Optimising inter-patient image registration for image-based data mining in breast radiotherapy

• Published in: Physics and imaging in radiation oncology 2024-10, Vol.32, p.100635, Article 100635
• Main Authors: Jaikuna, Tanwiwat, Wilson, Fiona, Azria, David, Chang-Claude, Jenny, De Santis, Maria Carmen, Gutiérrez-Enríquez, Sara, van Herk, Marcel, Hoskin, Peter, Kotzki, Lea, Lambrecht, Maarten, Lingard, Zoe, Seibold, Petra, Seoane, Alejandro, Sperk, Elena, Paul Symonds, R, Talbot, Christopher J., Rancati, Tiziana, Rattay, Tim, Reyes, Victoria, Rosenstein, Barry S., de Ruysscher, Dirk, Vega, Ana, Veldeman, Liv, Webb, Adam, West, Catharine ML, Aznar, Marianne C, Vasquez Osorio, Eliana
• Format: Article
• Language: English
• Subjects: Breast radiotherapy; Image registration; Image-based data mining; Spatial normalisation
• ISSN: 2405-6316; 2405-6316
• DOI: 10.1016/j.phro.2024.100635

•We demonstrated that intra-patient registration for breast imaging is feasible and robust.•A two-step registration approach facilitates the joint analysis of both supine and prone breast cancer patients.•Spatial normalisation in the breast region has lower uncertainty than in the shoulder region.•Robust inter-patient registration enabled by our approach is key for image-based data mining in breast cancer cohorts. Image-based data mining (IBDM) requires spatial normalisation to reference anatomy, which is challenging in breast radiotherapy due to variations in the treatment position, breast shape and volume. We aim to optimise spatial normalisation for breast IBDM. Data from 996 patients treated with radiotherapy for early-stage breast cancer, recruited in the REQUITE study, were included. Patients were treated supine (n = 811), with either bilateral or ipsilateral arm(s) raised (551/260, respectively) or in prone position (n = 185). Four deformable image registration (DIR) configurations for extrathoracic spatial normalisation were tested. We selected the best-performing DIR configuration and further investigated two pathways: i) registering prone/supine cohorts independently and ii) registering all patients to a supine reference. The impact of arm positioning in the supine cohort was quantified. DIR accuracy was estimated using Normalised Cross Correlation (NCC), Dice Similarity Coefficient (DSC), mean Distance to Agreement (MDA), 95 % Hausdorff Distance (95 %HD), and inter-patient landmark registration uncertainty (ILRU). DIR using B-spline and normalised mutual information (NMI) performed the best across all evaluation metrics. Supine-supine registrations yielded highest accuracy (0.98 ± 0.01, 0.91 ± 0.04, 0.23 ± 0.19 cm, 1.17 ± 1.18 cm, 0.51 ± 0.26 cm for NCC, DSC, MDA, 95 %HD, and ILRU), followed by prone-prone and supine-prone registrations. Arm positioning had no significant impact on registration performance. For the best DIR strategy, uncertainty of 0.44 and 0.81 cm in the breast and shoulder regions was found. B-spline algorithm using NMI and registered supine and prone cohorts independently provides the most optimal spatial normalisation strategy for breast IBDM.