Multi-center study of pelvic nodal auto-segmentation algorithm of Siemens Healthineers: comparison of male vs female pelvis

• Published in: Advances in radiation oncology p. 101326
• Main Authors: Rayn, K, Gokhroo, G, Jeffers, B, Gupta, V, Chaudhari, S, Clark, R, Magliari, A, Beriwal, S
• Format: Journal Article
• Language: English
• Published: 2023
• Subjects: Hematology, Oncology, and Palliative Medicine
• ISSN: 2452-1094; 2452-1094
• DOI: 10.1016/j.adro.2023.101326

AbstractPurposeThe auto-segmentation algorithm of Siemens Healthineers version VA 30 (AASH) (Siemens Healthineers, Erlangen, Germany) was trained and developed in the male pelvis, with no published data on its usability in the female pelvis. This is the first multi-institutional study to describe and evaluate an AI algorithm for auto-segmentation of the pelvic nodal region by gender. Methods and MaterialsWe retrospectively evaluated AASH pelvic nodal auto-segmentation in both male and female patients treated at our network of institutions. The automated pelvic nodal contours generated by AASH were evaluated by one board-certified radiation oncologist. A 4-point scale was used for each nodal region contour: a score of 4 is clinically usable with minimal edits, a score of 3 requires minor edits (missing nodal contour region, cutting through vessels, or including bowel loops) in 3 or fewer CT slices, a score of 2 requires major edits, as previously defined but in 4 or more CT slices, and a score of 1 requires complete  re-contouring of the region. Pelvic nodal regions included the right and left side of the common iliac, external iliac, internal iliac, obturator and midline presacral nodes. In addition, patients were graded based on their lowest nodal contour score. Statistical analysis was performed using Fisher's exact tests and Yates-corrected chi-squared tests. Results52 female and 51 male patients were included in the study, representing a total of 468 and 447 pelvic nodal regions, respectively. 96% and 99% of contours required minor edits at most (score of 3 or 4) for female and male patients, respectively (p=0.004 using Fisher's exact test, p=0.007 using Yates correction). No nodal regions had a statistically significant difference in scores between female and male patients. The percentage of patients requiring no more than minor edits was 87% (45 patients) and 92% (47 patients) for female and male patients, respectively (p=0.53 using Fisher's exact test, p=0.55 using Yates correction)). ConclusionAASH pelvic nodal auto-segmentation performed very well in both male and female pelvic nodal regions, although with better male pelvic nodal auto-segmentation. As auto-segmentation becomes more widespread, it may be important to have equal representation from all genders in training and validation of auto-segmentation algorithms.