Planning Workflow Research Articles

Fishbone diagram: Application of root cause analysis in internal audit planning

Purpose: This study applies a fishbone diagram to analyze the root cause of problems in the internal audit planning of J Corp, an Indonesian state-owned enterprise. Research methodology: A qualitative approach was employed to conduct a case study at the internal audit unit of an Indonesian state-owned enterprise. Research data were gathered from the results of focus group discussions with internal auditors, the analysis of the company’s standard operating procedure for internal auditing, and the observation of the workflow of internal audit planning. These data were then analyzed to identify the root causes of these problems. Results: Six key factors were identified that cause poor internal audit planning at J Corp. These are policies, processes, people, plants, programs, and products. To overcome these problems, this study provides several suggestions that can be implemented in the internal audit unit of J Corp. Limitations: This study is limited by the nature of the business and environment of J Corp, which affected the problems arising in the process of its internal audit planning; hence, the need to understand the entity to replicate this method for future research. Contribution: This study could be directly beneficial for internal auditors at J Corp to immediately improve the business process of internal audit planning. Furthermore, this study could contribute to future studies in which researchers or practitioners could replicate this method in another context. Novelty: The fishbone diagram was used to analyze the root causes of problems in the process of internal audit planning. Studies on the improvement of internal audit planning have been limited.

Automation Work Order And Master Production Schedule In Enterprise Resources Planning For Pt Sfp

<p>Abstract-In today's dynamic business landscape,<br />manufacturing enterprises like PT SFP face the constant<br />challenge of optimizing their production processes to remain<br />competitive. The Enterprise Resources Planning (ERP)<br />architecture will be used to develop an integrated solution to<br />automate work order administration and master production<br />scheduling. The production and planning division is a very<br />important process and is interconnected with one another.<br />Since manufacturing is the most demanding business<br />process in a company's activities, the significance of the<br />planning system is greatly raised. Even though the company<br />already has an ERP system that is quite integrated, there are<br />still many processes that are still carried out offline which<br />causes manual inefficiency, this not only increases waiting<br />time but can also cause anomalies. This project provides<br />ERP development ideas, especially in the Production and<br />Planning module for PT SFP by implementing automation<br />and integration in the work order planning workflow to<br />improve business processes. It includes the business process<br />of creating Order Confirmation (OC) Receiving Date Input,<br />and automation of planning work order creation, usage<br />standards in the work order and the work order itself. This<br />system is expected to be more effective and efficient in the field<br />of production planning using ERP web-based that can be<br />accessed online.</p>

Implementation of a Systematic, Digital Oncology Workflow for Patient Distress Screening in a National, Multi-Site Radiotherapy Outpatient Setting.

Distress screening is recommended as standard of care in oncology to improve the quality of personalized care for patients, however previously reported barriers have led to poor uptake and reporting of clinician follow up and interventions. Our purpose was to improve the quality of personalized care for patients with high patient participation rate (>50%), clinical and nurse workflow compliance rate (>70%) and create structured data for practice improvement. To achieve this purpose, an in-house systematic digital screen and templated well-being plan (WBP) workflow was implemented across 33 outpatient Radiation Oncology sites in a multi-institutional center. An in-house digital version of the NCCN Distress Thermometer and Problem Checklist (DT) was built in the integrated web-based portal for patients to complete at home or in a clinic setting. A digital workflow was co-designed with clinicians with automatic integration of the DT PDF document into the Electronic Medical Record (EMR), assigned for doctor review. Nurses subsequently recorded screening actions in the WBP. An extensive engagement, education and support program was completed nationally with phased implementation after an initial pilot at 3 sites. Staff and patient feedback were documented and presented with the collated data for review. The program was successfully implemented at 33 centers across Australia in the multi-site organization between March and October 2022. A total of 7788 distress screening forms were submitted with an uptake rate of 78% at baseline and 53% at end of treatment (EOT). DT document approval rates by doctors varied (41%-98%), and WBP was completed for 48-100% of patients, with variations of rates and use noted between states and individuals for both. Referrals were recorded in the WBP for 3% of patients, however, as up to 52% of documentation was not in a WBP (for some states), true referral numbers require further manual analysis. Pairwise analysis of screening scores between time points saw 42% of scores reduced, 34% increased and 24% with no change. Analysis of a subset of patients with increased or no change in score showed 57% had some change in categories of distress, 22% had complete change and 10% had no change. With an increasing global focus on improving patient centered care, implementation of a systematic digital workflow for distress screening and supportive care was achieved resulting in patient identified stressors being addressed as standard of care. Key barriers reported, include confidence discussing screening results with patients and manual workflows at EOT. The provision of a rich data set can also highlight opportunities for clinical practice improvement, cohort-based focus, clinical quality indicators, benchmarking and reporting.

