PROCEEDINGS ARTICLE | April 4, 2016
Proc. SPIE. 9783, Medical Imaging 2016: Physics of Medical Imaging
KEYWORDS: Tissues, Image processing, Digital filtering, Radiography, Electroluminescence, Bone, Artificial neural networks, Image filtering, Machine learning, Nonlinear filtering, Dual energy imaging, Network architectures, Neurons
Dual-energy imaging can enhance lesion conspicuity. However, the conventional (fast kilovoltage switching)
dual-shot dual-energy imaging is vulnerable to patient motion. The single-shot method requires a special design
of detector system. Alternatively, single-shot bone-suppressed imaging is possible using post-image processing
combined with a filter obtained from training an artificial neural network. In this study, the authors investigate
the general properties of artificial neural network filters for bone-suppressed digital radiography. The filter
properties are characterized in terms of various parameters such as the size of input vector, the number of hidden
units, the learning rate, and so on. The preliminary result shows that the bone-suppressed image obtained from
the filter, which is designed with 5,000 teaching images from a single radiograph, results in about 95% similarity
with a commercial bone-enhanced image.