Auto-ROIs of bone scan image using thin-plate spline with specific bone landmarks
- PDF / 5,423,913 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 93 Downloads / 191 Views
ORIGINAL PAPER
Auto-ROIs of bone scan image using thin-plate spline with specific bone landmarks Meilan Jimmy Hasugian 1,2 & Wen-Chen Lin 1 & Mei-Fen Chen 1 & Bang-Hung Yang 3 & Ren-Shyan Liu 4 & Kang-Ping Lin 1 Received: 7 June 2020 / Accepted: 21 September 2020 / Published online: 24 October 2020 # IUPESM and Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Bone scan image (BSI) is the most widely available technique for detecting cancer that has spread (metastasized) from the original location, such as breast or prostate cancer. One benefit of this process is as strong prognostic indicator of survival longevity for cancer patient. However, some challenging issues should be considered, i.e. variability in image brightness, abnormal bone shape or structure, asymmetry gesture position, and image noise due to muscle and fat tissue make the process to determine the region of interest (ROI) become more difficult, not to mention the required-time when inspecting the ROI of each bone part manually. The purposes of this study are to provide an effortless and meticulous ROI labeling as prerequired in clinical application. Finally, to propose a novel framework for determination of multiple ROI automatically by utilizing specific bone landmarks, in the hope of that could contribute to clinical observation in metastasis analysis. The results show that the proposed framework is promising method with high sensitivity (0.96), specificity (0.97), precision (0.94), Sørensen-Dice Index (0.96) and image content index (0.96). Keywords Skeletal scintigraphy . Thin-plate spline . Deformable ROI . Auto-ROI . Bone landmarks
1 Introduction Skeletal scintigraphy is a special type of nuclear medicine procedure that uses small amounts of radiopharmaceutical. In diagnosis variety of bone diseases and conditions, such as metabolic bone disease [1] and bone tumors [2] there are several radiopharmaceuticals that have been used. The most commonly used is Technetium labelled methylene diphosphonate (99 m Tc-MDP) [3]. Skeletal scintigraphy is the most widely available technique for detecting cancer that has spread (metastasized) from the original location, such as breast or prostate cancer [4]. One benefit of detecting the metastasis
in bone is as strong prognostic indicator of survival longevity for prostate and breast cancer patient [5–8]. Therefore, in three decades many attempts had been made to develop a computeraided diagnosis (CAD) system to assist nuclear medicine physicians in analyzing bone scan. The first CAD system is reported by Erdi et al. in [5] by employing region growing method. That system was semiautomated which required a physician to insert initial seed points manually. Yin and Chiu [9] developed a system by deploying a characteristic-point-based fuzzy inference system (CPFIS). Whole body bone images were segmented with fixed segmentation operation into six regions, i.e. head, chest,
* Kang-Ping Lin [email protected]
Ren-Shyan Liu [email protected]
Meilan Jimmy Hasugian [email protected]
1
Wen
Data Loading...
