The future of MRI in radiation therapy: Challenges and opportunities for the MR community.

Radiation therapy is a major component of cancer treatment pathways worldwide. The main aim of this treatment is to achieve tumor control through the delivery of ionizing radiation while preserving healthy tissues for minimal radiation toxicity. Because radiation therapy relies on accurate localization of the target and surrounding tissues, imaging plays a crucial role throughout the treatment chain. In the treatment planning phase, radiological images are essential for defining target volumes and organs-at-risk, as well as providing elemental composition (e.g., electron density) information for radiation dose calculations. At treatment, onboard imaging informs patient setup and could be used to guide radiation dose placement for sites affected by motion. Imaging is also an important tool for treatment response assessment and treatment plan adaptation. MRI, with its excellent soft tissue contrast and capacity to probe functional tissue properties, holds great untapped potential for transforming treatment paradigms in radiation therapy. The MR in Radiation Therapy ISMRM Study Group was established to provide a forum within the MR community to discuss the unmet needs and fuel opportunities for further advancement of MRI for radiation therapy applications. During the summer of 2021, the study group organized its first virtual workshop, attended by a diverse international group of clinicians, scientists, and clinical physicists, to explore our predictions for the future of MRI in radiation therapy for the next 25 years. This article reviews the main findings from the event and considers the opportunities and challenges of reaching our vision for the future in this expanding field.

Robot System Assistant (RoSA): Towards Intuitive Multi-Modal and Multi-Device Human-Robot Interaction.

This paper presents an implementation of RoSA, a Robot System Assistant, for safe and intuitive human-machine interaction. The interaction modalities were chosen and previously reviewed using a Wizard of Oz study emphasizing a strong propensity for speech and pointing gestures. Based on these findings, we design and implement a new multi-modal system for contactless human-machine interaction based on speech, facial, and gesture recognition. We evaluate our proposed system in an extensive study with multiple subjects to examine the user experience and interaction efficiency. It reports that our method achieves similar usability scores compared to the entirely human remote-controlled robot interaction in our Wizard of Oz study. Furthermore, our framework's implementation is based on the Robot Operating System (ROS), allowing modularity and extendability for our multi-device and multi-user method.

A qualitative study of prevalent laboratory information systems and data communication patterns for genetic test reporting.

PURPOSE: The availability of genetic test data within the electronic health record (EHR) is a pillar of the US vision for an interoperable health IT infrastructure and a learning health system. Although EHRs have been highly investigated, evaluation of the information systems used by the genetic labs has received less attention-but is necessary for achieving optimal interoperability. This study aimed to characterize how US genetic testing labs handle their information processing tasks. METHODS: We followed a qualitative research method that included interviewing lab representatives and a panel discussion to characterize the information flow models. RESULTS: Ten labs participated in the study. We identified three generic lab system models and their relevant characteristics: a backbone system with additional specialized systems for interpreting genetic results, a brokering system that handles housekeeping and communication, and a single primary system for results interpretation and report generation. CONCLUSION: Labs have heterogeneous workflows and generally have a low adoption of standards when sending genetic test reports back to EHRs. Core interpretations are often delivered as free text, limiting their computational availability for clinical decision support tools. Increased provision of genetic test data in discrete and standard-based formats by labs will benefit individual and public health.

A qualitative investigation of biomedical informatics interoperability standards for genetic test reporting: benefits, challenges, and motivations from the testing laboratory's perspective.

PURPOSE: Genetic laboratory test reports can often be of limited computational utility to the receiving clinical information systems, such as clinical decision support systems. Many health-care interoperability (HC) standards aim to tackle this problem, but the perceived benefits, challenges, and motivations for implementing HC interoperability standards from the labs' perspective has not been systematically assessed. METHODS: We surveyed genetic testing labs across the United States and conducted a semistructured interview with responding lab representatives. We conducted a thematic analysis of the interview transcripts to identify relevant themes. A panel of experts discussed and validated the identified themes. RESULTS: Nine labs participated in the interview, and 24 relevant themes were identified within five domains. These themes included the challenge of complex and changing genetic knowledge, the motivation of competitive advantage, provided financial incentives, and the benefit of supporting the learning health system. CONCLUSION: Our study identified the labs' perspective on various aspects of implementing HC interoperability standards in producing and communicating genetic test reports. Interviewees frequently reported that increased adoption of HC standards may be motivated by competition and programs incentivizing and regulating the incorporation of interoperability standards for genetic test data, which could benefit quality control, research, and other areas.

