Deep-learning-assisted algorithm for catheter reconstruction during MR-only gynecological interstitial brachytherapy.

Magnetic resonance imaging (MRI) offers excellent soft-tissue contrast enabling the contouring of targets and organs at risk during gynecological interstitial brachytherapy procedure. Despite its advantage, one of the main obstacles preventing a transition to an MRI-only workflow is that implanted plastic catheters are not reliably visualized on MR images. This study aims to evaluate the feasibility of a deep-learning-based algorithm for semiautomatic reconstruction of interstitial catheters during an MR-only workflow. MR images of 20 gynecological patients were used in this study. Note that 360 catheters were reconstructed using T1- and T2-weighted images by five experienced brachytherapy planners. The mean of the five reconstructed paths were used for training (257 catheters), validation (15 catheters), and testing/evaluation (88 catheters). To automatically identify and localize the catheters, a two-dimensional (2D) U-net algorithm was used to find their approximate location in each image slice. Once localized, thresholding was applied to those regions to find the extrema, as catheters appear as bright and dark regions in T1- and T2-weighted images, respectively. The localized dwell positions of the proposed algorithm were compared to the ground truth reconstruction. Reconstruction time was also evaluated. A total of 34 009 catheter dwell positions were evaluated between the algorithm and all planners to estimate the reconstruction variability. The average variation was 0.97 ± 0.66 mm. The average reconstruction time for this approach was 11 ± 1 min, compared with 46 ± 10 min for the expert planners. This study suggests that the proposed deep learning, MR-based framework has potential to replace the conventional manual catheter reconstruction. The adoption of this approach in the brachytherapy workflow is expected to improve treatment efficiency while reducing planning time, resources, and human errors.

Evaluation of an MR-only interstitial gynecologic brachytherapy workflow using MR-line marker for catheter reconstruction.

PURPOSE: Magnetic resonance imaging (MRI) offers excellent soft-tissue contrast enabling the contouring of targets and organs at risk (OARs) during gynecological interstitial brachytherapy procedure. Despite its benefit, one of the main challenges toward MRI-only workflows is that the implanted catheters are not reliably visualized on MR images. This study aims to evaluate the feasibility of MR-only workflow using an in-house MR line marker during interstitial gynecological high-dose-rate (HDR) brachytherapy. METHODS AND MATERIALS: Ten patients diagnosed with locally advanced cervical cancer treated with HDR brachytherapy were included in this study. The hybrid CT/MR-treated plan was used as the study reference plan. Five users manually reconstructed the catheter's path on MR images (3D T1- and T2-weighted). Subsequently, the dwell positions from the users' plans were superimposed on the reference plans to evaluate the dosimetric impact of the using MR-only for catheter reconstruction in comparison with hybrid CT/MR approach. Variability of dwell positions between users and reconstruction time was also evaluated. RESULTS: More than 96.90% of catheter reconstruction variations were < 2 mm. No statistical differences were reported between MR-only and hybrid CT/MR in gross tumor volume D98 and high-risk clinical target volume D90, respectively. For the OARs (bladder, sigmoid, rectum, and bowel), no significant changes were observed in any dose metrics between MR-only and hybrid CT/MR. The average reconstruction time was 51 ± 10 minutes across all ten patients. CONCLUSION: The feasibility of MR-only workflow using MR line marker during interstitial gynecological HDR brachytherapy has been validated in this study. The results show that the MR-only workflow is equivalent to the conventional hybrid CT/MR approach in terms of gross tumor volume and high-risk clinical target volume coverage and respecting of OARs dose limits.

Changes in Volume and Density Parameters Measured on Computed Tomography Images Following Stereotactic Body Radiation Therapy of Nonspine Bone Metastases.

