Comparison of skeletal segmentation by deep learning-based and atlas-based segmentation in prostate cancer patients
Tóm tắt
We aimed to compare the deep learning-based (VSBONE BSI) and atlas-based (BONENAVI) segmentation accuracy that have been developed to measure the bone scan index based on skeletal segmentation. We retrospectively conducted bone scans for 383 patients with prostate cancer. These patients were divided into two groups: 208 patients were injected with 99mTc-hydroxymethylene diphosphonate processed by VSBONE BSI, and 175 patients were injected with 99mTc-methylene diphosphonate processed by BONENAVI. Three observers classified the skeletal segmentations as either a “Match” or “Mismatch” in the following regions: the skull, cervical vertebrae, thoracic vertebrae, lumbar vertebrae, pelvis, sacrum, humerus, rib, sternum, clavicle, scapula, and femur. Segmentation error was defined if two or more observers selected “Mismatch” in the same region. We calculated the segmentation error rate according to each administration group and evaluated the presence of hot spots suspected bone metastases in "Mismatch" regions. Multivariate logistic regression analysis was used to determine the association between segmentation error and variables like age, uptake time, total counts, extent of disease, and gamma cameras. The regions of “Mismatch” were more common in the long tube bones for VSBONE BSI and in the pelvis and axial skeletons for BONENAVI. Segmentation error was observed in 49 cases (23.6%) with VSBONE BSI and 58 cases (33.1%) with BONENAVI. VSBONE BSI tended that “Mismatch” regions contained hot spots suspected of bone metastases in patients with multiple bone metastases and showed that patients with higher extent of disease (odds ratio = 8.34) were associated with segmentation error in multivariate logistic regression analysis. VSBONE BSI has a potential to be higher segmentation accuracy compared with BONENAVI. However, the segmentation error in VSBONE BSI occurred dependent on bone metastases burden. We need to be careful when evaluating multiple bone metastases using VSBONE BSI.
Tài liệu tham khảo
Van den Wyngaert T, Strobel K, Kampen WU, Kuwert T, van der Bruggen W, Mohan HK, et al. The EANM practice guidelines for bone scintigraphy. Eur J Nucl Med Mol Imaging. 2016;43:1723–38.
Sadik M, Suurkula M, Höglund P, Järund A, Edenbrandt L. Quality of planar whole-body bone scan interpretations—a nationwide survey. Eur J Nucl Med Mol Imaging. 2008;35:1464–72.
Sadik M, Jakobsson D, Olofsson F, Ohlsson M, Suurkula M, Edenbrandt L. A new computer-based decision-support system for the interpretation of bone scans. Nucl Med Commun. 2006;27:417–23.
Sadik M, Hamadeh I, Nordblom P, Suurkula M, Höglund P, Ohlsson M, et al. Computer-assisted interpretation of planar whole-body bone scans. J Nucl Med. 2008;49:1958–65.
Sadik M, Suurkula M, Höglund P, Järund A, Edenbrandt L. Improved classifications of planar whole-body bone scans using a computer-assisted diagnosis system: a multicenter, multiple-reader, multiple-case study. J Nucl Med. 2009;50:368–75.
Imbriaco M, Larson SM, Yeung HW, Mawlawi OR, Erdi Y, Venkatraman ES, et al. A new parameter for measuring metastatic bone involvement by prostate cancer: the Bone Scan Index. Clin Cancer Res. 1998;4:1765–72.
International Commission on Radiological Protection. Report of the Task Group on the Reference Man, ICRP Publication 23. New York: Pergamon Press; 1975.
Sabbatini P, Larson SM, Kremer A, Zhang ZF, Sun M, Yeung H, et al. Prognostic significance of extent of disease in bone in patients with androgen-independent prostate cancer. J Clin Oncol Citeseer. 1999;17:948–57.
Dennis ER, Jia X, Mezheritskiy IS, Stephenson RD, Schoder H, Fox JJ, et al. Bone scan index: a quantitative treatment response biomarker for castration-resistant metastatic prostate cancer. J Clin Oncol. 2012;30:519–24.
Knutsson H, Andersson M. Morphons: paint on priors and elastic canvas for segmentation and registration Image analysis. Berlin: Springer; 2005. p. 292–301.
Sjöstrand K, Ohlsson M, Edenbrandt L. Statistical regularization of deformation fields for atlas-based segmentation of bone scintigraphy images. Med Image Comput Comput Assist Interv. 2009;12:664–71.
Koizumi M, Wagatsuma K, Miyaji N, Murata T, Miwa K, Takiguchi T, 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. 2015;29:138–48.
Koizumi M, Miyaji N, Murata T, Motegi K, Miwa K, Koyama M, et al. Evaluation of a revised version of computer-assisted diagnosis system, BONENAVI version 2.1.7, for bone scintigraphy in cancer patients. Ann Nucl Med. 2015;29:659–65.
