<jats:sec><jats:title>Background</jats:title><jats:p>Robust approaches to quantify tumor heterogeneity are needed to provide early decision support for precise individualized therapy.</jats:p></jats:sec><jats:sec><jats:title>Purpose</jats:title><jats:p>To conduct a technical exploration of longitudinal changes in tumor heterogeneity patterns on dynamic contrast‐enhanced (DCE) magnetic resonance imaging (MRI), diffusion‐weighted imaging (DWI) and FDG positron emission tomography / computed tomography (PET/CT), and their association to radiation therapy (RT) response in cervical cancer.</jats:p></jats:sec><jats:sec><jats:title>Study Type</jats:title><jats:p>Prospective observational study with longitudinal MRI and PET/CT pre‐RT, early‐RT (2 weeks), and mid‐RT (5 weeks).</jats:p></jats:sec><jats:sec><jats:title>Population</jats:title><jats:p>Twenty‐one FIGO IB<jats:sub>2</jats:sub>‐IVA cervical cancer patients receiving definitive external beam RT and brachytherapy.</jats:p></jats:sec><jats:sec><jats:title>Field Strength/Sequence</jats:title><jats:p>1.5T, precontrast axial T<jats:sub>1</jats:sub>‐weighted, axial and sagittal T<jats:sub>2</jats:sub>‐weighted, sagittal DWI (multi‐b values), sagittal DCE MRI (<10 sec temporal resolution), postcontrast axial T<jats:sub>1</jats:sub>‐weighted.</jats:p></jats:sec><jats:sec><jats:title>Assessment</jats:title><jats:p>Response assessment 1 month after completion of treatment by a board‐certified radiation oncologist from manually delineated tumor volume changes.</jats:p></jats:sec><jats:sec><jats:title>Statistical Tests</jats:title><jats:p>Intensity histogram (IH) quantiles (DCE SI<jats:sub>10%</jats:sub> and DWI ADC<jats:sub>10%</jats:sub>, FDG‐PET SUV<jats:sub>max</jats:sub>) and distribution moments (mean, variance, skewness, kurtosis) were extracted. Differences in IH features between timepoints and modalities were evaluated by Skillings–Mack tests with Holm's correction. Area under receiver‐operating characteristic curve (AUC) and Mann–Whitney testing was performed to discriminate treatment response using IH features.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>Tumor IH means and quantiles varied significantly during RT (SUV<jats:sub>mean</jats:sub>: ↓28–47%, SUV<jats:sub>max</jats:sub>: ↓30–59%, SI<jats:sub>mean</jats:sub>: ↑8–30%, SI<jats:sub>10%</jats:sub>: ↑8–19%, ADC<jats:sub>mean</jats:sub>: ↑16%, <jats:italic>P</jats:italic> < 0.02 for each). Among IH heterogeneity features, FDG‐PET SUV<jats:sub>CoV</jats:sub> (↓16–30%, <jats:italic>P</jats:italic> = 0.011) and DW‐MRI ADC<jats:sub>skewness</jats:sub> decreased (<jats:italic>P</jats:italic> = 0.001). FDG‐PET SUV<jats:sub>CoV</jats:sub> was higher than DCE‐MRI SI<jats:sub>CoV</jats:sub> and DW‐MRI ADC<jats:sub>CoV</jats:sub> at baseline (<jats:italic>P</jats:italic> < 0.001) and 2 weeks (<jats:italic>P</jats:italic> = 0.010). FDG‐PET SUV<jats:sub>kurtosis</jats:sub> was lower than DCE‐MRI SI<jats:sub>kurtosis</jats:sub> and DW‐MRI ADC<jats:sub>kurtosis</jats:sub> at baseline (<jats:italic>P</jats:italic> = 0.001). Some IH features appeared to associate with favorable tumor response, including large early RT changes in DW‐MRI ADC<jats:sub>skewness</jats:sub> (AUC = 0.86).</jats:p></jats:sec><jats:sec><jats:title>Data Conclusion</jats:title><jats:p>Preliminary findings show tumor heterogeneity was variable between patients, modalities, and timepoints. Radiomic assessment of changing tumor heterogeneity has the potential to personalize treatment and power outcome prediction.</jats:p><jats:p><jats:bold>Level of Evidence:</jats:bold> 2</jats:p><jats:p><jats:bold>Technical Efficacy: Stage</jats:bold> 3</jats:p><jats:p>J. Magn. Reson. Imaging 2018;47:1388–1396.</jats:p></jats:sec>