Abstract
Purpose
We evaluated the performance of deep learning classifiers for bone scans of prostate cancer patients.
Methods
A total of 9113 consecutive bone scans (5342 prostate cancer patients) were initially evaluated. Bone scans were labeled as positive/negative for bone metastasis using clinical reports and image review for ground truth diagnosis. Two different 2D convolutional neural network (CNN) architectures were proposed: (1) whole body–based (WB) and (2) tandem architectures integrating whole body and local patches, here named as “global–local unified emphasis” (GLUE). Both models were trained using abundant (72%:8%:20% for training:validation:test sets) and limited training data (10%:40%:50%). The allocation of test sets was rotated across all images: therefore, fivefold and twofold cross-validation test results were available for abundant and limited settings, respectively.
Results
A total of 2991 positive and 6142 negative bone scans were used as input. For the abundant training setting, the receiver operating characteristics curves of both the GLUE and WB models indicated excellent diagnostic ability in terms of the area under the curve (GLUE: 0.936–0.955, WB: 0.933–0.957, P > 0.05 in four of the fivefold tests). The overall accuracies of the GLUE and WB models were 0.900 and 0.889, respectively. With the limited training setting, the GLUE models showed significantly higher AUCs than the WB models (0.894–0.908 vs. 0.870–0.877, P < 0.0001).
Conclusion
Our 2D-CNN models accurately classified bone scans of prostate cancer patients. While both showed excellent performance with the abundant dataset, the GLUE model showed higher performance than the WB model in the limited data setting.
Similar content being viewed by others
References
Siegel RL, Miller KD, Jemal A. Cancer statistics, 2020. CA Cancer J Clin. 2020;70:7–30. https://doi.org/10.3322/caac.21590.
Halabi S, Kelly WK, Ma H, Zhou H, Solomon NC, Fizazi K, et al. Meta-analysis evaluating the impact of site of metastasis on overall survival in men with castration-resistant prostate cancer. J Clin Oncol. 2016;34:1652–9. https://doi.org/10.1200/jco.2015.65.7270.
Crawford ED, Stone NN, Yu EY, Koo PJ, Freedland SJ, Slovin SF, et al. Challenges and recommendations for early identification of metastatic disease in prostate cancer. Urology. 2014;83:664–9. https://doi.org/10.1016/j.urology.2013.10.026.
Gandaglia G, Karakiewicz PI, Briganti A, Passoni NM, Schiffmann J, Trudeau V, et al. Impact of the site of metastases on survival in patients with metastatic prostate cancer. Eur Urol. 2015;68:325–34. https://doi.org/10.1016/j.eururo.2014.07.020.
Cook GJR, Azad G, Padhani AR. Bone imaging in prostate cancer: the evolving roles of nuclear medicine and radiology. Clin Transl Imaging. 2016;4:439–47. https://doi.org/10.1007/s40336-016-0196-5.
Schaeffer E, Srinivas S, Antonarakis ES, Armstrong AJ, Bekelman JE, Cheng H, et al. NCCN clinical practice guidelines in oncology. Prostate Cancer. Version 2.2020. 2020. https://www.nccn.org/professionals/physician_gls/pdf/prostate.pdf. Accessed March 8 2021.
Mottet N, Cornford P, van der Bergh RCE, Briers E, De Santis M, Fanti S, et al. EAU guideline - prostate cancer. Edn. presented at the EAU Annual Congress Amsterdam. 2020.
Agrawal K, Marafi F, Gnanasegaran G, Van der Wall H, Fogelman I. Pitfalls and limitations of radionuclide planar and hybrid bone imaging. Semin Nucl Med. 2015;45:347–72. https://doi.org/10.1053/j.semnuclmed.2015.02.002.
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. https://doi.org/10.1007/s00259-008-0721-5.
Choi H. Deep learning in nuclear medicine and molecular imaging: current perspectives and future directions. Nucl Med Mol Imaging. 2018;52:109–18. https://doi.org/10.1007/s13139-017-0504-7.
Sibille L, Seifert R, Avramovic N, Vehren T, Spottiswoode B, Zuehlsdorff S, et al. (18)F-FDG PET/CT Uptake Classification in lymphoma and lung cancer by using deep convolutional neural networks. Radiology. 2020;294:445–52. https://doi.org/10.1148/radiol.2019191114.
Capobianco N, Meignan M, Cottereau AS, Vercellino L, Sibille L, Spottiswoode B, et al. Deep-learning (18)F-FDG uptake classification enables total metabolic tumor volume estimation in diffuse large B-cell lymphoma. J Nucl Med. 2021;62:30–6. https://doi.org/10.2967/jnumed.120.242412.
Fu J, Yang Y, Singhrao K, Ruan D, Chu FI, Low DA, et al. Deep learning approaches using 2D and 3D convolutional neural networks for generating male pelvic synthetic computed tomography from magnetic resonance imaging. Med Phys. 2019;46:3788–98. https://doi.org/10.1002/mp.13672.
Seifert R, Weber M, Kocakavuk E, Rischpler C, Kersting D. Artificial intelligence and machine learning in nuclear medicine: future perspectives. Semin Nucl Med. 2021;51:170–7. https://doi.org/10.1053/j.semnuclmed.2020.08.003.
Lee JJ, Yang H, Franc BL, Iagaru A, Davidzon GA. Deep learning detection of prostate cancer recurrence with (18)F-FACBC (fluciclovine, Axumin®) positron emission tomography. Eur J Nucl Med Mol Imaging. 2020;47:2992–7. https://doi.org/10.1007/s00259-020-04912-w.
