99mTc-MDP WBBS shows a high sensitivity but relatively low specificity due to bone
variation [36]. While single-photon emission computed tomography (SPECT)/ CT could aid
in assessing suspicious bone metastasis [37], it is still ambigious for some lesions [38]. Other
radoiotracers like NaF or FDG can also be used to detect bone metastasis [39]. However, they
are not only expensive, but the patient also experiences higher radiation doses. Huang et al
described a computer-aided automatic lesion detection system that is useful and can be used
to identify possible bone lesions [40]. Medical image segmentation used in medical
applications includes quantitative clinical tools for elevating bone metastasis [35; 8; 41].
Feng et al demonstrated a model to detect gradient vector flow (GVF) and described a
quantitative scheme to detect possible abnormalities [42]. However, osseous metastases are
infrequent in endometrial cancer [43]. Bone metastases in endometrial cancer reflect the
disease aggressiveness [44]. This patient reported not only rare presentation of bone
metastasis in endometrial cancer but also showed disease progression. Even the WBBS
revealed a near-normalization uptake in the T-spine. However, spinal MRI and biopsy
confirmed malignancy. This is supposedly due to osteolytic bone lesions over the T-spine that
can be detected by IFV [28]. Otherwise, CT results can classify skeletal metastasis type as
osteoblastic, osteolytic, mixed (osteoblastic and osteolytic), and intertrabecular. In the early
stage of skeletal metastasis, when cancer cells reach the bone marrow and spread within the
bone marrow space (intertrabecular space), the changes in bone are minimal. Therefore, CT
scanning cannot detect intertrabecular type lesions, whereas bone scans can. FDG PET and
PET/CT are reportedly more sensitive to intertrabecular type skeletal metastasis than CT [34].
A comparison report between our proposed method and the other methods is shown in Table
5. According to MRI, CT, SPECT/CT, or PET/CT, assistant tools to confirm our CAD system
is good for physicians to obtain objective and correct interpretations and to provide early
diagnosis and treatment of patients. Fig. 21 shows where no active bony lesion is noted. But,
IFV found increased bone densities in shoulder, spine, r/o bone metastasis (shows Red arrow).
The red point means that the first gradient area had high irregular flux. Blue arrows indicate
the possible metastasis point. Arrowheads indicate high risk of metastasis in middle period
instead of metastasis period. In conclusion, IFV may increase the accuracy of detection of
bony metastases and thus aid physicians in diagnosis. However, this tool still needs more
study design and data for validation.
Table 5 Comparison reports between the proposed method and other methods Methods (sensitivity) & 95% CI Prostate ca. Breast ca. Lung ca.
Bone scintigraphy only 90.0 (78.0-97.0) 87.0 (82.1-90.9) 75.0 (0.70-0.79)
FDG-PET/CT 80.0 (67.0-90.0) 83.3 (78.2-90.8) 91.9 (88.8-94.3)
IFV/ BS-ROC (Result 2) 92.0 (91.0-93.0) 91.4 (90.0-92.0) 83.0 (82.0-84.0) IFV/ BS-SOM (Result 2) 93.0 (91.0-93.0) 91.0 (90.0-92.0) 83.0 (82.0-84.0)
BONENAVI version 1 [8] 83.0 78.0 90.0
BONENAVI version 2 [8] 86.0 82.0 88.0
BONENAVI version 2.0.5 [35] 88.0 86.0 82.0
BONENAVI version 2.1.7 [35] 82.7 75.6 87.5
*The study performed a comparison with clinical modalities (CT, MRI, or FDG PET/CT)
47
BONEVAVI, based on a bone scan index (BSI), is common software used ANN
detection bony metastasis and analysis in Japan. After their study performed a comparison
with clinical modalities (CT, MRI, or FDG PET/CT), the study of BONENAVI versions
sensitivity showed that prostate cancer is (83 %-88 %), the breast cancer is (75 %-86 %), and
(82 %-88 %) in lung cancer. On the other hand, our proposed approach had a higher
sensitivity than BONEVAVI results in prostate cancer (91-93 %), breast cancer (91-91.4 %),
lung cancer (82-83 %). In other words, if only using bone scintigraphy without of IFV
diagnostic assistant, the accuracy of detection bony metastasis decline to prostate cancer (89
%) than breast cancer (85 %) and lung cancer (72 %).(Table 5) This preliminary result is
similar to the clinical bone scintigraphy relative research with prostate cancer (90%), breast
cancer (87%) and lung cancer (75%). Actually, now we need clinical modalities to confirm
our IFV method is truly useful, IFV could earlier predict the progressive bony metastasis in
the future.
