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

Abstract

BackgroundMetastatic epidural spinal cord compression (MESCC) is a devastating complication of advanced cancer. A deep learning (DL) model for automated MESCC classification on MRI could aid earlier diagnosis and referral.PurposeTo develop a DL model for automated classification of MESCC on MRI.Materials and MethodsPatients with known MESCC diagnosed on MRI between September 2007 and 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 labeled using the Bilsky MESCC classification by a musculoskeletal radiologist (10-year experience) and a neuroradiologist (5-year experience). These labels were used to train a DL model utilizing a prototypical convolutional neural network. Internal and external test sets were labeled by the musculoskeletal radiologist as the reference standard. For assessment of DL model performance and interobserver variability, test sets were labeled independently by the neuroradiologist (5-year experience), a spine surgeon (5-year experience), and a radiation oncologist (11-year experience). Inter-rater agreement (Gwet’s kappa) and sensitivity/specificity were calculated.ResultsOverall, 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.ConclusionA DL model showed comparable agreement to a subspecialist radiologist and clinical specialists for the classification of malignant epidural spinal cord compression and could optimize earlier diagnosis and surgical referral.

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

“…Most recently, Hallinan et al (2022) developed a deep learning model for the prediction of low and high-grade Bilsky classification on MRI of the thoracic spine. On internal and external testing, the DL model showed high agreement (κ = 0.92-0.94, p < 0.001) for two-grade Bilsky classification, which was similar to specialist labelers (κ = 0.95-0.98, all p < 0.001), including a spine surgeon, a radiation oncologist, and a radiologist [36].…”

Application of Artificial Intelligence Methods for Imaging of Spinal Metastasis

“…Applications of deep learning models goes beyond tumour detection and differentiation, and they have the ability to automatically generate meaningful parameters from MRI and other modalities. Hallinan et al [ 94 ] developed a deep learning model for automated classification of metastatic epidural disease and/or spinal cord compression on MRI using the Bilsky classification. The model showed almost perfect agreement when compared to specialist readers on internal and external datasets with kappas of 0.92–0.98, p < 0.001 and 0.94–0.95, p < 0.001, respectively, for dichotomous Bilsky classification (low versus high grade).…”

State-of-the-Art Imaging Techniques in Metastatic Spinal Cord Compression

“…MSCC is a debilitating complication in cancer patients with spinal metastasis, and its incidence is expected to rise due to improving cancer treatments and survival [6,166]. As it is a time-sensitive diagnosis, prompt radiological evaluation within 24 h is necessary to avoid permanent neurological dysfunction.…”

“…For example, Wang DL tools in image interpretation have seen substantial growth over the past few years. In a recently published study by Hallinan et al (2022) [166], axial T2-weighted images of 177 MR spine studies in MSCC patients from Sept 2007 to Sept 2017 were utilized to create a DL model employing convolutional neural networks for automated MSCC classification into dichotomized Bilsky gradings (low-grade Bilsky was defined as Grade 0 to 1b, while high-grade Bilsky was defined as Grade 1c to 3). Internal testing on 38 MRI spine studies and external testing on 32 MRI spine studies showed near-perfect agreement of the DL model and other subspecialist readers (including a musculoskeletal radiologist, neuroradiologist, spine surgeon and radiation oncologist, all with at least 5 years of clinical experience) with the reference standard (internal testing kappas = 0.92-0.98, p < 0.001; external testing kappas = 0.94-0.95, p < 0.001).…”