Top

European Radiology

Published in:

01-09-2021 | Metastasis | Magnetic Resonance

Robust performance of deep learning for automatic detection and segmentation of brain metastases using three-dimensional black-blood and three-dimensional gradient echo imaging

Authors: Yae Won Park, Yohan Jun, Yangho Lee, Kyunghwa Han, Chansik An, Sung Soo Ahn, Dosik Hwang, Seung-Koo Lee

Published in: European Radiology | Issue 9/2021

Abstract

Objectives

To evaluate whether a deep learning (DL) model using both three-dimensional (3D) black-blood (BB) imaging and 3D gradient echo (GRE) imaging may improve the detection and segmentation performance of brain metastases compared to that using only 3D GRE imaging.

Methods

A total of 188 patients with brain metastases (917 lesions) who underwent a brain metastasis MRI protocol including contrast-enhanced 3D BB and 3D GRE were included in the training set. DL models based on 3D U-net were constructed. The models were validated in the test set consisting of 45 patients with brain metastases (203 lesions) and 49 patients without brain metastases.

Results

The combined 3D BB and 3D GRE model yielded better performance than the 3D GRE model (sensitivities of 93.1% vs 76.8%, p < 0.001), and this effect was significantly stronger in subgroups with small metastases (p interaction < 0.001). For metastases < 3 mm, ≥ 3 mm and < 10 mm, and ≥ 10 mm, the sensitivities were 82.4%, 93.2%, and 100%, respectively. The combined 3D BB and 3D GRE model showed a false-positive per case of 0.59 in the test set. The combined 3D BB and 3D GRE model showed a Dice coefficient of 0.822, while 3D GRE model showed a lower Dice coefficient of 0.756.

Conclusions

The combined 3D BB and 3D GRE DL model may improve the detection and segmentation performance of brain metastases, especially in detecting small metastases.

Key Points

• The combined 3D BB and 3D GRE model yielded better performance for the detection of brain metastases than the 3D GRE model (p < 0.001), with sensitivities of 93.1% and 76.8%, respectively.

• The combined 3D BB and 3D GRE model showed a false-positive rate per case of 0.59 in the test set.

• The combined 3D BB and 3D GRE model showed a Dice coefficient of 0.822, while the 3D GRE model showed a lower Dice coefficient of 0.756.

Available only for authorised users

Bradley KA, Mehta MP (2004) Management of brain metastases. Semin Oncol 31(5). WB Saunders, 2004

Loeffler J, Patchell R, Sawaya R (1997) Metastatic brain cancer. Cancer 2523

Kondziolka D, Patel A, Lunsford LD, Kassam A, Flickinger JC (1999) Stereotactic radiosurgery plus whole brain radiotherapy versus radiotherapy alone for patients with multiple brain metastases. Int J Radiat Oncol Biol Phys 45:427–434CrossRef

Patchell RA, Tibbs PA, Walsh JW et al (1990) A randomized trial of surgery in the treatment of single metastases to the brain. N Engl J Med 322:494–500CrossRef

Mehta MP, Rodrigus P, Terhaard C et al (2003) Survival and neurologic outcomes in a randomized trial of motexafin gadolinium and whole-brain radiation therapy in brain metastases. J Clin Oncol 21:2529–2536CrossRef

Growcott S, Dembrey T, Patel R, Eaton D, Cameron A (2020) Inter-observer variability in target volume delineations of benign and metastatic brain tumours for stereotactic radiosurgery: results of a national quality assurance programme. Clin Oncol (R Coll Radiol) 32:13–25CrossRef

Kamnitsas K, Ledig C, Newcombe VFJ et al (2017) Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal 36:61–78CrossRef

Charron O, Lallement A, Jarnet D, Noblet V, Clavier JB, Meyer P (2018) Automatic detection and segmentation of brain metastases on multimodal MR images with a deep convolutional neural network. Comput Biol Med 95:43–54CrossRef

Grøvik E, Yi D, Iv M, Tong E, Rubin D, Zaharchuk G (2020) Deep learning enables automatic detection and segmentation of brain metastases on multisequence MRI. J Magn Reson Imaging 51:175–182CrossRef

10.

