Lung cancer is one of the leading causes of death in the United States, surpassing breast, prostate, colon, and cervix cancers combined. One of the keys to improving the prognosis of lung cancer is early detection of small solitary lung nodules in chest radiographs, a task highly limited by the presence of anatomical variations in the image and by perceptual visualization processes. This project proposes a new method, Bi-plane Correlation Imaging (BCI), for improved detection of subtle lung nodules. The method involves the utilization of angular information in conjunction with digital acquisition and computer-assisted diagnosis (CAD) to cost-effectively reduce the degrading influence of anatomical variations with no increase in the patient dose. In BCI, two digital images of the chest are acquired within a short time interval from slightly different posterior projections. The image data are incorporated into an enhanced CAD algorithm in which nodules present in the thoracic cavity are detected by examining the geometrical correlation of the detected signals in the two views. Angular information minimizes the undesirable influence of anatomical noise by identifying and positively reinforcing the nodule signals, while CAD provides a complete search of the image data. The expected high sensitivity/specificity of the method has the potential to change the current state of practice, perhaps leading to a preventive lung cancer screening program for high-risk populations, similar to the mammography screening program currently in place for breast cancer. The project will be undertaken in two phases. The first phase aims to investigate the feasibility of the general approach via bi-plane images of a chest phantom with simulated lung nodules. A previously-developed single-view CAD algorithm will be used as a basis for the development of a dual-view CAD algorithm which incorporates the image data from the second view. The phantom images will be used to ascertain the detectability of the simulated nodules and to determine the optimum acquisition geometry and exposure. The applicability of the findings will also be qualitatively evaluated using actual anatomical backgrounds from six human subjects. In the second phase of the project, a dedicated imaging system will be assembled capable of high-speed bi-plane imaging of the chest. The high-speed imaging is necessary to minimize motion blur, including heart motion, in the bi-plane images, as the method requires perfect spatial correlation of nodule signals in the two views. The prototype unit will be used to acquire bi-plane paired digital radiographs from 100 high-risk human subjects with confirmed lung nodules and 50 normals. The BCI's performance in the detection of lung nodules in the collected database will be assessed, and the CAD algorithm subsequently refined. The findings will be used to demonstrate the capability of the approach for improving the detection of lung nodules, and thus the prognosis of lung cancer.
| Samei, Ehsan; Majdi-Nasab, Nariman; Dobbins 3rd, James T et al. (2012) Biplane correlation imaging: a feasibility study based on phantom and human data. J Digit Imaging 25:137-47 |
| Saunders Jr, Robert S; Samei, Ehsan; Hoeschen, Christoph (2004) Impact of resolution and noise characteristics of digital radiographic detectors on the detectability of lung nodules. Med Phys 31:1603-13 |
| Samei, Ehsan; Flynn, Michael J; Peterson, Edward et al. (2003) Subtle lung nodules: influence of local anatomic variations on detection. Radiology 228:76-84 |
| Saunders Jr, Robert S; Samei, Ehsan (2003) A method for modifying the image quality parameters of digital radiographic images. Med Phys 30:3006-17 |
| Dobbins 3rd, James T; Samei, Ehsan; Chotas, Harrell G et al. (2003) Chest radiography: optimization of X-ray spectrum for cesium iodide-amorphous silicon flat-panel detector. Radiology 226:221-30 |
