Abstract
Objective
It is important to detect parathyroid adenomas by parathyroid scintigraphy with 99m-technetium sestamibi (99mTc-MIBI) before surgery. This study aimed to develop and validate deep learning (DL)-based models to detect parathyroid adenoma in patients with primary hyperparathyroidism, from parathyroid scintigrams with 99mTc-MIBI.
Methods
DL-based models for detecting parathyroid adenoma in early- and late-phase parathyroid scintigrams were, respectively, developed and evaluated. The training dataset used to train the models was collected from 192 patients (165 adenoma cases, mean age: 64 years ± 13, 145 women) and the validation dataset used to tune the models was collected from 45 patients (30 adenoma cases, mean age: 67 years ± 12, 37 women). The images were collected from patients who were pathologically diagnosed with parathyroid adenomas or in whom no lesions could be detected by either parathyroid scintigraphy or ultrasonography at our institution from June 2010 to March 2019. The models were tested on a dataset collected from 44 patients (30 adenoma cases, mean age: 67 years ± 12, 38 women) who took scintigraphy from April 2019 to March 2020. The models’ lesion-based sensitivity and mean false positive indications per image (mFPI) were assessed with the test dataset.
Results
The sensitivity was 82% [95% confidence interval 72–92%] with mFPI of 0.44 for the scintigrams of the early-phase model and 83% [73–92%] with mFPI of 0.31 for the scintigrams of the delayed-phase model in the test dataset, respectively.
Conclusions
The DL-based models were able to detect parathyroid adenomas with a high sensitivity using parathyroid scintigraphy with 99m-technetium sestamibi.
Similar content being viewed by others
References
Fraser WD. Hyperparathyroidism. Lancet. 2009;374:145–58.
Westerdahl J, Bergenfelz A. Unilateral versus bilateral neck exploration for primary hyperparathyroidism: five-year follow-up of a randomized controlled trial. Ann Surg. 2007;246:976–80.
Ebner Y, Garti-Gross Y, Margulis A, Levy Y, Nabrisky D, Ophir D, et al. Parathyroid surgery: correlation between pre-operative localization studies and surgical outcomes. Clin Endocrinol (Oxf). 2015;83:733–8.
Grant CS, Thompson G, Farley D, van Heerden J. Primary hyperparathyroidism surgical management since the introduction of minimally invasive parathyroidectomy: Mayo Clinic experience. Arch Surg. 2005;140:472–8.
Kunstman JW, Udelsman R. Superiority of minimally invasive parathyroidectomy. Adv Surg. 2012;46:171–89.
Wei WJ, Shen CT, Song HJ, Qiu ZL, Luo QY. Comparison of SPET/CT, SPET and planar imaging using 99mTc-MIBI as independent techniques to support minimally invasive parathyroidectomy in primary hyperparathyroidism: a meta-analysis. Hell J Nucl Med. 2015;18:127–35.
Lavely WC, Goetze S, Friedman KP, Leal JP, Zhang Z, Garret-Mayer E, et al. Comparison of SPECT/CT, SPECT, and planar imaging with single- and dual-phase (99m)Tc-sestamibi parathyroid scintigraphy. J Nucl Med. 2007;48:1084–9.
Shafiei B, Hoseinzadeh S, Fotouhi F, Malek H, Azizi F, Jahed A, et al. Preoperative 99mTc-sestamibi scintigraphy in patients with primary hyperparathyroidism and concomitant nodular goiter: comparison of SPECT-CT, SPECT, and planar imaging. Nucl Med Commun. 2012;33:1070–6.
Treglia G, Sadeghi R, Schalin-Jäntti C, Caldarella C, Ceriani L, Giovanella L, et al. Detection rate of (99m) Tc-MIBI single photon emission computed tomography (SPECT)/CT in preoperative planning for patients with primary hyperparathyroidism: A meta-analysis. Head Neck. 2016;38:E2159–72.
Ruda JM, Hollenbeak CS, Stack BC Jr. A systematic review of the diagnosis and treatment of primary hyperparathyroidism from 1995 to 2003. Otolaryngol Head Neck Surg. 2005;132:359–72.
Gotthardt M, Lohmann B, Behr TM, Bauhofer A, Franzius C, Schipper ML, et al. Clinical value of parathyroid scintigraphy with technetium-99m methoxyisobutylisonitrile: discrepancies in clinical data and a systematic metaanalysis of the literature. World J Surg. 2004;28:100–7.
Cheung K, Wang TS, Farrokhyar F, Roman SA, Sosa JA. A meta-analysis of preoperative localization techniques for patients with primary hyperparathyroidism. Ann Surg Oncol. 2012;19:577–83.
Satava RM Jr, Beahrs OH, Scholz DA. Success rate of cervical exploration for hyperparathyroidism. Arch Surg. 1975;110:625–8.
