Development and clinical introduction of automated radiotherapy treatment planning for prostate cancer

Abstract

To develop an automated radiotherapy treatment planning and optimization workflow to efficiently create patient specifically optimized clinical grade treatment plans for prostate cancer and to implement it in clinical practice. A two-phased planning and optimization workflow was developed to automatically generate 77Gy 5-field simultaneously integrated boost intensity modulated radiation therapy (SIB-IMRT) plans for prostate cancer treatment. A retrospective planning study (n = 100) was performed in which automatically and manually generated treatment plans were compared. A clinical pilot (n = 21) was performed to investigate the usability of our method. Operator time for the planning process was reduced to <5 min. The retrospective planning study showed that 98 plans met all clinical constraints. Significant improvements were made in the volume receiving 72Gy (V72Gy) for the bladder and rectum and the mean dose of the bladder and the body. A reduced plan variance was observed. During the clinical pilot 20 automatically generated plans met all constraints and 17 plans were selected for treatment. The automated radiotherapy treatment planning and optimization workflow is capable of efficiently generating patient specifically optimized and improved clinical grade plans. It has now been adopted as the current standard workflow in our clinic to generate treatment plans for prostate cancer.

Planning comparison of five automated treatment planning solutions for locally advanced head and neck cancer

“…In order to overcome these issues, optimization modules were developed in order to automate part or the entire optimization [4–9] process. They all aim at reducing the inter-planner variability, reducing the planning time allocated for the optimization process and finally improving the overall plan quality [10, 11]. Nowadays, automated treatment planning and/or optimization systems (ATPS) are in the process of broad clinical implementation.…”

Evaluating the application of Pareto navigation guided automated radiotherapy treatment planning to prostate cancer

“…When comparing to previously published studies, for the tumour site of PSV a thorough summary has recently been presented by Heijmen et al [26]; with 12 studies identified as demonstrating small differences between automated and manual plans [2,10,18,[27][28][29][30][31][32][33][34][35], and only their more recent multi-centre study showing the overall dosimetric superiority of automation through reduced rectum doses [26]. For PPN, to the authors' knowledge two studies have been published.…”

“…A solution to this problem is automated planning, where high quality plans are generated autonomously with minimal operator interaction [2][3][4][5][6][7][8][9].A key challenge in automated planning is incorporating treatment planners' or oncologists' clinical experience and decisionmaking within the autonomous process. A number of different methods have been employed: knowledge based planning (KBP) utilises databases of previous clinical plans to correlate the relationship between patient geometry and the resultant dose distribution, which then informs the optimisation of new patients [3,[10][11][12][13]; sequential e-constraint planning (ec) optimises plans based on a list of clinically prioritised goals [2,7,8,[14][15][16]; and protocol based automatic iterative optimisation (PB-AIO) adapts optimisation parameters during the planning process, tailoring the optimisation to the individual patient [4,[17][18][19]. Whilst these techniques have been successfully applied to automated planning, a method for intuitive exploration of different 'trade-off' options during their calibration has not yet been demonstrated.Recently we developed a fully automated treatment planning solution, which is uniquely calibrated using Pareto navigation principles.…”

The influence of automation on tumor contouring

“…Once all the relevant contours are created, different 3D volumes are constructed, e.g., by lofting those contours. Radiation dose is then planned and validated (e.g., Winkel et al 2016) based on the dose constraints on these volumes. Among different contouring tasks, the GTV contouring task is especially important in radiotherapy planning since GTV is the basis for defining other volumes for the treatment planning and consequently, uncertainties in this step may introduce a systematic error for the complete treatment planning (van Herk 2004).…”

“…With the aging population, cancer incidence and mortality are expected to increase (Yancik and Ries 2004). There is an increasing need to optimize the radiotherapy workflows as well as to automate different (parts of) tasks in order to improve the efficiency of radiotherapy and to reduce the workload of the physicians (e.g., Olsen et al 2014;Kirrmann et al 2015;Winkel et al 2016).…”