The Statistical Evaluation of Data Obtained via the Manual Segmentation of MRI Images of a Pathological Tissue
The authors present a statistical evaluation of the MRI images of bones and soft tissues. MRI imaging of small bones is a problem issue because the measured bone images are loaded with susceptibility artifacts and low signal-to-noise ratio. Therefore, we compare the commonly used MRI contrast and looking for the best contrast to bone marrow imaging. The acquired images are classified in terms of the signal-to-noise ratio, intensity difference and steepness of the edges. The aim of this research was to statistically evaluate and determine the deviation of MRI images; this step was performed by several experts. These specialists conducted proper segmenting of pathological and healthy tissues, and they also compared the selected areas. In some cases, especially when the boundaries of the area are not clearly visible, the problem is to delimit the bone marrow area. Therefore, it is not possible to use automatic segmentation algorithms, and we focused on the manual evaluation of the statistical data in the area of the patients bone marrow pathology (e.g., the probability of cyst formation can be determined from abnormal levels of vitamin D and osteocalcin).
P.Marcon J.Mikulka E.Gescheidtova K.Bartusek A.Sprlakova
FEEC, Department of Theoretical and Experimental Electrical Engineering Brno University of Technolog Institute of Scientific Instruments of the ASCR v.v.i, Kralovopolska 147, Brno 612 64, Czech Republi Radiological Clinic, The University Hospital Brno Jihlavska 20, Brno 625 00, Czech Republic
国际会议
Progress in Electromagnetics Research Symposium 2014(2014年电磁学研究新进展学术研讨会)
广州
英文
1898-1901
2014-08-01（万方平台首次上网日期，不代表论文的发表时间）