Future Works
In the future, some issues will be addressed:
(1) Build a database that is suitable for patients of all ages instead of adults only.
(2) Develop another analysis algorithm to detect the “cold” (osteolytic) lesions.
(3) Create another image processing method to adjust the lesion threshold values.
(4) Complete the overall system construction and evaluation about the other cancer.
Result 1: The sensitivity of BS by IFV evaluation (1) BS: ROC Curve by IFV evaluation
Fig. I Index Grades-ROC Curve of Prostate Ca.
Fig. II Index Grades-ROC Curve of Breast Ca.
49
Fig. III Index Grades-ROC Curve of Lung Ca.
(2) IFV/BS: SOM-ROC Curve
Fig. IV SOM Method-ROC Curve of Prostate Ca.
Fig. V SOM Method-ROC Curve of Breast Ca.
Fig. VI SOM Method-ROC Curve of Lung Ca.
51
Result 2:
(3) IFV/BS comparison with clinical modalities (MRI, CT, FDG-PET/CT): ROC-Curve
Fig. VII Index Grades-ROC Curve of Prostate Ca.
Fig. VIII Index Grades-ROC Curve of Breast Ca.
Fig. IX. Index Grades-ROC Curve of Lung Ca.
(4)IFV/BS comparison with clinical modalities (MRI, CT, FDG-PET/CT): SOM-ROC-Curve
Fig. X SOM Method-ROC Curve of Prostate Ca.
53
Fig. XI SOM Method-ROC Curve of Breast Ca.
Fig. XII SOM Method-ROC Curve of Lung Ca.
REFERENCE
[1] Jacobson AF, “Bone scanning in metastatic disease,” In: Collier BD Jr, Fogelman I, Rosenthall L, eds.
[2] Sergieva S, Kirova G, Dudov A, “Current diagnostic approaches in tumor-induced bone disease,” J BUON. vol.12, pp. 493–504. 2, 2007.
[3] Abuzallouf S, Dayes I, Lukka H, “Baseline staging of newly diagnosed prostate cancer:
a summary of the literature,” J Urol. vol. 171, pp. 2122–2127, 2004.
[4] Bombardieri E, Gianni L, “The choice of the correct imaging modality in breast cancer management,” Eur J Nucl Med Mol Imaging. vol. 31(suppl), pp. S179–S186, 2004.
[5] Myers RE, Johnston M, Pritchard K, Levine M, Oliver T, “and the Breast Cancer Disease Site Group of the Cancer Care Ontario Practice Guidelines Initiative. Baseline staging tests in primary breast cancer: a practice guideline,” CMAJ. vol. 164, pp.1439–1444, 2001.
[6] Hendler A. and Hershkop M, “When to use bone scintigraphy. It can reveal things other studies cannot,” Postgraduate Medicine vol. 104, no. 5, pp. 54–66, 1998.
[7] Mu¨ller V., Steinhagen J., de Wit M., and Bohuslavizki H. K, “Bone scintigraphy in clinical routine,” Radiol Oncol, vol. 35, no. 1, pp. 21–30, 2001.
[8] Mitsuru Koizumi, Kei Wagatsuma, Noriaki Miyaji et al., “Evaluation of a computer-assisted diagnosis system, BONENAVI version 2, for bone scintigraphy in cancer patients in a routine clinical setting,” Ann Nucl Med, vol. 29, no. 2, 2015.
[9] J. Y. Huang, P. F. Kao, and Y. S. Chen, “A set of image processing algorithms for computer-aided Diagnosis in nuclear medicine whole body bone scan images,” IEEE Trans. Med. Imag., vol. 54, no. 3,pp. 9, 2007.
[10] G. B. Saha, “Fundamentals of Nuclear Pharmacy,” Springe, vol. 4, 1997.
55
[11] Noguchi M., Kikuchi H., Ishibashi M., and Noda S, “Percentage of the positive area of bone metastasis is an independent predictor of disease death in advanced prostate cancer,” British Journal of Cancer, vol. 88, pp. 195–201, 2003.