Application of the Integrated Deep Reinforcement Learning Solution in Automatic IMRT Planning for Gastric Cancer

The intensity-modulated radiation therapy (IMRT) treatment planning optimization process is usually a manual, tedious and time-consuming task. An unsupervised integrated automatic IMRT planning solution was discussed and implemented to simulate the manual operation during the whole planning process. Based on knowledge-based planning (KBP) and deep reinforcement learning (DRL) schemes, a novel integrated solution combining the multi-objectives optimization policy network (MOPN) and three-dimensional dose prediction module (3D-DPM) was proposed. The MOPN was trained to learn how to adjust multiple optimization objectives in commercial Eclipse treatment planning system (TPS). The 3D-DPM was developed to generate the patient-specific initial optimization objectives to reduce the overall exploration space during MOPN training. The Eclipse 15.6 TPS Scripting Application Programming Interface (ESAPI) was used to realize the automatic interaction between models and TPS. In this study, 100 previously treated gastric cancer cases were selected from the clinical database, 70 cases were used for the training of dose prediction model and MOPN, the remaining 30 cases for evaluating the feasibility and effectiveness of automatic treatment planning solution. For all tested cases, the complete automatic treatment plan for a new case was generated based on the integrated solution, with about 6 min. Compared with the MOPN initial plans, the actual dose of spinal cord, liver, kidney-left, kidney-right, and intestine in the MOPN final plans reduced 42.4%, 25.2%, 52.4%, 37.8%, 11.8% respectively. The dose result of OARs in the MOPN final plans was similar to those in the clinical plans. In addition, a new case was able to complete optimization with about 15 adjustment steps by the trained MOPN. We successfully developed an integrated solution for automatic treatment planning. It first includes the dose prediction module for obtaining patient-specific initial optimization objectives. We demonstrated that the trained MOPN can mimic the operations of the physicians to adjust multiple objectives and obtain a high-quality plan in a shorter time. This integrated solution contributes to improving the efficiency of the overall planning workflow and reducing the variation of plan quality in clinical practice. Although improvement is warranted, the proposed integrated solution is a promising practical and effective approach for automatic planning in commercial TPS.

Auto Assistant VMAT Planning with HID Automation

To develop a complete, robust, adaptable and fully customizable software interface for assisting treatment planning procedures on FDA approved commercial system. This will standardize treatment planning process and provide opening interface to other third-party clinical software packages, and introduce AI inference to optimize plan without breaking current clinical planning workflow. Based on our clinical planning workflow, Varian Eclipse TPS were used. The general HID interface AUTOFLOW was developed with scripting language AutoIt and includes optical character reorganization (OCR) ability. The AUTOFLOW is fully customizable and adaptable for different VMAT planning process. The planning workflow and objective constraints template defined by Northwell health, CFAM are applied. AUTOFLOW operates automatically 3 standard planning interfaces (contouring, external beam planning and optimization) of Eclipse based on information in action tables. The information in the tables, such as auxiliary structures, field set up and initial optimization parameters, can be preset according to the plan template or from other 3rd party packages. Based on Northwell CFAM clinical planning protocol, the planning starts from post-contour approval. AUTOFLOW operates Eclipse to create auxiliary structures, set up planning fields then initiate plan optimization. During the optimization, the AUTOFLOW fills the constraint parameters and monitor the objective goals achievement by OCR. The updated parameters are introduced with our developing machine learning package. The whole planning process were assisted by AUTOFLOW automatically, while the planner can intercept the planning process as need. The general interface, AUTOFLOW was developed and applied to automatically assist the VMAT procedure in prostate cases. For each prostate case, more than 213 human HID operations on computers were removed from the plan procedure in our CFAM planning protocol. 12 prostate cases without manual interception were tested. The interface succeeds to reducing the VMAT planning time and planner still own the planning control. The AUTOFLOW software interface can be used to perform VMAT planning in current commercial clinical planning system. It can automatically assist planner operation and provide standard interface to 3rd party software packages. The future works will focus on building a cohesive UI, reducing the time further by improving the prediction of optimization parameters and other treatment sites.

