ESTRO 2023 - Abstract Book

S1888

Digital Posters

ESTRO 2023

Fig.1. Mask discrepancy example.

Fig.2 Mask discrepancies culminate in feature differences that cause cluster change.

Conclusion We find radiomic analysis of the same data diverged due to inconsistent mask conversion between software. This work is relevant for multicentre and federated learning studies that access data from different institutions where use of the same mask conversion is not guaranteed. To mitigate this issue, one can incorporate mask perturbations [3] to assess feature susceptibility to mask variation and to ensure only robust features are used. [1] 10.1148/radiol.2020191145

[2] 10.1093/bioinformatics/btv428 [3] 10.1038/s41598-018-36938-4

PO-2104 MRI-Only SBRT in Gliomas: Dosimetry, Biology, and Radiomics Evaluation of a Pseudo-CT Generation

X. Yang 1 , B. Feng 1 , F. Jin 1 , X. Wang 2 , H. Yang 1 , H. Luo 1 , H. Peng 1

1 Chongqing University Cancer Hospital, Department of Radiation Oncology, Chongqing, China; 2 Philips HealthTech China, Philips Oncology, Beijing, China