Toward patient identification using chest CT scan Odry, Benjamin L.; Shen, Hong; Qing, Shuping ...
International Multimedia Conference: Proceedings of the 2003 ACM SIGMM workshop on Biometrics methods and applications,
11/2003
Conference Proceeding
3D digital medical images are usually generated by computerized medical equipment such as CT scanners and MRI machines. Selected anatomic information and structures can be extracted as features from ...this type of volume data. These features, if unique enough, can be used to identify the patient. This can be viewed as a special field of biometrics-- identification of individuals using biological traits. As an example of implementation, we present a solution for same-patient decision in chest CT volume data. Our method uses the lung area profiles along the sagital, coronal and axial planes. The area profile curves of the two volume data are cross-correlated to find the best scale factors as well as the best offsets. The extension of this work is to evaluate the "goodness-of-fit" in order to classify two studies being or not from the same patient. We apply our method to 3 panels of pairs of the same patient and pairs of different patient and report classification performance.
The performance of any image retrieval system relies over the image descriptor used for matching. The recently proposed descriptors mainly suffer due to the ‘less discriminative power’ and ‘curse of ...dimensionality’. A novel image descriptor using local bit-plane dissimilarity pattern (LBDISP) is introduced. The descriptor is computed by finding the dissimilarity map between the centre pixel and its neighbours over each bit-plane. The relationship between the centre pixel and dissimilarity map is then encoded to form the LBDISP descriptor. The dimension of the descriptor depends upon the number of neighbours only. A retrieval experiment over NEMA-CT database confirms the superiority and efficiency of the LBDISP descriptor.
Full text
Available for:
FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
Although Low-dose computed tomography (LDCT) is the most effective way for early lung cancer screening, it's still a challenge to further reduce radiation dose on the premise of ensuring image ...quality. Penalized weighted least-squares (PWLS) image reconstruction with nonlocal means (NLM) prior has shown excellent performance to improve the image quality for LDCT, especially when the nonlocal weights are calculated from previous full-dose CT (FDCT) image. However, the previous FDCT image of the same patient is not readily available, and registration between the LDCT and FDCT images must be considered because of the scanning misalignment. This paper proposed a new NLM prior model to reconstruct high quality LDCT image without image registering. In order to estimate the nonlocal weights of NLM prior, a database was trained from FDCT images of different patients, from which the patch samples similar to each target patch of the LDCT were extracted. Then the nonlocal weights were determined by the patch samples, and integrated into PWLS reconstruction with the priori information of local structures from FDCT. Experiments with 10mAs LDCT data have shown its superiority in reducing noise, streaking artifacts and preserving structure detail, indicating the potential of further dose reduction in ultra-LDCT lung screening.
A new approach to bio-medical image retrieval, local extreme co-occurrence edge binary pattern (LECoEBP) pattern proposed. Local extreme edge binary patterns (LEEBP) give the texture information and ...gray level co-occurrence matrix finds the co-occurrence of binary patterns. LEEBP extracts the four edges for each pixel and GLCM applied on each edge to find the joint occurrence of edge binary patterns. In LEEBP, each edge has directional relative information of all possible directions of a pixel. The directional relative information calculated based on the sign code magnitudes of local differences from center pixel to its directional pixels. The combination of LEEBP and GLCM showed significant results compared with the current algorithms on benchmark databases Emphysema-CT and OASIS-MRI.