Spatial planning of urban communities via deep reinforcement learning.

Effective spatial planning of urban communities plays a critical role in the sustainable development of cities. Despite the convenience brought by geographic information systems and computer-aided design, determining the layout of land use and roads still heavily relies on human experts. Here we propose an artificial intelligence urban-planning model to generate spatial plans for urban communities. To overcome the difficulty of diverse and irregular urban geography, we construct a graph to describe the topology of cities in arbitrary forms and formulate urban planning as a sequential decision-making problem on the graph. To tackle the challenge of the vast solution space, we develop a reinforcement learning model based on graph neural networks. Experiments on both synthetic and real-world communities demonstrate that our computational model outperforms plans designed by human experts in objective metrics and that it can generate spatial plans responding to different circumstances and needs. We also propose a human-artificial intelligence collaborative workflow of urban planning, in which human designers can substantially benefit from our model to be more productive, generating more efficient spatial plans with much less time. Our method demonstrates the great potential of computational urban planning and paves the way for more explorations in leveraging computational methodologies to solve challenging real-world problems in urban science.

In silico trial of simulation-free hippocampal-avoidance whole brain adaptive radiotherapy

Background and PurposeHippocampal-avoidance whole brain radiotherapy (HA-WBRT) can be a time-consuming process compared to conventional whole brain techniques, thus potentially limiting widespread utilization. Therefore, we evaluated the in silico clinical feasibility, via dose-volume metrics and timing, by leveraging a computed tomography (CT)-based commercial adaptive radiotherapy (ART) platform and workflow in order to create and deliver patient-specific, simulation-free HA-WBRT. Materials and methodsTen patients previously treated for central nervous system cancers with cone-beam computed tomography (CBCT) imaging were included in this study. The CBCT was the adaptive image-of-the-day to simulate first fraction on-board imaging. Initial contours defined on the MRI were rigidly matched to the CBCT. Online ART was used to create treatment plans at first fraction. Dose-volume metrics of these simulation-free plans were compared to standard-workflow HA-WBRT plans on each patient CT simulation dataset. Timing data for the adaptive planning sessions were recorded. ResultsFor all ten patients, simulation-free HA-WBRT plans were successfully created utilizing the online ART workflow and met all constraints. The median hippocampi D100% was 7.8 Gy (6.6–8.8 Gy) in the adaptive plan vs 8.1 Gy (7.7–8.4 Gy) in the standard workflow plan. All plans required adaptation at first fraction due to both a failing hippocampal constraint (6/10 adaptive fractions) and sub-optimal target coverage (6/10 adaptive fractions). Median time for the adaptive session was 45.2 min (34.0–53.8 min). ConclusionsSimulation-free HA-WBRT, with commercially available systems, was clinically feasible via plan-quality metrics and timing, in silico.

PP03 Presentation Time: 8:38 AM: Clinical Implementation of MRI-Only Treatment Planning (MRTP) Workflow for Gynecological HDR Brachytherapy

PP03 Presentation Time: 8:38 AM: Clinical Implementation of MRI-Only Treatment Planning (MRTP) Workflow for Gynecological HDR Brachytherapy

Critical considerations for communicating environmental DNA science.

