Display options
Cite
Masoudi S, Mehralivand S, Harmon SA, et al. Deep Learning Based Staging of Bone Lesions From Computed Tomography Scans. IEEE Access. 2021;9:87531-87542doi: 10.1109/access.2021.3074051.
Masoudi, S., Mehralivand, S., Harmon, S. A., Lay, N., Lindenberg, L., Mena, E., Pinto, P. A., Citrin, D. E., Gulley, J. L., Wood, B. J., Dahut, W. L., Madan, R. A., Bagci, U., Choyke, P. L., & Turkbey, B. (2021). Deep Learning Based Staging of Bone Lesions From Computed Tomography Scans. IEEE access : practical innovations, open solutions, 987531-87542. https://doi.org/10.1109/access.2021.3074051
Masoudi, Samira, et al. "Deep Learning Based Staging of Bone Lesions From Computed Tomography Scans." IEEE access : practical innovations, open solutions vol. 9 (2021): 87531-87542. doi: https://doi.org/10.1109/access.2021.3074051
Masoudi S, Mehralivand S, Harmon SA, Lay N, Lindenberg L, Mena E, Pinto PA, Citrin DE, Gulley JL, Wood BJ, Dahut WL, Madan RA, Bagci U, Choyke PL, Turkbey B. Deep Learning Based Staging of Bone Lesions From Computed Tomography Scans. IEEE Access. 2021;9:87531-87542. doi: 10.1109/access.2021.3074051. Epub 2021 Apr 20. PMID: 34733603; PMCID: PMC8562651.
Copy Download .nbib Format: NLM
Share it on

IEEE Access. 2021;9:87531-87542. doi: 10.1109/access.2021.3074051. Epub 2021 Apr 20.

Deep Learning Based Staging of Bone Lesions From Computed Tomography Scans.

IEEE access : practical innovations, open solutions

Samira Masoudi, Sherif Mehralivand, Stephanie A Harmon, Nathan Lay, Liza Lindenberg, Esther Mena, Peter A Pinto, Deborah E Citrin, James L Gulley, Bradford J Wood, William L Dahut, Ravi A Madan, Ulas Bagci, Peter L Choyke, Baris Turkbey

Affiliations

  1. Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD 20892, USA.
  2. Department of Radiology, Northwestern University, Chicago, IL 60611, USA.

PMID: 34733603 PMCID: PMC8562651 DOI: 10.1109/access.2021.3074051

Abstract

In this study, we formulated an efficient deep learning-based classification strategy for characterizing metastatic bone lesions using computed tomography scans (CTs) of prostate cancer patients. For this purpose, 2,880 annotated bone lesions from CT scans of 114 patients diagnosed with prostate cancer were used for training, validation, and final evaluation. These annotations were in the form of lesion full segmentation, lesion type and labels of either benign or malignant. In this work, we present our approach in developing the state-of-the-art model to classify bone lesions as benign or malignant, where (1) we introduce a valuable dataset to address a clinically important problem, (2) we increase the reliability of our model by patient-level stratification of our dataset following lesion-aware distribution at each of the training, validation, and test splits, (3) we explore the impact of lesion texture, morphology, size, location, and volumetric information on the classification performance, (4) we investigate the functionality of lesion classification using different algorithms including lesion-based average 2D ResNet-50, lesion-based average 2D ResNeXt-50, 3D ResNet-18, 3D ResNet-50, as well as the ensemble of 2D ResNet-50 and 3D ResNet-18. For this purpose, we employed a train/validation/test split equal to 75%/12%/13% with several data augmentation methods applied to the training dataset to avoid overfitting and to increase reliability. We achieved an accuracy of 92.2% for correct classification of benign vs. malignant bone lesions in the test set using an ensemble of lesion-based average 2D ResNet-50 and 3D ResNet-18 with texture, volumetric information, and morphology having the greatest discriminative power respectively. To the best of our knowledge, this is the highest ever achieved lesion-level accuracy having a very comprehensive data set for such a clinically important problem. This level of classification performance in the early stages of metastasis development bodes well for clinical translation of this strategy.

Keywords: Bone lesion; CT scan; classification; deep learning; lesion-aware data stratification

References

  1. Comput Methods Programs Biomed. 2017 Jan;138:49-56 - PubMed
  2. Annu Int Conf IEEE Eng Med Biol Soc. 2015;2015:6374-7 - PubMed
  3. IEEE Trans Med Imaging. 2016 May;35(5):1160-1169 - PubMed
  4. IEEE Trans Med Imaging. 2016 May;35(5):1285-98 - PubMed
  5. Med Phys. 2019 May;46(5):2052-2063 - PubMed
  6. PLoS One. 2020 Aug 14;15(8):e0237213 - PubMed
  7. Lancet. 2018 Dec 1;392(10162):2388-2396 - PubMed
  8. BMC Cancer. 2020 Mar 17;20(1):227 - PubMed
  9. Nat Rev Cancer. 2005 Jan;5(1):21-8 - PubMed
  10. Med Image Anal. 2018 Oct;49:76-88 - PubMed
  11. Sci Rep. 2016 Apr 15;6:24454 - PubMed
  12. J Cancer Res Ther. 2016 Apr-Jun;12(2):787-92 - PubMed
  13. J Nucl Med. 2008 Dec;49(12):1958-65 - PubMed
  14. Mol Imaging Biol. 2016 Jun;18(3):411-9 - PubMed

Publication Types

Grant support