INTRODUCTION: Volumetric and density parameters measured from computed tomography scans were investigated for evaluating treatment response of nonspine bone lesions following stereotactic body radiation therapy. METHODS: Twenty-three patients treated with stereotactic body radiation therapy to nonspine bone metastases with pre- and post-treatment radiological follow-up with computed tomography imaging were identified in a retrospective review. An expert radiologist classified 26 lesions by type (lytic, sclerotic) and by response. Two independent radiation oncologists created separate contours of the bone and soft tissue lesion volumes. Density and volume were assessed relative to baseline values. RESULTS: For bone-only lesions, all lesions designated as local control decreased in volume or remained within 20% of baseline volumes. Lytic lesions classified as progressive disease exhibited much larger volume increases. Lytic bone lesions showed indications of remineralization with some exhibiting immediate increases in density (1-6 months) and others decreasing initially then increasing back toward baseline between 7 and 12 months. The majority of sclerotic lesions, all classified as local control, decreased slightly in both volume and density. Lesions with both soft tissue and boney involvement resulted in contradictory results when employing both radiological and size parameters for assessing treatment response. Classification was dominated by changes in soft tissue volume, despite associated volume or density changes in the corresponding boney lesion. In contrast, when soft tissue volume changes were minimal (<20% increase), classification appeared to be related primarily to density changes and not bone volume. CONCLUSIONS: Volume and density changes show promise as quantitative parameters for classifying treatment responses of nonspine osseous lesions. Further work is required for clarifying how these metrics can be applied to lesions with both boney and soft tissue components.

The Development and Implementation of Radiation Oncology IQ Script Enabled Plans at the Odette Cancer Centre.

BACKGROUND: Radiation oncology Care Plans are predefined procedures that outline a patient's radiation therapy (RT) path of care. Care Plans allow for standardization of centre-specific procedures and workflows, thereby laying the foundation for autoforwarding of RT tasks and mandatory information capture via assessment forms. However, the integration of Care Plans at a large centre with established workflows is challenging and requires a redesign of numerous processes across all disciplines and site groups in an electronic data management system. Here, we describe the development and implementation experience of IQ Script enabled MOSAIQ Care Plans at the Odette Cancer Centre between summer 2014 and summer 2016. METHODS: A core Care Plan development group was formed that included membership from key stakeholders in RT, oncology, and physics. Care Plan pre-development planning was performed in three phases that included (1) collection and organization of all site and technique-specific protocols and procedures, (2) creation of workflow process maps and intimate discussions with potential stakeholders regarding automation and information capture, and (3) integration of design concepts into the IQ Script enabled Care Plans authoring framework. Following pre-planning, IQ Script enabled Care Plans authoring was performed on a test server with standardized naming conventions and tracking sheets for all IQ scripting triggers and events. Care Plan workflows were tested, and a senior therapist transferred individual Care Plans to the production server. Care Plans were then released gradually over a 1-year period, starting with pilot sites with the highest site group member buy-in. A post-implementation survey was performed to assess end-user feedback. SUMMARY AND CONCLUSIONS: IQ Script enabled Care Plans resulted in standardization of clinical processes including patient booking, autoforwarding of RT tasks, and mandatory information capture. Survey results indicated stakeholder satisfaction with the implementation process. Comments for improving Care Plans included changes to computed tomography simulation assessment forms for more robust capture of dose prescription and fractionation. Overall, the transition to Care Plans allowed our center to enhance information documentation, streamline our RT workflow, and ultimately improve the accuracy and efficiency of patient care. For the radiation oncologist, the use of Care Plans has also eliminated the use of another software system in which to request planning.

Consensus Recommendations for Developing IQ Script Enabled Radiation Oncology Care Plans in the MOSAIQ Oncology Information System.

BACKGROUND: IQ script enabled radiation oncology (RO) Care Plans are a unique functionality of the MOSAIQ oncology information system and enables standardization of clinical workflow via predefined order sets, strategic launching of assessment forms, and automated forwarding of clinical tasks. However, the development of RO Care Plans is center-specific and must be adapted to each center's clinical workflow. To our knowledge, little to no guidelines exist for RO Care Plan implementation. This article is a collaborative article from 5 different centers of varying sizes and adoption stage that provides consensus strategies for RO Care Plan development. METHODS: In 2016, 5 different centers of varying sizes and adoption stages met to develop strategies for RO Care Plan development. Before the meeting, an initial draft was circulated to all participating centers for feedback and incorporated into a refined document. The refined recommendations underwent a formal, 3-stage consensus process mediated by a radiation therapist to arrive at the final document. RESULTS: Overall, 17 recommendations were provided that focused on 7 areas of Care Plan development: (1) predevelopment planning, (2) current-state RO workflow evaluation, (3) future-state RO integration planning, (4) Care Plan authoring, (5) pre-implementation, (6) implementation, and (7) post-implementation evaluation and review. CONCLUSIONS: Care Plan development is a center-specific process, and the resulting recommendations provide a blueprint for a broad range of cancer centers for implementing Care Plans, or similar oncology information system modules, into their clinical processes.