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.
|Yankeelov, Thomas E; Mankoff, David A; Schwartz, Lawrence H et al. (2016) Quantitative Imaging in Cancer Clinical Trials. Clin Cancer Res 22:284-90|
|Yu, Kun-Hsing; Zhang, Ce; Berry, Gerald J et al. (2016) Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features. Nat Commun 7:12474|
|Finlayson, Samuel G; Levy, Mia; Reddy, Sunil et al. (2016) Toward rapid learning in cancer treatment selection: An analytical engine for practice-based clinical data. J Biomed Inform 60:104-13|
|Liu, T T; Achrol, A S; Mitchell, L A et al. (2016) Computational Identification of Tumor Anatomic Location Associated with Survival in 2 Large Cohorts of Human Primary Glioblastomas. AJNR Am J Neuroradiol 37:621-8|
|Lekadir, Karim; Galimzianova, Alfiia; Betriu, Angels et al. (2016) A Convolutional Neural Network for Automatic Characterization of Plaque Composition in Carotid Ultrasound. IEEE J Biomed Health Inform :|
|Depeursinge, Adrien; Chin, Anne S; Leung, Ann N et al. (2015) Automated classification of usual interstitial pneumonia using regional volumetric texture analysis in high-resolution computed tomography. Invest Radiol 50:261-7|
|Diamant, Idit; Hoogi, Assaf; Beaulieu, Christopher et al. (2015) Improved patch based automated liver lesion classification by separate analysis of the interior and boundary regions. IEEE J Biomed Health Inform :|
|Depeursinge, Adrien; Yanagawa, Masahiro; Leung, Ann N et al. (2015) Predicting adenocarcinoma recurrence using computational texture models of nodule components in lung CT. Med Phys 42:2054-63|
|Echegaray, Sebastian; Gevaert, Olivier; Shah, Rajesh et al. (2015) Core samples for radiomics features that are insensitive to tumor segmentation: method and pilot study using CT images of hepatocellular carcinoma. J Med Imaging (Bellingham) 2:041011|
|Chen, Qiang; Leng, Theodore; Niu, Sijie et al. (2014) A false color fusion strategy for drusen and geographic atrophy visualization in optical coherence tomography images. Retina 34:2346-58|
Showing the most recent 10 out of 35 publications