Abstract
Purpose
Spinal bone metastases directly affect quality of life, and patients with lytic-dominant lesions are at high risk for neurological symptoms and fractures. To detect and classify lytic spinal bone metastasis using routine computed tomography (CT) scans, we developed a deep learning (DL)-based computer-aided detection (CAD) system.
Methods
We retrospectively analyzed 2125 diagnostic and radiotherapeutic CT images of 79 patients. Images annotated as tumor (positive) or not (negative) were randomized into training (1782 images) and test (343 images) datasets. YOLOv5m architecture was used to detect vertebra on whole CT scans. InceptionV3 architecture with the transfer-learning technique was used to classify the presence/absence of lytic lesions on CT images showing the presence of vertebra. The DL models were evaluated via fivefold cross-validation. For vertebra detection, bounding box accuracy was estimated using intersection over union (IoU). We evaluated the area under the curve (AUC) of a receiver operating characteristic curve to classify lesions. Moreover, we determined the accuracy, precision, recall, and F1 score. We used the gradient-weighted class activation mapping (Grad-CAM) technique for visual interpretation.
Results
The computation time was 0.44 s per image. The average IoU value of the predicted vertebra was 0.923 ± 0.052 (0.684–1.000) for test datasets. In the binary classification task, the accuracy, precision, recall, F1-score, and AUC value for test datasets were 0.872, 0.948, 0.741, 0.832, and 0.941, respectively. Heat maps constructed using the Grad-CAM technique were consistent with the location of lytic lesions.
Conclusion
Our artificial intelligence-aided CAD system using two DL models could rapidly identify vertebra bone from whole CT images and detect lytic spinal bone metastasis, although further evaluation of diagnostic accuracy is required with a larger sample size.
Similar content being viewed by others
References
Nguyen QN, Chun SG, Chow E, Komaki R, Liao Z, Zacharia R, Szeto BK, Welsh JW, Hahn SM, Fuller CD, Moon BS, Bird JE, Satcher R, Lin PP, Jeter M, O’Reilly MS, Lewis VO (2019) Single-fraction stereotactic vs conventional multifraction radiotherapy for pain relief in patients with predominantly nonspine bone metastases: a randomized phase 2 trial. JAMA Oncol 5(6):872–878
Gerszten PC, Burton SA, Ozhasoglu C, Welch WC (2007) Radiosurgery for spinal metastases: clinical experience in 500 cases from a single institution. Spine (Phila Pa 1976) 32(2):193–199
Myrehaug S, Sahgal A, Hayashi M, Levivier M, Ma L, Martinez R, Paddick I, Regis J, Ryu S, Slotman B, De Salles A (2017) Reirradiation spine stereotactic body radiation therapy for spinal metastases: systematic review. J Neurosurg Spine 27(4):428–435
Sahgal A, Myrehaug SD, Siva S, Masucci L, Foote MC, Brundage M, Butler J, Chow E, Fehlings MG, Gabos Z, Greenspoon J, Kerba M, Lee YK, Liu MC, Maralani P, Thibault I, Wong R, Hum M, Ding K, Parulekar W (2020) CCTG SC.24/TROG 17.06: a randomized phase II/III study comparing 24Gy in 2 stereotactic body radiotherapy (sbrt) fractions versus 20Gy in 5 conventional palliative radiotherapy (CRT) fractions for patients with painful spinal metastases. Int J Radiat Oncol Biol Phys 108(5):1397–1398
Hirai T, Shinoda Y, Tateishi R, Asaoka Y, Uchino K, Wake T, Kobayashi H, Ikegami M, Sawada R, Haga N, Koike K, Tanaka S (2019) Early detection of bone metastases of hepatocellular carcinoma reduces bone fracture and paralysis. Jpn J Clin Oncol 49(6):529–536
Qu X, Huang X, Yan W, Wu L, Dai K (2012) A meta-analysis of 18FDG-PET-CT, 18FDG-PET, MRI and bone scintigraphy for diagnosis of bone metastases in patients with lung cancer. Eur J Radiol 81(5):1007–1015
Takenaka D, Ohno Y, Matsumoto K, Aoyama N, Onishi Y, Koyama H, Nogami M, Yoshikawa T, Matsumoto S, Sugimura K (2009) Detection of bone metastases in non-small cell lung cancer patients: comparison of whole-body diffusion-weighted imaging (DWI), whole-body MR imaging without and with DWI, whole-body FDG-PET/CT, and bone scintigraphy. J Magn Reson Imaging 30(2):298–308
Burns JE, Yao J, Wiese TS, Muñoz HE, Jones EC, Summers RM (2013) Automated detection of sclerotic metastases in the thoracolumbar spine at CT. Radiology 268(1):69–78
Mercadante S (1997) Malignant bone pain: pathophysiology and treatment. Pain 69(1–2):1–18
Rubens RD (1998) Bone metastases–the clinical problem. Eur J Cancer 34(2):210–213
