Automated Color-Coding of Lesion Changes in Contrast-Enhanced 3D T1-Weighted Sequences for MRI Follow-up of Brain Metastases

Dual-energy computed tomography material decomposition improves prediction accuracy of hematoma expansion in traumatic intracranial hemorrhage

OBJECTIVE

The angiographic spot sign (AS) on CT angiography (CTA) is known to be useful for predicting expansion in intracranial hemorrhage, but its use is limited due to its relatively low sensitivity. Recently, dual-energy computed tomography (DECT) has been shown to be superior in distinguishing between hemorrhage and iodine. This study aimed to evaluate the diagnostic performance of hematoma expansion (HE) using DECT AS in traumatic intracranial hemorrhage.

METHODS

We recruited participants with intracranial hemorrhage confirmed via CTA for suspected traumatic cerebrovascular injuries. We evaluated AS on both conventional-like and fusion images of DECT. AS is grouped into three categories: intralesional enhancement without change, delayed enhancement (DE), and growing contrast leakage (GL). HE was evaluated by measuring hematoma size on DECT and follow-up CT. Logistic regression analysis was used to evaluate whether AS on fusion images was a significant risk factor for HE. Diagnostic accuracy was calculated, and the results from conventional-like and fusion images were compared.

RESULTS

Thirty-nine hematomas in 24 patients were included in this study. Of these, 18 hematomas in 13 patients showed expansion on follow-up CT. Among the expanders, AS and GL on fusion images were noted in 13 and 5 hematomas, respectively. In non-expanders, 10 and 1 hematoma showed AS and GL, respectively. In the logistic regression model, GL on the fusion image was a significant independent risk factor for predicting HE. However, when AS was used on conventional-like images, no factors significantly predicted HE. In the receiver operating characteristic curve analysis, the area under the curve of AS on the fusion images was 0.71, with a sensitivity and specificity of 66.7% and 76.2%, respectively.

CONCLUSIONS

GL on fusion images of DECT in traumatic intracranial hemorrhage is a significant independent radiologic risk factor for predicting HE. The AS of DECT fusion images has improved sensitivity compared to that of conventional-like images.

Automatically tracking brain metastases after stereotactic radiosurgery

Background and purpose

Patients with brain metastases (BMs) are surviving longer and returning for multiple courses of stereotactic radiosurgery. BMs are monitored after radiation with follow-up magnetic resonance (MR) imaging every 2-3 months. This study investigated whether it is possible to automatically track BMs on longitudinal imaging and quantify the tumor response after radiotherapy.

Methods

The METRO process (MEtastasis Tracking with Repeated Observations was developed to automatically process patient data and track BMs. A longitudinal intrapatient registration method for T1 MR post-Gd was conceived and validated on 20 patients. Detections and volumetric measurements of BMs were obtained from a deep learning model. BM tracking was validated on 32 separate patients by comparing results with manual measurements of BM response and radiologists' assessments of new BMs. Linear regression and residual analysis were used to assess accuracy in determining tumor response and size change.

Results

A total of 123 irradiated BMs and 38 new BMs were successfully tracked. 66 irradiated BMs were visible on follow-up imaging 3-9 months after radiotherapy. Comparing their longest diameter changes measured manually vs. METRO, the Pearson correlation coefficient was 0.88 (p < 0.001); the mean residual error was -8 ± 17%. The mean registration error was 1.5 ± 0.2 mm.

Conclusions

Automatic, longitudinal tracking of BMs using deep learning methods is feasible. In particular, the software system METRO fulfills a need to automatically track and quantify volumetric changes of BMs prior to, and in response to, radiation therapy.