Automated Classification of Intramedullary Spinal Cord Tumors and Inflammatory Demyelinating Lesions Using Deep Learning

Zhizheng Zhuo, Jie Zhang, Yunyun Duan, Liying Qu, Chenlu Feng, Xufang Huang, Dan Cheng, Xiaolu Xu, Ting Sun, Zhaohui Li, Xiaopeng Guo, Xiaodong Gong, Yongzhi Wang, Wenqing Jia, Decai Tian, Xinghu Zhan, Fudong Shi, Sven Haller, Frederik Barkhof, Chuyang YeYaou Liu*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

16 Citations (Scopus)

Abstract

Accurate differentiation of intramedullary spinal cord tumors and inflammatory demyelinating lesions and their subtypes are warranted because of their overlapping characteristics at MRI but with different treatments and prognosis. The authors aimed to develop a pipeline for spinal cord lesion segmentation and classification using two-dimensional MultiResUNet and DenseNet121 networks based on T2-weighted images. A ret-rospective cohort of 490 patients (118 patients with astrocytoma, 130 with ependymoma, 101 with multiple sclerosis [MS], and 141 with neu-romyelitis optica spectrum disorders [NMOSD]) was used for model development, and a prospective cohort of 157 patients (34 patients with astrocytoma, 45 with ependymoma, 33 with MS, and 45 with NMOSD) was used for model testing. In the test cohort, the model achieved Dice scores of 0.77, 0.80, 0.50, and 0.58 for segmentation of astrocytoma, ependymoma, MS, and NMOSD, respectively, against manual la-beling. Accuracies of 96% (area under the receiver operating characteristic curve [AUC], 0.99), 82% (AUC, 0.90), and 79% (AUC, 0.85) were achieved for the classifications of tumor versus demyelinating lesion, astrocytoma versus ependymoma, and MS versus NMOSD, respectively. In a subset of radiologically difficult cases, the classifier showed an accuracy of 79%–95% (AUC, 0.78–0.97). The established deep learning pipeline for segmentation and classification of spinal cord lesions can support an accurate radiologic diagnosis.

Original languageEnglish
Article numbere210292
JournalRadiology: Artificial Intelligence
Volume4
Issue number6
DOIs
Publication statusPublished - Nov 2022

Keywords

  • Astrocytoma
  • Deep Learning
  • Ependymoma
  • Multiple Sclerosis
  • Neuromyelitis Optica Spectrum Disorder
  • Spinal Cord MRI

Fingerprint

Dive into the research topics of 'Automated Classification of Intramedullary Spinal Cord Tumors and Inflammatory Demyelinating Lesions Using Deep Learning'. Together they form a unique fingerprint.

Cite this