Published Paper Details:

In the computer aided schemes in computed tomography (CT) lung analysis identification and characterization of diffuse parenchyma lung disease (DPLD) patterns is a challenge. Due to low contrast and noisy images it is hard to perceive these patterns . In this paper, we propose adaptive enhancement techniques at different wavelet scales using dual tree complex wavelet processing. Moreover, dual tree complex wavelet transform also provides an special feature extraction method for identification and characterization of DPLD patterns. The algorithm projected in this paper has been experimented on number of clinical images, the results are compared with those obtained from other algorithms proposed in the literature through both analytical indexes and the opinions of radiologists. From the results obtained it can be concluded that the proposed algorithm improved the diagnosis in the early detection schemes with respect to other approaches.