A Statistical Approach for Achievable Dose Querying in IMRT Planning

Abstract

Abstract. The task of IMRT planning, particularly in head-and-neck cancer, is a difficult one, often requiring days of work from a trained dosimetrist. One of the main challenges is the prescription of achievable target doses that will be used to optimize a treatment plan. This work explores a data-driven approach in which effort spent on past plans is used to assist in the planning of new patients. Using a database of treated patients, we identify the features of patient geometry that are correlated with received dose and use these to prescribe target dose levels for new patients. We incorporate our approach in a quality-control system, identifying patients with organs that received a dose significantly higher than the one recommended by our method. For all these patients, we have found that a replan using our predicted dose results in noticeable sparing of the organ without compromising dose to other treatment volumes.

Knowledge-driven decision support for assessing dose distributions in radiation therapy of head and neck cancer

“…Many recent studies incorporate anatomical descriptors such as the overlap volume histogram, which quantify: (i) the distance between OARs and the closest PTV surface and (ii) volumetric overlap between the PTV and OARs [14][15][16]. An example demonstrating differences in spatial planning target volume (PTV) characteristics between two cases, and their impact on the dose distributions (represented by the dose volume histograms on the right) of those cases.…”

“…Automation of treatment plan development and evaluation is currently a popular topic of research [10][11][12][13][14][15][16]. Many recent studies incorporate anatomical descriptors such as the overlap volume histogram, which quantify: (i) the distance between OARs and the closest PTV surface and (ii) volumetric overlap between the PTV and OARs [14][15][16].…”

“…The decision support module and discussion sections will highlight previous publications and systems related to this work [10][11][12][13][14][15][16][17][18].…”

A Survey on Statistical Modeling and Machine Learning Approaches to Computer Assisted Medical Intervention: Intraoperative Anatomy Modeling and Optimization of Interventional Procedures

“…However, optimized planning which realizes such an ideal radiation also becomes more complex. Simari et al proposed to use the radiation therapy plan database of past patients for efficient optimization of the plan of a new patient using a statistical approach [122]. A shape relation descriptor, the overlap volume histogram (OVH), was proposed [123] and the statistical features of OVH were used to query for the lowest achievable dose [122].…”

Sparse Dose Painting Based on a Dual-Pass Kinetic-Oxygen Mapping of Dynamic PET Images

“…Molecular imaging modalities, such as positron-emission tomography (PET), can be applied to improve the therapy outcome by conforming the dose distribution to the heterogeneous tumor microenvironment, which is called dose painting [4]. Inverse planning and intensity-modulated radiotherapy (IMRT) with dynamic multileaf collimators are applied to shape the delivery to match the dose prescription [5]. To prescribe a proper and efficient dose distribution based on the acquired molecular images is one key factor for successful dose painting.…”