Colorectal carcinoma is the second leading cause of death from cancer in the United States. Since most cancers arise from polyps over 5-15 years of malignant transformation, screening programs to detect small polyps less than 10mm in diameter have been advocated. Unfortunately, most people do not follow this recommendation even though removing polyps prior to malignant transformation can prevent cancer. This reluctance is in reaction to the discomfort, embarrassment and risk associated with the invasive optical colonoscopy procedure. Recently, a new procedure, known as virtual colonoscopy (VC), has been developed for colon cancer screening. Using computed tomography (CT) images of the patient's abdomen, a computer visualization system allows the physician to virtually navigate within a constructed 3D model of the colon looking for polyps. Studies have shown this non-invasive procedure to be accurate, comfortable technique for screening. From the physician's perspective, however, VC still requires careful inspection of the entire length of the colon, a somewhat tedious process that takes at least 15 minutes. For several years our research groups at Stony Brook University and those at Viatronix Inc. have been advancing VC development and commercialization. Currently our focus is on the research and development of 3D texture-based computer aided detection (CAD) techniques using 3D texture information within the colon wall. The goal of this effort is to exploit polyp characteristics in the CT data to automatically identify suspicious regions of the colon wall.
Our specific aims are: (1) To exploit 3D subsurface morphology and texture to rapidly identify and accurately classify polyps. (2) To develop interactive CAD reading strategies. (3) To accelerate the CAD processing and interactive rendering using commodity graphics hardware. (4) To integrate CAD and interactive rendering into the commercial Viatronix V3D system. (5) To validate the integrated system on a patient database. We anticipate that integration of texture-based CAD technology into the Viatronix V3D system will substantially enhance VC by providing superior CAD detection performance while dramatically increasing the physician's efficiency of reading the VC data as well as the overall sensitivity of the procedure. Improving the cancer-finding capability and cost-effectiveness of VC will ultimately result in better health care.
| Hong, Wei; Qiu, Feng; Kaufman, Arie (2006) A pipeline for computer aided polyp detection. IEEE Trans Vis Comput Graph 12:861-8 |
