI research in V/Q scintigraphy for acute PE diagnosis in the mid-90s to early 2000s yielded promising results but has since been largely neglected and thus have yet to benefit from today's state-of-the art machine-learning techniques, such as deep neural networks. Recently, the main application of AI for V/Q has shifted towards generating synthetic ventilation and perfusion images from CT. There is therefore considerable potential to expand and modernize the use of real V/Q studies with state-of-the-art deep learning approaches, especially for workflow optimization and PE detection at both acute and chronic stages. We discuss future challenges and potential directions to compensate for the lag in this domain and enhance the value of this traditional nuclear medicine scan.

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.

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.

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.

Quantification of lung function on CT images based on pulmonary radiomic filtering

PURPOSE

To develop a radiomics filtering technique for characterizing spatial-encoded regional pulmonary ventilation information on lung computed tomography (CT).

METHODS

The lung volume was segmented on 46 CT images, and a 3D sliding window kernel was implemented across the lung volume to capture the spatial-encoded image information. Fifty-three radiomic features were extracted within the kernel, resulting in a fourth-order tensor object. As such, each voxel coordinate of the original lung was represented as a 53-dimensional feature vector, such that radiomic features could be viewed as feature maps within the lungs. To test the technique as a potential pulmonary ventilation biomarker, the radiomic feature maps were compared to paired functional images (Galligas PET or DTPA-SPECT) based on the Spearman correlation (ρ) analysis.

RESULTS

The radiomic feature maps GLRLM-based Run-Length Non-Uniformity and GLCOM-based Sum Average are found to be highly correlated with the functional imaging. The achieved ρ (median [range]) for the two features are 0.46 [0.05, 0.67] and 0.45 [0.21, 0.65] across 46 patients and 2 functional imaging modalities, respectively.

CONCLUSIONS

The results provide evidence that local regions of sparsely encoded heterogeneous lung parenchyma on CT are associated with diminished radiotracer uptake and measured lung ventilation defects on PET/SPECT imaging. These findings demonstrate the potential of radiomics to serve as a complementary tool to the current lung quantification techniques and provide hypothesis-generating data for future studies.

Volumetric multiphase ventilation imaging based on four-dimensional computed tomography for functional lung avoidance radiotherapy

PURPOSE

Current computed tomography (CT)-based lung ventilation imaging (CTVI) techniques derive a static ventilation image without temporal information. This research aims to develop a four-dimensional CT (4DCT)-based multiphase dynamic ventilation imaging framework capable of recovering the entire ventilation process throughout the breathing cycle for functional lung avoidance radiotherapy (FLART).

METHODS

A total of 15 free-breathing thoracic 4DCT scans of lung or esophageal cancer patients were collected from the public datasets. The lung region of each phase image was first delineated, and then the mask-free isotropic total variation image registration algorithm was used to derive the deformation vector fields between the end-expiration (EE) phase and other phases. As a surrogate of ventilation, the voxel-wise local expansion ratio of each phase relative to the EE phase was estimated using the parameterized Integrated Jacobian Formulation method in the EE phase coordinate. Lastly, the dynamic ventilation images were generated by warping these phase-specific local expansion distributions with a same geometry into their respective breathing phases. Quantitative analysis, including interphase Spearman correlation coefficients, voxel-wise, and regional-wise expansion/contraction tracking, were performed to indirectly validate the proposed method.

RESULTS

The proposed method maintains the physiological meaning of ventilation on each phase and enables to recover the dynamic lung ventilation process. The mean interphase Spearman correlations ranged between 0.23 ± 0.20 and 0.93 ± 0.04 and decreased near the EE phase. Only 26.2% (2.59E + 6 out of 9.89E + 6) of lung voxels exhibited the same expansion/contraction pattern as the global lung. Qualitative and quantitative evaluations of the interphase ventilation distribution difference show that ventilation spatiotemporal heterogeneities generally exist during respiration.

CONCLUSIONS

In contrast to conventional CTVI metrics, our method enables to extract additional phase-resolved respiration-correlated information and reflects the generally existed ventilation spatiotemporal heterogeneities. Subsequent studies with quantitative phase-by-phase cross-modality evaluations will further explore its potential to deepen our understanding of lung function and respiration mechanics and also to facilitate more accurate implementation of FLART.

