Quantitative imaging methods promise to improve the ability of cancer researchers to evaluate tumor burden and treatment response, but progress is thwarted by the lack of software infrastructure to record quantitative imaging information efficiently and reproducibly in the routine clinical workflow, and by the inability to store and share image metadata in standard formats. Many different quantitative imaging features that could more completely describe tumor burden are not being captured because collecting this information is laborious without tool support. Our objective is to develop software infrastructure that meets these needs of cancer researchers through three aims: (1) creating tools leveraging caBIG technologies to standardize quantitative imaging assessment of tumor burden. These tools will enable comprehensive and reproducible assessment of the quantitative imaging features of tumor burden as part of the routine clinical workflow and will improve the coordination of radiologists and oncologists in collecting quantitative image data. Through a commercial partnership, we will incorporate features of our tools in a commercial image interpretation workstation to introduce our methods into clinical practice;(2) developing methods to analyze quantitative image metadata and to help oncologists evaluate quantitative criteria on images collected as part of clinical trials;and (3) evaluating the utility of our infrastructure by applying our tools in two clinical trials and demonstrating the ability of our software infrastructure to quantitatively and more reproducibly measure tumor burden, helping researchers to assess the response to treatment in individual patients and patient cohorts. Our infrastructure will provide new ways of looking at quantitative imaging information related to treatment response along multiple dimensions so that researchers can recognize the effectiveness of treatments in clinical trials better and potentially sooner than using current unassisted approaches. Our work will accelerate quantitative imaging in cancer research, and will provide an essential complement to other centers in the Quantitative Imaging Network that focus on individual quantitative imaging methods.
The methods and tools we develop will improve the ability of cancer researchers to collect and use quantitative imaging data to accurately assess tumor burden and to develop improved methods for evaluating whether treatment is effective. Improving the accuracy of quantitative imaging in assessing treatment response in individual patients will enable better treatment choices and improve human health.
|Banerjee, Imon; Chen, Matthew C; Lungren, Matthew P et al. (2018) Radiology report annotation using intelligent word embeddings: Applied to multi-institutional chest CT cohort. J Biomed Inform 77:11-20|
|Echegaray, Sebastian; Bakr, Shaimaa; Rubin, Daniel L et al. (2018) Quantitative Image Feature Engine (QIFE): an Open-Source, Modular Engine for 3D Quantitative Feature Extraction from Volumetric Medical Images. J Digit Imaging 31:403-414|
|Lam, Carson; Yu, Caroline; Huang, Laura et al. (2018) Retinal Lesion Detection With Deep Learning Using Image Patches. Invest Ophthalmol Vis Sci 59:590-596|
|Banerjee, Imon; Malladi, Sadhika; Lee, Daniela et al. (2018) Assessing treatment response in triple-negative breast cancer from quantitative image analysis in perfusion magnetic resonance imaging. J Med Imaging (Bellingham) 5:011008|
|Bakr, Shaimaa; Gevaert, Olivier; Echegaray, Sebastian et al. (2018) A radiogenomic dataset of non-small cell lung cancer. Sci Data 5:180202|
|Graim, Kiley; Liu, Tiffany Ting; Achrol, Achal S et al. (2017) Revealing cancer subtypes with higher-order correlations applied to imaging and omics data. BMC Med Genomics 10:20|
|Lekadir, Karim; Galimzianova, Alfiia; Betriu, Angels et al. (2017) A Convolutional Neural Network for Automatic Characterization of Plaque Composition in Carotid Ultrasound. IEEE J Biomed Health Inform 21:48-55|
|Hoogi, Assaf; Subramaniam, Arjun; Veerapaneni, Rishi et al. (2017) Adaptive Estimation of Active Contour Parameters Using Convolutional Neural Networks and Texture Analysis. IEEE Trans Med Imaging 36:781-791|
|Akkus, Zeynettin; Galimzianova, Alfiia; Hoogi, Assaf et al. (2017) Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions. J Digit Imaging 30:449-459|
|Hoogi, Assaf; Beaulieu, Christopher F; Cunha, Guilherme M et al. (2017) Adaptive local window for level set segmentation of CT and MRI liver lesions. Med Image Anal 37:46-55|
Showing the most recent 10 out of 50 publications