Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT

• Published in: Cancers Vol. 14; no. 13; p. 3219
• Main Authors: Hallinan, James Thomas Patrick Decourcy, Zhu, Lei, Zhang, Wenqiao, Kuah, Tricia, Lim, Desmond Shi Wei, Low, Xi Zhen, Cheng, Amanda J L, Eide, Sterling Ellis, Ong, Han Yang, Muhamat Nor, Faimee Erwan, Alsooreti, Ahmed Mohamed, AlMuhaish, Mona I, Yeong, Kuan Yuen, Teo, Ee Chin, Barr Kumarakulasinghe, Nesaretnam, Yap, Qai Ven, Chan, Yiong Huak, Lin, Shuxun, Tan, Jiong Hao, Kumar, Naresh, Vellayappan, Balamurugan A, Ooi, Beng Chin, Quek, Swee Tian, Makmur, Andrew
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 30.06.2022; MDPI
• Subjects: Asymptomatic; Cancer; Classification; Compression; Datasets; Deep learning; Diagnosis; Epidural; Magnetic resonance imaging; Malignancy; Medical imaging; Metastases; Metastasis; Pain; Patients; Radiation therapy; Spinal cord; Spine; Singapore; deep learning model; CT; metastatic epidural spinal cord compression; spinal metastatic disease; metastatic spinal cord compression; MRI; spinal metastases classification; Bilsky classification; epidural spinal cord compression
• ISSN: 2072-6694; 2072-6694
• DOI: 10.3390/cancers14133219

Background: Metastatic epidural spinal cord compression (MESCC) is a disastrous complication of advanced malignancy. Deep learning (DL) models for automatic MESCC classification on staging CT were developed to aid earlier diagnosis. Methods: This retrospective study included 444 CT staging studies from 185 patients with suspected MESCC who underwent MRI spine studies within 60 days of the CT studies. The DL model training/validation dataset consisted of 316/358 (88%) and the test set of 42/358 (12%) CT studies. Training/validation and test datasets were labeled in consensus by two subspecialized radiologists (6 and 11-years-experience) using the MRI studies as the reference standard. Test sets were labeled by the developed DL models and four radiologists (2−7 years of experience) for comparison. Results: DL models showed almost-perfect interobserver agreement for classification of CT spine images into normal, low, and high-grade MESCC, with kappas ranging from 0.873−0.911 (p < 0.001). The DL models (lowest κ = 0.873, 95% CI 0.858−0.887) also showed superior interobserver agreement compared to two of the four radiologists for three-class classification, including a specialist (κ = 0.820, 95% CI 0.803−0.837) and general radiologist (κ = 0.726, 95% CI 0.706−0.747), both p < 0.001. Conclusion: DL models for the MESCC classification on a CT showed comparable to superior interobserver agreement to radiologists and could be used to aid earlier diagnosis.