Zhang M, Young GS, Chen H et al (2020) Deep-learning detection of cancer metastases to the brain on MRI. J Magn Reson Imaging. https://doi.org/10.1002/jmri.27129

11.

Xue J, Wang B, Ming Y et al (2020) Deep learning-based detection and segmentation-assisted management of brain metastases. Neuro Oncol 22:505–514CrossRef

12.

Zhou Z, Sanders JW, Johnson JM et al (2020) Computer-aided detection of brain metastases in T1-weighted MRI for stereotactic radiosurgery using deep learning single-shot detectors. Radiology 295:407–415CrossRef

13.

Lin X, DeAngelis LM (2015) Treatment of brain metastases. J Clin Oncol 33:3475–3484CrossRef

14.

Park J, Kim J, Yoo E, Lee H, Chang J-H, Kim EY (2012) Detection of small metastatic brain tumors: comparison of 3D contrast-enhanced whole-brain black-blood imaging and MP-RAGE imaging. Invest Radiol 47:136–141CrossRef

15.

Park J, Kim EY (2010) Contrast-enhanced, three-dimensional, whole-brain, black-blood imaging: application to small brain metastases. Magn Reson Med 63:553–561CrossRef

16.

Park YW, Ahn SJ (2018) Comparison of contrast-enhanced T2 FLAIR and 3D T1 black-blood fast spin-echo for detection of leptomeningeal metastases. Investig Magn Reson Imaging 22:86–93CrossRef

17.

Suh CH, Jung SC, Kim KW, Pyo J (2016) The detectability of brain metastases using contrast-enhanced spin-echo or gradient-echo images: a systematic review and meta-analysis. J Neurooncol 129:363–371CrossRef

18.

Kaufmann TJ, Smits M, Boxerman J et al (2020) Consensus recommendations for a standardized brain tumor imaging protocol for clinical trials in brain metastases. Neuro Oncol 22:757–772CrossRef

19.

Roy S, Butman JA, Pham DL (2017) Robust skull stripping using multiple MR image contrasts insensitive to pathology. Neuroimage 146:132–147CrossRef

20.

Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. International conference on medical image computing and computer-assisted intervention. Springer, Cham

21.

Myronenko A (2018) 3D MRI brain tumor segmentation using autoencoder regularization. International MICCAI Brain Lesion Workshop. Springer, Cham

22.

Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. Proc icml 3(1)

23.

Wu Y, He K (2018) Group normalization. Proceedings of the European conference on computer vision (ECCV)

24.

Abadi M, Barham P, Chen J et al (2016) TensorFlow: a system for large-scale machine learning. 12th {USENIX} symposium on operating systems design and implementation ({OSDI} 16)

25.

Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:14126980 22

26.

Zeger SL, Liang KY, Albert PS (1988) Models for longitudinal data: a generalized estimating equation approach. Biometrics 44:1049–1060CrossRef

27.

Consul P, Famoye F (1992) Generalized Poisson regression model. Commun Stat Theory Methods 21:89–109CrossRef

28.

Lin NU, Lee EQ, Aoyama H et al (2015) Response assessment criteria for brain metastases: proposal from the RANO group. Lancet Oncol 16:e270–e278CrossRef

29.

Sunwoo L, Kim YJ, Choi SH et al (2017) Computer-aided detection of brain metastasis on 3D MR imaging: observer performance study. PLoS One 12:e0178265CrossRef

30.

Chang K, Beers AL, Bai HX et al (2019) Automatic assessment of glioma burden: a deep learning algorithm for fully automated volumetric and bidimensional measurement. Neuro Oncol 21:1412–1422CrossRef

31.

Kickingereder P, Isensee F, Tursunova I et al (2019) Automated quantitative tumour response assessment of MRI in neuro-oncology with artificial neural networks: a multicentre, retrospective study. Lancet Oncol 20:728–740CrossRef

32.