SFPD: Simultaneous Face and Person Detection in Real-Time for Human-Robot Interaction.

Face and person detection are important tasks in computer vision, as they represent the first component in many recognition systems, such as face recognition, facial expression analysis, body pose estimation, face attribute detection, or human action recognition. Thereby, their detection rate and runtime are crucial for the performance of the overall system. In this paper, we combine both face and person detection in one framework with the goal of reaching a detection performance that is competitive to the state of the art of lightweight object-specific networks while maintaining real-time processing speed for both detection tasks together. In order to combine face and person detection in one network, we applied multi-task learning. The difficulty lies in the fact that no datasets are available that contain both face as well as person annotations. Since we did not have the resources to manually annotate the datasets, as it is very time-consuming and automatic generation of ground truths results in annotations of poor quality, we solve this issue algorithmically by applying a special training procedure and network architecture without the need of creating new labels. Our newly developed method called Simultaneous Face and Person Detection (SFPD) is able to detect persons and faces with 40 frames per second. Because of this good trade-off between detection performance and inference time, SFPD represents a useful and valuable real-time framework especially for a multitude of real-world applications such as, e.g., human-robot interaction.

Physicians' pharmacogenomics information needs and seeking behavior: a study with case vignettes.

BACKGROUND: Genetic testing, especially in pharmacogenomics, can have a major impact on patient care. However, most physicians do not feel that they have sufficient knowledge to apply pharmacogenomics to patient care. Online information resources can help address this gap. We investigated physicians' pharmacogenomics information needs and information-seeking behavior, in order to guide the design of pharmacogenomics information resources that effectively meet clinical information needs. METHODS: We performed a formative, mixed-method assessment of physicians' information-seeking process in three pharmacogenomics case vignettes. Interactions of 6 physicians' with online pharmacogenomics resources were recorded, transcribed, and analyzed for prominent themes. Quantitative data included information-seeking duration, page navigations, and number of searches entered. RESULTS: We found that participants searched an average of 8 min per case vignette, spent less than 30 s reviewing specific content, and rarely refined search terms. Participants' information needs included a need for clinically meaningful descriptions of test interpretations, a molecular basis for the clinical effect of drug variation, information on the logistics of carrying out a genetic test (including questions related to cost, availability, test turn-around time, insurance coverage, and accessibility of expert support).Also, participants sought alternative therapies that would not require genetic testing. CONCLUSION: This study of pharmacogenomics information-seeking behavior indicates that content to support their information needs is dispersed and hard to find. Our results reveal a set of themes that information resources can use to help physicians find and apply pharmacogenomics information to the care of their patients.

Machine learning automated treatment planning for online magnetic resonance guided adaptive radiotherapy of prostate cancer.

Background and purpose: No best practices currently exist for achieving high quality radiation therapy (RT) treatment plan adaptation during magnetic resonance (MR) guided RT of prostate cancer. This study validates the use of machine learning (ML) automated RT treatment plan adaptation and benchmarks it against current clinical RT plan adaptation methods. Materials and methods: We trained an atlas-based ML automated treatment planning model using reference MR RT treatment plans (42.7 Gy in 7 fractions) from 46 patients with prostate cancer previously treated at our institution. For a held-out test set of 38 patients, retrospectively generated ML RT plans were compared to clinical human-generated adaptive RT plans for all 266 fractions. Differences in dose-volume metrics and clinical objective pass rates were evaluated using Wilcoxon tests (p < 0.05) and Exact McNemar tests (p < 0.05), respectively. Results: Compared to clinical RT plans, ML RT plans significantly increased sparing and objective pass rates of the rectum, bladder, and left femur. The mean ± standard deviation of rectum D20 and D50 in ML RT plans were 2.5 ± 2.2 Gy and 1.6 ± 1.3 Gy lower than clinical RT plans, respectively, with 14 % higher pass rates; bladder D40 was 4.6 ± 2.9 Gy lower with a 20 % higher pass rate; and the left femur D5 was 0.8 ± 1.8 Gy lower with a 7 % higher pass rate. Conclusions: ML automated RT treatment plan adaptation increases robustness to interfractional anatomical changes compared to current clinical adaptive RT practices by increasing compliance to treatment objectives.

