Andrew Alexis Miller

Comparison of prostate IMRT and VMAT biologically optimised treatment plans.

Recently, a new radiotherapy delivery technique has become clinically available--volumetric modulated arc therapy (VMAT). VMAT is the delivery of IMRT while the gantry is in motion using dynamic leaf motion. The perceived benefit of VMAT over IMRT is a reduction in delivery time. In this study, VMAT was compared directly with IMRT for a series of prostate cases. For 10 patients, a biologically optimized seven-field IMRT plan was compared with a biologically optimized VMAT plan using the same planning objectives. The Pinnacle RTPS was used. The resultant target and organ-at-risk dose-volume histograms (DVHs) were compared. The normal tissue complication probability (NTCP) for the IMRT and VMAT plans was calculated for 3 model parameter sets. The delivery efficiency and time for the IMRT and VMAT plans was compared. The VMAT plans resulted in a statistically significant reduction in the rectal V25Gy parameter of 8.2% on average over the IMRT plans. For one of the NTCP parameter sets, the VMAT plans had a statistically significant lower rectal NTCP. These reductions in rectal dose were achieved using 18.6% fewer monitor units and a delivery time reduction of up to 69%. VMAT plans resulted in reductions in rectal doses for all 10 patients in the study. This was achieved with significant reductions in delivery time and monitor units. Given the target coverage was equivalent, the VMAT plans were superior.

Rectal dose reduction with IMRT for prostate radiotherapy

Dose escalation in radiation therapy has led to increased control rates with some clinical trial evidence that rectal toxicity may be reduced when using intensity‐modulated radiotherapy (IMRT) over 3D conformal radiotherapy (3DCRT) for dose‐escalated prostate radiotherapy. However, IMRT for prostate patients is not yet standard in many Australian radiation oncology centres. This study investigates dosimetric changes that can be observed between IMRT and 3DCRT in prostate radiotherapy. Fifteen patients were selected for analysis. Two target definitions were investigated – prostate‐only and prostate plus seminal vesicles (p + SVs). A five‐field 3DCRT and seven‐field IMRT plan were created for each patient and target definition. The planning target volume coverage was matched for both plans. Doses to the rectum, bladder and femoral heads were compared using dose volume histograms. The rectal normal tissue complication probabilities (NTCPs) were calculated and compared for the 3DCRT and IMRT plans. The delivery efficiency was investigated. The IMRT plans resulted in reductions in the V25, V50, V60, V70 and V75 Gy values for both the prostate‐only and p + SVs targets. Rectal NTCP was reduced with IMRT for three different sets of model parameters. The reductions in rectal dose and NTCP were much larger for the p + SVs target. Delivery of IMRT plans was less efficient than for 3DCRT plans. IMRT resulted in superior plans based on dosimetric and biological endpoints. The dosimetric gains with IMRT were greater for the more complex p + SVs target. The gains made came at the cost of decreased delivery efficiency.

Mixed-Initiative Argumentation: Group Decision Support in Medicine

This paper identifies ways in which traditional approaches to argumentation can be modified to meet the needs of practical group decision support. Three specific modifications are proposed. Firstly, a framework for accrual-based argumentation is presented. Second, a framework for outcome-driven decision rationale management is proposed that permits a novel conception of mixed-initiative argumentation. The framework is evaluated in the context of group decision support in medicine.

A Contemporary Case Study Illustrating the Integration of Health Information Technologies into the Organisation and Clinical Practice of Radiation Oncology

The development of software in radiation oncology departments has seen the increase in capability from the Record and Verify software focused on patient safety to a fully-fledged Oncology Information System (OIS). This paper reports on the medical aspects of the implementation of a modern Oncology Information System (IMPAC MultiAccess®, also known as the Siemens LANTIS®) in a New Zealand hospital oncology department. The department was successful in translating paper procedures into electronic procedures, and the report focuses on the changes in approach to organisation and data use that occurred. The difficulties that were faced, which included procedural re-design, management of change, removal of paper, implementation cost, integration with the HIS, quality assurance and datasets, are highlighted along with the local solutions developed to overcome these problems.

Semantic Monitoring and Compensation in Socio-technical Processes

Socio-technical processes are becoming increasingly important, with the growing recognition of the computational limits of full automation, the growth in popularity of crowd sourcing, the complexity and openness of modern organizations etc. A key challenge in managing socio-technical processes is dealing with the flexible, and sometimes dynamic, nature of the execution of human-mediated tasks. It is well-recognized that human execution does not always conform to predetermined coordination models, and is often error-prone. This paper addresses the problem of semantically monitoring the execution of socio-technical processes to check for non-conformance, and the problem of recovering from (or compensating for) non-conformance. This paper proposes a semantic solution to the problem, by leveraging semantically annotated process models to detect non-conformance, and using the same semantic annotations to identify compensatory human-mediated tasks.