Sakamoto R, Yakami M, Fujimoto K, Nakagomi K, Kubo T, Emoto Y, Akasaka T, Aoyama G, Yamamoto H, Miller MI, Mori S, Togashi K (2017) Temporal subtraction of serial CT images with large deformation diffeomorphic metric mapping in the identification of bone metastases. Radiology 285(2):629–639
Horger M, Ditt H, Liao S, Weisel K, Fritz J, Thaiss WM, Kaufmann S, Nikolaou K, Kloth C (2017) Automated “Bone Subtraction” image analysis software package for improved and faster CT monitoring of longitudinal spine involvement in patients with multiple myeloma. Acad Radiol 24(5):623–632
Ueno M, Aoki T, Murakami S, Kim H, Terasawa T, Fujisaki A, Hayashida Y, Korogi Y (2018) CT temporal subtraction method for detection of sclerotic bone metastasis in the thoracolumbar spine. Eur J Radiol 107:54–59
O’Connor SD, Yao J, Summers RM (2007) Lytic metastases in thoracolumbar spine: computer-aided detection at CT–preliminary study. Radiology 242(3):811–816
Hammon M, Dankerl P, Tsymbal A, Wels M, Kelm M, May M, Suehling M, Uder M, Cavallaro A (2013) Automatic detection of lytic and blastic thoracolumbar spine metastases on computed tomography. Eur Radiol 23(7):1862–1870
Sahgal A, Myrehaug SD, Siva S, Masucci GL, Maralani PJ, Brundage M, Butler J, Chow E, Fehlings MG, Foote M, Gabos Z, Greenspoon J, Kerba M, Lee Y, Liu M, Liu SK, Thibault I, Wong RK, Hum M, Ding K, Parulekar WR, Trial investigators (2021) Stereotactic body radiotherapy versus conventional external beam radiotherapy in patients with painful spinal metastases: an open-label, multicentre, randomised, controlled, phase 2/3 trial. Lancet Oncol 22(7):1023–1033
Zhu X, Lyu S, Wang X, Zhao Q (2021) TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. 2021 IEEE/CVF international conference on computer vision workshops (ICCVW). 2778–2788
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You Only Look Once: unified, real-time object detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 779–788
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 2818–2826
Deng J, Dong W, Socher R, Li LJ, Kai L, Li F-F (2009) ImageNet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248–255
Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-CAM: visual explanations from deep networks via gradient-based localization. In: 2017 IEEE international conference on computer vision (ICCV), pp 618–626
Harada GK, Siyaji ZK, Mallow GM, Hornung AL, Hassan F, Basques BA, Mohammed HA, Sayari AJ, Samartzis D, An HS (2021) Artificial intelligence predicts disk re-herniation following lumbar microdiscectomy: development of the “RAD” risk profile. Eur Spine J 30(8):2167–2175
Hornung AL, Hornung CM, Mallow GM, Barajas JN, Rush A 3rd, Sayari AJ, Galbusera F, Wilke HJ, Colman M, Phillips FM, An HS, Samartzis D (2022) Artificial intelligence in spine care: current applications and future utility. Eur Spine J 31(8):2057–2081
Liu Y, Yang P, Pi Y, Jiang L, Zhong X, Cheng J, Xiang Y, Wei J, Li L, Yi Z, Cai H, Zhao Z (2021) Automatic identification of suspicious bone metastatic lesions in bone scintigraphy using convolutional neural network. BMC Med Imaging 21(1):131
Zhao Z, Pi Y, Jiang L, Xiang Y, Wei J, Yang P, Zhang W, Zhong X, Zhou K, Li Y, Li L, Yi Z, Cai H (2020) Deep neural network based artificial intelligence assisted diagnosis of bone scintigraphy for cancer bone metastasis. Sci Rep 10(1):17046
Chiu JS, Wang YF, Su YC, Wei LH, Liao JG, Li YC (2009) Artificial neural network to predict skeletal metastasis in patients with prostate cancer. J Med Syst 33(2):91–100
Noguchi S, Nishio M, Sakamoto R, Yakami M, Fujimoto K, Emoto Y, Kubo T, Iizuka Y, Nakagomi K, Miyasa K, Satoh K, Nakamoto Y (2022) Deep learning-based algorithm improved radiologists’ performance in bone metastases detection on CT. Eur Radiol 32(11):7976–7987
Hornung AL, Hornung CM, Mallow GM, Barajas JN, Espinoza Orias AA, Galbusera F, Wilke HJ, Colman M, Phillips FM, An HS, Samartzis D (2022) Artificial intelligence and spine imaging: limitations, regulatory issues and future direction. Eur Spine J 31(8):2007–2021
Funding
This work was supported by the Japan Society for the Promotion of Science KAKENHI [Grant Number 20K16742].
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
This study was approved by the ethical committee of Kansai Medical University (No. 2020064).
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Koike, Y., Yui, M., Nakamura, S. et al. Artificial intelligence-aided lytic spinal bone metastasis classification on CT scans. Int J CARS 18, 1867–1874 (2023). https://doi.org/10.1007/s11548-023-02880-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-023-02880-8