Representing NIH Genetic Test Registry Data in the FHIR Genomic Study Resource.

The National Institute of Health (NIH) Genetic Testing Registry (GTR) provides a variety of information about genetic tests such as relevant methods, conditions, and performing laboratories. This study mapped a subset of GTR data to the newly developed HL7®-FHIR® Genomic Study resource. Using open-source tools, a web application was developed to implement data mapping and provides many GTR test records as Genomic Study resources. The developed system demonstrates the feasibility of using open-source tools and the FHIR Genomic Study resource to represent publicly available genetic testing information. This study validates the overall design of the Genomic Study resource and proposes two enhancements to support additional data elements.

Domain adaptation of automated treatment planning from computed tomography to magnetic resonance.

Objective.Machine learning (ML) based radiation treatment planning addresses the iterative and time-consuming nature of conventional inverse planning. Given the rising importance of magnetic resonance (MR) only treatment planning workflows, we sought to determine if an ML based treatment planning model, trained on computed tomography (CT) imaging, could be applied to MR through domain adaptation.Methods.In this study, MR and CT imaging was collected from 55 prostate cancer patients treated on an MR linear accelerator. ML based plans were generated for each patient on both CT and MR imaging using a commercially available model in RayStation 8B. The dose distributions and acceptance rates of MR and CT based plans were compared using institutional dose-volume evaluation criteria. The dosimetric differences between MR and CT plans were further decomposed into setup, cohort, and imaging domain components.Results.MR plans were highly acceptable, meeting 93.1% of all evaluation criteria compared to 96.3% of CT plans, with dose equivalence for all evaluation criteria except for the bladder wall, penile bulb, small and large bowel, and one rectum wall criteria (p< 0.05). Changing the input imaging modality (domain component) only accounted for about half of the dosimetric differences observed between MR and CT plans. Anatomical differences between the ML training set and the MR linac cohort (cohort component) were also a significant contributor.Significance.We were able to create highly acceptable MR based treatment plans using a CT-trained ML model for treatment planning, although clinically significant dose deviations from the CT based plans were observed. Future work should focus on combining this framework with atlas selection metrics to create an interpretable quality assurance QA framework for ML based treatment planning.

Performance stability evaluation of atlas-based machine learning radiation therapy treatment planning in prostate cancer.

Atlas-based machine learning (ML) for radiation therapy (RT) treatment planning is effective at tailoring dose distributions to account for unique patient anatomies by selecting the most appropriate patients from the training database (atlases) to inform dose prediction for new patients. However, variations in clinical practice between the training dataset and a new patient to be planned may impact ML performance by confounding atlas selection. In this study, we simulated various contouring practices in prostate cancer RT to investigate the impact of changing input data on atlas-based ML treatment planning. We generated 225 ML plans for nine bespoke contouring protocol scenarios (reduced target margins, modified organ-at-risk (OAR) definitions, and inclusion of optional OARs less represented in the training database) on 25 patient datasets by applying a single, previously trained and validated ML model for prostate cancer followed by dose mimicking to create a final deliverable plan. ML treatment plans for each scenario were compared to base ML treatment plans that followed a contouring protocol consistent with the model training data. ML performance was evaluated based on atlas distance metrics that are calculated during ML dose prediction. There were significant changes between atlases selected for the base ML treatment plans and treatment plans when planning target volume margins were reduced and/or optional OARs were included. The deliverability of ML predicted dose distributions based on gamma analysis between predicted and mimicked final deliverable dose showed significant differences for seven out of eight scenarios compared with the base ML treatment plans. Overall, there were small but statistically significant dosimetric changes in predicted and mimicked dose with addition of optional OAR contours. This work presents a framework for benchmarking and performance monitoring of ML treatment planning algorithms in the context of evolving clinical practices.

