ABSTRACT Purpose We sought to exploit the heterogeneity afforded by patient-derived tumor xenografts (PDX) to optimize robust radiomic features associated with response to therapy in the context of a co-clinical trial and implement PDX-optimized image features in the corresponding clinical study to predict and assess response to therapy using machine-learning (ML) algorithms. Methods TNBC patients and subtype-matched PDX were recruited into a co-clinical FDG-PET imaging study to predict response to therapy. One hundred thirty-one imaging features were extracted from PDX and human segmented tumors. Robust image features were identified based on reproducibility, cross-correlation, and volume independence. A rank importance of predictors using ReliefF was used to identify predictive radiomic features in the preclinical PDX trial in conjunction with ML algorithms: classification and regression tree (CART), Naïve Bayes (NB), and support vector machines (SVM). The top four PDX-optimized image features, defined as radiomic signatures (RadSig), from each task were then used to predict or assess response to therapy. Performance of RadSig in predicting/assessing response was compared to SUV mean , SUV max , and lean body mass normalized SUL peak measures. Results Sixty-four out of 131 preclinical imaging features were identified as robust. NB-RadSig performed highest in predicting and assessing response to therapy in the preclinical PDX trial. In the clinical study, the performance of SVM-RadSig and NB-RadSig to predict and assess response was practically identical and superior to SUV mean , SUV max , and SUL peak , measures. Conclusions We optimized robust FDG-PET radiomic signatures (RadSig) to predict and assess response to therapy in a context of a co-clinical imaging trial. DECLARATIONS Funding This work was supported by NCI grants U24CA209837, U24CA253531, and U54CA224083; U2CCA233303, and K12CA167540; Siteman Cancer Center (SCC) Support Grant P30CA091842; and Internal funds provided by Mallinckrodt Institute of Radiology. Conflicts of interest/Competing interests. None. Availability of data and material All the co-clinical data will be available for download through the Washington University School of Medicine Co-Clinical Imaging Research Resource web portal at https://c2ir2.wustl.edu/ , co-clinical database (CCDB). Code availability Not applicable. Authors’ contributions Conceptualization: SR, FOA, KIS; Methodology: SR, TDW, SL, KIS; Formal analysis and investigation: SR, KIS; Writing - original draft preparation: SR; Writing - review and editing: RLW, FD, KIS; Funding acquisition: RWL, FOA, SL, KIS; Resources: SL; Supervision: FD, KIS. All authors read and approved the final manuscript. Ethics approval All studies were performed with approval from the Washington University Humans subjects research committee and animal studies committee. Consent to participate Informed consent to participate in the study was obtained from all participants. Consent for publication Not applicable.