Name
Title | ||
|---|---|---|
Multi-projection Correlation Imaging as a New Diagnostic Tool for Improved Breast Cancer Detection |
Abstract | ||
|---|---|---|
Multi-projection imaging technique offers an advantage over single projection imaging techniques in rendering pathology that may be surrounded by a complex cloud of anatomical structures. The process of harnessing the geometrical and statistical dependences between the multiple images available in a multi-projection system to determine the final diagnosis is termed Correlation Imaging (CI). In this study, we are investigating the potential improvement in breast cancer detection via CI. As a key step towards that, the acquisition scheme of CI was first optimized to maximize its diagnostic performance. Toward that end, first a clinically-realistic task was designed and each component of acquisition, namely, the acquisition dose level, the number of projections, and their angular span was systematically changed to determine a specific combination that yielded maximum performance in that task. Finally, the performance of the optimized system was compared with that of standard planar mammography. The results indicated that the performance of CI may potentially be optimized between 15-17 projections spanning an angular arc of 45o. This optimum performance further improved with increasing dose levels; however, at dose level comparable to mammography, CI provided a factor of 1.1 improvement over mammography. The framework developed in this study to evaluate multi-projections system may be applied to any other multi-projection imaging modality, and by including reconstruction, may be extended to digital breast tomosynthesis and breast computed tomography. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1007/978-3-540-70538-3_88 | Digital Mammography / IWDM |
Keywords | Field | DocType |
multi-projection imaging technique,acquisition scheme,multi-projection correlation imaging,digital breast tomosynthesis,acquisition dose level,dose level,improved breast cancer detection,new diagnostic tool,diagnostic performance,breast computed tomography,maximum performance,optimum performance,breast cancer detection,computed tomography | Biomedical engineering,Mammography,Tomosynthesis,Pattern recognition,Breast cancer,Breast imaging,Computer science,Correlation,Artificial intelligence,Anatomical structures,Rendering (computer graphics),Acquisition Scheme | Conference |
Volume | ISSN | Citations |
5116 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 1 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Amarpreet S. Chawla | 1 | 10 | 3.65 |
| Ehsan Samei | 2 | 28 | 14.00 |
| Joseph Y. Lo | 3 | 261 | 27.03 |
| Thomas Mertelmeier | 4 | 21 | 10.81 |