ESTRO 2021 Abstract Book

S1029

ESTRO 2021

none had grade 3-4 cystitis and perianal skin erythema. Conclusion IMRT is feasible in the preoperative treatment of rectal cancer with superior dosimetry, lower dose to small bowel and minimal grade 3-4 toxicity, with good pathological response. PO-1246 Prediction of response to neo-adjuvant chemoradiotherapy using radiomics in rectal cancer F. Lucia 1 , A. Bordron 2 , V. Bourbonne 1 , E. Rio 3 , B. Badic 4 , O. Miranda 5 , O. Pradier 1 , M. Hatt 6 , D. Visvikis 7 , U. Schick 1 1 University hospital of Brest, Radiation Oncology Department, Brest, France; 2 University hospital of Brest, Radiation Oncology Department, Brest, France; 3 ICO Cancer Center, Radiation Oncology Department, , Nantes, France; 4 University Hospital of Brest, Department of General and Digestive Surgery, Brest, France; 5 CHIC Quimper, Radiation Oncology Department, Quimper, France; 6 UBO, LaTIM UMR 1101 INSERM, , Brest, France; 7 UBO, LaTIM UMR 1101 INSERM, Brest, France Purpose or Objective In locally advanced rectal cancer (LARC) patients treated with neoadjuvant chemoradiotherapy (CRT), surgery could be omitted in patients with complete pathological response (pCR) without compromising progression- free and overall survivals. Our objective is to develop a radiomic model based on Magnetic Resonance Imaging (MRI) and contrast-enhanced computed tomography (CT) scans to predict the pathologic complete response (pCR) to neoadjuvant CRT in LARC. Materials and Methods All patients treated for a LARC with neoadjuvant CRT and subsequent surgery in 2 centers in the West of France (Insitut of Cancerologie Brittany Occidental (ICBO) and Nantes) were considered. Both pre-CRT pelvic MRIs and contrast-enhanced CT-scans were mandatory for inclusion. The tumor was manually segmented on the T2-weighted and diffusion axial sequences and on the contrast-enhanced CT-scan. Eighty-eight radiomic parameters (15 shape and geometry features, 11 first-order and 62 second-order) were extracted from each sequence using the in-house MirasÓ software, with a total of 1056 features by patient. The overall cohort was randomly split into two independent cohorts (training : 70% and testing : 30%). A strict feature set selection workflow based on the Spearman’s correlation coefficient and the Area Under the Curve (AUC) was developed to reduce the number of features. Based on these selected features, three pCR prediction models (clinical, radiomics and combined : clinical+radiomics) were developed on the training set only with a random forest approach and a Boostrap internal validation with n = 1000 replications. An optimal cut-off maximizing the model’s performance was defined on the training set. Each model was then evaluated on the testing set, based on the AUC and the C-statistic calculated with the pre-defined cut-off. Finally, a posteriori harmonization using the ComBat approach was applied to account for imaging modalities heterogenity. Results Of the 124 included patients, 14 had a complete response (11,3%). In the training set, the clinical model based on 2 parameters (initial T-stage and degree of tumor differenciation) obtained an AUC of 0.67 and a C-statistic of 0.65. The radiomic model based on 1 parameter (entropy histogram derived from T2 sequence) obtained an AUC of 1 and a C-statistic of 1. The combined clinical and radiomic model was strictly identical to the radiomics model and thus had the same performance. On the testing set, models resulted in a C-statistic of 0.70/0.73/0.73 for the clinical, radiomics and combined models, respectively. Finally, after harmonization, the radiomic model achieved a C-statistic of 0.77 on the testing set while the combined resulted in a C- statistic of 0 .75. Conclusion Radiomic model based on T2-weighted pre-therapeutic MRIs sequences could help to predict pCR after neoadjuvant CRT in LARC. PO-1247 Radiochemotherapy in anal cancer, what is the optimal dose? A single istitutional experience N. Giannini 1 , A. Gonnelli 2 , G. Gadducci 2 , S. Montrone 2 , A. Sainato 2 , B. Manfredi 2 , F. Pasqualetti 2 , C. Laliscia 2 , G. Malfatti 2 , E. Calistri 2 , R. Morganti 3 , F. Paiar 2 1 AOUP, Department of Radiation Oncology, University Hospital of Pisa, Pisa, Italy; 2 AOUP, Department of Radiation Oncology, University Hospital of Pisa, PISA, Italy; 3 AOUP, Department of Statistics, University Hospital of Pisa, pisa, Italy Purpose or Objective Radiation therapy(RT) plus concurrent 5-fluorouracil(5-FU) and mitomycin(MMC) represents the preferred standard of care for squamous cell carcinoma of the anus.To date remains unclear what RT doses are commonly prescribed in the treatment of this cancer.Our aim was to evaluate how the dose influenced local control(LC) and overall survival(OS) of patients with anal carcinoma. Materials and Methods Between September 2010 and July 2019, 54 patients with pathologically proven anal canal carcinoma were treated with Radiochemotherapy(RT-CT) at Pisa University Hospital. Stage distribution was as follows: I,19(35%); II-III 35(65%). The median age was 65.5 years(range, 42-90 years), M:F=19:35.RT was performed with IMRT technique.Regarding CT, patients were treated with capecitabine 825 mg/mq BID 1-28 or continuous infusion of 5-FU(1000 mg/m2) and MMC(10 mg/m2).Median overall treatment time (OTT) was 46 days (range, 34-115 days).Patients were stratified by RT dose at primary tumor: <56 Gy, 56Gy, > 56Gy.Patient’s age, HIV status, stage, OTT, and RT dose were variables analyzed for OS and LC. Results Median follow-up time was 47.5 months(range, 9-114 months).Complete response after 6 months was observed in 43 patients(79%).Local recurrence occurred in 9(16%) patients, and of these, 7 were rescued by surgery.Distant metastasis was observed in 11 patients (20%). Interruption of RT-CT higher than 5 days as a result of acute toxicity was necessary in 7 patients(12%). When the treatment is suspended for more than 10