Abstract Objective: To build an association map between medical images (CT/PET) and gene expression microarrays for Non-Small Cell Lung Cancer (NSCLC) from which to derive relationships between imaging features and gene expression. Methods: We studied 26 cases of NSCLC using CT and PET images and microarray data from excised tumors. An experienced thoracic radiologist annotated the CT image using “semantic features” from a controlled vocabulary, a nuclear medicine physician extracted the Standard Uptake Value (SUV) from the PET scan, and we developed and applied algorithms to extract “computational features” that characterized the lesion's image texture using Gabor and other texture features, the sharpness of lesion boundaries and the lesion boundary shape, including notions of compactness, roughness, and other shape signatures. We preprocessed the microarray data using log transformation and quantile normalization, obtained 100 co-expressed gene clusters using k-means clustering, and computed a metagene for each cluster using its first principal component. We performed (a) univariate and (b) multivariate analyses to integrate imaging features and metagenes using (a) Significance Analysis of Microarrays (SAM) with False Discovery Rate (FDR) multiple testing correction, and (b) Sparse Canonical Correlation Analysis (SCCA), respectively. Results: Image features included 44 semantic terms, 107 computational features, and SUV for each tumor. In a univariate analysis, 60 CT-features and SUV were significantly associated with at least one metagene, and on average 3.8 metagenes (FDR<0.05). Several of these associations were thought provoking. For example Metagene 10 was enriched for target genes of the RAS oncogene (p=1.07e-5) and significantly upregulated in tumors with a concave margin. Secondly, Metagene 90 was anti-correlated with irregular tumor margins and contains a potential tumor suppressor gene called IGF2R. High levels of IGF2R cause more regular shaped tumors. Moreover, using public domain data linking gene expression to survival, we found that Metagene 90 was correlated to survival (log-rank p=0.02), suggesting that tumors with regular margins have better prognosis than tumors with irregular margins. In multivariate analysis, a set of 10 metagenes was significantly correlated with a group of 5 Gabor texture features and explained over 82% of the correlation between both data sources using SCCA analysis (p=0.02). These metagenes are enriched with genes associated with good survival outcome in NSCLC (p <1.11 e-16) indicating a link between the lesion's texture and survival. Conclusion: The integration of medical image features and gene expression promises to reveal molecular characteristics underlying medical image features. For translational purposes, this work highlights the potential use of medical image features as predictive markers for molecularly-targeted therapeutics. Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the 102nd Annual Meeting of the American Association for Cancer Research; 2011 Apr 2-6; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2011;71(8 Suppl):Abstract nr 4148. doi:10.1158/1538-7445.AM2011-4148