Skip to main content
Journal cover image

Machine-Learning Approach to Differentiation of Benign and Malignant Peripheral Nerve Sheath Tumors: A Multicenter Study.

Publication ,  Journal Article
Zhang, M; Tong, E; Hamrick, F; Lee, EH; Tam, LT; Pendleton, C; Smith, BW; Hug, NF; Biswal, S; Seekins, J; Mattonen, SA; Napel, S; Campen, CJ ...
Published in: Neurosurgery
August 16, 2021

BACKGROUND: Clinicoradiologic differentiation between benign and malignant peripheral nerve sheath tumors (PNSTs) has important management implications. OBJECTIVE: To develop and evaluate machine-learning approaches to differentiate benign from malignant PNSTs. METHODS: We identified PNSTs treated at 3 institutions and extracted high-dimensional radiomics features from gadolinium-enhanced, T1-weighted magnetic resonance imaging (MRI) sequences. Training and test sets were selected randomly in a 70:30 ratio. A total of 900 image features were automatically extracted using the PyRadiomics package from Quantitative Imaging Feature Pipeline. Clinical data including age, sex, neurogenetic syndrome presence, spontaneous pain, and motor deficit were also incorporated. Features were selected using sparse regression analysis and retained features were further refined by gradient boost modeling to optimize the area under the curve (AUC) for diagnosis. We evaluated the performance of radiomics-based classifiers with and without clinical features and compared performance against human readers. RESULTS: A total of 95 malignant and 171 benign PNSTs were included. The final classifier model included 21 imaging and clinical features. Sensitivity, specificity, and AUC of 0.676, 0.882, and 0.845, respectively, were achieved on the test set. Using imaging and clinical features, human experts collectively achieved sensitivity, specificity, and AUC of 0.786, 0.431, and 0.624, respectively. The AUC of the classifier was statistically better than expert humans (P = .002). Expert humans were not statistically better than the no-information rate, whereas the classifier was (P = .001). CONCLUSION: Radiomics-based machine learning using routine MRI sequences and clinical features can aid in evaluation of PNSTs. Further improvement may be achieved by incorporating additional imaging sequences and clinical variables into future models.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Neurosurgery

DOI

EISSN

1524-4040

Publication Date

August 16, 2021

Volume

89

Issue

3

Start / End Page

509 / 517

Location

United States

Related Subject Headings

  • Retrospective Studies
  • Neurology & Neurosurgery
  • Neurofibrosarcoma
  • Nerve Sheath Neoplasms
  • Magnetic Resonance Imaging
  • Machine Learning
  • Humans
  • 5202 Biological psychology
  • 3209 Neurosciences
  • 3202 Clinical sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zhang, M., Tong, E., Hamrick, F., Lee, E. H., Tam, L. T., Pendleton, C., … Mahan, M. A. (2021). Machine-Learning Approach to Differentiation of Benign and Malignant Peripheral Nerve Sheath Tumors: A Multicenter Study. Neurosurgery, 89(3), 509–517. https://doi.org/10.1093/neuros/nyab212
Zhang, Michael, Elizabeth Tong, Forrest Hamrick, Edward H. Lee, Lydia T. Tam, Courtney Pendleton, Brandon W. Smith, et al. “Machine-Learning Approach to Differentiation of Benign and Malignant Peripheral Nerve Sheath Tumors: A Multicenter Study.Neurosurgery 89, no. 3 (August 16, 2021): 509–17. https://doi.org/10.1093/neuros/nyab212.
Zhang M, Tong E, Hamrick F, Lee EH, Tam LT, Pendleton C, et al. Machine-Learning Approach to Differentiation of Benign and Malignant Peripheral Nerve Sheath Tumors: A Multicenter Study. Neurosurgery. 2021 Aug 16;89(3):509–17.
Zhang, Michael, et al. “Machine-Learning Approach to Differentiation of Benign and Malignant Peripheral Nerve Sheath Tumors: A Multicenter Study.Neurosurgery, vol. 89, no. 3, Aug. 2021, pp. 509–17. Pubmed, doi:10.1093/neuros/nyab212.
Zhang M, Tong E, Hamrick F, Lee EH, Tam LT, Pendleton C, Smith BW, Hug NF, Biswal S, Seekins J, Mattonen SA, Napel S, Campen CJ, Spinner RJ, Yeom KW, Wilson TJ, Mahan MA. Machine-Learning Approach to Differentiation of Benign and Malignant Peripheral Nerve Sheath Tumors: A Multicenter Study. Neurosurgery. 2021 Aug 16;89(3):509–517.
Journal cover image

Published In

Neurosurgery

DOI

EISSN

1524-4040

Publication Date

August 16, 2021

Volume

89

Issue

3

Start / End Page

509 / 517

Location

United States

Related Subject Headings

  • Retrospective Studies
  • Neurology & Neurosurgery
  • Neurofibrosarcoma
  • Nerve Sheath Neoplasms
  • Magnetic Resonance Imaging
  • Machine Learning
  • Humans
  • 5202 Biological psychology
  • 3209 Neurosciences
  • 3202 Clinical sciences