Functional lung imaging in thoracic tumor radiotherapy: Application and progress

Radiotherapy plays an irreplaceable and unique role in treating thoracic tumors, but the occurrence of radiation-induced lung injury has limited the increase in tumor target doses and has influenced patients’ quality of life. However, the introduction of functional lung imaging has been incorporating functional lungs into radiotherapy planning. The design of the functional lung protection plan, while meeting the target dose requirements and dose limitations of the organs at risk (OARs), minimizes the radiation dose to the functional lung, thus reducing the occurrence of radiation-induced lung injury. In this manuscript, we mainly reviewed the lung ventilation or/and perfusion functional imaging modalities, application, and progress, as well as the results based on the functional lung protection planning in thoracic tumors. In addition, we also discussed the problems that should be explored and further studied in the practical application based on functional lung radiotherapy planning.

Deriving Pulmonary Ventilation Images From Clinical 4D-CBCT Using a Deep Learning-Based Model

Purpose

The current algorithms for measuring ventilation images from 4D cone-beam computed tomography (CBCT) are affected by the accuracy of deformable image registration (DIR). This study proposes a new deep learning (DL) method that does not rely on DIR to derive ventilation images from 4D-CBCT (CBCT-VI), which was validated with the gold-standard single-photon emission-computed tomography ventilation image (SPECT-VI).

Materials and Methods

This study consists of 4D-CBCT and 99mTc-Technegas SPECT/CT scans of 28 esophagus or lung cancer patients. The scans were rigidly registered for each patient. Using these data, CBCT-VI was derived using a deep learning-based model. Two types of model input data are studied, namely, (a) 10 phases of 4D-CBCT and (b) two phases of peak-exhalation and peak-inhalation of 4D-CBCT. A sevenfold cross-validation was applied to train and evaluate the model. The DIR-dependent methods (density-change-based and Jacobian-based methods) were used to measure the CBCT-VIs for comparison. The correlation was calculated between each CBCT-VI and SPECT-VI using voxel-wise Spearman's correlation. The ventilation images were divided into high, medium, and low functional lung regions. The similarity of different functional lung regions between SPECT-VI and each CBCT-VI was evaluated using the dice similarity coefficient (DSC). One-factor ANONA model was used for statistical analysis of the averaged DSC for the different methods of generating ventilation images.

Results

The correlation values were 0.02 ± 0.10, 0.02 ± 0.09, and 0.65 ± 0.13/0.65 ± 0.15, and the averaged DSC values were 0.34 ± 0.04, 0.34 ± 0.03, and 0.59 ± 0.08/0.58 ± 0.09 for the density change, Jacobian, and deep learning methods, respectively. The strongest correlation and the highest similarity with SPECT-VI were observed for the deep learning method compared to the density change and Jacobian methods.

Conclusion

The results showed that the deep learning method improved the accuracy of correlation and similarity significantly, and the derived CBCT-VIs have the potential to monitor the lung function dynamic changes during radiotherapy.

A deep learning method for translating 3D-CT to SPECT ventilation imaging: First comparison with 81m Kr-gas SPECT ventilation imaging

PURPOSE

This study aimed to evaluate the accuracy of deep learning (DL)-based computed tomography (CT) ventilation imaging (CTVI).

METHODS

A total of 71 cases who underwent single-photon emission CT ^81m Kr-gas ventilation (SPECT V) and CT imaging were included. Sixty cases were assigned to the training and validation sets and the remaining 11 cases were assigned to the test set. To directly transform 3DCT (free-breathing CT) images to SPECT V images, a DL-based model was implemented based on the U-Net architecture. The input and output data were 3DCT- and SPECT V-masked, respectively, except for whole-lung volumes. These data were rearranged in voxel size, registered rigidly, cropped, and normalized in pre-processing. In addition to a standard estimation method (i.e., without dropout during the estimation process), a Monte-Carlo Dropout (MCD) method (i.e., with dropout during the estimation process) was used to calculate prediction uncertainty. To evaluate the two models' (CTVI_{MCD U-Net} , CTVI_U-Net ) performance, we used five-fold cross-validation for the training and validation sets. To test the final model performances for both approaches, we applied the test set to each trained model and averaged the test prediction results from the five trained models to acquire the mean test result (bagging) for each approach. For the MCD method, the models were predicted repeatedly (sample size = 200), and the average and standard deviation maps were calculated in each voxel from the predicted results: the average maps were defined as test prediction results in each fold. As an evaluation index, the voxel-wise Spearman rank correlation coefficient (Spearman r_s ) and dice similarity coefficient (DSC) were calculated. The DSC was calculated for three functional regions (high, moderate, and low) separated by an almost equal volume. The coefficient of variation was defined as prediction uncertainty, and these average values were calculated within three functional regions. The Wilcoxon signed-rank test was used to test for a significant difference between the two DL-based approaches RESULTS: The average indexes with one standard deviation (1SD) between CTVI_{MCD U-Net} and SPECT V were 0.76 ± 0.06, 0.69 ± 0.07, 0.51 ± 0.06, and 0.75 ± 0.04 for Spearman r_s , DSC_high , DSC_moderate , and DSC_low , respectively. The average indexes with 1SD between CTVI_U-Net and SPECT V were 0.72 ± 0.05, 0.66 ± 0.04, 0.48 ± 0.04, and 0.74 ± 0.06 for Spearman r_s , DSC_high , DSC_moderate , and DSC_low , respectively. These indexes between CTVI_{MCD U-Net} and CTVI_U-Net showed no significance difference (Spearman r_s , p = 0.175; DSC_high , p = 0.123; DSC_moderate , p = 0.278; DSC_low , p = 0.520). The average coefficient of variations with 1SD were 0.27 ± 0.00, 0.27 ± 0.01, and 0.36 ± 0.03 for the high-, moderate-, and low-functional regions, respectively, and the low-functional region showed a tendency to exhibit larger uncertainties than the others.

