Skip to main content

Advertisement

SpringerLink
Log in

Automated detection and segmentation of sclerotic spinal lesions on body CTs using a deep convolutional neural network

  • Scientific Article
  • Published:
Skeletal Radiology Aims and scope Submit manuscript

Abstract

Purpose

To develop a deep convolutional neural network capable of detecting spinal sclerotic metastases on body CTs.

Materials and methods

Our study was IRB-approved and HIPAA-compliant. Cases of confirmed sclerotic bone metastases in chest, abdomen, and pelvis CTs were identified. Images were manually segmented for 3 classes: background, normal bone, and sclerotic lesion(s). If multiple lesions were present on a slice, all lesions were segmented. A total of 600 images were obtained, with a 90/10 training/testing split. Images were stored as 128 × 128 pixel grayscale and the training dataset underwent a processing pipeline of histogram equalization and data augmentation. We trained our model from scratch on Keras/TensorFlow using an 80/20 training/validation split and a U-Net architecture (64 batch size, 100 epochs, dropout 0.25, initial learning rate 0.0001, sigmoid activation). We also tested our model’s true negative and false positive rate with 1104 non-pathologic images. Global sensitivity measured model detection of any lesion on a single image, local sensitivity and positive predictive value (PPV) measured model detection of each lesion on a given image, and local specificity measured the false positive rate in non-pathologic bone.

Results

Dice scores were 0.83 for lesion, 0.96 for non-pathologic bone, and 0.99 for background. Global sensitivity was 95% (57/60), local sensitivity was 92% (89/97), local PPV was 97% (89/92), and local specificity was 87% (958/1104).

Conclusion

A deep convolutional neural network has the potential to assist in detecting sclerotic spinal metastases.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Coleman RE. Clinical features of metastatic bone disease and risk of skeletal morbidity. Clin Cancer Res Off J Am Assoc Cancer Res. 2006;12(20 Pt 2):6243s-s6249.

    Article  Google Scholar 

  2. Li S, Peng Y, Weinhandl ED, Blaes AH, Cetin K, Chia VM, et al. Estimated number of prevalent cases of metastatic bone disease in the US adult population. Clin Epidemiol. 2012;4:87–93.

    PubMed  PubMed Central  Google Scholar 

  3. Burns JE, Yao J, Wiese TS, Muñoz HE, Jones EC, Summers RM. Automated detection of sclerotic metastases in the thoracolumbar spine at CT. Radiology. 2013;268(1):69–78.

    Article  Google Scholar 

  4. Söderlund V. Radiological diagnosis of skeletal metastases. Eur Radiol. 1996;6(5):587–95.

    Article  Google Scholar 

  5. Clemons M, Gelmon KA, Pritchard KI, Paterson AHG. Bone-targeted agents and skeletal-related events in breast cancer patients with bone metastases: the state of the art. Curr Oncol Tor Ont. 2012;19(5):259–68.

    Article  CAS  Google Scholar 

  6. Hamaoka T, Madewell JE, Podoloff DA, Hortobagyi GN, Ueno NT. Bone imaging in metastatic breast cancer. J Clin Oncol Off J Am Soc Clin Oncol. 2004;22(14):2942–53.

    Article  Google Scholar 

  7. Chang CY, Gill CM, Joseph Simeone F, Taneja AK, Huang AJ, Torriani M, et al. Comparison of the diagnostic accuracy of 99 m-Tc-MDP bone scintigraphy and 18 F-FDG PET/CT for the detection of skeletal metastases. Acta Radiol Stockh Swed 1987. 2016;57(1):58–65.

  8. Hammon M, Dankerl P, Tsymbal A, Wels M, Kelm M, May M, et al. Automatic detection of lytic and blastic thoracolumbar spine metastases on computed tomography. Eur Radiol. 2013;23(7):1862–70.

    Article  Google Scholar 

  9. Gorelik N, Chong J, Lin DJ. Pattern recognition in musculoskeletal imaging using artificial intelligence. Semin Musculoskelet Radiol. 2020;24(1):38–49.

    Article  Google Scholar 

  10. Roth HR, Lu L, Liu J, Yao J, Seff A, Cherry K, et al. Improving computer-aided detection using convolutional neural networks and random view aggregation. IEEE Trans Med Imaging. 2016;35(5):1170–81.

    Article  Google Scholar 

  11. O’Connor SD, Yao J, Summers RM. Lytic metastases in thoracolumbar spine: computer-aided detection at CT–preliminary study. Radiology. 2007;242(3):811–6.

