TY - JOUR
T1 - Automated Classification of Intramedullary Spinal Cord Tumors and Inflammatory Demyelinating Lesions Using Deep Learning
AU - Zhuo, Zhizheng
AU - Zhang, Jie
AU - Duan, Yunyun
AU - Qu, Liying
AU - Feng, Chenlu
AU - Huang, Xufang
AU - Cheng, Dan
AU - Xu, Xiaolu
AU - Sun, Ting
AU - Li, Zhaohui
AU - Guo, Xiaopeng
AU - Gong, Xiaodong
AU - Wang, Yongzhi
AU - Jia, Wenqing
AU - Tian, Decai
AU - Zhan, Xinghu
AU - Shi, Fudong
AU - Haller, Sven
AU - Barkhof, Frederik
AU - Ye, Chuyang
AU - Liu, Yaou
N1 - Publisher Copyright:
© RSNA, 2022.
PY - 2022/11
Y1 - 2022/11
N2 - 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.
AB - 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.
KW - Astrocytoma
KW - Deep Learning
KW - Ependymoma
KW - Multiple Sclerosis
KW - Neuromyelitis Optica Spectrum Disorder
KW - Spinal Cord MRI
UR - http://www.scopus.com/inward/record.url?scp=85143975979&partnerID=8YFLogxK
U2 - 10.1148/ryai.210292
DO - 10.1148/ryai.210292
M3 - Article
AN - SCOPUS:85143975979
SN - 2638-6100
VL - 4
JO - Radiology: Artificial Intelligence
JF - Radiology: Artificial Intelligence
IS - 6
M1 - e210292
ER -