CONCLUSION

We evaluated DL-based framework for estimating lung-functional ventilation images only from CT images. The results indicated that the DL-based approach could potentially be used for lung-ventilation estimation. This article is protected by copyright. All rights reserved.

Investigating the use of machine learning to generate ventilation images from CT scans

Background

Radiotherapy treatment planning incorporating ventilation imaging can reduce the incidence of radiation‐induced lung injury. The gold‐standard of ventilation imaging, using nuclear medicine, has limitations with respect to availability and cost.

Purpose

An alternative type of ventilation imaging to nuclear medicine uses 4DCT (or breath‐hold CT [BHCT] pair) with deformable image registration (DIR) and a ventilation metric to produce a CT ventilation image (CTVI). The purpose of this study is to investigate the application of machine learning as an alternative to DIR‐based methods when producing CTVIs.

Methods

A patient dataset of 15 inhale and exhale BHCTs and Galligas PET ventilation images were used to train and test a 2D U‐Net style convolutional neural network. The neural network established relationships between axial input BHCT image pairs and axial labeled Galligas PET images and was evaluated using eightfold cross‐validation. Once trained, the neural network could produce a CTVI from an input BHCT image pair. The CTVIs produced by the neural network were qualitatively assessed visually and quantitatively compared to a Galligas PET ventilation image using a Spearman correlation and Dice similarity coefficient (DSC). The DSC measured the spatial overlap between three segmented equal lung volumes by ventilation (high, medium, and low functioning lung [LFL]).

Results

The mean Spearman correlation between the CTVIs and the Galligas PET ventilation images was 0.58 ± 0.14. The mean DSC over high, medium, and LFL between the CTVIs and Galligas PET ventilation images was 0.55 ± 0.06. Visually, a systematic overprediction of ventilation within the lung was observed in the CTVIs with respect to the Galligas PET ventilation images, with jagged regions of ventilation in the sagittal and coronal planes.

Conclusions

A convolutional neural network was developed that could produce a CTVI from a BHCT image pair, which was then compared with a Galligas PET ventilation image. The performance of this machine learning method was comparable to previous benchmark studies investigating a DIR‐based CTVI, warranting future development, and investigation of applying machine learning to a CTVI.

Deep learning in structural and functional lung image analysis

The recent resurgence of deep learning (DL) has dramatically influenced the medical imaging field. Medical image analysis applications have been at the forefront of DL research efforts applied to multiple diseases and organs, including those of the lungs. The aims of this review are twofold: (i) to briefly overview DL theory as it relates to lung image analysis; (ii) to systematically review the DL research literature relating to the lung image analysis applications of segmentation, reconstruction, registration and synthesis. The review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. 479 studies were initially identified from the literature search with 82 studies meeting the eligibility criteria. Segmentation was the most common lung image analysis DL application (65.9% of papers reviewed). DL has shown impressive results when applied to segmentation of the whole lung and other pulmonary structures. DL has also shown great potential for applications in image registration, reconstruction and synthesis. However, the majority of published studies have been limited to structural lung imaging with only 12.9% of reviewed studies employing functional lung imaging modalities, thus highlighting significant opportunities for further research in this field. Although the field of DL in lung image analysis is rapidly expanding, concerns over inconsistent validation and evaluation strategies, intersite generalisability, transparency of methodological detail and interpretability need to be addressed before widespread adoption in clinical lung imaging workflow.

