ESTRO 2023 - Abstract Book

S593

Monday 15 May 2023

ESTRO 2023

MO-0725 Radiomics-based prediction of radiosensitivity from preclinical HNSCC histopathology images S. Michlikova 1,2 , A. Rabasco Meneghetti 1,2 , S. Löck 1,3,4 , A. Yakimovich 5,6 , T. Rassamegevanon 1,3 , C. von Neubeck 1,3,7 , A. Dietrich 1,3 , M. Krause 1,2,3,4,8 1 OncoRay – National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany; 2 Helmholtz-Zentrum Dresden - Rossendorf, Institute of Radiooncology - OncoRay, Dresden, Germany; 3 German Cancer Consortium (DKTK), Partner Site Dresden, German Cancer Research Center (DKFZ), Heidelberg, Germany; 4 Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Department of Radiotherapy and Radiation Oncology, Dresden, Germany; 5 Helmholtz-Zentrum Dresden - Rossendorf e.V. (HZDR), Center for Advanced Systems Understanding (CASUS), Görlitz, Germany; 6 University College London, Royal Free Hospital Campus, Division of Medicine, Department of Renal Medicine, Bladder Infection and Immunity Group (BIIG), London, United Kingdom; 7 University of Duisburg-Essen, Department of Particle Therapy, University Hospital Essen, Essen, Germany; 8 National Center for Tumor Diseases (NCT), Partner Site Dresden, Dresden, Germany Purpose or Objective Biomedical images are a source of high-dimensional information that can be extracted using feature-based machine learning (radiomics). Moreover, preclinical radiotherapy research using animal models generates an enormous number of images that are generally overlooked as a source of quantitative image-based biomarkers. Here we apply radiomics feature extraction methods to 2D histopathology data from a published animal trial (Rassamegevanon et al., Radiother. Oncol., 2019) to classify HNSCC tumors based on their known radiosensitivity. Materials and Methods Athymic mice were xenotransplanted with three HNSCC tumor models of varying radiosensitivity. The tumors were irradiated in vivo with 2 – 8 Gy, excised 24 hours post-treatment, and stained for nuclear marker DAPI. Up to 13 ROIs per tumor were imaged using fluorescence microscopy and the nuclei were segmented using ImageJ plugin StarDist. Standardized radiomic features were extracted and clustered using the radiomics processor MIRP. Then, the feature set was processed via 33 repetitions of 3-fold cross-validation (CV) of the training cohort with the machine learning framework FAMILIAR, using the MIFS algorithm for feature selection. A final radiomics signature was derived based on the power to classify resistant and sensitive tumors, using cumulative scoring across the CV folds and hyperparameter optimisation. A logistic regression model was trained to predict tumor radiosensitivity using the final signature. Its performance was validated on an independent data set. Results Twenty-four tumors from one radioresistant model (SAS) and 24 tumors in total from two radiosensitive models (SKX and XF354) were used for the initial analysis. More than 250 ROIs per sensitivity class were considered and assigned to the training (2/3) and validation (1/3) cohorts. ROIs originating from the same tumor were treated as independent samples. 223 radiomic features were extracted from each ROI and the three best performing features for the classification of tumors as radioresistant or radiosensitive were identified (one morphological and two texture-based features). The logistic regression model using the final signature yielded a high accuracy: 0.96 (95% CI 0.94 – 0.98) and 0.93 (95% CI 0.89 – 0.97) for the training and validation cohort, respectively. Implementation of additional pre-processing and quality control steps such as stability analysis and batch effect control will be presented. Conclusion Quantitative image features can be extracted from 2D preclinical immunofluorescence data with a potential to classify tumors based on their radiosensitivity. However, further modifications are required to increase the robustness of the classification signature. Radiomics analysis of preclinical image data can serve as a basis for biological hypotheses and design of preclinical validation experiments, and support the interpretability of clinically relevant radiomics models. MO-0726 Doxorubicin enhances the abscopal effect depending on tumor cell mitochondrial DNA and STING L. Wang 1 , R. Luo 2 , K. Onyshchenko 3 , G. Niedermann 4 1 University of Freiburg, Department of Radiation Oncology, Freiburg, Germany; 2 Department of Thoracic Oncology Ward, Cancer Center and State Key Laboratory of Biotherapy, West China Hospital, Chengdu, China; 3 Department of Radiation Oncology, University of Freiburg, Freiburg, Germany; 4 Department of Radiation Oncology, University of Freiburg , Freiburg , Germany Purpose or Objective Localized radiotherapy (RT) can cause a T cell-mediated abscopal effect on non-irradiated tumor lesions, especially in combination with immune checkpoint blockade (ICB). However, this effect is still clinically rare and improvements are highly desirable. We investigated whether triple combination with a low dose of clinically approved liposomal doxorubicin (Doxil) could augment abscopal responses compared with RT plus ICB and Doxil plus ICB. Materials and Methods We used Doxil in combination with RT and α PD-1 in two tumor models (B16-CD133 melanoma and MC38 colon carcinoma) with mice bearing two tumors, only one of which was irradiated. Results We show in these two models that triple therapy with RT, α PD-1, and single low-dose Doxil strongly enhanced the RT- induced abscopal effect. Complete cures of non-irradiated tumors were mainly observed in triple-treated mice. Triple therapy induced more cross-presenting dendritic cells (DCs) and more tumor-specific CD8+ T cells than RT/ α PD-1 and Doxil/ α PD-1, particularly in non-irradiated tumors. CD8+ T cell depletion or implantation of STING-deficient tumor cells abolished the abscopal effect. cGAS/STING detects cytosolic DNA, triggering type I IFN expression, which drives antitumor CD8+ T cell responses through cross-presenting DCs. To date, it is not fully understood how doxorubicin/Doxil induces type I IFN and which nucleic acid species is critical for this. By using inhibitors and knockout cells, we show that