[12] K. Doi, “Computer-aided diagnosis in medical imaging: Historical review, current status and future potential,” SDOL Comput. Med. Imag. Graph., vol. 31, pp. 14, 2007.
[13] T. K. Yin and N. T. Chiu, “A computer-aided diagnosis for locating abnormalities in bone scintigraphy by a fuzzy system with a three-step minimization approach,” IEEE Trans. Med. Imag., vol. 23, no. 5, pp. 16, 2004.
[14] Karan Peepre, “99mTc-MDP Bone Scan In the Detection of Bone Metastases in Breast cancer,” IOSR Journal of Dental and Medical Sciences, vol. 13, issue. 1, ver. IV, pp.
82-86, 2014.
[15] Feng, J.H. and Gong, J.L, “Improved Gradient Vector Flow Model and Its Applications.
Journal of Numerical Methods and Computer Applications,” vol. 31, pp. 30-38, 2010.
[16] Xu, C.Y. and Prince, J.L, “Snakes, Shapes, and Gradient Vector Flow,” IEEE Transactions on Image Processing, vol. 7, pp. 359-369, 1998.
[17] Xu, C.Y. and Prince, J.L, “Gradient Vector Flow Deformable Models,” In: Handbook of Medical Imaging, 2000.
[18] Ji Zhao, Lina Zhang, Minmin Yin, “Medical Image Segmentation Based on Wavelet Analysis and Gradient Vector Flow,” Journal of Software Engineering and Applications, vol. 7, pp. 1019-1030, 2014.
[19] Zelinka T, Timmers HJ, Kozupa A, Chen CC, Carrasquillo JA, Reynolds JC, et al. Role of positron emission tomography and bone scintigraphy in the evaluation of bone involvement in metastatic pheochromocytoma and paraganglioma: specific implications for succinate dehydrogenase enzyme subunit B gene mutations. Endocr Relat Cancer., vol.15 (1), pp.311-323, 2008.
[20] Daldrup-Link HE, Franzius C, Link TM, et al. Whole-body MR imaging for detection of bone metastases in children and young adults: comparison with skeletal scintigraphy and FDG PET. AJR Am J Roentgenol., vol. 177(1), pp. 229-236, 2001.
[21] Ohta M, Tokuda Y, Suzuki Y, et al. Whole body PET for the evaluation of bony metastases in patients with breast cancer: comparison with 99Tcm-MDP bone scintigraphy. Nucl Med Commun, vol. 22(8), pp. 875-879, 2001.
[22] Kao CH, Hsieh JF, Tsai SC, et al. Comparison and discrepancy of 18F-2-deoxyglucose positron emission tomography and Tc-99m MDP bone scan to detect bone metastases.
Anticancer Res. vol. 20(3B), pp. 2189-2192, 2000.
[23] Franzius C, Sciuk J, Daldrup-Link HE, et al. FDG-PET for detection of osseous metastases from malignant primary bone tumours: comparison with bone scintigraphy.
Eur J Nucl Med., vol. 27(9), pp.1305-1311, 2000.
[24] Korn, Theresa M.; Korn, Granino Arthur, “Mathematical Handbook for Scientists and Engineers: Definitions, Theorems, and Formulas for Reference and Review,” New York:
Dover Publications, pp. 157–160, 2000.
[25] Kohonen, Teuvo; Honkela, Timo., “Kohonen Network,” Scholarpedia, 2007.
[26] Kohonen, Teuvo., “Self-Organized Formation of Topologically Correct Feature Maps,”
Biological Cybernetics, vol. 43, no. 1, pp. 59–69, 1982.
[27] Von der Malsburg, C., “Self-organization of orientation sensitive cells in the striate cortex,” Kybernetik, vol. 14, pp. 85–100, 1973.
[28] Turing, Alan, “The chemical basis of morphogenesis,” Phil. Trans. Of the Royal Society vol. 237, pp. 5–72, 1952.
[29] "Self-organizing map", https://en.wikipedia.org/wiki/Self-organizing_map
[30] Ultsch, Alfred; Siemon, H. Peter “Kohonen's Self Organizing Feature Maps for Exploratory Data Analysis,” In Widrow, Bernard; Angeniol, Bernard. Proceedings of the
57
International Neural Network Conference (INNC-90), Paris, France, July 9–13, 1990 1.
