Top

Published in:

01-12-2021 | Metastasis | Original research

Preliminary study of AI-assisted diagnosis using FDG-PET/CT for axillary lymph node metastasis in patients with breast cancer

Authors: Zongyao Li, Kazuhiro Kitajima, Kenji Hirata, Ren Togo, Junki Takenaka, Yasuo Miyoshi, Kohsuke Kudo, Takahiro Ogawa, Miki Haseyama

Published in: EJNMMI Research | Issue 1/2021

Abstract

Background

To improve the diagnostic accuracy of axillary lymph node (LN) metastasis in breast cancer patients using 2-[¹⁸F]FDG-PET/CT, we constructed an artificial intelligence (AI)-assisted diagnosis system that uses deep-learning technologies.

Materials and methods

Two clinicians and the new AI system retrospectively analyzed and diagnosed 414 axillae of 407 patients with biopsy-proven breast cancer who had undergone 2-[¹⁸F]FDG-PET/CT before a mastectomy or breast-conserving surgery with a sentinel lymph node (LN) biopsy and/or axillary LN dissection. We designed and trained a deep 3D convolutional neural network (CNN) as the AI model. The diagnoses from the clinicians were blended with the diagnoses from the AI model to improve the diagnostic accuracy.

Results

Although the AI model did not outperform the clinicians, the diagnostic accuracies of the clinicians were considerably improved by collaborating with the AI model: the two clinicians' sensitivities of 59.8% and 57.4% increased to 68.6% and 64.2%, respectively, whereas the clinicians' specificities of 99.0% and 99.5% remained unchanged.

Conclusions

It is expected that AI using deep-learning technologies will be useful in diagnosing axillary LN metastasis using 2-[¹⁸F]FDG-PET/CT. Even if the diagnostic performance of AI is not better than that of clinicians, taking AI diagnoses into consideration may positively impact the overall diagnostic accuracy.

Available only for authorised users

Siegel RL, Miller KD, Jemal A. Cancer statistics, 2019. CA Cancer J Clin. 2019;69:7–34. https://doi.org/10.3322/caac.21551.CrossRefPubMed

Arriagada R, Le NG, Dunant A, Tubiana M, Contesso G. Twenty-five years of follow-up in patients with operable breast carcinoma: correlation between clinicopathologic factors and the risk of death in each 5-year period. Cancer. 2006;106:743–50. https://doi.org/10.1002/cncr.21659.CrossRefPubMed

Heusner TA, Kuemmel S, Hahn S, Koeninger A, Otterbach F, Hamami ME, et al. Diagnostic value of full-dose FDG PET/CT for axillary lymph node staging in breast cancer patients. Eur J Nucl Med Mol Imaging. 2009;36:1543–50. https://doi.org/10.1007/s00259-009-1145-6.CrossRefPubMed

Riegger C, Koeninger A, Hartung V, Otterbach F, Kimmig R, Forsting M, et al. Comparison of the diagnostic value of FDG-PET/CT and axillary ultrasound for the detection of lymph node metastases in breast cancer patients. Acta Radiol. 2012;53:1092–8. https://doi.org/10.1258/ar.2012.110635.CrossRefPubMed

Liang X, Yu J, Wen B, Xie J, Cai Q, Yang Q. MRI and FDG-PET/CT based assessment of axillary lymph node metastasis in early breast cancer: a meta-analysis. Clin Radiol. 2017;72:295–301. https://doi.org/10.1016/j.crad.2016.12.001.CrossRefPubMed

Song, Bong-Il, Hae Won Kim, and Kyoung Sook Won. Predictive value of 18 F-FDG PET/CT for axillary lymph node metastasis in invasive ductal breast cancer. Ann Surg Oncol 2017;24:2174–81. doi: https://doi.org/10.1245/s10434-017-5860-0.

Peare R, Staff RT, Heys SD. The use of FDG-PET in assessing axillary lymph node status in breast cancer: a systematic review and meta-analysis of the literature. Breast Cancer Res Treat. 2010;123:281–90. https://doi.org/10.1007/s10549-010-0771-9.CrossRefPubMed

Robertson IJ, Hand F, Kell MR. FDG-PET/CT in the staging of local/regional metastases in breast cancer. The Breast. 2011;20:491–4. https://doi.org/10.1016/j.breast.2011.07.002.CrossRefPubMed

Kitajima K, Fukushima K, Miyoshi Y, Katsuura T, Igarashi Y, Kawanaka Y, et al. Diagnostic and prognostic value of 18 F-FDG PET/CT for axillary lymph node staging in patients with breast cancer. Jpn J Radiol. 2016;34:220–8. https://doi.org/10.1007/s11604-015-0515-1.CrossRefPubMed

10.

