AUTHOR=Hallinan James Thomas Patrick Decourcy , Zhu Lei , Zhang Wenqiao , Lim Desmond Shi Wei , Baskar Sangeetha , Low Xi Zhen , Yeong Kuan Yuen , Teo Ee Chin , Kumarakulasinghe Nesaretnam Barr , Yap Qai Ven , Chan Yiong Huak , Lin Shuxun , Tan Jiong Hao , Kumar Naresh , Vellayappan Balamurugan A. , Ooi Beng Chin , Quek Swee Tian , Makmur Andrew 

TITLE=Deep Learning Model for Classifying Metastatic Epidural Spinal Cord Compression on MRI

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.849447

DOI=10.3389/fonc.2022.849447

ISSN=2234-943X

ABSTRACT=Background

Metastatic epidural spinal cord compression (MESCC) is a devastating complication of advanced cancer. A deep learning (DL) model for automated Bilsky MESCC classification on MRI could aid earlier diagnosis and referral.

Purpose

To develop a DL model for automated classification of MESCC on MRI.

Materials and methods

Patients with known MESCC, diagnosed on MRI, between September 2007 to September 2017 were eligible. MRI studies with instrumentation, suboptimal image quality, and non- thoracic regions were excluded. Axial T2-weighted images were utilized. The internal dataset split was 82% and 18% for training/validation and test sets, respectively. External testing was also performed.
Internal training/validation data were labelled using the Bilsky MESCC classification by a musculoskeletal radiologist (10-years-experience) and a neuroradiologist (5-years- experience). These labels were used to train a DL model utilising a prototypical convolutional neural network. Internal and external test sets were labelled by the musculoskeletal radiologist as the reference standard. For assessment of DL model performance and interobserver variability, test sets were labelled independently by the neuroradiologist (5- years-experience), a spine surgeon (5-years-experience), and a radiation oncologist (11-years- experience). Inter-rater agreement (Gwet’s kappa) and sensitivity/specificity were calculated.

Results

Overall, 215 MRI spine studies were analyzed (164 patients, mean age=62±12[SD]) with 177(82%) for training/validation and 38(18%) for internal testing. For internal testing, the DL model and specialists all showed almost perfect agreement (kappas=0.92-0.98,p<0.001) for dichotomous Bilsky classification (low versus high-grade) compared to the reference standard. Similar performance was seen for external testing on a set of 32 MRI spines with the DL model and specialists all showing almost perfect agreement (kappas=0.94- 0.95,p<0.001) compared to the reference standard.

Conclusion

A deep learning model showed comparable agreement to a subspecialist radiologist and clinical specialists for the classification of malignant epidural spinal cord compression, and could optimise earlier diagnosis and surgical referral.