Deep Learning on MRI Images for Diagnosis of Lung Cancer Spinal Bone Metastasis

Overview

Journal Contrast Media Mol Imaging

Specialty Radiology

Date 2021 Aug 6

PMID 34354553

Citations 5

Authors

Xiaojie Fan

Xiaoyu Zhang

Zibo Zhang

Yifang Jiang

Affiliations

Soon will be listed here.

Abstract

This paper aimed to explore the adoption of deep learning algorithms in lung cancer spinal bone metastasis diagnosis. Comprehensive analysis was carried out with the aid of AdaBoost algorithm and Chan-Vese (CV) algorithm. 87 patients with lung cancer spinal bone metastasis were taken as research subjects, and comprehensive evaluation was made in terms of preliminary classification of images, segmentation results, Dice index, and Jaccard coefficient. After the case of misjudgment on whether there was hot spot was excluded, the initial classification accuracy of the AdaBoost algorithm can reach 96.55%. True positive rate (TPR) was 2.3%, and false negative rate (FNR) was 1.15%. 45 MRI images with hot spots were utilized as test set to detect the segmentation accuracy of CV, maximum between-cluster variance method (OTSU), and region growing algorithm. The results showed that the Dice index and Jaccard coefficient of the CV algorithm were 0.8591 and 0.8002, respectively, which were considerably superior to OTSU (0.6125 and 0.5541) and region growing algorithm (0.7293 and 0.6598). In summary, the AdaBoost algorithm was adopted for image preliminary classification, and CV algorithm for image segmentation was ideal for the diagnosis of lung cancer spinal bone metastasis and it was worthy of clinical promotion.

Citing Articles

The Classification of Metastatic Spine Cancer and Spinal Compression Fractures by Using CNN and SVM Techniques.

Jeong W, Baek C, Lee D, Song S, Na J, Hidayat M Bioengineering (Basel). 2025; 11(12.

PMID: 39768082 PMC: 11673390. DOI: 10.3390/bioengineering11121264.

Advances in imaging modalities for spinal tumors.

Takamiya S, Malvea A, Ishaque A, Pedro K, Fehlings M Neurooncol Adv. 2024; 6(Suppl 3):iii13-iii27.

PMID: 39430391 PMC: 11485884. DOI: 10.1093/noajnl/vdae045.

Artificial Intelligence in Detection, Management, and Prognosis of Bone Metastasis: A Systematic Review.

Papalia G, Brigato P, Sisca L, Maltese G, Faiella E, Santucci D Cancers (Basel). 2024; 16(15).

PMID: 39123427 PMC: 11311270. DOI: 10.3390/cancers16152700.

Deep learning image segmentation approaches for malignant bone lesions: a systematic review and meta-analysis.

Rich J, Bhardwaj L, Shah A, Gangal K, Rapaka M, Oberai A Front Radiol. 2023; 3:1241651.

PMID: 37614529 PMC: 10442705. DOI: 10.3389/fradi.2023.1241651.

Emerging Applications of Deep Learning in Bone Tumors: Current Advances and Challenges.

Zhou X, Wang H, Feng C, Xu R, He Y, Li L Front Oncol. 2022; 12:908873.

PMID: 35928860 PMC: 9345628. DOI: 10.3389/fonc.2022.908873.

References

Miret M, Horvath-Puho E, Deruaz-Luyet A, Sorensen H, Ehrenstein V . Potential paraneoplastic syndromes and selected autoimmune conditions in patients with non-small cell lung cancer and small cell lung cancer: A population-based cohort study. PLoS One. 2017; 12(8):e0181564. PMC: 5540596. DOI: 10.1371/journal.pone.0181564. View

Zhang F, Kaufman H, Deng Y, Drabier R . Recursive SVM biomarker selection for early detection of breast cancer in peripheral blood. BMC Med Genomics. 2013; 6 Suppl 1:S4. PMC: 3552693. DOI: 10.1186/1755-8794-6-S1-S4. View

Li W, Zhao S, Liu L . [The Methods and Clinical Significance of Early Diagnosis of Lung Cancer]. Sichuan Da Xue Xue Bao Yi Xue Ban. 2017; 48(3):331-335. View

Kim J, Cai W, Feng D, Wu H . A new way for multidimensional medical data management: volume of interest (VOI)-based retrieval of medical images with visual and functional features. IEEE Trans Inf Technol Biomed. 2006; 10(3):598-607. DOI: 10.1109/titb.2006.872045. View

