An error detection method for real-time EPID-based treatment delivery quality assurance

In vivo EPID-based daily treatment error identification for volumetric-modulated arc therapy in head and neck cancers with a hierarchical convolutional neural network: a feasibility study

We proposed a deep learning approach to classify various error types in daily VMAT treatment of head and neck cancer patients based on EPID dosimetry, which could provide additional information to support clinical decisions for adaptive planning. 146 arcs from 42 head and neck patients were analyzed. Anatomical changes and setup errors were simulated in 17,820 EPID images of 99 arcs obtained from 30 patients using in-house software for model training, validation, and testing. Subsequently, 141 clinical EPID images from 47 arcs belonging to the remaining 12 patients were utilized for clinical testing. The hierarchical convolutional neural network (HCNN) model was trained to classify error types and magnitudes using EPID dose difference maps. Gamma analysis with 3%/2 mm (dose difference/distance to agreement) criteria was also performed. The F1 score, a combination of precision and recall, was utilized to evaluate the performance of the HCNN model and gamma analysis. The adaptive fractioned doses were calculated to verify the HCNN classification results. For error type identification, the overall F1 score of the HCNN model was 0.99 and 0.91 for primary type and subtype identification, respectively. For error magnitude identification, the overall F1 score in the simulation dataset was 0.96 and 0.70 for the HCNN model and gamma analysis, respectively; while the overall F1 score in the clinical dataset was 0.79 and 0.20 for the HCNN model and gamma analysis, respectively. The HCNN model-based EPID dosimetry can identify changes in patient transmission doses and distinguish the treatment error category, which could potentially provide information for head and neck cancer treatment adaption.

IPEM topical report: guidance for the clinical implementation of online treatment monitoring solutions for IMRT/VMAT

This report provides guidance for the implementation of online treatment monitoring (OTM) solutions in radiotherapy (RT), with a focus on modulated treatments. Support is provided covering the implementation process, from identification of an OTM solution to local implementation strategy. Guidance has been developed by a RT special interest group (RTSIG) working party (WP) on behalf of the Institute of Physics and Engineering in Medicine (IPEM). Recommendations within the report are derived from the experience of the WP members (in consultation with manufacturers, vendors and user groups), existing guidance or legislation and a UK survey conducted in 2020 (Stevenset al2021). OTM is an inclusive term representing any system capable of providing a direct or inferred measurement of the delivered dose to a RT patient. Information on each type of OTM is provided but, commensurate with UK demand, guidance is largely influenced byin vivodosimetry methods utilising the electronic portal imager device (EPID). Sections are included on the choice of OTM solutions, acceptance and commissioning methods with recommendations on routine quality control, analytical methods and tolerance setting, clinical introduction and staffing/resource requirements. The guidance aims to give a practical solution to sensitivity and specificity testing. Functionality is provided for the user to introduce known errors into treatment plans for local testing. Receiver operating characteristic analysis is discussed as a tool to performance assess OTM systems. OTM solutions can help verify the correct delivery of radiotherapy treatment. Furthermore, modern systems are increasingly capable of providing clinical decision-making information which can impact the course of a patient's treatment. However, technical limitations persist. It is not within the scope of this guidance to critique each available solution, but the user is encouraged to carefully consider workflow and engage with manufacturers in resolving compatibility issues.

Strip detector array (SDA) for beam monitoring in radiotherapy: reconstruction of MLC parameters from multiple projections of flux

Objective:In this paper we propose and investigate a new detector with multiple strip detector arrays (SDA) for monitoring MLC shaped x-ray beams for radiotherapy treatment.Approach:Each SDA measures 1D dose profiles equivalent to dose projections. The goal of such a detector is to determine individual MLC leaf positions as well as the Monitor Units (MU) per MLC segment during radiotherapy. In the present work we investigate an optimal SDA detector configuration and reconstruction algorithm. We determine the accuracy of SDA for different treatment sites (spine, pelvis, retroperitoneum, prostate, brain SRT, SRS, lung and head and neck). We perform a simulation study accounting for different type of MLC leaf positional errors: random MLC leaf, systematic for the whole leaf bank and systematic for an individual leaf. In a similar fashion, we also account for errors in Monitor Units per segment.Main results:We demonstrate that for a broad range of IMRT treatment plans a robust reconstruction of errors is achievable with only 3 projections (3 sets of SDA oriented at at 0◦, 45◦ and 135◦). The SDA is capable of capturing both systematic errors in leaf banks and individual leaves as well as random errors sufficient for practical clinical purposes.Significance:These features of the SDA detector makes it suitable for real-time Quality Control of MLC collimated linac output.

A method for in vivo treatment verification of IMRT and VMAT based on electronic portal imaging device

Background

Intensity-modulated radiation therapy (IMRT) and volume-modulated arc therapy (VMAT) are rather complex treatment techniques and require patient-specific quality assurance procedures. Electronic portal imaging devices (EPID) are increasingly used in the verification of radiation therapy (RT). This work aims to develop a novel model to predict the EPID transmission image (TI) with fluence maps from the RT plan. The predicted TI is compared with the measured TI for in vivo treatment verification.

Methods

The fluence map was extracted from the RT plan and corrections of penumbra, response, global field output, attenuation, and scatter were applied before the TI was calculated. The parameters used in the model were calculated separately for central axis and off-axis points using a series of EPID measurement data. Our model was evaluated using a CIRS thorax phantom and 20 clinical plans (10 IMRT and 10 VMAT) optimized for head and neck, breast, and rectum treatments.

Results

Comparisons of the predicted and measured images were carried out using a global gamma analysis of 3%/2 mm (10% threshold) to validate the accuracy of the model. The gamma pass rates for IMRT and VMAT were greater than 97.2% and 94.5% at 3%/2 mm, respectively.

Conclusion

We have developed an accurate and straightforward EPID-based quality assurance model that can potentially be used for in vivo treatment verification of the IMRT and VMAT delivery.

PSCNN: PatchShuffle Convolutional Neural Network for COVID-19 Explainable Diagnosis

Objective: COVID-19 is a sort of infectious disease caused by a new strain of coronavirus. This study aims to develop a more accurate COVID-19 diagnosis system. Methods: First, the n-conv module (nCM) is introduced. Then we built a 12-layer convolutional neural network (12l-CNN) as the backbone network. Afterwards, PatchShuffle was introduced to integrate with 12l-CNN as a regularization term of the loss function. Our model was named PSCNN. Moreover, multiple-way data augmentation and Grad-CAM are employed to avoid overfitting and locating lung lesions. Results: The mean and standard variation values of the seven measures of our model were 95.28 ± 1.03 (sensitivity), 95.78 ± 0.87 (specificity), 95.76 ± 0.86 (precision), 95.53 ± 0.83 (accuracy), 95.52 ± 0.83 (F1 score), 91.7 ± 1.65 (MCC), and 95.52 ± 0.83 (FMI). Conclusion: Our PSCNN is better than 10 state-of-the-art models. Further, we validate the optimal hyperparameters in our model and demonstrate the effectiveness of PatchShuffle.