Optimizing geometric accuracy of four-dimensional CT scans acquired using the wall- and couch-mounted Varian® Real-time Position Management™ camera systems

METnet: A novel deep learning model predicting MET dysregulation in non-small-cell lung cancer on computed tomography images

BACKGROUND

Mesenchymal epithelial transformation (MET) is a key molecular target for diagnosis and treatment of non-small cell lung cancer (NSCLC). The corresponding molecularly targeted therapeutics have been approved by Food and Drug Administration (FDA), achieving promising results. However, current detection of MET dysregulation requires biopsy and gene sequencing, which is invasive, time-consuming and difficult to obtain tumor samples.

METHODS

To address the above problems, we developed a noninvasive and convenient deep learning (DL) model based on Computed tomography (CT) imaging data for prediction of MET dysregulation. We introduced the unsupervised algorithm RK-net for automated image processing and utilized the MedSAM large model to achieve automated tissue segmentation. Based on the processed CT images, we developed a DL model (METnet). The model based on the grouped convolutional block. We evaluated the performance of the model over the internal test dataset using the area under the receiver operating characteristic curve (AUROC) and accuracy. We conducted subgroup analysis on the basis of clinical data of the lung cancer patients and compared the performance of the model in different subgroups.

RESULTS

The model demonstrated a good discriminative ability over the internal test dataset. The accuracy of METnet was 0.746 with an AUC value of 0.793 (95% CI 0.714-0.871). The subgroup analysis revealed that the model exhibited similar performance across different subgroups.

CONCLUSIONS

METnet realizes prediction of MET dysregulation in NSCLC, holding promise for guiding precise tumor diagnosis and treatment at the molecular level.

Towards a multi-scale computer modeling workflow for simulation of pulmonary ventilation in advanced COVID-19

Physics-based multi-scale in silico models offer an excellent opportunity to study the effects of heterogeneous tissue damage on airflow and pressure distributions in COVID-19-afflicted lungs. The main objective of this study is to develop a computational modeling workflow, coupling airflow and tissue mechanics as the first step towards a virtual hypothesis-testing platform for studying injury mechanics of COVID-19-afflicted lungs. We developed a CT-based modeling approach to simulate the regional changes in lung dynamics associated with heterogeneous subject-specific COVID-19-induced damage patterns in the parenchyma. Furthermore, we investigated the effect of various levels of inflammation in a meso-scale acinar mechanics model on global lung dynamics. Our simulation results showed that as the severity of damage in the patient's right lower, left lower, and to some extent in the right upper lobe increased, ventilation was redistributed to the least injured right middle and left upper lobes. Furthermore, our multi-scale model reasonably simulated a decrease in overall tidal volume as the level of tissue injury and surfactant loss in the meso-scale acinar mechanics model was increased. This study presents a major step towards multi-scale computational modeling workflows capable of simulating the effect of subject-specific heterogenous COVID-19-induced lung damage on ventilation dynamics.

Investigating the impact of tumour motion on TomoTherapy stereotactic ablative body radiotherapy (SABR) deliveries on 3-dimensional and 4-dimensional computed tomography

TomoTherapy can provide highly accurate SABR deliveries, but currently it does not have any effective motion management techniques. Shallow breathing has been identified as one possible motion management solution on TomoTherapy, which has been made possible with the BreatheWell audiovisual biofeedback (AVB) device. Since both the shallow breathing technique and the clinical use of the BreatheWell device are novel, their implementation requires comprehensive verification and validation work. As the first stage of the validation, this paper investigates the impact of target motion on a TomoTherapy SABR delivery is assessed on both 3D CT and 4D CT using a 4D respiratory phantom. A dosimetric study on a 4D respiratory phantom was conducted, with the phantom's insert designed to move at four different amplitudes in the superior-inferior direction. SABR plans on 3D and 4D CT scans were created and measured. Critical plan statistics and measurement results were compared. It is found that for TomoTherapy SABR deliveries, by reducing the targets respiratory motion, target coverage, organ-at-risk (OAR) sparing, and delivery accuracy were improved.