Interoperable genetic lab test reports: mapping key data elements to HL7 FHIR specifications and professional reporting guidelines.

OBJECTIVE: In many cases, genetic testing labs provide their test reports as portable document format files or scanned images, which limits the availability of the contained information to advanced informatics solutions, such as automated clinical decision support systems. One of the promising standards that aims to address this limitation is Health Level Seven International (HL7) Fast Healthcare Interoperability Resources Clinical Genomics Implementation Guide-Release 1 (FHIR CG IG STU1). This study aims to identify various data content of some genetic lab test reports and map them to FHIR CG IG specification to assess its coverage and to provide some suggestions for standard development and implementation. MATERIALS AND METHODS: We analyzed sample reports of 4 genetic tests and relevant professional reporting guidelines to identify their key data elements (KDEs) that were then mapped to FHIR CG IG. RESULTS: We identified 36 common KDEs among the analyzed genetic test reports, in addition to other unique KDEs for each genetic test. Relevant suggestions were made to guide the standard implementation and development. DISCUSSION AND CONCLUSION: The FHIR CG IG covers the majority of the identified KDEs. However, we suggested some FHIR extensions that might better represent some KDEs. These extensions may be relevant to FHIR implementations or future FHIR updates.The FHIR CG IG is an excellent step toward the interoperability of genetic lab test reports. However, it is a work-in-progress that needs informative and continuous input from the clinical genetics' community, specifically professional organizations, systems implementers, and genetic knowledgebase providers.

Enabling health information exchange at a US Poison Control Center.

OBJECTIVE: The objective of this project was to enable poison control center (PCC) participation in standards-based health information exchange (HIE). Previously, PCC participation was not possible due to software noncompliance with HIE standards, lack of informatics infrastructure, and the need to integrate HIE processes into workflow. MATERIALS AND METHODS: We adapted the Health Level Seven Consolidated Clinical Document Architecture (C-CDA) consultation note for the PCC use case. We used rapid prototyping to determine requirements for an HIE dashboard for use by PCCs and developed software called SNOWHITE that enables poison center HIE in tandem with a poisoning information system. RESULTS: We successfully implemented the process and software at the PCC and began sending outbound C-CDAs from the Utah PCC on February 15, 2017; we began receiving inbound C-CDAs on October 30, 2018. DISCUSSION: With the creation of SNOWHITE and initiation of an HIE process for sending outgoing C-CDA consultation notes from the Utah Poison Control Center, we accomplished the first participation of PCCs in standards-based HIE in the US. We faced several challenges that are also likely to be present at PCCs in other states, including the lack of a robust set of patient identifiers to support automated patient identity matching, challenges in emergency department computerized workflow integration, and the need to build HIE software for PCCs. CONCLUSION: As a multi-disciplinary, multi-organizational team, we successfully developed both a process and the informatics tools necessary to enable PCC participation in standards-based HIE and implemented the process at the Utah PCC.

Public Health Data for Individual Patient Care: Mapping Poison Control Center Data to the C-CDA Consultation Note.

We are developing a new process of health information exchange supported collaboration that leverages the HL7 consolidated CDA standard through four document types (consultation note, history and physical, progress note and discharge summary). The focus of the present study is the C-CDA consultation note template that will be submitted from poison control centers (PCC)s to emergency departments (EDs) with treatment recommendations. Specifically, we aimed to (i) create computable mappings between a poison control center database and the C-CDA consultation note template; and (ii) assess the extent and nature of information types that successfully map to discrete data elements in a poison control center database. The resulting template and mappings can be used to implement standards-based health information exchange between PCCs and EDs in the U.S. This is a part of the first formal effort to leverage health information exchange standards to support PCC-ED collaboration.