Iglesias JE, Sabuncu MR. Multi-atlas segmentation of biomedical images: a survey. Med Image Anal. 2015;24:205–19.
Shimizu A, Wakabayashi H, Kanamori T, Saito A, Nishikawa K, Daisaki H, et al. Automated measurement of bone scan index from a whole-body bone scintigram. Int J Comput Assist Radiol Surg. 2020;15:389–400.
Higashiyama S, Yoshida A, Kawabe J. Study of the usefulness of bone scan index calculated from 99m-technetium- hydroxymethylene diphosphonate (99mTc-HMDP) bone scintigraphy for bone metastases from prostate cancer using deep learning algorithms. Curr Med Imaging Rev. 2021;17:89–96.
Aoki Y, Nakayama M, Nomura K, Tomita Y, Nakajima K, Yamashina M, et al. The utility of a deep learning-based algorithm for bone scintigraphy in patient with prostate cancer. Ann Nucl Med. 2020;34:926–31.
Yoshida A, Higashiyama S, Kawabe J. Assessment of a software for semi-automatically calculating the bone scan index on bone scintigraphy scans. Clin Imaging. 2021;78:14–8.
Soloway MS, Hardeman SW, Hickey D, Raymond J, Todd B, Soloway S, et al. Stratification of patients with metastatic prostate cancer based on extent of disease on initial bone scan. Cancer. 1988;61:195–202.
Sekuboyina A, Rempfler M, Kukačka J, Tetteh G, Valentinitsch A, Kirschke JS, et al. (2018) Btrfly Net: vertebrae labelling with energy-based adversarial learning of local spine prior. In: 21st International conference on medical image computing and computer assisted intervention—MICCAI, Granada, Spain, Sept 16–20, 2018, Proceedings, Part IV, pp 649–57
Nakajima K, Nakajima Y, Horikoshi H, Ueno M, Wakabayashi H, Shiga T, et al. Enhanced diagnostic accuracy for quantitative bone scan using an artificial neural network system: a Japanese multi-center database project. EJNMMI Res. 2013;3:83.
Kikuchi A, Onoguchi M, Horikoshi H, Sjöstrand K, Edenbrandt L. Automated segmentation of the skeleton in whole-body bone scans. Nucl Med Commun. 2012;33:947–53.
Umeda T, Koizumi M, Fukai S, Miyaji N, Motegi K, Nakazawa S, et al. Evaluation of bone metastatic burden by bone SPECT/CT in metastatic prostate cancer patients: defining threshold value for total bone uptake and assessment in radium-223 treated patients. Ann Nucl Med Springer. 2018;32:105–13.
Kanda Y. Investigation of the freely available easy-to-use software “EZR” for medical statistics. Bone Marrow Transplant. 2013;48:452–8.
Mota JM, Armstrong AJ, Larson SM, Fox JJ, Morris MJ. Measuring the unmeasurable: automated bone scan index as a quantitative endpoint in prostate cancer clinical trials. Prostate Cancer Prostatic Dis. 2019;22:522–30.
Armstrong AJ, Anand A, Edenbrandt L, Bondesson E, Bjartell A, Widmark A, et al. Phase 3 assessment of the automated bone scan index as a prognostic imaging biomarker of overall survival in men with metastatic castration-resistant prostate cancer: a secondary analysis of a randomized clinical trial. JAMA Oncol. 2018;4:944–51.
Doan NT, de Xivry JO, Macq B. Effect of inter-subject variation on the accuracy of atlas-based segmentation applied to human brain structures. In: SPIE Medical Imaging. International Society for Optics and Photonics; 2010. p. 76231S.
Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. Cham: Springer; 2015. p. 234–41.
Jackson P, Hardcastle N, Dawe N, Kron T, Hofman MS, Hicks RJ. Deep learning renal segmentation for fully automated radiation dose estimation in unsealed source therapy. Front Oncol. 2018;8:215.
Ichikawa H, Miwa K, Okuda K, Shibutani T, Kato T, Nagaki A, et al. Current state of bone scintigraphy protocols and practice in Japan. Asia Ocean J Nucl Med Biol. 2020;8:116–22.
Shibutani T, Onoguchi M, Yoneyama H, Konishi T, Nakajima K. Performance of SwiftScan planar and SPECT technology using low-energy high-resolution and sensitivity collimator compared with Siemens SPECT system. Nucl Med Commun. 2021;42:732–7.
Ljungberg M, Pretorius PH. SPECT/CT: an update on technological developments and clinical applications. Br J Radiol. 2018;91:20160402.
Koulikov V, Lerman H, Kesler M, Even-Sapir E. (99m)Tc-MDP bone scintigraphy of the hand: comparing the use of novel cadmium zinc telluride (CZT) and routine NaI(Tl) detectors. EJNMMI Res. 2015;5:63.