An image‐guided radiotherapy decision support framework incorporating a Bayesian network and visualization tool

Integrating Deep Learning-Based Dose Distribution Prediction with Bayesian Networks for Decision Support in Radiotherapy for Upper Gastrointestinal Cancer

PURPOSE

Selecting the better techniques to harbor optimal motion management, either a stereotactic linear accelerator delivery using TrueBeam (TBX) or magnetic resonance-guided gated delivery using MRIdian (MRG), is time-consuming and costly. To address this challenge, we aimed to develop a decision-supporting algorithm based on a combination of deep learning-generated dose distributions and clinical data.

MATERIALS AND METHODS

We retrospectively analyzed 65 patients with liver or pancreatic cancer who underwent both TBX and MRG simulations and planning process. We trained three-dimensional U-Net deep learning models to predict dose distributions and generated dose volume histograms (DVHs) for each system. We integrated predicted DVH metrics into a Bayesian network (BN) model incorporating clinical data.

RESULTS

The MRG prediction model outperformed the TBX model, demonstrating statistically significant superiorities in predicting normalized dose to the planning target volume (PTV) and liver. We developed a final BN prediction model integrating the predictive DVH metrics with patient factors like age, PTV size, and tumor location. This BN model an area under the receiver operating characteristic curve index of 83.56%. The decision tree derived from the BN model showed that the tumor location (abutting vs. apart of PTV to hollow viscus organs) was the most important factor to determine TBX or MRG. It provided a potential framework for selecting the optimal radiation therapy (RT) system based on individual patient characteristics.

CONCLUSION

We demonstrated a decision-supporting algorithm for selecting optimal RT plans in upper gastrointestinal cancers, incorporating both deep learning-based dose prediction and BN-based treatment selection. This approach might streamline the decision-making process, saving resources and improving treatment outcomes for patients undergoing RT.

A fully automatic MRI-guided decision support system for lumbar disc herniation using machine learning

Background

Normalized decision support system for lumbar disc herniation (LDH) will improve reproducibility compared with subjective clinical diagnosis and treatment. Magnetic resonance imaging (MRI) plays an essential role in the evaluation of LDH. This study aimed to develop an MRI-based decision support system for LDH, which evaluates lumbar discs in a reproducible, consistent, and reliable manner.

Methods

The research team proposed a system based on machine learning that was trained and tested by a large, manually labeled data set comprising 217 patients' MRI scans (3255 lumbar discs). The system analyzes the radiological features of identified discs to diagnose herniation and classifies discs by Pfirrmann grade and MSU classification. Based on the assessment, the system provides clinical advice.

Results

Eventually, the accuracy of the diagnosis process reached 95.83%. An 83.5% agreement was observed between the system's prediction and the ground-truth in the Pfirrmann grade. In the case of MSU classification, 95.0% precision was achieved. With the assistance of this system, the accuracy, interpretation efficiency and interrater agreement among surgeons were improved substantially.

Conclusion

This system showed considerable accuracy and efficiency, and therefore could serve as an objective reference for the diagnosis and treatment procedure in clinical practice.

Improving the Quality of Care in Radiation Oncology using Artificial Intelligence

Radiation therapy is a complex process involving multiple professionals and steps from simulation to treatment planning to delivery, and these procedures are prone to error. Additionally, the imaging and treatment delivery equipment in radiotherapy is highly complex and interconnected and represents another risk point in the quality of care. Numerous quality assurance tasks are carried out to ensure quality and to detect and prevent potential errors in the process of care. Recent developments in artificial intelligence provide potential tools to the radiation oncology community to improve the efficiency and performance of quality assurance efforts. Targets for artificial intelligence enhancement include the quality assurance of treatment plans, target and tissue structure delineation used in the plans, delivery of the plans and the radiotherapy delivery equipment itself. Here we review recent developments of artificial intelligence applications that aim to improve quality assurance processes in radiation therapy and discuss some of the challenges and limitations that require further development work to realise the potential of artificial intelligence for quality assurance.