An approach to plan and evaluate the location of radiotherapy services and its application in the New South Wales, Australia

This paper proposes an integrated modelling approach for location planning of radiotherapy treatment services based on cancer incidence and road network-based accessibility. Previous research efforts have established travel distance/time barriers as a key factor affecting access to cancer treatment services, as well as epidemiological studies have shown that cancer incidence rates vary with population demography. Our study is built on the evidence that the travel distances to treatment centres and demographic profiles of the accessible regions greatly influence the uptake of cancer radiotherapy (RT) services. An integrated service planning approach that combines spatially-explicit cancer incidence projections, and the placement of new RT services based on road network based accessibility measures have never been attempted. This research presents a novel approach for the location planning of RT services, and demonstrates its viability by modelling cancer incidence rates for different age-sex groups in New South Wales, Australia based on observed cancer incidence trends; and estimations of the road network-based access to current NSW treatment centres. Using three indices (General Efficiency, Service Availability and Equity), we show how the best location for a new RT centre may be chosen when there are multiple competing locations.

Support-Based Distributed Optimisation: An Approach to Radiotherapy Scheduling

The public health system is plagued by inefficient use of resources. Frequently, the results are lengthy patient treatment waiting times. While many solutions for patient scheduling in health systems exist, few address the problem of coordination between independent autonomous departments. In this study, we describe the use of a distributed dynamic constraint optimisation algorithm (Support Based Distributed Optimisation) for the generation and optimisation of schedules across autonomous units. We model the problem of scheduling radiotherapy patients across several independent oncology units as a dynamic distributed constraint optimisation problem. Such an approach minimises the sharing of private information such as department operation details as well as patient privacy information while taking into consideration patient preferences as well as resource utilisation to find a pareto-optimal solution.

Implementation of a rapid learning platform: Predicting 2-year survival in laryngeal carcinoma patients in a clinical setting

Background and Purpose To improve quality and personalization of oncology health care, decision aid tools are needed to advise physicians and patients. The aim of this work is to demonstrate the clinical relevance of a survival prediction model as a first step to multi institutional rapid learning and compare this to a clinical trial dataset. Materials and Methods Data extraction and mining tools were used to collect uncurated input parameters from Illawarra Cancer Care Centres (clinical cohort) oncology information system. Prognosis categories previously established from the Maastricht Radiation Oncology (training cohort) dataset, were applied to the clinical cohort and the radiotherapy only arm of the RTOG-9111 (trial cohort). Results Data mining identified 125 laryngeal carcinoma patients, ending up with 52 patients in the clinical cohort who were eligible to be evaluated by the model to predict 2-year survival and 177 for the trial cohort. The model was able to classify patients and predict survival in the clinical cohort, but for the trial cohort it failed to do so. Conclusions The technical infrastructure and model is able to support the prognosis prediction of laryngeal carcinoma patients in a clinical cohort. The model does not perform well for the highly selective patient population in the trial cohort.

Assessing the prognostic impact of 3D CT image tumour rind texture features on lung cancer survival modelling

In this paper we examine a technique for developing prognostic image characteristics, termed radiomics, for non-small cell lung cancer based on a tumour edge region-based analysis. Texture features were extracted from the rind of the tumour in a publicly available 3D CT data set to predict two-year survival. The derived models were compared against the previous methods of training radiomic signatures that are descriptive of the whole tumour volume. Radiomic features derived solely from regions external, but neighbouring, the tumour were shown to also have prognostic value. By using additional texture features an increase in accuracy, of 3%, is shown over previous approaches for predicting two-year survival, upon examining the outside rind including the volume compared to the volume without the rind. This indicates that while the centre of the tumour is currently the main clinical target for radiotherapy treatment, the tissue immediately around the tumour is also clinically important.

SU-E-T-23: A Developing Australian Network for Datamining and Modelling Routine Radiotherapy Clinical Data and Radiomics Information for Rapid Learning and Clinical Decision Support

Purpose: Large amounts of routine radiotherapy (RT) data are available, which can potentially add clinical evidence to support better decisions. A developing collaborative Australian network, with a leading European partner, aims to validate, implement and extend European predictive models (PMs) for Australian practice and assess their impact on future patient decisions. Wider objectives include: developing multi-institutional rapid learning, using distributed learning approaches; and assessing and incorporating radiomics information into PMs. Methods: Two initial standalone pilots were conducted; one on NSCLC, the other on larynx, patient datasets in two different centres. Open-source rapid learning systems were installed, for data extraction and mining to collect relevant clinical parameters from the centres’ databases. The European DSSs were learned (“training cohort”) and validated against local data sets (“clinical cohort”). Further NSCLC studies are underway in three more centres to pilot a wider distributed learning network. Initial radiomics work is underway. Results: For the NSCLC pilot, 159/419 patient datasets were identified meeting the PM criteria, and hence eligible for inclusion in the curative clinical cohort (for the larynx pilot, 109/125). Some missing data were imputed using Bayesian methods. For both, the European PMs successfully predicted prognosis groups, but with some differences in practice reflected. For example, the PM-predicted good prognosis NSCLC group was differentiated from a combined medium/poor prognosis group (2YOS 69% vs. 27%, p<0.001). Stage was less discriminatory in identifying prognostic groups. In the good prognosis group two-year overall survival was 65% in curatively and 18% in palliatively treated patients. Conclusion: The technical infrastructure and basic European PMs support prognosis prediction for these Australian patient groups, showing promise for supporting future personalized treatment decisions, improved treatment quality and potential practice changes. The early indications from the distributed learning and radiomics pilots strengthen this. Improved routine patient data quality should strengthen such rapid learning systems.