The economic and methodological efficiencies of environmental DNA (eDNA) based survey approaches provide an unprecedented opportunity to assess and monitor aquatic environments. However, instances of inadequate communication from the scientific community about confidence levels, knowledge gaps, reliability, and appropriate parameters of eDNA-based methods have hindered their uptake in environmental monitoring programs and, in some cases, has created misperceptions or doubts in the management community. To help remedy this situation, scientists convened a session at the Second National Marine eDNA Workshop to discuss strategies for improving communications with managers. These include articulating the readiness of different eDNA applications, highlighting the strengths and limitations of eDNA tools for various applications or use cases, communicating uncertainties associated with specified uses transparently, and avoiding the exaggeration of exploratory and preliminary findings. Several key messages regarding implementation, limitations, and relationship to existing methods were prioritized. To be inclusive of the diverse managers, practitioners, and researchers, we and the other workshop participants propose the development of communication workflow plans, using RACI (Responsible, Accountable, Consulted, Informed) charts to clarify the roles of all pertinent individuals and parties and to minimize the chance for miscommunications. We also propose developing decision support tools such as Structured Decision-Making (SDM) to help balance the benefits of eDNA sampling with the inherent uncertainty, and developing an eDNA readiness scale to articulate the technological readiness of eDNA approaches for specific applications. These strategies will increase clarity and consistency regarding our understanding of the utility of eDNA-based methods, improve transparency, foster a common vision for confidently applying eDNA approaches, and enhance their benefit to the monitoring and assessment community.

Customized Three-Dimensional Printed Nuss Bar Molds for Repair of Pectus Excavatum

BackgroundThe minimally invasive Nuss procedure has emerged as the standard of care for correction of pectus excavatum. The site of chest wall insertion and bar shape are currently contoured on the basis of the surgeon's judgment. To optimize and individualize Nuss bar configuration, we aimed to create a virtual surgical planning workflow and 3-dimensional (3D) printed Nuss bar molds customized to each patient’s defect. MethodsStandard thin-section chest computed tomography images were imported into the planning software, and segmentation was used to extract anatomically relevant features including ribs, cartilage, sternum, and skin surface. Curves representing the ideal Nuss bar contour are splined on axial imaging. Molds designed from the Nuss bars are created within medical computer-aided design software and then 3D printed with a biocompatible sterilizable photosensitive resin, labeled with the correct orientation. ResultsVirtual surgical planning and 3D reconstruction were used to create patient-specific sterilizable Nuss bar molds in 9 patients presenting with pectus excavatum. The Nuss bar was bent in the operating room to the optimized curve and fitted to the mold. Six male patients with a median age of 26 years underwent customized Nuss bar placement with no intraoperative complications and a procedural time of 126 minutes. The median length of stay was 4 days. No early postoperative revisions were required. ConclusionsAlthough further prospective studies are warranted, this initial pilot demonstrates a replicable technique for virtual surgical planning workflows and patient-specific customizable Nuss bar molds for patients with pectus excavatum.

Data-driven intelligent computational design for products: method, techniques, and applications

Abstract Data-driven intelligent computational design (DICD) is a research hotspot that emerged under fast-developing artificial intelligence. It emphasizes utilizing deep learning algorithms to extract and represent the design features hidden in historical or fabricated design process data and then learn the combination and mapping patterns of these design features for design solution retrieval, generation, optimization, evaluation, etc. Due to its capability of automatically and efficiently generating design solutions and thus supporting human-in-the-loop intelligent and innovative design activities, DICD has drawn the attention of both academic and industrial fields. However, as an emerging research subject, many unexplored issues still limit the development and application of DICD, such as specific dataset building, engineering design-related feature engineering, systematic methods and techniques for DICD implementation in the entire product design process, etc. In this regard, a systematic and operable road map for DICD implementation from a full-process perspective is established, including a general workflow for DICD project planning, an overall framework for DICD project implementation, the common mechanisms and calculation principles during DICD, key enabling technologies for detailed DICD implementation, and three case scenarios of DICD application. The road map can help academic researchers to locate their specific research directions for the further development of DICD and provide operable guidance for the engineers in their specific DICD applications.

Cone beam computed tomography image guidance within a magnetic resonance imaging-only planning workflow.

Magnetic Resonance Imaging (MRI)-only planning workflows offer many advantages but raises challenges regarding image guidance. The study aimed to assess the viability of MRI to Cone Beam Computed Tomography (CBCT) based image guidance for MRI-only planning treatment workflows. An MRI matching training package was developed. Ten radiation therapists, with a range of clinical image guidance experience and experience with MRI, completed the training package prior to matching assessment. The matching assessment was performed on four match regions: prostate gold seed, prostate soft tissue, rectum/anal canal and gynaecological. Each match region consisted of five patients, with three CBCTs per patient, resulting in fifteen CBCTs for each match region. The ten radiation therapists performed the CBCT image matching to CT and to MRI for all regions and recorded the match values. The median inter-observer variation for MRI-CBCT matching and CT-CBCT matching for all regions were within 2mm and 1 degree. There was no statistically significant association in the inter-observer variation in mean match values and radiation therapist image guidance experience levels. There was no statistically significant association in inter-observer variation in mean match values for MRI experience levels for prostate soft tissue and gynaecological match regions, while there was a statistically significant difference for prostate gold seed and rectum match regions. The results of this study support the concept that with focussed training, an MRI to CBCT image guidance approach can be successfully implemented in a clinical planning workflow.

