Evaluation of chemotherapy response in ovarian cancer treatment using quantitative CT image biomarkers: a preliminary study

Yuchen Qiu, Maxine Tan, Scott McMeekin, Theresa Thai, Kathleen Moore, Kai Ding, Hong Liu, Bin Zheng

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review


The purpose of this study is to identify and apply quantitative image biomarkers for early prediction of the tumor response to the chemotherapy among the ovarian cancer patients participated in the clinical trials of testing new drugs. In the experiment, we retrospectively selected 30 cases from the patients who participated in Phase I clinical trials of new drug or drug agents for ovarian cancer treatment. Each case is composed of two sets of CT images acquired pre- and post-treatment (4-6 weeks after starting treatment). A computer-aided detection (CAD) scheme was developed to extract and analyze the quantitative image features of the metastatic tumors previously tracked by the radiologists using the standard Response Evaluation Criteria in Solid Tumors (RECIST) guideline. The CAD scheme first segmented 3-D tumor volumes from the background using a hybrid tumor segmentation scheme. Then, for each segmented tumor, CAD computed three quantitative image features including the change of tumor volume, tumor CT number (density) and density variance. The feature changes were calculated between the matched tumors tracked on the CT images acquired pre- and post-treatments. Finally, CAD predicted patient's 6-month progression-free survival (PFS) using a decision-tree based classifier. The performance of the CAD scheme was compared with the RECIST category. The result shows that the CAD scheme achieved a prediction accuracy of 76.7% (23/30 cases) with a Kappa coefficient of 0.493, which is significantly higher than the performance of RECIST prediction with a prediction accuracy and Kappa coefficient of 60% (17/30) and 0.062, respectively. This study demonstrated the feasibility of analyzing quantitative image features to improve the early predicting accuracy of the tumor response to the new testing drugs or therapeutic methods for the ovarian cancer patients.

Original languageEnglish
Title of host publicationMedical Imaging 2015
Subtitle of host publicationComputer-Aided Diagnosis
EditorsLubomir M. Hadjiiski, Georgia D. Tourassi
ISBN (Electronic)9781628415049
Publication statusPublished - 2015
Externally publishedYes
EventConference on Medical Imaging - Computer-Aided Diagnosis 2015 - Orlando, United States of America
Duration: 22 Feb 201525 Feb 2015
https://www.spiedigitallibrary.org/conference-proceedings-of-spie/9414.toc (Proceedings)

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
ISSN (Print)1605-7422


ConferenceConference on Medical Imaging - Computer-Aided Diagnosis 2015
Country/TerritoryUnited States of America
Internet address


  • Computer aided diagnosis (CAD)
  • Early chemotherapy response evaluation
  • Efficacy of clinical trials
  • Ovarian cancer
  • Quantitative CT image analysis
  • Response evaluation criteria in solid tumors (RECIST)

Cite this