Deep Learning MRI Models for the Differential Diagnosis of Tumefactive Demyelination versus <i>IDH</i> Wild-Type Glioblastoma.
Authors
Affiliations (8)
Affiliations (8)
- From the Department of Radiology (G.M.C., M.M., Y.N., B.J.E.), Mayo Clinic, Rochester, Minnesota.
- Deptartment of Quantitative Health Sciences (P.A.D., M.L.K., J.E.E.-P.), Mayo Clinic, Rochester, Minnesota.
- Department of Neurology (C.B.M., J.A.S., M.W.R., F.S.G., H.K.P., D.H.L., W.O.T.), Mayo Clinic, Rochester, Minnesota.
- Dell Medical School (M.F.-E.), University of Texas, Austin, Texas.
- Department of Neurosurgery (T.C.B.), Mayo Clinic, Rochester, Minnesota.
- Department of Laboratory Medicine & Pathology (R.B.J.), Mayo Clinic, Rochester, Minnesota.
- Center for Multiple Sclerosis and Autoimmune Neurology (W.O.T.), Mayo Clinic, Rochester, Minnesota.
- Deptartment of Quantitative Health Sciences (P.A.D., M.L.K., J.E.E.-P.), Mayo Clinic, Rochester, Minnesota [email protected].
Abstract
Diagnosis of tumefactive demyelination can be challenging. The diagnosis of indeterminate brain lesions on MRI often requires tissue confirmation via brain biopsy. Noninvasive methods for accurate diagnosis of tumor and nontumor etiologies allows for tailored therapy, optimal tumor control, and a reduced risk of iatrogenic morbidity and mortality. Tumefactive demyelination has imaging features that mimic <i>isocitrate dehydrogenase</i> wild-type glioblastoma (<i>IDH</i>wt GBM). We hypothesized that deep learning applied to postcontrast T1-weighted (T1C) and T2-weighted (T2) MRI can discriminate tumefactive demyelination from <i>IDH</i>wt GBM. Patients with tumefactive demyelination (<i>n</i> = 144) and <i>IDH</i>wt GBM (<i>n</i> = 455) were identified by clinical registries. A 3D DenseNet121 architecture was used to develop models to differentiate tumefactive demyelination and <i>IDH</i>wt GBM by using both T1C and T2 MRI, as well as only T1C and only T2 images. A 3-stage design was used: 1) model development and internal validation via 5-fold cross validation by using a sex-, age-, and MRI technology-matched set of tumefactive demyelination and <i>IDH</i>wt GBM, 2) validation of model specificity on independent <i>IDH</i>wt GBM, and 3) prospective validation on tumefactive demyelination and <i>IDH</i>wt GBM. Stratified area under the receiver operating curves (AUROCs) were used to evaluate model performance stratified by sex, age at diagnosis, MRI scanner strength, and MRI acquisition. The deep learning model developed by using both T1C and T2 images had a prospective validation AUROC of 88% (95% CI: 0.82-0.95). In the prospective validation stage, a model score threshold of 0.28 resulted in 91% sensitivity of correctly classifying tumefactive demyelination and 80% specificity (correctly classifying <i>IDH</i>wt GBM). Stratified AUROCs demonstrated that model performance may be improved if thresholds were chosen stratified by age and MRI acquisition. MRI can provide the basis for applying deep learning models to aid in the differential diagnosis of brain lesions. Further validation is needed to evaluate how well the model generalizes across institutions, patient populations, and technology, and to evaluate optimal thresholds for classification. Next steps also should incorporate additional tumor etiologies such as CNS lymphoma and brain metastases.