The implementation of MOSAIQ-based image-guided radiation therapy image matching within radiation therapy education

Image-guided radiation therapy (IGRT) technologies are routinely used by radiation therapists (RTs) in clinical departments. However, there is limited literature on the acquisition and assessment of IGRT image-matching competencies in undergraduate educational environments. This commentary paper aims to share the authors' experiences in the development of teaching IGRT and image-matching concepts in an undergraduate radiation therapy programme. It outlines how MOSAIQ oncology information systems (OIS) have enabled the university to embed hands-on IGRT image matching on a range of clinical cases. The hands-on exposure to case-based planar and volumetric kilovoltage (kV) image matching has resulted in improved teaching and better preparation of students for clinical IGRT encounters. Students are likely to benefit from critical image assessment and decision-making as well as the improved engagement in teaching and learning.

Ontologies in radiation oncology

Ontologies are a formal, computer-compatible method for representing scientific knowledge about a given domain. They provide a standardized vocabulary, taxonomy and set of relations between concepts. When formatted in a standard way, they can be read and reasoned upon by computers as well as by humans. At the 2019 International Conference on the Use of Computers in Radiation Therapy, there was a session devoted to ontologies in radiation therapy. This paper is a compilation of the material presented, and is meant as an introduction to the subject. This is done by means of a didactic introduction to the topic followed by a series of applications in radiation therapy. The goal of this article is to provide the medical physicist and related professionals with sufficient background that they can understand their construction as well as their practical uses.

The Application of the Virtual Environment for Radiotherapy Training to Strengthen IGRT Education

The use of simulation to enhance the quality of preclinical teaching and learning in radiation therapy is increasing. This article discusses the use of the Virtual Environment for Radiotherapy Training (VERT) in supporting teaching on image-guided radiation therapy (IGRT) and image matching concepts. The authors review the capabilities of VERT and discuss how it is currently applied in undergraduate radiation therapy teaching. The integration of IGRT theory with hands-on image matching practice using VERT simulation in educational environments has many potential benefits. These include the potential to strengthen the students' knowledge and skills in online-image acquisition and review of planar two-dimensional images and cone beam computed tomography images. It is anticipated that learner engagement will improve as well as refine analytical skills and confident practice in critical assessment of IGRT images. The authors encourage the utilization of technology that provides students with hands-on skills so they are better prepared for clinical environments.

A decision support system for assessing management interventions in a mental health ecosystem: The case of Bizkaia (Basque Country, Spain)

Evidence-informed strategic planning is a top priority in Mental Health (MH) due to the burden associated with this group of disorders and its societal costs. However, MH systems are highly complex, and decision support tools should follow a systems thinking approach that incorporates expert knowledge. The aim of this paper is to introduce a new Decision Support System (DSS) to improve knowledge on the health ecosystem, resource allocation and management in regional MH planning. The Efficient Decision Support-Mental Health (EDeS-MH) is a DSS that integrates an operational model to assess the Relative Technical Efficiency (RTE) of small health areas, a Monte-Carlo simulation engine (that carries out the Monte-Carlo simulation technique), a fuzzy inference engine prototype and basic statistics as well as system stability and entropy indicators. The stability indicator assesses the sensitivity of the model results due to data variations (derived from structural changes). The entropy indicator assesses the inner uncertainty of the results. RTE is multidimensional, that is, it was evaluated by using 15 variable combinations called scenarios. Each scenario, designed by experts in MH planning, has its own meaning based on different types of care. Three management interventions on the MH system in Bizkaia were analysed using key performance indicators of the service availability, placement capacity in day care, health care workforce capacity, and resource utilisation data of hospital and community care. The potential impact of these interventions has been assessed at both local and system levels. The system reacts positively to the proposals by a slight increase in its efficiency and stability (and its corresponding decrease in the entropy). However, depending on the analysed scenario, RTE, stability and entropy statistics can have a positive, neutral or negative behaviour. Using this information, decision makers can design new specific interventions/policies. EDeS-MH has been tested and face-validated in a real management situation in the Bizkaia MH system.