Bakas S, Reyes M, Jakab A et al (2018) Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge. arXiv preprint arXiv:181102629

33.

Weninger L, Rippel O, Koppers S, Merhof D (2018) Segmentation of brain tumors and patient survival prediction: methods for the BraTS 2018 challenge. International MICCAI Brain Lesion Workshop. Springer, Cham

34.

Park YW, Han K, Ahn SS et al (2018) Prediction of IDH1-mutation and 1p/19q-codeletion status using preoperative MR imaging phenotypes in lower grade gliomas. AJNR Am J Neuroradiol 39:37–42CrossRef

35.

Anzalone N, Essig M, Lee SK et al (2013) Optimizing contrast-enhanced magnetic resonance imaging characterization of brain metastases: relevance to stereotactic radiosurgery. Neurosurgery 72:691–701CrossRef

36.

Nagao E, Yoshiura T, Hiwatashi A et al (2011) 3D turbo spin-echo sequence with motion-sensitized driven-equilibrium preparation for detection of brain metastases on 3T MR imaging. AJNR Am J Neuroradiol 32:664–670CrossRef

37.

Kato Y, Higano S, Tamura H et al (2009) Usefulness of contrast-enhanced T1-weighted sampling perfection with application-optimized contrasts by using different flip angle evolutions in detection of small brain metastasis at 3T MR imaging: comparison with magnetization-prepared rapid acquisition of gradient echo imaging. AJNR Am J Neuroradiol 30:923–929CrossRef

38.

Woo I, Lee A, Jung SC et al (2019) Fully automatic segmentation of acute ischemic lesions on diffusion-weighted imaging using convolutional neural networks: comparison with conventional algorithms. Korean J Radiol 20:1275–1284CrossRef

39.

Xue Y, Farhat FG, Boukrina O et al (2020) A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images. Neuroimage Clin 25:102118CrossRef

40.

Cagney DN, Martin AM, Catalano PJ et al (2017) Incidence and prognosis of patients with brain metastases at diagnosis of systemic malignancy: a population-based study. Neuro Oncol 19:1511–1521CrossRef

41.

Jun Y, Eo T, Kim T et al (2018) Deep-learned 3D black-blood imaging using automatic labelling technique and 3D convolutional neural networks for detecting metastatic brain tumors. Sci Rep 8:1–11

Title: Robust performance of deep learning for automatic detection and segmentation of brain metastases using three-dimensional black-blood and three-dimensional gradient echo imaging
Authors: Yae Won Park
Yohan Jun
Yangho Lee
Kyunghwa Han
Chansik An
Sung Soo Ahn
Dosik Hwang
Seung-Koo Lee
Publication date: 01-09-2021
Publisher: Springer Berlin Heidelberg
Keyword: Metastasis
Published in: European Radiology / Issue 9/2021
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-021-07783-3

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Robust performance of deep learning for automatic detection and segmentation of brain metastases using three-dimensional black-blood and three-dimensional gradient echo imaging

Abstract

Objectives

Methods

Results

Conclusions

Key Points

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Objectives

Methods

Results

Conclusions

Key Points

Please log in to get access to this content

Other articles of this Issue 9/2021

Machine learning–based MRI texture analysis to predict occult lymph node metastasis in early-stage oral tongue squamous cell carcinoma

The validity, reliability, and reviewer acceptance of VI-RADS in assessing muscle invasion by bladder cancer: a multicenter prospective study

Targetoid appearance on T2-weighted imaging and signs of tumor vascular involvement: diagnostic value for differentiating HCC from other primary liver carcinomas

Low keV portal venous phase as a surrogate for pancreatic phase in a pancreatic protocol dual-energy CT: feasibility, image quality, and lesion conspicuity

Reduced-iodine-dose dual-energy coronary CT angiography: qualitative and quantitative comparison between virtual monochromatic and polychromatic CT images

Quantitative assessment of HCC wash-out on CT is a predictor of early complete response to TACE