A deep learning-based dual-omics prediction model for radiation pneumonitis

PURPOSE

Radiation pneumonitis (RP) is the main source of toxicity in thoracic radiotherapy. This study proposed a deep learning-based dual-omics model, which aims to improve the RP prediction performance by integrating more data points and exploring the data in greater depth.

MATERIALS AND METHODS

The bimodality data were the original dose (OD) distribution and the ventilation image (VI) derived from four-dimensional computed tomography (4DCT). The functional dose (FD) distribution was obtained by weighting OD with VI. A pre-trained three-dimensional convolution (C3D) network was used to extract the features from FD, VI, and OD. The extracted features were then filtered and selected using entropy-based methods. The prediction models were constructed with four most commonly used binary classifiers. Cross-validation, bootstrap, and nested sampling methods were adopted in the process of training and hyper-tuning.

RESULTS

Data from 217 thoracic cancer patients treated with radiotherapy were used to train and validate the prediction model. The 4DCT-based VI showed the inhomogeneous pulmonary function of the lungs. More than half of the extracted features were singular (of none-zero value for few patients), which were eliminated to improve the stability of the model. The area under curve (AUC) of the dual-omics model was 0.874 (95% confidence interval: 0.871-0.877), and the AUC of the single-omics model was 0.780 (0.775-0.785, VI) and 0.810 (0.804-0.811, OD), respectively.

CONCLUSIONS

The dual-omics outperformed single-omics for RP prediction, which can be contributed to: (1) using more data points; (2) exploring the data in greater depth; and (3) incorporating of the bimodality data.

Machine learning applications in radiation oncology

Machine learning technology has a growing impact on radiation oncology with an increasing presence in research and industry. The prevalence of diverse data including 3D imaging and the 3D radiation dose delivery presents potential for future automation and scope for treatment improvements for cancer patients. Harnessing this potential requires standardization of tools and data, and focused collaboration between fields of expertise. The rapid advancement of radiation oncology treatment technologies presents opportunities for machine learning integration with investments targeted towards data quality, data extraction, software, and engagement with clinical expertise. In this review, we provide an overview of machine learning concepts before reviewing advances in applying machine learning to radiation oncology and integrating these techniques into the radiation oncology workflows. Several key areas are outlined in the radiation oncology workflow where machine learning has been applied and where it can have a significant impact in terms of efficiency, consistency in treatment and overall treatment outcomes. This review highlights that machine learning has key early applications in radiation oncology due to the repetitive nature of many tasks that also currently have human review. Standardized data management of routinely collected imaging and radiation dose data are also highlighted as enabling engagement in research utilizing machine learning and the ability integrate these technologies into clinical workflow to benefit patients. Physicists need to be part of the conversation to facilitate this technical integration.

Investigation of a Novel Deep Learning-Based Computed Tomography Perfusion Mapping Framework for Functional Lung Avoidance Radiotherapy

Functional lung avoidance radiation therapy aims to minimize dose delivery to the normal lung tissue while favoring dose deposition in the defective lung tissue based on the regional function information. However, the clinical acquisition of pulmonary functional images is resource-demanding, inconvenient, and technically challenging. This study aims to investigate the deep learning-based lung functional image synthesis from the CT domain. Forty-two pulmonary macro-aggregated albumin SPECT/CT perfusion scans were retrospectively collected from the hospital. A deep learning-based framework (including image preparation, image processing, and proposed convolutional neural network) was adopted to extract features from 3D CT images and synthesize perfusion as estimations of regional lung function. Ablation experiments were performed to assess the effects of each framework component by removing each element of the framework and analyzing the testing performances. Major results showed that the removal of the CT contrast enhancement component in the image processing resulted in the largest drop in framework performance, compared to the optimal performance (~12%). In the CNN part, all the three components (residual module, ROI attention, and skip attention) were approximately equally important to the framework performance; removing one of them resulted in a 3–5% decline in performance. The proposed CNN improved ~4% overall performance and ~350% computational efficiency, compared to the U-Net model. The deep convolutional neural network, in conjunction with image processing for feature enhancement, is capable of feature extraction from CT images for pulmonary perfusion synthesis. In the proposed framework, image processing, especially CT contrast enhancement, plays a crucial role in the perfusion synthesis. This CTPM framework provides insights for relevant research studies in the future and enables other researchers to leverage for the development of optimized CNN models for functional lung avoidance radiation therapy.