Hu W, Liu Z, Xiao X, Yang Y, Sun Z, Wang X . Comparison of diagnostic efficacy of MRI and PET/CT in lung cancer of mouse with spinal metastasis. Cell Mol Biol (Noisy-le-grand). 2020; 66(3):138-142. View

Chambard L, Girard N, Ollier E, Rousseau J, Duboeuf F, Carlier M . Bone, muscle, and metabolic parameters predict survival in patients with synchronous bone metastases from lung cancers. Bone. 2018; 108:202-209. DOI: 10.1016/j.bone.2018.01.004. View

Rueda J, Sola I, Pascual A, Subirana Casacuberta M . Non-invasive interventions for improving well-being and quality of life in patients with lung cancer. Cochrane Database Syst Rev. 2011; (9):CD004282. PMC: 7197367. DOI: 10.1002/14651858.CD004282.pub3. View

Sathiakumar N, Delzell E, Yun H, Jooste R, Godby K, Falkson C . Accuracy of Medicare Claim-based Algorithm to Detect Breast, Prostate, or Lung Cancer Bone Metastases. Med Care. 2017; 55(12):e144-e149. DOI: 10.1097/MLR.0000000000000539. View

Zhi X, Shi Y, Yu J . [Standards for the diagnosis and treatment of primary lung cancer (2015 version) in China]. Zhonghua Zhong Liu Za Zhi. 2015; 37(1):67-78. View

10.

Zhang C, Wang G, Han X, Ren Z, Duo J . Comparison of the therapeutic effects of surgery combined with postoperative radiotherapy and standalone radiotherapy in treating spinal metastases of lung cancer. Clin Neurol Neurosurg. 2016; 141:38-42. DOI: 10.1016/j.clineuro.2015.12.011. View

11.

Lundervold A, Lundervold A . An overview of deep learning in medical imaging focusing on MRI. Z Med Phys. 2018; 29(2):102-127. DOI: 10.1016/j.zemedi.2018.11.002. View

12.

Shibahara I, Saito R, Osada Y, Kanamori M, Sonoda Y, Kumabe T . Incidence of initial spinal metastasis in glioblastoma patients and the importance of spinal screening using MRI. J Neurooncol. 2018; 141(2):337-345. DOI: 10.1007/s11060-018-03036-4. View

13.

Gelsomino F, Facchini G, Barbera M, Lamberti G, Brocchi S, Rossi G . Complete Recalcification Following Arterial Embolization of Massive Osteolytic Bone Metastasis From NSCLC. J Thorac Oncol. 2018; 14(1):141-143. DOI: 10.1016/j.jtho.2018.10.151. View

14.

Tang Q, Zhao H, Jia R, Liu L . [Correlation of the levels of the bone turnover markers BAP and β-CTX with bone metastasis progress in lung cancer patients]. Zhongguo Fei Ai Za Zhi. 2013; 16(3):144-7. PMC: 6015133. DOI: 10.3779/j.issn.1009-3419.2013.03.05. View

15.

Roth H, Lu L, Lay N, Harrison A, Farag A, Sohn A . Spatial aggregation of holistically-nested convolutional neural networks for automated pancreas localization and segmentation. Med Image Anal. 2018; 45:94-107. DOI: 10.1016/j.media.2018.01.006. View

16.

Akkus Z, Galimzianova A, Hoogi A, Rubin D, Erickson B . Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions. J Digit Imaging. 2017; 30(4):449-459. PMC: 5537095. DOI: 10.1007/s10278-017-9983-4. View

17.

Foruzan A, Chen Y . Improved segmentation of low-contrast lesions using sigmoid edge model. Int J Comput Assist Radiol Surg. 2015; 11(7):1267-83. DOI: 10.1007/s11548-015-1323-x. View

18.

Litjens G, Kooi T, Bejnordi B, Setio A, Ciompi F, Ghafoorian M . A survey on deep learning in medical image analysis. Med Image Anal. 2017; 42:60-88. DOI: 10.1016/j.media.2017.07.005. View

19.

Sonn K, Kannan A, Bellary S, Yun C, Hashmi S, Nelson J . Effect of recombinant human bone morphogenetic protein-2 on a novel lung cancer spine metastasis model in rodents. J Orthop Res. 2015; 34(7):1274-81. DOI: 10.1002/jor.23139. View