    Article  Google Scholar 

  12. Yao J, Burns JE, Sanoria V, Summers RM. Mixed spine metastasis detection through positron emission tomography/computed tomography synthesis and multiclassifier. J Med Imaging Bellingham Wash. 2017;4(2):024504.

    Article  Google Scholar 

  13. Chen L, Bentley P, Rueckert D. Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks. NeuroImage Clin. 2017;15:633–43.

    Article  Google Scholar 

  14. Le EPV, Wang Y, Huang Y, Hickman S, Gilbert FJ. Artificial intelligence in breast imaging. Clin Radiol. 2019;74(5):357–66.

    Article  CAS  Google Scholar 

  15. Zhou L-Q, Wang J-Y, Yu S-Y, Wu G-G, Wei Q, Deng Y-B, et al. Artificial intelligence in medical imaging of the liver. World J Gastroenterol. 2019;25(6):672–82.

    Article  Google Scholar 

  16. Orhan K, Bayrakdar IS, Ezhov M, Kravtsov A, Özyürek T. Evaluation of artificial intelligence for detecting periapical pathosis on cone-beam computed tomography scans. Int Endod J. 2020;53(5):680–9.

    Article  CAS  Google Scholar 

  17. Chen X-Z, Liu C-G, Chen Y, Wang L-Q, Zhu Q-Z, Lin P. Arthroscopy-assisted surgery for tibial plateau fractures. Arthrosc J Arthrosc Relat Surg Off Publ Arthrosc Assoc N Am Int Arthrosc Assoc. 2015;31(1):143–53.

    Article  Google Scholar 

  18. Helbren E, Fanshawe TR, Phillips P, Mallett S, Boone D, Gale A, et al. The effect of computer-aided detection markers on visual search and reader performance during concurrent reading of CT colonography. Eur Radiol. 2015;25(6):1570–8.

    Article  Google Scholar 

  19. Zhang S, Han F, Liang Z, Tan J, Cao W, Gao Y, et al. An investigation of CNN models for differentiating malignant from benign lesions using small pathologically proven datasets. Comput Med Imaging Graph Off J Comput Med Imaging Soc. 2019;77:101645.

    Article  Google Scholar 

  20. Pesce E, Joseph Withey S, Ypsilantis P-P, Bakewell R, Goh V, Montana G. Learning to detect chest radiographs containing pulmonary lesions using visual attention networks. Med Image Anal. 2019;53:26–38.

    Article  Google Scholar 

  21. Jaworek-Korjakowska J. A deep learning approach to vascular structure segmentation in dermoscopy colour images. BioMed Res Int. 2018;2018:5049390.

    Article  Google Scholar 

  22. Hemke R, Buckless CG, Tsao A, Wang B, Torriani M. Deep learning for automated segmentation of pelvic muscles, fat, and bone from CT studies for body composition assessment. Skeletal Radiol. 2020;49(3):387–95.

    Article  Google Scholar 

  23. Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention. Springer; 2015. p. 234–41.

  24. Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J. TensorFlow: a system for large-scale machine learning. OSDI; 2016. 265–83 p. Available from: usenix.org

  25. Dice L. Measure of the amount of ecologic assocation between species. Ecology. 1945;26(3):297–302.

    Article  Google Scholar 

  26. Huang S, Chang K. Automatic detection of bone metastases in vertebrae by using CT images. Paper presented at: Proceedings of the World Congress on Engineering; July 4–6, 2012; London, UK.

  27. Klein A, Warszawski J, Hillengaß J, Maier-Hein KH. Automatic bone segmentation in whole-body CT images. Int J Comput Assist Radiol Surg. 2019;14(1):21–9.

    Article  Google Scholar 

  28. Löffler MT, Sekuboyina A, Jacob A, Grau A-L, Scharr A, El Husseini M, et al. A vertebral segmentation dataset with fracture grading. Radiol Artif Intell. 2020;2(4):e190138.

    Article  Google Scholar 

  29. Jang S, Graffy PM, Ziemlewicz TJ, Lee SJ, Summers RM, Pickhardt PJ. Opportunistic osteoporosis screening at routine abdominal and thoracic CT: normative L1 trabecular attenuation values in more than 20 000 adults. Radiology. 2019;291(2):360–7.

    Article  Google Scholar 

  30. Cha KH, Hadjiiski L, Samala RK, Chan H-P, Caoili EM, Cohan RH. Urinary bladder segmentation in CT urography using deep-learning convolutional neural network and level sets. Med Phys. 2016;43(4):1882.