Lane MJ, Desser TS, Weigel RJ, Jeffrey RB Jr. Use of color and power Doppler sonography to identify feeding arteries associated with parathyroid adenomas. AJR Am J Roentgenol. 1998;171:819–23.
Reeder SB, Desser TS, Weigel RJ, Jeffrey RB. Sonography in primary hyperparathyroidism: review with emphasis on scanning technique. J Ultrasound Med. 2002;21:539–52.
Mariani G, Gulec SA, Rubello D, Boni G, Puccini M, Pelizzo MR, et al. Preoperative localization and radioguided parathyroid surgery. J Nucl Med. 2003;44:1443–58.
Lumachi F, Ermani M, Basso S, Zucchetta P, Borsato N, Favia G. Localization of parathyroid tumours in the minimally invasive era: which technique should be chosen? Population-based analysis of 253 patients undergoing parathyroidectomy and factors affecting parathyroid gland detection. Endocr Relat Cancer. 2001;8:63–9.
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–44.
Hinton G. Deep learning: a technology with the potential to transform health. JAMA. 2018;320:1101–2.
Ueda D, Shimazaki A, Miki Y. Technical and clinical overview of deep learning in radiology. Jpn J Radiol. 2019;37:15–33.
Nensa F, Demircioglu A, Rischpler C. Artificial intelligence in nuclear medicine. J Nucl Med. 2019;60:29S-37S.
Yasaka K, Akai H, Kunimatsu A, Kiryu S, Abe O. Deep learning with convolutional neural network in radiology. Jpn J Radiol. 2018;36(4):257–72. https://doi.org/10.1007/s11604-018-0726-3.
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. 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.
Ding Y, Sohn JH, Kawczynski MG, Trivedi H, Harnish R, Jenkins NW, et al. A deep learning model to predict a diagnosis of Alzheimer disease by using 18 F-FDG PET of the brain. Radiology. 2019;290:456–64.
Choi H, Ha S, Kang H, Lee H, Lee DS. Alzheimer’s disease neuroimaging initiative. Deep learning only by normal brain PET identify unheralded brain anomalies. EBioMedicine. 2019;43:447–53.
Teramoto A, Fujita H, Yamamuro O, Tamaki T. Automated detection of pulmonary nodules in PET/CT images: Ensemble false-positive reduction using a convolutional neural network technique. Med Phys. 2016;43:2821–7.
Xu L, Tetteh G, Lipkova J, Zhao Y, Li H, Christ P, et al. Automated whole-body bone lesion detection for multiple myeloma on 68 Ga-Pentixafor PET/CT imaging using deep learning methods. Contrast Media Mol Imaging. 2018;2018:2391925.
Zhao Y, Gafita A, Vollnberg B, Tetteh G, Haupt F, Afshar-Oromieh A, et al. Deep neural network for automatic characterization of lesions on 68 Ga-PSMA-11 PET/CT. Eur J Nucl Med Mol Imaging. 2020;47:603–13.
Stefaniak B, Cholewiński W, Tarkowska A. Application of artificial neural network algorithm to detection of parathyroid adenoma. Nuclear medicine review. Cent East Eur. 2003;6:111–7.
Bilezikian JP, Brandi ML, Eastell R, Silverberg SJ, Udelsman R, Marcocci C, et al. Guidelines for the management of asymptomatic primary hyperparathyroidism: summary statement from the Fourth International Workshop. J Clin Endocrinol Metab. 2014;99:3561–9.
Lin TY, Goyal P, Girshick R, He K, Dollar P. Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell. 2020;42:318–27.
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–8.
Lin T, Dollár P, Girshick R, He K, Hariharan B, Belongie S. Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 936–44.
Bunch PC, Hamilton JF, Sanderson GK, Simmons AH. Free response approach to measurement and characterization of radiographic observer performance. AJR Am J Roentgenol. 1978;130:382.
R Core Team. R: A language and environment for statistical computing. 2013. http://www.R-project.org/. Accessed 12 Mar 2021.
Kunstman JW, Kirsch JD, Mahajan A, Udelsman R. Clinical review: parathyroid localization and implications for clinical management. J Clin Endocrinol Metab. 2013;98:902–12.
Coakley AJ, Kettle AG, Wells CP, O’Doherty MJ, Collins RE. 99Tcm sestamibi–a new agent for parathyroid imaging. Nucl Med Commun. 1989;10:791–4.
Silverberg SJ, Shane E, Jacobs TP, Siris E, Bilezikian JP. A 10-year prospective study of primary hyperparathyroidism with or without parathyroid surgery. N Engl J Med. 1999;341:1249–55.
Acknowledgements
This manuscript has been proofread by Mrs. Shannon L. Walston.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Yoshida, A., Ueda, D., Higashiyama, S. et al. Deep learning-based detection of parathyroid adenoma by 99mTc-MIBI scintigraphy in patients with primary hyperparathyroidism. Ann Nucl Med 36, 468–478 (2022). https://doi.org/10.1007/s12149-022-01726-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12149-022-01726-8