Fully automated volumetry of ventricular subregions on computed tomography using object detection and semantic segmentation

TL;DR

This paper presents a machine learning pipeline for automatically measuring brain ventricle subregions in CT scans, which could help detect subtle changes in ventricular volume for clinical evaluation.

Contribution

A novel deep learning pipeline combining object detection and semantic segmentation for automated ventricular subregion volumetry on CT.

Findings

The pipeline achieved high precision in segmenting ventricular subregions on CT scans.

Best mean Dice scores were 0.92 ± 0.1 for the body of the left lateral ventricle.

A user-friendly graphical interface was developed for clinical integration of the method.

Abstract

Our goal was to develop and validate machine learning models that are capable of fully automatic identification and segmentation of frontal, temporal, and posterior horns, the body of the lateral ventricle, the third and fourth ventricle, as well as the atrium on either side.

Patients shunted for hydrocephalus were included. Data from two centers was used for development/external validation, respectively. Manual labelling of ventricular subregions on computed tomography (CT) was performed. First, an object detection algorithm (YOLOv5) was trained. This allowed for precise cropping of the subregions that could then be used as input for a 2D U-Net. For comparison, a nnU-Net was also trained. Precision, recall, mean average precision 50 and 50–95 (mAP50; mAP50-95) were used as performance metrics for the YOLO algorithm. Dice score, Jaccard score, and 95th percentile Hausdorff distance assessed performance for the U-Net.

80 CTs from patients at our center were included, as well as 50 from a second center. The mean age was 68.59 ± 15.89 and 75.94 ± 4.17 for the first and second centers, and 43 (52.5%) and 30 (60%) were male. MAP 50, mAP50-95 was 0.728, 0.453 for internal and 0.274, 0.124 for external validation across all classes. Best mean Dice scores were 0.92 ± 0.1 and 0.90 ± 0.05 for the body of the left lateral ventricle.

Automatic segmentation and volumetry of ventricles including their subregions was feasible with high precision on computed tomography, potentially helping the clinical evaluation of even subtle changes in ventricular volume.

•Our pipeline enables reliable automated volumetry of anatomical subregions of the internal ventricular system.•Combining object detection with semantic segmentation improves accuracy of ventricular subregion segmentation.•A user-friendly graphical interface facilitates clinical integration of the deep learning pipeline.

Our pipeline enables reliable automated volumetry of anatomical subregions of the internal ventricular system.

Combining object detection with semantic segmentation improves accuracy of ventricular subregion segmentation.

A user-friendly graphical interface facilitates clinical integration of the deep learning pipeline.

Figures