Colon cancer, the second leading cause of cancer deaths for men and women in the United States, can be prevented if precursor colonic lesions are detected and removed. The long-term goal of the proposed project is to develop an image-based diagnostic method that advances the early detection of colon cancer. Computed tomographic colonography (CTC), or virtual colonoscopy, is an emerging alternative screening tool for colon cancer in average risk patients. Based on the high per-patient sensitivity and specificity in the detection of clinically significant polyps that were demonstrated by the recent large-scale, multi-center clinical trials, including the National CT Colonography Trial, CTC is now listed as a viable screening option for colorectal cancer in the joint guideline from the American Cancer Society, the U.S. Multi-Society Task Force, and the American College of Radiology. In a recent U.S. series reported by Soetikno et al., it became clear that both Asian and Western populations may develop non-polypoidal colorectal neoplasia, which contribute to 54% of all early colorectal cancers and tend to be associated with in situ or submucosal invasive carcinomas. The finding that morphologically flat lesions have high rates of serious pathology suggests that effective screening methods will need to accurately identify these lesions. Current problem with CTC as a screening tool is that its performance for the detection of flat lesions varies across studies and thus remains undetermined. The short-term goal of the proposed project is to develop and evaluate a computer-aided flat-lesion detection (CAfD) scheme that automatically detects flat lesions in high-resolution CTC images, and to develop and evaluate a flat-lesion interpretation system that assists radiologists in detecting flat lesions quickly and accurately. We hypothesize that the CAfD scheme will yield clinically acceptable high detection performance for flat lesions, and that the flat-lesion interpretation system will improve radiologists'performance in the detection of flat lesions in CTC images. Successful development of the proposed flat-lesion interpretation system will substantially advance the clinical implementation of CT-based colon cancer screening in large populations, lead to an increased screening rate, promote the early diagnosis of colon cancer, and ultimately reduce the mortality due to colon cancer.

Public Health Relevance

The significance of this proposal is that successful development of the proposed flat-lesion interpretation system will substantially improve radiologists'performance in the detection of flat lesions in CTC examinations. Such an interpretation system will make CTC a viable option for screening of large population, lead to an increased screening rate, promote the early diagnosis of colon cancer, and ultimately reduce the mortality due to colon cancer.

Agency
National Institute of Health (NIH)
Institute
National Cancer Institute (NCI)
Type
Small Research Grants (R03)
Project #
1R03CA139600-01
Application #
7664820
Study Section
Special Emphasis Panel (ZCA1-SRLB-F (J1))
Program Officer
Marquez, Guillermo
Project Start
2009-04-24
Project End
2011-03-31
Budget Start
2009-04-24
Budget End
2010-03-31
Support Year
1
Fiscal Year
2009
Total Cost
$88,250
Indirect Cost
Name
Massachusetts General Hospital
Department
Type
DUNS #
073130411
City
Boston
State
MA
Country
United States
Zip Code
02199
Näppi, Janne J; Kim, Se Hyung; Yoshida, Hiroyuki (2012) Volumetric detection of colorectal lesions for noncathartic dual-energy computed tomographic colonography. Conf Proc IEEE Eng Med Biol Soc 2012:3740-3
Näppi, Janne J; Regge, Daniele; Yoshida, Hiroyuki (2011) Probabilistic method for context-sensitive detection of polyps in CT colonography. Proc SPIE Int Soc Opt Eng 7963: