Artificial Intelligence | News | Insights | AiThority
[bsfp-cryptocurrency style=”widget-18″ align=”marquee” columns=”6″ coins=”selected” coins-count=”6″ coins-selected=”BTC,ETH,XRP,LTC,EOS,ADA,XLM,NEO,LTC,EOS,XEM,DASH,USDT,BNB,QTUM,XVG,ONT,ZEC,STEEM” currency=”USD” title=”Cryptocurrency Widget” show_title=”0″ icon=”” scheme=”light” bs-show-desktop=”1″ bs-show-tablet=”1″ bs-show-phone=”1″ custom-css-class=”” custom-id=”” css=”.vc_custom_1523079266073{margin-bottom: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

Further Clinical Implementation of Deep Learning Segmentation in Treatment Planning System

0

RaySearch Laboratories AB (publ) announces that its advanced deep learning segmentation functionality for lung delineation in breast radiation therapy has been carried out using treatment planning system RayStation® * at Leeds Cancer Centre (LCC) in the UK.

Clinicians at LCC have successfully implemented the deep learning segmentation thorax solution available in RayStation following thorough investigation of the geometric and dosimetric accuracy of the generated organs-at-risk structures. Reference contours and deep learning segmentation contours were produced for 10 patients, including left- and right-sided breast and chest wall treatments. A robust auto-contouring evaluation and commissioning method, based on templates and scripted analysis within RayStation 8B, has been developed as a result.

Recommended AI News: Gogo Now Providing Inflight Connectivity Beginning At 3,000 Feet

The in-built deep learning segmentation thorax model in RayStation 8B provides fast and excellent performance for ipsilateral lung contouring in the hypofractionated breast RT scenario. Given the positive results, the medical physics department at LCC is working closely with RaySearch to develop other machine learning models for safe and effective clinical implementation for other treatment sites. LCC staff are developing a script-driven quality management workflow for both deep learning segmentation model training on local data and semi-automated evaluation. This approach will allow them to have clinical confidence in models produced locally from clinical data. Their assessment of clinical confidence and utility in deep learning functionality in RayStation hinged on the assessment of geometric accuracy, dosimetric impact, efficiency and independent, automated checking of patient-specific deep learning segmentation outputs.

The study, which originally concerned the thorax model, was quickly changed to implement the breast hypo fractionation as a consequence of the ongoing COVID-19 situation. As a result of this comprehensive approach, coupled with the quality of the deep learning segmentation contours produced by the RaySearch model, staff at LCC were able to implement deep learning segmentation-derived OAR structures for clinical use.

Recommended AI News: Incubeta Launches Free Advisory Sessions To Brands

Dr Vivian Cosgrove, head of radiotherapy physics at LCC, says: “We are really pleased with the new planning innovations that RayStation is bringing to our radiotherapy service. Deep learning segmentation is a highly advanced `next-step’ that will provide further efficiencies to how we plan breast radiotherapy.”

Johan Löf, founder and CEO, RaySearch, says: “LCC has become a frontrunner in the use of advanced algorithms to improve cancer treatment. I am pleased that RayStation has been chosen to support the groundbreaking and important work being carried out in Leeds and I look forward to further collaboration in the future.”

Recommended AI News: Artilux Unveils Artilux Connect HDMI 2.1 All Optical Solution

Leave A Reply

Your email address will not be published.