Elekta has patented a method using machine learning to generate fluence maps for radiotherapy treatment plans. The method involves obtaining image data of target dose and organs at risk areas, generating anatomy projection images, and using a trained neural network model to create fluence maps. The neural network model is trained in a generative adversarial network (GAN) to improve accuracy. GlobalData’s report on Elekta gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Elekta, Vaping device aerosol generators was a key innovation area identified from patents. Elekta's grant share as of May 2024 was 50%. Grant share is based on the ratio of number of grants to total number of patents.
Generating fluence maps for radiotherapy using machine learning prediction
A recently granted patent (Publication Number: US11992702B2) discloses a computer-implemented method for generating fluence maps used in radiotherapy treatment plans. The method involves obtaining a three-dimensional set of image data representing target dose areas and organs-at-risk areas in a patient's anatomy, generating anatomy projection images from this data, and using a trained neural network model to produce estimated fluence maps based on these images. The neural network model is trained in a generative adversarial network (GAN) using pairs of training anatomy projection images and fluence maps, with the generative model generating synthetic fluence maps and the discriminative model distinguishing between synthetic and real fluence maps. The method aims to optimize radiation doses in radiotherapy treatments, particularly volume modulated arc therapy (VMAT), by shaping multiple radiotherapy beams to deliver a prescribed radiation dose efficiently.
Furthermore, the patent describes a system and a computer-readable storage medium implementing this method, emphasizing the use of neural network models trained in GANs to generate fluence maps and optimize radiotherapy treatment plans. The system includes memory devices to store image data and processors to execute the neural network model, while the storage medium contains instructions for identifying image data, generating fluence maps, and performing numerical optimization to create a pareto-optimal fluence plan. The method's application in VMAT radiotherapy, arc sequencing, and direct aperture optimization is highlighted, showcasing its potential to enhance treatment planning accuracy and efficiency in radiotherapy settings. The patent's innovative approach to utilizing neural networks and GANs for fluence map generation underscores its contribution to advancing radiotherapy treatment planning techniques.
To know more about GlobalData’s detailed insights on Elekta, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