Dordrecht, Netherlands: Kluwer. pp. 305–308, 1990.
[31] Ultsch, Alfred, “U*-Matrix: A tool to visualize clusters in high dimensional data,”
Department of Computer Science, University of Marburg, Technical Report Nr. 36, pp.
1-12, 2003.
[32] Ultsch, Alfred, “Emergence in Self-Organizing Feature Maps,” In Ritter, H.; Haschke, R.
Proceedings of the 6th International Workshop on Self-Organizing Maps (WSOM '07).
Bielefeld, Germany: Neuroinformatics Group, 2007.
[33] Schey, H.M., Div, Grad, Curl, and All That (2nd ed.), W.W. Norton, 1992.
[34] Evangelista L, Panunzio A, Polverosi R, Ferretti A, Chondrogiannis S, Pomerri F, et al.
Early bone marrow metastasis detection: the additional value of FDG-PET/CT vs. CT imaging. Biomed Pharmacother. Vol. 66, pp. 448–453, 2012.
[35] Kikushima S, Hanawa N, Kotake F, “Diagnostic performance of bone scintigraphy
analyzed by three artificial neural network systems,” Ann Nucl Med. vol.29, no. 2,
pp.125-31, 2015.
[36] Luna A1, Vilanova JC, Alcalá Mata L, “ Total body MRI in early detection of bone metastasis and its indication in comparison to bone scan and other imaging techniques
(only abstract) ,” Arch. Esp. Urol, vol. 68, no. 3, pp. 371-390, 2015.
[37] Utsunomiya D, Shiraishi S, Imuta M, et al. , “Added value of spect/ct fusion in
assessing suspected bone metastasis: Comparison with scintigraphy alone and
nonfused scintigraphy and ct ,” Radiology, vol. 238, pp. 264-271, 2006.
[38] Harisankar CN, Agrawal K, Bhattacharya A, Mittal BR, “ F-18 fluoro-deoxy-glucose
and F-18 sodium fluoride cocktail PET/CT scan in patients with breast cancer having
equivocal bone SPECT/CT,” Indian J Nucl Med. vol. 29, no. 2, pp. 81-86, 2014.
[39] Tarnawska-Pierscinska M, Holody L, Braziewicz J, et al., “Bone metastases diagnosis
possibilities in studies with the use of 18F-NaF and 18F-FDG,” Nucl Med Rev. vol. 14,
pp. 105-108, 2011.
[40] Huang JY, Kao PF, Chen YS, “A set of image processing algorithms for
computer-aided diagnosis in nuclear medicine whole body bone scan images,” IEEE
Transactions on Nuclear Science, vol. 54, no. 3, pp. 514-522, 2007.
[41] Sadik M, Hamadeh I, Nordblom P, and et al, “Computer-assisted interpretation of
planar whole-body bone scans,” J Nucl Med. vol. 49, no. 12, pp. 1958-65, 2008.
[42] Feng, J.H. and Gong, J.L, “Improved gradient vector flow model and its applications,”
J Numer Methods Comput Appl, vol. 31, pp. 30-38, 2010.
[43] Munné J, Alameda F, Bergueiro A, et al., “Unusual presentation of endometrial cancer: a
clinicopathological study of one case,” vol. 5, pp. 23-27, 2015.
[44] Loizzi V, Cormio G, Cuccovillo A, et al., “ Two cases of endometrial cancer diagnosis
associated with bone metastasis,” Gynecol Obstet Invest, vol. 61, no. 1, pp. 49-52, 2006.