Plan Quality Analysis of Automated Treatment Planning Workflow With Commercial Auto-Segmentation Tools and Clinical Knowledge-Based Planning Models for Prostate Cancer.

This study evaluated the feasibility of using artificial intelligence (AI) segmentation software for volume-modulated arc therapy (VMAT) prostate planning in conjunction with knowledge-based planning to facilitate a fully automated workflow. Two commercially available AI software programs, Radformation AutoContour (Radformation, New York, NY) and Siemens AI-Rad Companion (Siemens Healthineers, Malvern, PA) were used to auto-segment the rectum, bladder, femoral heads, and bowel bag on 30 retrospective clinical cases (10 intact prostate, 10 prostate bed, and 10 prostate and lymph node). Physician-segmented target volumes were transferred to AI structure sets. In-house RapidPlan models were used to generate plans using the original, physician-segmented structure sets as well as Radformation and Siemens AI-generated structure sets. Thus, there were three plans for each of the 30 cases, totaling 90 plans. Following RapidPlan optimization, planning target volume (PTV) coverage was set to 95%. Then, the plans optimized using AI structures were recalculated on the physician structure set with fixed monitor units. In this way, physician contours were used as the gold standard for identifying any clinically relevant differences in dose distributions. One-way analysis of variation (ANOVA) was used for statistical analysis. No statistically significant differences were observed across the three sets of plans for intact prostate, prostate bed, or prostate and lymph nodes. The results indicate that an automated volumetric modulated arc therapy (VMAT) prostate planning workflow can consistently achieve high plan quality. However, our results also show that small but consistent differences in contouring preferences may lead to subtle differences in planning results. Therefore, the clinical implementation of auto-contouring should be carefully validated.

Exploring the Spatial Pattern of Urban Forest Ecosystem Services based on i-Tree Eco and Spatial Interpolation: A Case Study of Kyoto City, Japan.

Urban forest, as an essential urban green infrastructure, is critical in providing ecosystem services to cities. To enhance the mainstreaming of ecosystem services in urban planning, it is necessary to explore the spatial pattern of urban forest ecosystem services in cities. This study provides a workflow for urban forest planning based on field investigation, i-Tree Eco, and geostatistical interpolation. Firstly, trees across an array of land use types were investigated using a sampling method. Then i-Tree Eco was applied to quantify ecosystem services and ecosystem service value in each plot. Based on the ecosystem services estimates for plots, four interpolation methods were applied and compared by cross-validation. The Empirical Bayesian Kriging was determined as the best interpolation method with higher prediction accuracy. With the results of Empirical Bayesian Kriging, this study compared urban forest ecosystem services and ecosystem service value across land use types. The spatial correlations between ecosystem service value and four types of point of interest in urban places were explored using the bivariate Moran's I statistic and the bivariate local indicators of spatial association. Our results show that the residential area in the built-up area of Kyoto city had higher species richness, tree density, ecosystem services, and total ecosystem service value. Positive spatial correlations were found between ecosystem service value and the distribution of urban space types including the tourist attraction distribution, urban park distribution, and school distribution. This study provides a specific ecosystem service-oriented reference for urban forest planning based on land use and urban space types.

