1309 The impact of artificial intelligence for gynaecological cancer delineation

Introduction/BackgroundIncidence of gynaecological cancer is increasing as the number of radiotherapy (RT) treatments. As a low-income country, we suffer from a lack of radiotherapy departments leading to an overload. Artificial intelligence (AI) is introduced to assist the radiation community to im...

Full description

Saved in:
Bibliographic Details
Published in:International journal of gynecological cancer Vol. 34; no. Suppl 1; pp. A557 - A558
Main Authors: Kchaou, Lina, Mousli, Alia, Ghorbel, Asma, Zid, Khedija Ben, Zarraa, Semia, Yahiaoui, Safia, Abidi, Rim, Nasr, Chiraz
Format: Journal Article
Language:English
Published: Kidlington BMJ Publishing Group Ltd 01.03.2024
Elsevier Inc
Elsevier Limited
Subjects:
ISSN:1048-891X, 1525-1438
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Introduction/BackgroundIncidence of gynaecological cancer is increasing as the number of radiotherapy (RT) treatments. As a low-income country, we suffer from a lack of radiotherapy departments leading to an overload. Artificial intelligence (AI) is introduced to assist the radiation community to improve their work. The objective of this work is to assess the added value of AI delineation in terms of quality and resources gain in Salah Azaiez Institute.MethodologyAutomatic delineation using Limbus AI was used for 20 gynaecological cancer patients’ CT scans. The organs at risk (OARs) and target volumes were delineated according to the latest ASTRO guidelines. In each case, a radiation oncologist evaluated the contours and applied the required corrections.ResultsThe contoured planning CT scans were distributed as follows: 9 external RT for endometrial cancer, 7 external RT for cervical cancer and 4 intracavitary high dose rate (HDR) brachytherapy (BT) for cervical cancer. Despite contouring being a straightforward task, the process of anatomically individualised targets is time-consuming. Limbus Contour has significantly reduced the time spent contouring by one-third. Only minor corrections were required for the clinical target volume (CTV). This enhancement in productivity allowed for better management of urgent planning requests such as HDR BT. The ease of use, speed and accuracy enabled standardization of the process and improvement of treatment outcomes.ConclusionAI has demonstrated its value in terms of time savings and clinical relevance. While we do not expect complete replacement of human knowledge and experience, the use of AI as an effective supportive software tool for delineation has reduced patient wait time and improved the RT workflow. This is particularly crucial considering the large volume of treated patients, thus providing dosimetry more time to focus on planning and optimization.DisclosuresNo conflict of interest.
Bibliography:ESGO 2024 Congress Abstracts
14. Organization of gynaecological cancer care
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1048-891X
1525-1438
DOI:10.1136/ijgc-2024-ESGO.1094