    Article  Google Scholar 

  31. Cuocolo R, Cipullo MB, Stanzione A, Ugga L, Romeo V, Radice L, et al. Machine learning applications in prostate cancer magnetic resonance imaging. Eur Radiol Exp. 2019;3(1):35.

    Article  Google Scholar 

  32. Chen Y, Villanueva-Meyer JE, Morrison MA, Lupo JM. Toward automatic detection of radiation-induced cerebral microbleeds using a 3D deep residual network. J Digit Imaging. 2019;32(5):766–72.

    Article  Google Scholar 

  33. Nazari-Farsani S, Nyman M, Karjalainen T, Bucci M, Isojärvi J, Nummenmaa L. Automated segmentation of acute stroke lesions using a data-driven anomaly detection on diffusion weighted MRI. J Neurosci Methods. 2020;333:108575.

    Article  Google Scholar 

  34. Hsieh Y-Z, Luo Y-C, Pan C, Su M-C, Chen C-J, Hsieh KL-C. Cerebral small vessel disease biomarkers detection on MRI-sensor-based image and deep learning. Sensors. 2019;19(11).

  35. Kamnitsas K, Ledig C, Newcombe VFJ, Simpson JP, Kane AD, Menon DK, et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal. 2017;36:61–78.

    Article  Google Scholar 

  36. Hashemi L, Webster BS, Clancy EA. Trends in disability duration and cost of workers’ compensation low back pain claims (1988–1996). J Occup Environ Med. 1998;40(12):1110–9.

    Article  CAS  Google Scholar 

  37. Yoo Y, Tang LYW, Brosch T, Li DKB, Kolind S, Vavasour I, et al. Deep learning of joint myelin and T1w MRI features in normal-appearing brain tissue to distinguish between multiple sclerosis patients and healthy controls. NeuroImage Clin. 2018;17:169–78.

    Article  Google Scholar 

  38. Wang H, Ahmed SN, Mandal M. Automated detection of focal cortical dysplasia using a deep convolutional neural network. Comput Med Imaging Graph Off J Comput Med Imaging Soc. 2020;79:101662.

    Article  Google Scholar 

  39. Nair T, Precup D, Arnold DL, Arbel T. Exploring uncertainty measures in deep networks for multiple sclerosis lesion detection and segmentation. Med Image Anal. 2020;59:101557.

    Article  Google Scholar 

  40. Alex V, Vaidhya K, Thirunavukkarasu S, Kesavadas C, Krishnamurthi G. Semisupervised learning using denoising autoencoders for brain lesion detection and segmentation. J Med Imaging Bellingham Wash. 2017;4(4):041311.

    Google Scholar 

  41. Sundaresan V, Zamboni G, Le Heron C, Rothwell PM, Husain M, Battaglini M, et al. Automated lesion segmentation with BIANCA: impact of population-level features, classification algorithm and locally adaptive thresholding. NeuroImage. 2019;202:116056.

    Article  Google Scholar 

  42. Cai S-L, Li B, Tan W-M, Niu X-J, Yu H-H, Yao L-Q, et al. Using a deep learning system in endoscopy for screening of early esophageal squamous cell carcinoma (with video). Gastrointest Endosc. 2019;90(5):745-753.e2.

    Article  Google Scholar 

  43. Zago GT, Andreão RV, Dorizzi B, TeatiniSalles EO. Diabetic retinopathy detection using red lesion localization and convolutional neural networks. Comput Biol Med. 2020;116:103537.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Division of Musculoskeletal Imaging and Intervention, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street, YAW 6, Boston, MA, 02114, USA

    Connie Y. Chang, Colleen Buckless, Kaitlyn J. Yeh & Martin Torriani

Authors
  1. Connie Y. Chang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Colleen Buckless
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kaitlyn J. Yeh
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Martin Torriani
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Connie Y. Chang.

Ethics declarations

Ethical approval

All procedures performed in studies involving human participants were carried out in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Declaration of Helsinki and its later amendments or comparable ethical standards.

Informed consent

Informed consent was waived for individual participants included in the study. The study was approved by the local Institutional Review Board (IRB) and HIPAA-compliant.

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

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chang, C.Y., Buckless, C., Yeh, K.J. et al. Automated detection and segmentation of sclerotic spinal lesions on body CTs using a deep convolutional neural network. Skeletal Radiol 51, 391–399 (2022). https://doi.org/10.1007/s00256-021-03873-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00256-021-03873-x

Keywords

Search

Navigation