Litjens G, Kooi T, Bejnord BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;4:60–88. https://doi.org/10.1016/j.media.2017.07.005.CrossRef

11.

Wang H, Zhou Z, Li Y, Chen Z, Lu P, Wang W, et al. Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18 F-FDG PET/CT images. EJNMMI Res. 2017;7:11. https://doi.org/10.1186/s13550-017-0260-9.CrossRefPubMedPubMedCentral

12.

Wahl RL, Siegel BA, Coleman RE, Gatsonis CG. Prospective multicenter study of axillary nodal staging by positron emission tomography in breast cancer: a report of the staging breast cancer with PET Study Group. J Clin Oncol. 2004;22:277–85.CrossRefPubMed

13.

Ueda S, Tsuda H, Asakawa H, Omata J, Fukatsu K, Kondo N, et al. Utility of 18F-fluoro-deoxyglucose emission tomography/computed tomography fusion imaging (18F-FDG PET/CT) in combination with ultrasonography for axillary staging in primary breast cancer. BMC Cancer. 2007;8:165. https://doi.org/10.1186/1471-2407-8-165.CrossRef

14.

Shen D, Wu G, Suk H-I. Deep learning in medical image analysis. Annu Rev Biomed Eng. 2017;19:221–48. https://doi.org/10.1146/annurev-bioeng-071516-044442.CrossRefPubMedPubMedCentral

15.

He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). doi: https://doi.org/10.1109/CVPR.2016.90.

16.

Fukui H, Hirakawa T, Yamashita T, Fujiyoshi H. Attention branch network: Learning of attention mechanism for visual explanation. In: 2019 proceedings of the IEEE conference on computer vision and pattern recognition. 2019. https://arxiv.org/abs/1812.10025.

17.

Asan O, Bayrak AE, Choudhury A. Artificial intelligence and human trust in healthcare: focus on clinicians. J Med Internet Res. 2020;22(6):e15154. https://doi.org/10.2196/15154.CrossRefPubMedPubMedCentral

18.

Maddox TM, Rumsfeld JS, Payne PRO. Questions for artificial intelligence in health care. JAMA. 2019;321(1):31–2. https://doi.org/10.1001/jama.2018.18932.CrossRefPubMed

19.

Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2(4):230–43. https://doi.org/10.1136/svn-2017-000101.CrossRefPubMedPubMedCentral

20.

Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A. Learning deep features for discriminative localization. In: 2016 proceedings of the IEEE conference on computer vision and pattern recognition. 2016. https://arxiv.org/abs/1512.04150.

21.

Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vis. 2020;128:336–59. https://doi.org/10.1007/s11263-019-01228-7.CrossRef

Title: Preliminary study of AI-assisted diagnosis using FDG-PET/CT for axillary lymph node metastasis in patients with breast cancer
Authors: Zongyao Li
Kazuhiro Kitajima
Kenji Hirata
Ren Togo
Junki Takenaka
Yasuo Miyoshi
Kohsuke Kudo
Takahiro Ogawa
Miki Haseyama
Publication date: 01-12-2021
Publisher: Springer Berlin Heidelberg
Keywords: Metastasis
Breast Cancer
Artificial Intelligence
Breast Cancer
Published in: EJNMMI Research / Issue 1/2021
Electronic ISSN: 2191-219X
DOI: https://doi.org/10.1186/s13550-021-00751-4

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Preliminary study of AI-assisted diagnosis using FDG-PET/CT for axillary lymph node metastasis in patients with breast cancer

Abstract

Background

Materials and methods

Results

Conclusions

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Abstract

Background

Materials and methods

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 1/2021

Quantitative SPECT/CT parameters of myocardial 99mTechnetium-3,3-diphosphono-1,2-propanodicarboxylic acid (DPD) uptake in suspected cardiac transthyretin amyloidosis

A dual-time-window protocol to reduce acquisition time of dynamic tau PET imaging using [18F]MK-6240

Impact of contouring methods on pre-treatment and post-treatment dosimetry for the prediction of tumor control and survival in HCC patients treated with selective internal radiation therapy

Investigation of atovaquone-induced spatial changes in tumour hypoxia assessed by hypoxia PET/CT in non-small cell lung cancer patients

Comparison of [18F] NaF PET/CT dynamic analysis methods and a static analysis method including derivation of a semi-population input function for site-specific measurements of bone formation in a population with chronic kidney disease-mineral and bone disorder

Performance of nanoScan PET/CT and PET/MR for quantitative imaging of 18F and 89Zr as compared with ex vivo biodistribution in tumor-bearing mice