Synthetic pulmonary perfusion images from 4DCT for functional avoidance using deep learning

Incorporation of Functional Lung Imaging Into Radiation Therapy Planning in Patients With Lung Cancer: A Systematic Review and Meta-Analysis

Our purpose was to provide an understanding of current functional lung imaging (FLI) techniques and their potential to improve dosimetry and outcomes for patients with lung cancer receiving radiation therapy (RT). Excerpta Medica dataBASE (EMBASE), PubMed, and Cochrane Library were searched from 1990 until April 2023. Articles were included if they reported on FLI in one of: techniques, incorporation into RT planning for lung cancer, or quantification of RT-related outcomes for patients with lung cancer. Studies involving all RT modalities, including stereotactic body RT and particle therapy, were included. Meta-analyses were conducted to investigate differences in dose-function parameters between anatomic and functional RT planning techniques, as well as to investigate correlations of dose-function parameters with grade 2+ radiation pneumonitis (RP). One hundred seventy-eight studies were included in the narrative synthesis. We report on FLI modalities, dose-response quantification, functional lung (FL) definitions, FL avoidance techniques, and correlations between FL irradiation and toxicity. Meta-analysis results show that FL avoidance planning gives statistically significant absolute reductions of 3.22% to the fraction of well-ventilated lung receiving 20 Gy or more, 3.52% to the fraction of well-perfused lung receiving 20 Gy or more, 1.3 Gy to the mean dose to the well-ventilated lung, and 2.41 Gy to the mean dose to the well-perfused lung. Increases in the threshold value for defining FL are associated with decreases in functional parameters. For intensity modulated RT and volumetric modulated arc therapy, avoidance planning results in a 13% rate of grade 2+ RP, which is reduced compared with results from conventional planning cohorts. A trend of increased predictive ability for grade 2+ RP was seen in models using FL information but was not statistically significant. FLI shows promise as a method to spare FL during thoracic RT, but interventional trials related to FL avoidance planning are sparse. Such trials are critical to understanding the effect of FL avoidance planning on toxicity reduction and patient outcomes.

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.

Predicting pulmonary ventilation damage after radiation therapy for nonsmall cell lung cancer using a ResNet generative adversarial network

BACKGROUND

Functional lung avoidance radiation therapy (RT) is a technique being investigated to preferentially avoid specific regions of the lung that are predicted to be more susceptible to radiation-induced damage. Reducing the dose delivered to high functioning regions may reduce the occurrence radiation-induced lung injuries (RILIs) and toxicities. However, in order to develop effective lung function-sparing plans, accurate predictions of post-RT ventilation change are needed to determine which regions of the lung should be spared.

PURPOSE

To predict pulmonary ventilation change following RT for nonsmall cell lung cancer using machine learning.

METHODS

A conditional generative adversarial network (cGAN) was developed with data from 82 human subjects enrolled in a randomized clinical trial approved by the institution's IRB to predict post-RT pulmonary ventilation change. The inputs to the network were the pre-RT pulmonary ventilation map and radiation dose distribution. The loss function was a combination of the binary cross-entropy loss and an asymmetrical structural similarity index measure (aSSIM) function designed to increase penalization of under-prediction of ventilation damage. Network performance was evaluated against a previously developed polynomial regression model using a paired sample t-test for comparison. Evaluation was performed using eight-fold cross-validation.

RESULTS

From the eight-fold cross-validation, we found that relative to the polynomial model, the cGAN model significantly improved predicting regions of ventilation damage following radiotherapy based on true positive rate (TPR), 0.14±0.15 to 0.72±0.21, and Dice similarity coefficient (DSC), 0.19±0.16 to 0.46±0.14, but significantly declined in true negative rate, 0.97±0.05 to 0.62±0.21, and accuracy, 0.79±0.08 to 0.65±0.14. Additionally, the average true positive volume increased from 104±119 cc in the POLY model to 565±332 cc in the cGAN model, and the average false negative volume decreased from 654±361 cc in the POLY model to 193±163 cc in the cGAN model.

CONCLUSIONS

The proposed cGAN model demonstrated significant improvement in TPR and DSC. The higher sensitivity of the cGAN model can improve the clinical utility of functional lung avoidance RT by identifying larger volumes of functional lung that can be spared and thus decrease the probability of the patient developing RILIs.

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.