Apiparakoon T, Rakratchatakul N, Chantadisai M, Vutrapongwatana U, Kingpetch K, Sirisalipoch S, et al. MaligNet: semisupervised learning for bone lesion instance segmentation using bone scintigraphy. IEEE Access. 2020;8:27047–66. https://doi.org/10.1109/ACCESS.2020.2971391.
Papandrianos N, Papageorgiou E, Anagnostis A, Feleki A. A deep-learning approach for diagnosis of metastatic breast cancer in bones from whole-body scans. Applied Science. 2020;10:997. https://doi.org/10.3390/app10030997.
Papandrianos N, Papageorgiou E, Anagnostis A, Papageorgiou K. Bone metastasis classification using whole body images from prostate cancer patients based on convolutional neural networks application. PLoS ONE. 2020;15: e0237213. https://doi.org/10.1371/journal.pone.0237213.
Zhao Z, Pi Y, Jiang L, Xiang Y, Wei J, Yang P, et al. Deep neural network based artificial intelligence assisted diagnosis of bone scintigraphy for cancer bone metastasis. Sci Rep. 2020;10:17046. https://doi.org/10.1038/s41598-020-74135-4.
Panicek DM, Hricak H. How Sure Are You, Doctor? A standardized lexicon to describe the radiologist’s level of certainty. AJR Am J Roentgenol. 2016;207:2–3. https://doi.org/10.2214/ajr.15.15895.
Son HJ, Oh JS, Oh M, Kim SJ, Lee JH, Roh JH, et al. The clinical feasibility of deep learning-based classification of amyloid PET images in visually equivocal cases. Eur J Nucl Med Mol Imaging. 2020;47:332–41. https://doi.org/10.1007/s00259-019-04595-y.
Scher HI, Halabi S, Tannock I, Morris M, Sternberg CN, Carducci MA, et al. Design and end points of clinical trials for patients with progressive prostate cancer and castrate levels of testosterone: recommendations of the Prostate Cancer Clinical Trials Working Group. J Clin Oncol. 2008;26:1148–59. https://doi.org/10.1200/jco.2007.12.4487.
Han S, Woo S, Kim YI, Lee JL, Wibmer AG, Schoder H, et al. Concordance between response assessment using prostate-specific membrane antigen PET and serum prostate-specific antigen levels after systemic treatment in patients with metastatic castration resistant prostate cancer: a systematic review and meta-analysis. Diagnostics (Basel). 2021;11. https://doi.org/10.3390/diagnostics11040663.
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. https://doi.org/10.2967/jnumed.108.055061.
Ulmert D, Kaboteh R, Fox JJ, Savage C, Evans MJ, Lilja H, et al. A novel automated platform for quantifying the extent of skeletal tumour involvement in prostate cancer patients using the Bone Scan Index. Eur Urol. 2012;62:78–84. https://doi.org/10.1016/j.eururo.2012.01.037.
Horikoshi H, Kikuchi A, Onoguchi M, Sjöstrand K, Edenbrandt L. Computer-aided diagnosis system for bone scintigrams from Japanese patients: importance of training database. Ann Nucl Med. 2012;26:622–6. https://doi.org/10.1007/s12149-012-0620-5.
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 research. 2013;3:83-. https://doi.org/10.1186/2191-219X-3-83.
Hesamian MH, Jia W, He X, Kennedy P. Deep learning techniques for medical image segmentation: achievements and challenges. J Digit Imaging. 2019;32:582–96. https://doi.org/10.1007/s10278-019-00227-x.
Brui E, Efimtcev AY, Fokin VA, Fernandez R, Levchuk AG, Ogier AC, et al. Deep learning-based fully automatic segmentation of wrist cartilage in MR images. NMR Biomed. 2020;33: e4320. https://doi.org/10.1002/nbm.4320.
Cawley GC, Talbot NLC. On over-fitting in model selection and subsequent selection bias in performance evaluation. J Mach Learn Res. 2010;11:2079–107.
Acknowledgements
We appreciate the substantial contributions and support from members in the Division of Research Information, Department of Data Convergence, Asan Medical Center, Seoul, Korea, for retrieving clinical information on the study population.
Funding
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (Ministry of Science and ICT; No. NRF-2020M2D9A1094074; 2021R1A2C3009056) and by a grant from the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (HI18C2383).
Author information
Authors and Affiliations
Contributions
Sangwon Han, Jungsu S. Oh, and Jong Jin Lee contributed to the study conceptualization, data acquisition, data analysis, data interpretation, writing, and editing of the manuscript.
Corresponding authors
Ethics declarations
Ethics approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and the principles of the 1964 Declaration of Helsinki and its subsequent amendments or comparable ethical standards.
Informed consent
This retrospective study was approved by the local institutional review board (IRB No. 2020–1098). The need for informed consent was waived by the committee.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Jong Jin Lee and Jungsu S. Oh contributed equally to this work as the corresponding authors.
This article is part of the Topical Collection on Advanced Image Analyses (Radiomics and Artificial Intelligence).
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Han, S., Oh, J.S. & Lee, J.J. Diagnostic performance of deep learning models for detecting bone metastasis on whole-body bone scan in prostate cancer. Eur J Nucl Med Mol Imaging 49, 585–595 (2022). https://doi.org/10.1007/s00259-021-05481-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00259-021-05481-2