Deep Learning for Pediatric Posterior Fossa Tumor Detection and Classification: A Multi-Institutional Study.

BACKGROUND AND PURPOSE: Posterior fossa tumors are the most common pediatric brain tumors. MR imaging is key to tumor detection, diagnosis, and therapy guidance. We sought to develop an MR imaging-based deep learning model for posterior fossa tumor detection and tumor pathology classification. MATERIALS AND METHODS: The study cohort comprised 617 children (median age, 92 months; 56% males) from 5 pediatric institutions with posterior fossa tumors: diffuse midline glioma of the pons (n = 122), medulloblastoma (n = 272), pilocytic astrocytoma (n = 135), and ependymoma (n = 88). There were 199 controls. Tumor histology served as ground truth except for diffuse midline glioma of the pons, which was primarily diagnosed by MR imaging. A modified ResNeXt-50-32x4d architecture served as the backbone for a multitask classifier model, using T2-weighted MRIs as input to detect the presence of tumor and predict tumor class. Deep learning model performance was compared against that of 4 radiologists. RESULTS: Model tumor detection accuracy exceeded an AUROC of 0.99 and was similar to that of 4 radiologists. Model tumor classification accuracy was 92% with an F1 score of 0.80. The model was most accurate at predicting diffuse midline glioma of the pons, followed by pilocytic astrocytoma and medulloblastoma. Ependymoma prediction was the least accurate. Tumor type classification accuracy and F1 score were higher than those of 2 of the 4 radiologists. CONCLUSIONS: We present a multi-institutional deep learning model for pediatric posterior fossa tumor detection and classification with the potential to augment and improve the accuracy of radiologic diagnosis.

Hydrocephalus decreases arterial spin-labeled cerebral perfusion.

BACKGROUND AND PURPOSE: Reduced cerebral perfusion has been observed with elevated intracranial pressure. We hypothesized that arterial spin-labeled CBF can be used as a marker for symptomatic hydrocephalus. MATERIALS AND METHODS: We compared baseline arterial spin-labeled CBF in 19 children (median age, 6.5 years; range, 1-17 years) with new posterior fossa brain tumors and clinical signs of intracranial hypertension with arterial spin-labeled CBF in 16 age-matched controls and 4 patients with posterior fossa tumors without ventriculomegaly or signs of intracranial hypertension. Measurements were recorded in the cerebrum at the vertex, deep gray nuclei, and periventricular white matter and were assessed for a relationship to ventricular size. In 16 symptomatic patients, we compared cerebral perfusion before and after alleviation of hydrocephalus. RESULTS: Patients with uncompensated hydrocephalus had lower arterial spin-labeled CBF than healthy controls for all brain regions interrogated (P < .001). No perfusion difference was seen between asymptomatic patients with posterior fossa tumors and healthy controls (P = 1.000). The median arterial spin-labeled CBF increased after alleviation of obstructive hydrocephalus (P < .002). The distance between the frontal horns inversely correlated with arterial spin-labeled CBF of the cerebrum (P = .036) but not the putamen (P = .156), thalamus (P = .111), or periventricular white matter (P = .121). CONCLUSIONS: Arterial spin-labeled-CBF was reduced in children with uncompensated hydrocephalus and restored after its alleviation. Arterial spin-labeled-CBF perfusion MR imaging may serve a future role in the neurosurgical evaluation of hydrocephalus, as a potential noninvasive method to follow changes of intracranial pressure with time.

Prognostic role for diffusion-weighted imaging of pediatric optic pathway glioma.

Optic pathway glioma (OPG) has an unpredictable course, with poor correlation between conventional imaging features and tumor progression. We investigated whether diffusion-weighted MRI (DWI) predicts the clinical behavior of these tumors. Twelve children with OPG (median age 2.7 years; range 0.4-6.2 years) were followed for a median 4.4 years with DWI. Progression-free survival (time to requiring therapy) was compared between tumors stratified by apparent diffusion coefficient (ADC) from initial pre-treatment scans. Tumors with baseline ADC greater than 1,400 × 10(-6) mm(2)/s required treatment earlier than those with lower ADC (log-rank p = 0.002). In some cases, ADC increased leading up to treatment, and declined following treatment with surgery, chemotherapy, or radiation. Baseline ADC was higher in tumors that eventually required treatment (1,562 ± 192 × 10(-6) mm(2)/s), compared with those conservatively managed (1,123 ± 114 × 10(-6) mm(2)/s) (Kruskal-Wallis test p = 0.013). Higher ADC predicted earlier tumor progression in this cohort and in some cases declined after therapy. Evaluation of OPG with DWI may therefore be useful for predicting tumor behavior and assessing treatment response.

Diffusion-weighted MRI: distinction of skull base chordoma from chondrosarcoma.

BACKGROUND AND PURPOSE: Chordoma and chondrosarcoma of the skull base are rare tumors with overlapping presentations and anatomic imaging features but different prognoses. We hypothesized that these tumors might be distinguished by using diffusion-weighted MR imaging. MATERIALS AND METHODS: We retrospectively reviewed 19 patients with pathologically confirmed chordoma or chondrosarcoma who underwent both conventional and diffusion-weighted MR imaging. Differences in distributions of ADC were assessed by the Kruskal-Wallis test. Associations between histopathologic diagnosis and conventional MR imaging features (T2 signal intensity, contrast enhancement, and tumor location) were assessed with the Fisher exact test. RESULTS: Chondrosarcoma was associated with the highest mean ADC value (2051 ± 261 × 10(-6) mm(2)/s) and was significantly different from classic chordoma (1474 ± 117 × 10(-6) mm(2)/s) and poorly differentiated chordoma (875 ± 100 × 10(-6) mm(2)/s) (P < .001). Poorly differentiated chordoma was characterized by low T2 signal intensity (P = .001), but other conventional MR imaging features of enhancement and/or lesion location did not reliably distinguish these tumor types. CONCLUSIONS: Diffusion-weighted MR imaging may be useful in assessing clival tumors, particularly in differentiating chordoma from chondrosarcoma. A prospective study of a larger cohort will be required to determine the value of ADC in predicting histopathologic diagnosis.