Abstract
Purpose
This study aims to develop a 2.5-dimensional (2.5D) deep-learning, object detection model for the automated detection of brain metastases, into which three consecutive slices were fed as the input for the prediction in the central slice, and to compare its performance with that of an ordinary 2-dimensional (2D) model.
Methods
We analyzed 696 brain metastases on 127 contrast-enhanced computed tomography (CT) scans from 127 patients with brain metastases. The scans were randomly divided into training (n = 79), validation (n = 18), and test (n = 30) datasets. Single-shot detector (SSD) models with a feature fusion module were constructed, trained, and compared using the lesion-based sensitivity, positive predictive value (PPV), and the number of false positives per patient at a confidence threshold of 50%.
Results
The 2.5D SSD model had a significantly higher PPV (t test, p < 0.001) and a significantly smaller number of false positives (t test, p < 0.001). The sensitivities of the 2D and 2.5D models were 88.1% (95% confidence interval [CI], 86.6–89.6%) and 88.7% (95% CI, 87.3–90.1%), respectively. The corresponding PPVs were 39.0% (95% CI, 36.5–41.4%) and 58.9% (95% CI, 55.2–62.7%), respectively. The numbers of false positives per patient were 11.9 (95% CI, 10.7–13.2) and 4.9 (95% CI, 4.2–5.7), respectively.
Conclusion
Our results indicate that 2.5D deep-learning, object detection models, which use information about the continuity between adjacent slices, may reduce false positives and improve the performance of automated detection of brain metastases compared with ordinary 2D models.
Similar content being viewed by others
References
Achrol AS, Rennert RC, Anders C, Soffietti R, Ahluwalia MS, Nayak L et al (2019) Brain metastases Nat Rev Dis Primers 5:5
Pope WB (2018) Brain metastases: neuroimaging. Handb Clin Neurol 149:89–112
Losch M (2015) Detection and segmentation of brain metastases with deep convolutional networks. http://kth.divaportal.org/smash/record.jsf?pid=diva2%3A853460&dswid=-6718. Accessed 24 June 2021
Noguchi T, Uchiyama F, Kawata Y, Machitori A, Shida Y, Okafuji T et al (2020) A fundamental study assessing the diagnostic performance of deep learning for a brain metastasis detection task. Magn Reson Med Sci 19:184–194
Han C, Murao K, Noguchi T, Kawata Y, Uchiyama F, Rundo L et al (2019) Learning more with less: conditional PGGAN-based data augmentation for brain metastases detection using highly-rough annotation on MR images. Proceedings of the 28th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, Beijing, China, pp 119–127
Zhang M, Young GS, Chen H, Li J, Qin L, McFaline-Figueroa JR et al (2020) Deep-learning detection of cancer metastases to the brain on MRI. J Magn Reson Imaging 52:1227–1236
Zhou Z, Sanders JW, Johnson JM, Gule-Monroe MK, Chen MM, Briere TM et al (2020) Computer-aided detection of brain metastases in T1-weighted MRI for stereotactic radiosurgery using deep learning single-shot detectors. Radiology 295:407–415
Amemiya S, Takao H, Kato S, Yamashita H, Sakamoto N, Abe O (2021) Automatic detection of brain metastases on contrast-enhanced CT with deep-learning feature-fused single-shot detectors. Eur J Radiol 136:109577
Yoo Y, Ceccaldi P, Liu S, Re TJ, Cao Y, Balter JM et al (2021) Evaluating deep learning methods in detecting and segmenting different sizes of brain metastases on 3D post-contrast T1-weighted images. J Med Imaging (Bellingham) 8:037001
Kato S, Amemiya S, Takao H, Yamashita H, Sakamoto N, Abe O (2021) Automated detection of brain metastases on non-enhanced CT using single-shot detectors. Neuroradiology 63:1995–2004
Amemiya S, Takao H, Kato S, Yamashita H, Sakamoto N, Abe O (2021) Feature-fusion improves MRI single-shot deep learning detection of small brain metastases. J Neuroimaging. https://doi.org/10.1111/jon.12916
Takao H, Amemiya S, Kato S, Yamashita H, Sakamoto N, Abe O (2021) Deep-learning single-shot detector for automatic detection of brain metastases with the combined use of contrast-enhanced and non-enhanced computed tomography images. Eur J Radiol 144:110015
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 95:43–54
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 51:175–182
Cao Y, Vassantachart A, Ye JC, Yu C, Ruan D, Sheng K et al (2021) Automatic detection and segmentation of multiple brain metastases on magnetic resonance image using asymmetric UNet architecture. Phys Med Biol 66:015003
Pennig L, Shahzad R, Caldeira L, Lennartz S, Thiele F, Goertz L et al (2021) Automated detection and segmentation of brain metastases in malignant melanoma: evaluation of a dedicated deep learning model. AJNR Am J Neuroradiol 42:655–662
Park YW, Jun Y, Lee Y, Han K, An C, Ahn SS et al (2021) Robust performance of deep learning for automatic detection and segmentation of brain metastases using three-dimensional black-blood and three-dimensional gradient echo imaging. Eur Radiol. https://doi.org/10.1007/s00330-021-07783-3
Jünger ST, Hoyer UCI, Schaufler D, Laukamp KR, Goertz L, Thiele F et al (2021) Fully automated MR detection and segmentation of brain metastases in non-small cell lung cancer using deep learning. J Magn Reson Imaging. https://doi.org/10.1002/jmri.27741
Rudie JD, Weiss DA, Colby JB, Rauschecker AM, Laguna B, Braunstein S et al (2021) Three-dimensional U-net convolutional neural network for detection and segmentation of intracranial metastases. Radiol Artif Intell 3:e200204
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y et al (2015) SSD: single shot multibox detector. https://arxiv.org/abs/1512.02325. Accessed 24 June 2021
Cao G, Xie X, Yang W, Liao Q, Shi G, Wu J (2017) Feature-fused SSD: fast detection for small objects. https://arxiv.org/abs/1709.05054. Accessed 24 June 2021
Ashburner J, Friston KJ (2005) Unified segmentation. Neuroimage 26:839–851
Girshick R, Donahue J, Darrell T, Malik J (2013) Rich feature hierarchies for accurate object detection and semantic segmentation. https://arxiv.org/abs/1311.2524. Accessed 24 August 2021
Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. https://arxiv.org/abs/1506.01497. Accessed 24 August 2021
Redmon J, Divvala S, Girshick R, Farhadi A (2015) You only look once: unified, real-time object detection. https://arxiv.org/abs/1506.02640. Accessed 24 August 2021
Tian Z, Shen C, Chen H, He T (2019) FCOS: fully convolutional one-stage object detection. https://arxiv.org/abs/1904.01355. Accessed 24 August 2021
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval
This retrospective study was approved by our institutional ethics committee.
Consent to participate
The need for written informed consent was waived because of the retrospective nature of the study.
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.
Rights and permissions
About this article
Cite this article
Takao, H., Amemiya, S., Kato, S. et al. Deep-learning 2.5-dimensional single-shot detector improves the performance of automated detection of brain metastases on contrast-enhanced CT. Neuroradiology 64, 1511–1518 (2022). https://doi.org/10.1007/s00234-022-02902-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00234-022-02902-3