Development of a novel methodology for QA of respiratory-gated and VMAT beam delivery using Octavius 4D phantom

The objective of this study was to develop and evaluate a series of quality assurance (QA) techniques based on Octavius 4D phantom for testing of respiratory-gated treatment delivery, integrity of dose rate vs gantry speed in volumetric-modulated arc therapy (VMAT) commissioning, and multileaf collimator (MLC) positioning accuracy of a linear accelerator. An Octavius 4D phantom capable of rotating with the gantry and recording the detector signal with a sampling rate of 10 Hz was isocentrally set up and an inclinometer was also installed to measure the gantry angle simultaneously. A simple arc test was created and delivered with gating function activated to measure the timing accuracy of the gating window. A tailor-made dose rate vs gantry speed plan was also designed to test the accuracy of measured dose rate, gantry speed, and actual control points. All experiments were conducted while machine log files were collected for comparison. The variations of beam flatness, symmetry, and field size were analyzed as a function of gantry angle to evaluate the influence from the modulation of dose rate and gantry speed. MLC position accuracy was evaluated based on specific garden fence plans. The time of gating window was measured to be less than 10-millisecond deviation from the log data. Gantry backlash was observed and quantified to be 1.72° with an extra stabilization time of 1.16 seconds for a gating arc with gantry speed of 6°/s. In the dose rate vs gantry speed test, the mean deviation between measured gantry angle and log data was less than 0.2° after a time delay of 0.25 second was corrected. The measured dose rate agreed with the log data very well with a mean deviation of 0.05%, and even the transit of modulation was tracked successfully. There was a statistically significant difference on the variation of beam parameters between a VMAT plan and a simple arc plan. The induced MLC position errors were detected with an accuracy of 0.05 mm. The leaf position reproducibility was found to be better than 0.02 mm, whereas the routine MLC position accuracy was better than 0.1 mm. A time-resolved method using Octavius 4D phantom has been developed and proven to be convenient for respiratory gating QA, dose rate vs gantry speed test, and MLC QA. Gating time, dose rate, and gantry speed-induced leave position error could be directly measured with high accuracy after comparison with the machine log data. This study also highlights the capability of the phantom in quantifying the variation of flatness, symmetry, and field size during gantry rotation.

Time-resolved dosimetric verification of respiratory-gated radiotherapy exposures using a high-resolution 2D ionisation chamber array

The aim of this work was to track and verify the delivery of respiratory-gated irradiations, performed with three versions of TrueBeam linac, using a novel phantom arrangement that combined the OCTAVIUS(®) SRS 1000 array with a moving platform. The platform was programmed to generate sinusoidal motion of the array. This motion was tracked using the real-time position management (RPM) system and four amplitude gating options were employed to interrupt MV beam delivery when the platform was not located within set limits. Time-resolved spatial information extracted from analysis of x-ray fluences measured by the array was compared to the programmed motion of the platform and to the trace recorded by the RPM system during the delivery of the x-ray field. Temporal data recorded by the phantom and the RPM system were validated against trajectory log files, recorded by the linac during the irradiation, as well as oscilloscope waveforms recorded from the linac target signal. Gamma analysis was employed to compare time-integrated 2D x-ray dose fluences with theoretical fluences derived from the probability density function for each of the gating settings applied, where gamma criteria of 2%/2 mm, 1%/1 mm and 0.5%/0.5 mm were used to evaluate the limitations of the RPM system. Excellent agreement was observed in the analysis of spatial information extracted from the SRS 1000 array measurements. Comparisons of the average platform position with the expected position indicated absolute deviations of  <0.5 mm for all four gating settings. Differences were observed when comparing time-resolved beam-on data stored in the RPM files and trajectory logs to the true target signal waveforms. Trajectory log files underestimated the cycle time between consecutive beam-on windows by 10.0  ±  0.8 ms. All measured fluences achieved 100% pass-rates using gamma criteria of 2%/2 mm and 50% of the fluences achieved pass-rates  >90% when criteria of 0.5%/0.5 mm were used. Results using this novel phantom arrangement indicate that the RPM system is capable of accurately gating x-ray exposure during the delivery of a fixed-field treatment beam.