Development and validation of a novel craniofacial statistical shape model for the virtual reconstruction of bilateral maxillary defects

Bilateral maxillary defects are a challenge for fibula free flap reconstruction (FFFR) surgery due to limitations in virtual surgical planning (VSP) workflows. While meshes of unilateral defects can be mirrored to virtually reconstruct missing anatomy, Brown class c and d defects lack a contralateral reference and associated anatomical landmarks. This often results in poor placement of osteotomized fibula segments. This study was performed to improve the VSP workflow for FFFR using statistical shape modeling (SSM) – a form of unsupervised machine learning – to virtually reconstruct premorbid anatomy in an automated, reproducible, and patient-specific manner. A training set of 112 computed tomography scans was sourced from an imaging database by stratified random sampling. The craniofacial skeletons were segmented, aligned, and processed via principal component analysis. Reconstruction performance was validated on a set of 45 unseen skulls containing various digitally generated defects (Brown class IIa–d). Validation metrics demonstrated promising accuracy: mean 95th percentile Hausdorff distance of 5.47 ± 2.39 mm, mean volumetric Dice coefficient of 48.8 ± 14.5%, compactness of 7.28 × 105 mm2, specificity of 1.18 mm, and generality of 8.12 × 10−6 mm. SSM-guided VSP will allow surgeons to create patient-centric treatment plans, increasing FFFR accuracy, reducing complications, and improving postoperative outcomes.

Technical note: Multi-MATE, a high-throughput platform for automated image-guidedsmall-animal irradiation.

Small animal irradiation is essential to study the radiation response of new interventions before or parallel to human therapy. Image-guided radiotherapy (IGRT) and intensity-modulated radiotherapy (IMRT) are recently adopted in small animal irradiation to more closely mimic human treatments. However, sophisticated techniques require exceedingly high time, resources, and expertize that are often impractical. We propose a high throughput and high precision platform named Multiple Mouse Automated Treatment Environment (Multi-MATE) to streamline image-guided small animal irradiation. Multi-MATE consists of six parallel and hexagonally arranged channels, each equipped with a transfer railing, a 3D-printed immobilization pod, and an electromagnetic control unit, computer-controlled via an Arduino interface. The mouse immobilization pods are transferred along the railings between the home position outside the radiation field and the imaging/irradiation position at the irradiator isocenter. All six immobilization pods are transferred to the isocenter in the proposed workflow for parallel CBCT scans and treatment planning. The immobilization pods are then sequentially transported to the imaging/therapy position for dose delivery. The positioning reproducibility of Multi-MATE are evaluated using CBCT and radiochromic films. While parallelizing and automating the image-guided small animal radiation delivery, Multi-MATE achieved the average pod position reproducibility of 0.17 ± 0.04 mm in the superior-inferior direction, 0.20 ± 0.04 mm in the left-right direction, and 0.12 ± 0.02mm in the anterior-posterior direction in repeated CBCT tests. Additionally, in image-guided dose delivery tasks, Multi-MATE demonstrated the positioning reproducibility of 0.17 ± 0.06 mm in the superior-inferior direction, 0.19 ± 0.06 mm in the left-right direction. We designed, fabricated, and tested a novel automated irradiation platform, Multi-MATE to accelerate and automate image-guided small animal irradiation. The automated platform minimizes human operation and achieves high setup reproducibility and image-guided dose delivery accuracy. Multi-MATE thus removes a major barrier to implementing high-precision preclinical radiation research.

A goal-oriented planning approach for two-dimensional cutting components in architectural design: Coupling BIM and Parametric design (PD)

Two-dimensional (2-d) cutting components are essential in the Architecture, Engineering, and Construction (AEC) industry. However, due to the complexity of computing cut components' reuse, the 2-d cutting component still lacks appropriate design-aid tools to generate accurate graphical and numerical results in the architectural design process, leading to material waste and hindering the entry of intelligent technologies. This research proposed a grid-based planning workflow based on the BIM and parametric design (PD) to accurately generate and optimize 2-d cutting components' planning. The proposed workflow combined the “2-d bin packing problem” problem-solving method in operations research to compute the components' reuse. Moreover, an evolutionary algorithm was used to enable the workflow can goal-oriented optimize the design alternatives according to requirements, expanding the workflow's adaptability. A prototype system was developed to verify the proposed workflow. The results show that compared with current design-aid approaches, the proposed workflow can generate accurate graphical and numerical results while reducing material waste by 7%–12% due to the refined design. The outcomes improve the intelligence of the AEC industry while promoting the industry's sustainable development.

Feasibility and Acceptability of Community-Based Telehealth to Prevent Long-Term Care Readmission.

