Vienna, Austria

ESTRO 2023

Session Item

Saturday
May 13
16:45 - 17:45
Business Suite 1-2
Technical improvements in radiotherapy practice
Rianne de Jong, The Netherlands
1630
Poster Discussion
RTT
Introduction of AI segmentation to drive improvements in Breast Cancer radiotherapy
Ashleigh Wowk, United Kingdom
PD-0317

Abstract

Introduction of AI segmentation to drive improvements in Breast Cancer radiotherapy
Authors:

Ashleigh Wowk1

1Northern Centre for Cancer Care, Freeman Hospital, Dose Planning, Newcastle-Upon-Tyne, United Kingdom

Show Affiliations
Purpose or Objective

An evaluation of AI auto-segmentation for routine clinical practice in breast radiotherapy planning was carried out. Analysis of technique improvements, clinical outcomes and efficiency gains within the department is presented.

Material and Methods

We introduced AI segmentation (MVision AI, Helsinki) models for all breast patients requiring nodal therapy, planned using Raystation 9B Planning System (RaySearch Laboratories).

AI assisted in the generation of volumes for breast lymph nodes (as per ESTRO guidelines) as well as creation of breast or chest wall CTVs. AI contours were used for field definition, plan optimisation and dose statistics, and replaced the traditional field-based target structure for both the SMLC (Segmental Multi Leaf Collimation) breast planning technique and a newly introduced VMAT technique for Internal Mammary Node (IMN) positive disease.

Results

AI has facilitated nodal outlining in routine clinical practice, as the demands on clinician time previously limited its use. From an initial review of nodal volumes for 30 patients, clinicians assessed that 67% required no edits or minor edits only. For the SMLC planning technique, AI volumes have allowed Dosimetrists to individualise the match plane based on nodal coverage, rather than the traditional method using bony anatomy, reducing need for clinician review before plan optimisation. We have therefore removed this review activity (Figure 1), and clinicians and dosimetrists report efficiencies when using AI for field placement.

This has been particularly beneficial for the transition to VMAT delivery for IMN positive patients, as the clinician only needs to review and amend the contours.

Evolution in delivery technique to VMAT means we can offer DIBH to more patients, and better optimise dose distributions for OAR sparing.  For one 26-year-old patient with IMN involvement these improvements allowed us to reduce average heart dose from 5.9Gy to 3.5Gy, and ipsilateral lung V17 from 24% to 17.7%.

AI segmentation is satisfactory even when set-up is non-standard i.e., patients with arms by their side, and clinician and dosimetrist confidence in the quality of AI contours has grown with use. The generation of additional OAR and true target volumes, with almost no extra time requirement, allows review of dose statistics for a full range of structures, and facilitates comparison with NHS England breast metrics for 9 OARs and Breast PTVs.


Conclusion

Use of AI volumes for breast patients requiring nodal treatment has streamlined the existing Breast/Chest wall ┬▒axilla and SCF carepath, and accelerated VMAT roll-out for all high-risk breast patients, with anticipated toxicity reduction. An increase in confidence for dosimetrists in nodal plan optimisation has reduced routine tasks requiring clinician input.