ESTRO 2022 - Abstract Book

S1138

Abstract book

ESTRO 2022

Figure 1.

Figure 2.

Conclusion Both DFS and OS are adequately correlated with the new prognostic risk group classification at diagnosis. The histological subtype is an important predictor for both DFS and OS in the high-risk group.

PO-1343 Radiomic model to predict 2ysOS in Cervical Cancer patients underwent neoadjuvant chemoradiotherapy

G. Panza 1 , R. Autorino 2 , D. Cusumano 2 , L. Boldrini 2 , B. Gui 2 , L. Russo 2 , C. Votta 3 , N. Dinapoli 3 , G. Ferrandina 4 , A. Nardangeli 2 , M. Campitelli 2 , G. Macchia 5 , V. Valentini 3 , M.A. Gambacorta 3 1 Istituto di Radiologia, Università Cattolica del Sacro Cuore, Roma , 2. Dipartimento di Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, Fondazione Policlinico A. Gemelli IRCCS, Roma, rome, Italy; 2 Fondazione Policlinico A. Gemelli IRCCS, Roma, 2. Dipartimento di Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, , ROMA, Italy; 3 Fondazione Policlinico A. Gemelli IRCCS, Roma, 2. Dipartimento di Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, ROMA, Italy; 4 Fondazione Policlinico A. Gemelli IRCCS, Roma, Dipartimento di Ginecologia, ROMA, Italy; 5 Università Cattolica del Sacro Cuore, Campobasso, Gemelli Molise Hospital, Campobasso, Italy Purpose or Objective The aim of this study is to determine if radiomics features from T2-weighted 1.5 T magnetic resonance (MR) images could predict 2 years overall survival (2yOS), in patients with Locally Advanced Cervical Cancer (LACC) after neoadjuvant chemo- radiotherapy (NACRT). We retrospectively enrolled 175 patients from two institutions (142 for the training cohort and 33 for the validation one) with LACC diagnosis (stage from IB2 to IIIC at International Federation of Gynecology and Obstetrics), that underwent NACRT followed by radical surgery from 2005 to 2018. A total of 1557 radiomics features belonging to four families (statistical, textural, morphological and fractal features) were extracted from pre-treatment MR images. The ability of each feature in predicting 2yOS was quantified in terms of Wilcoxon Mann Whitney test. Among the significant features, Pearson Correlation Coefficient (PCC) was calculated to quantify the correlation among the different predictors. Materials and Methods