59
PUBLICATION
Journal Papers
1. Hung Pin Chan, Chin Hu, Chang-Ching Yu, Tsung-Chi Huang, Nan-Jing Peng, “ Added
value of using a cocktail of F-18 sodium fluoride and F-18 fluorodeoxyglucose in
positron emission tomography/computed tomography for detecting bony metastasis: a
case report”, Medicine (Baltimore). vol. 94, no.13, e687, 2015.04. (SCI Paper Published
2015.04)
2. Chang-Ching Yu, Chi-Tsung Chen, Chung-Ming Kuo, Hueisch-Jy Din, Nan-Jing Peng,
Hung-Pin Chan, “Added values for the detection of bone metastases in whole body bone
scans with a computer-aided detection scheme: Irregular flux viewer (IFV)”, Clinical
Nuclear Medicine, CNM-D-15-00534, 2015.07. (Transferred to MEDICINE)
3. Hung Pin Chan, Shyh-Jer Lin, Yu-Li Chiu, Chang-Chaing Yu, Tsung-Chi Huang,
Nan-Jing Peng, “Incidental finding of solitary plasmacytoma in Thallium-201
myocardial perfusion scintigraphy”, Circulation. Vol. 132, no. 22, pp. 2164-2166. (SCI
Paper Published 2015.12)
4. Hung-Pin Chan, Chang-Ching Yu, Chung-Shun Wu, Nan-Jing Peng, “Extramedullary
Hematopoiesis Presented as a Posterior Mediastinal Mass in a woman with Thalassemia
Intermedia”, Annals of Nuclear Medicine and Molecular Imaging. vol. 28, no.4, pp.
174-177, 2015.12.
Conference Papers
1. Chang-Ching Yu, Pi-Yun Tseng, Chung-Ming Kuo, Hueisch-Jy Ding, “Using
Segmentation and Texture Features Around Mapped Injection Point for Sentinel Lymph
Nodes in Lymphoscintigrams by Computer-Aided Detection Scheme”, Macao
Radiological Technologists’ Association, Macao, China, 2014.10.
2. Chang-Ching Yu, Pi-Yun Tseng, Chung-Ming Kuo, Hueisch-Jy Ding, “To Evaluate The
Detection Efficiency of Sentinel Lymph Nodes (SLNs) in Lymphoscintigraphy by
SPECT/CT”, The 30th Japan Conference of Radiological Technologists (30JCRT) and
the 21st East Asia Conference of Radiological Technologists (21EACRT), Beppu, Japan,
2014.09.
3. Chang-Ching Yu, Pi-Yun Tseng, Chung-Ming Kuo, Hueisch-Jy Ding, “The role of nitric
oxide in rat skin vascular destruction and leakage induced by Thallium-201 and
Dipyridamole”. 47rd Annual Meeting of TWSRT and 18th East Asia Conference Of
Radiological Technologists（EACRT）, Chia-Yi Chang-Gung Memorial Hospital, 2014.03.
4. Chang-Ching Yu, Chun-Mei Chang, Chung-Ming Kuo, Hueisch-Jy Ding, “The impact
of radiation in rats’ vascular destruction and leakage of skin, heart, liver and kidney:
detecting by radial isotope modalities”. 45rd Annual Meeting of 2013 TWSNM, Taipei
Veterans General Hospital, 2013.10. (榮獲2013年核醫年會壁報論文基礎組 佳作獎) 5. 吳忠順、張春梅、俞長青俞長青俞長青、彭南靖，骨髓炎加作全身造影臨床效益之評估，俞長青 2013
61
年中華民國核醫學學會年會暨國際學術研討會，台北榮民總醫院，2013.10.
6. 張春梅、俞俞俞俞長青長青長青、彭南靖，核子醫學掃描診斷膀胱輸尿管逆流之臨床價值。長青 2013 年中華民國核醫學學會年會暨國際學術研討會，台北榮民總醫院，2013.10.
7. Chang-Ching Yu, Pi-Yun Tseng, Chun-Mei Chang, Chi-Chon Chen, “Analysis of
Tc-99m HMPAO-SPECT regional cerebral blood flow in Alzheimer’s disease by using
image strength of fluctuation”, 42rd Annual Meeting of 2010 TWSNM, National Cheng
Kung University Hospital, 2010.09.
8. Chang-Ching Yu, Pi-Yun Tseng, Chun-Mei Chang, Wei-Ning Tu, “To achieve a high
quality standard of brain perfusion 99mTc-ECD brain SPECT image”, 43rd Annual
Meeting of TWSRT and 14th East Asia Conference of Radiological Technologists
(EACRT), Kaohsiung Veterans General Hospital, 2010.01.
9. Pi-Yun Tseng, Chang-Ching Yu, Chun-Mei Chang, Wei-Ning Tu, “Experience in
lymphoscintigraphy with 99mTc-Sulfur colloid and gamma-probe detection”, 43rd
Annual Meeting of TWSRT and 14th East Asia Conference of Radiological Technologists
(EACRT), Kaohsiung Veterans General Hospital, 2010.01.