التفاصيل البيبلوغرافية
| العنوان: |
A Set of Image Processing Algorithms for Computer-Aided Diagnosis in Nuclear Medicine Whole Body Bone Scan Images. |
| المؤلفون: |
Jia-Yann Huang1, Pan-Fu Kao2, Yung-Sheng Chen1 eeyschen@saturn.yzu.edu.tw |
| المصدر: |
IEEE Transactions on Nuclear Science. Jun2007 Part 1 of 2, Vol. 54 Issue 3, p514-522. 9p. |
| مصطلحات موضوعية: |
*ALGORITHMS, *COMPUTER-aided design, *PHYSICIANS, DIAGNOSIS, NUCLEAR medicine, RADIOACTIVE tracers, PATIENTS, BONES, PHYSIOLOGICAL effects of radioactivity |
| مستخلص: |
Adjustment of brightness and contrast in nuclear medicine whole body bone scan images may confuse nuclear medicine physicians when identifying small bone lesions as well as making the identification of subtle bone lesion changes in sequential studies difficult. In this study, we developed a computer-aided diagnosis system, based on the fuzzy sets histogram thresholding method and anatomical knowledge-based image segmentation method that was able to analyze and quantify raw image data and identify the possible location of a lesion. To locate anatomical reference points, the fuzzy sets histogram thresholding method was adopted as a first processing stage to suppress the soft tissue in the bone images. Anatomical knowledge-based image segmentation method was then applied to segment the skeletal frame into different regions of homogeneous bones. For the different segmented bone regions, the lesion thresholds were set at different cut-oils. To obtain lesion thresholds in different segmented regions, the ranges and standard deviations of the image's gray-level distribution were obtained from 100 normal patients' whole body bone images and then, another 62 patients' images were used for testing. The two groups of images were independent. The sensitivity and the mean number of false lesions detected were used as performance indices to evaluate the proposed system. The overall sensitivity of the system is 92.1% (222 of 241) and 7.58 false detections per patient scan image. With a high sensitivity and an acceptable false lesions detection rate, this computer-aided automatic lesion detection system is demonstrated as useful and will probably in the future be able to help nuclear medicine physicians to identify possible bone lesions. [ABSTRACT FROM AUTHOR] |
|
Copyright of IEEE Transactions on Nuclear Science is the property of IEEE and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Business Source Index |
