ESTRO 2023 - Abstract Book

S1137

Digital Posters

ESTRO 2023

Figure 2. Confusion matric for pCR

Conclusion The pre-chemoradiotherapy T1-weighted 3D MR image-based deep learning model showed acceptable performance in predicting pCR in patients with rectal cancer.

PO-1408 Prognostic value of 18F-FDG PET/CT assessment in anal carcinoma in patients from FFCD-ANABASE cohort

V. Combet-Curt 1

1 Hôpital Haut-Lévêque, CHU Bordeaux, Radiotherapy, Bordeaux, France

Purpose or Objective The study aimed to evaluate prognostic value of 18F-FDG PET/CT qualitative assessment after radiotherapy (RT) of squamous cell carcinoma of the anus (SCCA). Secondary objectives were to evaluate prognostic value of baseline and post-therapeutic quantitative FDG-PET parameters. Materials and Methods All consecutive patients with a PET/CT at baseline and 4-6 months after RT or chemoradiotherapy (CRT) for a localized SCCA from the French multicentric cohort FFCD-ANABASE were included. Qualitative assessment separated patients with complete metabolic response (CMR) and non-CMR. Quantitative parameters were measured on baseline and post-treatment PET/CT. Overall survival (OS), recurrence-free survival (RFS), and colostomy-free survival (CFS) were analyzed using Kaplan-