Transitioning to community living after long-term care requires multiple complex individualized interventions to prevent readmission. The current focus of home and community-based services (HCBS) is on increasing consumer engagement and individualizing care. Telehealth interventions provide additional services without the burden of face-to-face encounters and have yet to be evaluated for feasibility and acceptability in rural HCBS. West Virginia Bureau for Medical Services and West Virginia University implemented and evaluated a telehealth intervention with 26 Aged and Disabled Waiver or Traumatic Brain Injury Waiver participants who were transitioning back into their communities from a long-term care facility. Feasibility was assessed through recruitment process, fidelity to planned intervention, number of people eligible for participation, number of individuals enrolling in the intervention, enrollment process, completed enrollment, engagement in the intervention, number of weeks participating in the intervention, type of devices provided, attrition, and fidelity to original intervention. Satisfaction with services was used as a marker of acceptability for both participants and providers. Half (n = 12) of the enrolled population completed the full 24-week telehealth monitoring period and modification of the original intervention was necessary for most. Provider and participant satisfaction was high. Recruitment and enrollment may have been affected by COVID-19. Future implementation will continue to track recruitment and retention efforts. Individualized care plans, demonstration and practice with equipment, family or direct-care worker presence, and live technical support through the phone are needed. Primary care provider and in-home direct-care worker satisfaction workflow planning and evaluation are required.

Magnetic resonance guided SBRT reirradiation in locally recurrent prostate cancer: a multicentric retrospective analysis

AimsReirradiation of prostate cancer (PC) local recurrences represents an emerging challenge for current radiotherapy. In this context, stereotactic body radiation therapy (SBRT) allows the delivery of high doses, with curative intent. Magnetic Resonance guided Radiation Therapy (MRgRT) has shown promising results in terms of safety, feasibility and efficacy of delivering SBRT thanks to the enhanced soft tissue contrast and the online adaptive workflow. This multicentric retrospective analysis evaluates the feasibility and efficacy of PC reirradiation, using a 0.35 T hybrid MR delivery unit.MethodsPatients affected by local recurrences of PC and treated in five institutions between 2019 and 2022 were retrospectively collected. All patients had undergone previous Radiation Therapy (RT) in definitive or adjuvant setting. Re-treatment MRgSBRT was delivered with a total dose ranging from 25 to 40 Gy in 5 fractions. Toxicity according to CTCAE v 5.0 and treatment response were assessed at the end of the treatment and at follow-up.ResultsEighteen patients were included in this analysis. All patients had previously undergone external beam radiation therapy (EBRT) up to a total dose of 59.36 to 80 Gy. Median cumulative biologically effective dose (BED) of SBRT re-treatment was 213,3 Gy (103,1-560), considering an α/β of 1.5. Complete response was achieved in 4 patients (22.2%). No grade ≥ 2 acute genitourinary (GU) toxicity events were recorded, while gastrointestinal (GI) acute toxicity events occurred in 4 patients (22.2%).ConclusionThe low rates of acute toxicity of this experience encourages considering MRgSBRT a feasibile therapeutic approach for the treatment of clinically relapsed PC. Accurate gating of target volumes, the online adaptive planning workflow and the high definition of MRI treatment images allow delivering high doses to the PTV while efficiently sparing organs at risk (OARs).

Learning image representations for content-based image retrieval of radiotherapy treatment plans

Objective. In this work, we propose a content-based image retrieval (CBIR) method for retrieving dose distributions of previously planned patients based on anatomical similarity. Retrieved dose distributions from this method can be incorporated into automated treatment planning workflows in order to streamline the iterative planning process. As CBIR has not yet been applied to treatment planning, our work seeks to understand which current machine learning models are most viable in this context. Approach. Our proposed CBIR method trains a representation model that produces latent space embeddings of a patient’s anatomical information. The latent space embeddings of new patients are then compared against those of previous patients in a database for image retrieval of dose distributions. All source code for this project is available on github. Main results. The retrieval performance of various CBIR methods is evaluated on a dataset consisting of both publicly available image sets and clinical image sets from our institution. This study compares various encoding methods, ranging from simple autoencoders to more recent Siamese networks like SimSiam, and the best performance was observed for the multitask Siamese network. Significance. Our current results demonstrate that excellent image retrieval performance can be obtained through slight changes to previously developed Siamese networks. We hope to integrate CBIR into automated planning workflow in future works.