Automated Lateral Ventricular and Cranial Vault Volume Measurements in 13,851 Patients Using Deep Learning Algorithms

Automated ventricular segmentation and shunt failure detection using convolutional neural networks

While ventricular shunts are the main treatment for adult hydrocephalus, shunt malfunction remains a common problem that can be challenging to diagnose. Computer vision-derived algorithms present a potential solution. We designed a feasibility study to see if such an algorithm could automatically predict ventriculomegaly indicative of shunt failure in a real-life adult hydrocephalus population. We retrospectively identified a consecutive series of adult shunted hydrocephalus patients over an eight-year period. Associated computed tomography scans were extracted and each scan was reviewed by two investigators. A machine learning algorithm was trained to identify the lateral and third ventricles, and then applied to test scans. Results were compared to human performance using Sørensen-Dice coefficients, calculated total ventricular volumes, and ventriculomegaly as documented in the electronic medical record. 5610 axial images from 191 patients were included for final analysis, with 52 segments (13.6% of total data) reserved for testing. Algorithmic performance on the test group averaged a Dice score of 0.809 ± 0.094. Calculated total ventricular volumes did not differ significantly between computer-derived volumes and volumes marked by either the first reviewer or second reviewer (p > 0.05). Algorithm detection of ventriculomegaly was correct in all test cases and this correlated with correct prediction of need for shunt revision in 92.3% of test cases. Though development challenges remain, it is feasible to create automated algorithms that detect ventriculomegaly in adult hydrocephalus shunt malfunction with high reliability and accuracy.

CT-guided spatial normalization of nuclear hybrid imaging adapted to enlarged ventricles: Impact on striatal uptake quantification

INTRODUCTION

Spatial normalization is a prerequisite step for the quantitative analysis of SPECT or PET brain images using volume-of-interest (VOI) template or voxel-based analysis. MRI-guided spatial normalization is the gold standard, but the wide use of PET/CT or SPECT/CT in routine clinical practice makes CT-guided spatial normalization a necessary alternative. Ventricular enlargement is observed with aging, and it hampers the spatial normalization of the lateral ventricles and striatal regions, limiting their analysis. The aim of the present study was to propose a robust spatial normalization method based on CT scans that takes into account features of the aging brain to reduce bias in the CT-guided striatal analysis of SPECT images.

METHODS

We propose an enhanced CT-guided spatial normalization pipeline based on SPM12. Performance of the proposed pipeline was assessed on visually normal [123I]-FP-CIT SPECT/CT images. SPM12 default CT-guided spatial normalization was used as reference method. The metrics assessed were the overlap between the spatially normalized lateral ventricles and caudate/putamen VOIs, and the computation of caudate and putamen specific binding ratios (SBR).

RESULTS

In total 231 subjects (mean age ± SD = 61.9 ± 15.5 years) were included in the statistical analysis. The mean overlap between the spatially normalized lateral ventricles of subjects and the caudate VOI and the mean SBR of caudate were respectively 38.40 % (± SD = 19.48 %) of the VOI and 1.77 (± 0.79) when performing SPM12 default spatial normalization. The mean overlap decreased to 9.13 % (± SD = 1.41 %, P < 0.001) of the VOI and the SBR of caudate increased to 2.38 (± 0.51, P < 0.0001) when performing the proposed pipeline. Spatially normalized lateral ventricles did not overlap with putamen VOI using either method. The mean putamen SBR value derived from the proposed spatial normalization (2.75 ± 0.54) was not significantly different from that derived from the default SPM12 spatial normalization (2.83 ± 0.52, P > 0.05).

CONCLUSION

The automatic CT-guided spatial normalization used herein led to a less biased spatial normalization of SPECT images, hence an improved semi-quantitative analysis. The proposed pipeline could be implemented in clinical routine to perform a more robust SBR computation using hybrid imaging.

Correlating Age and Hematoma Volume with Extent of Midline Shift in Acute Subdural Hematoma Patients: Validation of an Artificial Intelligence Tool for Volumetric Analysis

OBJECTIVE

Decision for intervention in acute subdural hematoma patients is based on a combination of clinical and radiographic factors. Age has been suggested as a factor to be strongly considered when interpreting midline shift (MLS) and hematoma volume data for assessing critical clinical severity during operative intervention decisions for acute subdural hematoma patients. The objective of this study was to demonstrate the use of an automated volumetric analysis tool to measure hematoma volume and MLS and quantify their relationship with age.

METHODS

A total of 1789 acute subdural hematoma patients were analyzed using qER-Quant software (Qure.ai, Mumbai, India) for MLS and hematoma volume measurements. Univariable and multivariable regressions analyzed association between MLS, hematoma volume, age, and MLS:hematoma volume ratio.

RESULTS

In comparison to young patients (≤ 70 years), old patients (>70 years) had significantly higher average hematoma volume (old: 62.2 mL vs. young 46.8 mL, P < 0.0001), lower average MLS (old: 6.6 mm vs. young: 7.4 mm, P = 0.025), and lower average MLS:hematoma volume ratio (old: 0.11 mm/mL vs. young 0.15 mm/mL, P < 0.0001). Young patients had an average of 1.5 mm greater MLS for a given hematoma volume in comparison to old patients. With increasing age, the ratio between MLS and hematoma volume significantly decreases (P = 0.0002).

CONCLUSIONS

Commercially available, automated, artificial intelligence (AI)-based tools may be used for obtaining quantitative radiographic measurement data in patients with acute subdural hematoma. Our quantitative results are consistent with the qualitative relationship previously established between age, hematoma volume, and MLS, which supports the validity of using AI-based tools for acute subdural hematoma volume estimation.