Identification of origin for spinal metastases from MRI images: comparison between radiomics and deep learning methods.

Researchers

Journal

Modalities

Models

Abstract

To determine whether spinal metastatic lesions originated from lung cancer or from other cancers, based on spinal contrast-enhanced T1 (CET1) MR images analyzed using radiomics and deep learning methods.We recruited and retrospectively reviewed 173 patients diagnosed with spinal metastases at two different centers between July 2018 and June 2021. Of these, 68 involved lung cancer, and 105 were other types of cancer. They were assigned to an internal cohort of 149 patients, randomly divided into a training set and a validation set, and to an external cohort of 24 patients. All patients underwent CET1 MR imaging before surgery or biopsy. We developed two predictive algorithms: a deep learning (DL) model, and a radiomics (RAD) model. We compared performance between models, and against human radiological assessment, via accuracy (ACC) and receiver operating characteristic (ROC) analyses. Furthermore, we analyzed the correlation between RAD and DL features.The DL model outperformed RAD model across the board, with ACC/AUC values of 0.93/0.94 (DL) versus 0.84/0.93 (RAD) when applied to the training set from the internal cohort, 0.74/0.76 versus 0.72/0.75 when applied to the validation set, and 0.72/0.76 versus 0.69/0.72 when applied to the external test cohort. For the validation set, it also outperformed expert radiological assessment (ACC: 0.65, AUC: 0.68). We only found weak correlations between DL and RAD features.The deep learning algorithm successfully identified the origin of spinal metastases from preoperative CET1 MR images, outperforming both radiomics models and expert assessment by trained radiologists.Copyright © 2023. Published by Elsevier Inc.