ESTRO 2020 Abstract book

S323 ESTRO 2020

(1) the patient cohort included both glioblastoma and low- grade glioma; (2) lacking external validation cohort

PD-0541 Transfer learning for automatic sarcopenia evaluation at T12 vertebral level D. Mcsweeney 1 , A. Green 1 , P.A. Bromiley 2 , M. Van Herk 1 , W. Mansoor 3 , J. Weaver 4 , A. McWilliam 1 1 University of Manchester/ The Christie Foundation Trust, Division of Cancer Sciences/Radiotherapy Related Research, Manchester, United Kingdom ; 2 University of Manchester, Division of Informatics- Imaging and Data Sciences, Manchester, United Kingdom ; 3 University of Manchester/ The Christie Foundation Trust, Division of Cancer Sciences/Department of Medical Oncology, Manchester, United Kingdom ; 4 The Christie Foundation Trust, Department of Medical Oncology, Manchester, United Kingdom Purpose or Objective Sarcopenia is a progressive loss of muscle mass and is emerging as a potential important prognostic factor for RT patients. It is typically assessed by segmenting skeletal muscle at the L3 vertebral level and extracting features of the muscle. However, L3 is not visible on most RT planning scans. In this work we use transfer learning to re-train an existing model, originally for segmenting muscle at L3, to segment muscle at the T12 vertebral level. The use of transfer learning significantly reduces the number of training images required. To show prognostic value, mean skeletal muscle attenuation (SMA) at L3 and T12 were compared both directly and in survival models. Material and Methods An existing model was available, pre-trained to segment the muscle compartment at L3 (Green et al, ESTRO 2019). Transfer learning was used to fine-tune the model using manual delineations at T12 (training n=16, validation n=2, unseen=10). To ensure no bone remained, a threshold of 226 HU was applied to the CT scan, expanded isotropically by 0.5 mm and the resulting mask excluded from the segmentation. Dice score and Distance-To-Agreement (DTA) were calculated for the unseen patients. 208 oesophago-gastric (OG) cancer patients were available for testing prognostic value. In this cohort, L3 had been previously segmented and validated. Segmentations at T12 were generated and visually assessed, to determine the failure rate. SMA was extracted and compared for patients with successful L3 and T12 segmentations by calculating their correlation and performing a paired t-test. Finally, prognostic value was investigated in Kaplan-Meier curves (split on median SMA) and multivariate Cox models including either L3 or T12 SMA controlling for performance status, age and sex. Results Transfer learning with 16 segmentations resulted in a mean Dice score of 0.75(σ=0.05) and mean DTA of 0.56(σ=0.40) cm in the unseen patients. Of the 208 scans in the OG cancer cohort 191 segmentations at T12 were successful (Fig 1). SMA at L3 and T12 were strongly correlated (R=0.80), but mean SMA was different (25 HU vs 34 HU, p<0.001), Fig 1. Kaplan-Meier curves for L3 and T12 showed significant differences in survival when split on median density, Fig 2. Multivariate Cox models identified performance status and skeletal muscle density as predictive of overall survival. SMA at both L3 and T12 were found to be prognostic (p=0.03 and p<0.01, respectively) with hazard ratios 0.98 and 0.97 per HU showing increased muscle density is beneficial.

Conclusion We demonstrated a fully automated method for sarcopenia assessment at T12. Transfer learning with a small training set resulted in accurate muscle segmentation. Analysis on a cohort of OG cancer patients shows that SMA at L3 and T12 are correlated and are both prognostic for patient outcome. Automating skeletal muscle segmentation at T12 provides a significant step forwards in exploring the prognostic value of sarcopenia in larger cohorts of patients treated by RT. PD-0542 External validation of individual nodal failure prediction models including radiomics in HNC T. Zhai 1 , F. Wesseling 2 , J. Langendijk 3 , Z. Shi 2 , P. Kalendralis 2 , L. Van Dijk 3 , F. Hoebers 2 , R. Steenbakkers 3 , A. Dekker 2 , L. Wee 2 , N. Sijtsema 3 1 Cancer Hospital of Shantou University Medical College, Radiation Oncology, Shantou, China ; 2 GROW School for Oncology and Development Biology Maastricht University Medical Centre+, Radiation Oncology, Maastricht, The Netherlands ; 3 University of Groningen University Medical Center Groningen, Radiation Oncology, Groningen, The Netherlands Purpose or Objective Three pre-treatment prediction models (clinical, radiomic and combined) were developed to identify pathological lymph nodes (pLNs) that are at risk to persist or recur after definitive radiotherapy with or without systemic treatment in head and neck squamous cell carcinoma (HNSCC) patients. These models can be used to select high-risk lymph nodes for radiotherapy treatment intensification or direct surgical dissection, or in case of recurrence for super-selective neck dissection, to limit morbidity of salvage surgery. The main goal of the current study was to validate the three models in a large and independent external cohort to make these models available for clinical application. Material and Methods The external validation cohort consisted of 374 pLNs from 113 HNSCC patients treated between July 2007 and June 2016 by curative radiotherapy with or without systemic treatment in another hospital. Imaging and pathology reports during follow-up were analyzed to indicate persisting or recurring nodes. The prognostic scores of pLNs were calculated using the three models that were